10,000 Matching Annotations
  1. Jul 2025
    1. Note de synthèse détaillée : Vie affective et sexuelle des jeunes - Prévenir les risques et promouvoir les pratiques positives

      Cette synthèse reprend les points clés et les idées principales des interventions présentées lors de la matinale sur la vie affective et sexuelle des jeunes, organisée par l'IREPS Occitanie et le DRAPPS, avec la participation du projet Sexpert (INSERM), du SIMS de l'Université de Toulouse, et de l'Académie de Toulouse.

      L'objectif général est de "prévenir les risques et promouvoir les pratiques positives" en matière de santé sexuelle chez les jeunes.

      1. Contexte général et définitions (Delphine Soulignac - IREPS/DRAPPS)

      La matinale s'inscrit dans un cycle "Santé des jeunes" initié en avril 2023.

      Elle met en lumière l'importance de la santé sexuelle comme thématique de santé publique centrale.

      Définition de la Santé Sexuelle (OMS, 2006) : Bien plus qu'une simple absence de maladie ou de dysfonctionnement, la santé sexuelle est définie comme "un état de bien-être physique, émotionnel, mental et social".

      Elle inclut "l'absence de toute forme de coercition, de discrimination et de violence".

      Cette approche est "résolument positive" et s'appuie sur les "ressources des personnes, leur capacité à agir" et l'encouragement de "la multiplicité des leviers d'action possibles qu'il soient individuels, relationnels, organisationnels ou encore sociaux".

      Politiques Publiques : La thématique est soutenue par la Stratégie Nationale de Santé Sexuelle (2017-2030) et ses déclinaisons régionales, comme le Projet Régional de Santé en Occitanie.

      Déterminants de Santé : Promouvoir la santé sexuelle, c'est aussi "agir sur les déterminants de santé", notamment le "développement des compétences psychosociales", souvent considérées comme les "déterminants des déterminants".

      Le DRAPPS (Dispositif Régional d'Appui en Prévention et Promotion de la Santé), porté par l'IREPS, vise à "s'informer, se former et échanger" et est fondé sur les besoins remontés par les acteurs de terrain.

      L'événement de ce matin participe à la "production et diffusion de connaissance" et à la "diffusion d'outils", en favorisant la rencontre entre équipes de recherche et acteurs de terrain.

      2. Le projet Sexpert : Comprendre et agir avec les jeunes (Philippe Martin - INSERM)

      Le projet Sexpert, issu d'une thèse et financé par l'ANR, se concentre sur la santé sexuelle et reproductive des 15-24 ans. Il vise à développer, mettre en œuvre et évaluer une action d'éducation à la sexualité et de promotion de la santé sexuelle.

      Enjeux et préoccupations des jeunes : La jeunesse est une période marquée par l'autonomisation, la socialisation et des "enjeux de santé sexuelle avec des questionnements, des intérêts, des besoins d'information".

      La santé sexuelle "englobe de manière globale les questions de vie affective, sexuelle, relationnelle et reproductive incluant la non-discrimination, le plaisir sexuel ou encore les identités sexuelles et de genre qui sont bien évidemment des sujets centraux dans la vie des jeunes."

      Au-delà des risques : Si les IST, les violences ou les grossesses non désirées sont des préoccupations, la santé sexuelle doit aussi être pensée sous l'angle des "comportements favorables de santé", comme l'usage de protections, le consentement, et les "relations positives".

      • Approche participative : Les stratégies internationales et nationales prônent une "approche participative" et l'utilisation de "différents leviers éducatifs".

      Le projet Sexpert a "questionné finalement les points de vue des jeunes sur leur préoccupation générale de santé sexuelle mais aussi sur leurs propositions concrètes en terme d'action d'éducation qu'on pourrait mettre en place en éducation à la sexualité sur Internet et par les nouveaux outils de communication."

      • Perceptions des jeunes :Période complexe : La période adolescente et jeune adulte est "peu simple" et marquée par de "nombreux enjeux de vie qui dépassaient strictement le cadre professionnel".

      • Recherche d'information : Les jeunes se tournent vers leurs "proches, leurs familles, leurs amis" et les "professionnels". Internet n'est pas toujours le premier recours, sauf pour des questions immédiates (IST, contraception).

      • Difficulté à formuler les questions : La "gêne" est une "vraie barrière à la communication sur des questions et des problématiques de santé sexuelle". Richie (24 ans) exprime : "j'aurais trouvé gênant de matérialiser les questions que je me posais que ce soit sur Internet ou dans la vraie vie".

      • Priorités diverses : Certains jeunes ne considèrent pas toujours la vie affective et sexuelle comme une priorité immédiate, comme Els (16 ans) : "Je ne me pose pas forcément de questions, je prends les choses comme elles viennent et puis je ne me prends pas trop la tête avec ça".

      • Besoin d'intervenants spécialisés : Les jeunes expriment un besoin d'intervenants spécialisés sur les "dimensions émotionnelles, les IST, les violences ou encore les questions de contraception".

      • Importance du climat de confiance : Pour aborder des sujets intimes, "un climat de confiance" est essentiel, ce qui a été observé lors des focus groups. Initialement centrés sur IST/contraception, les discussions se sont élargies à la "déconstruction des normes de genre, la question de plaisir et également des questions liées à la communication" une fois la confiance établie. Exemples de sujets importants pour les jeunes : "Tu es un garçon, les règles ça te concerne aussi", "Le plaisir, c'est être libre", "Le consentement, c'est communiquer".

      • Propositions concrètes des jeunes pour l'éducation sexuelle numérique :Contenus éducatifs : Informations "valides, crédibles et bien classées", couvrant la santé sexuelle de manière globale mais aussi des sujets plus généraux liés à la vie des jeunes (santé mentale, autonomisation). Le contenu ne doit pas être "trop institutionnel".

      • Plateforme : Doit être "sécurisée, modérée et personnalisée", avec des "espaces de réponse à leurs questions".

      • Ressources : Offrir des "ressources géolocalisées" pour cibler les services proches des jeunes.

      • Dispositif Sexpert (fin 2023) : Intégrera "des espaces informationnels, des espaces interactifs et des activités ludiques" dans un "espace sécurisé, modéré et également participatif et interactif". Une évaluation mesurera l'amélioration des "connaissances, attitudes positives et comportements favorables de santé sexuelle".

      3. Actions du SIMS de l'Université de Toulouse (Benedict Allard & Pascal Faget)

      Le Service de Santé des Étudiants (SIMS) de l'Université de Toulouse, obligatoire dans toutes les universités françaises, intervient auprès de plus de 100 000 étudiants.

      Consultations de sexologie : Mises en place depuis 2020.

      Le Dr Faget, médecin généraliste et sexologue, pose systématiquement la question * des violences ("Est-ce que vous avez été victime ou témoin de violence physique ou sexuelle ?") et * de la sexualité ("Est-ce que vous avez des questions en lien avec la sexualité ?") * à tous les patients, quel que soit le motif de consultation, pour "ouvrir une porte".

      Outils pédagogiques : Utilisation de modèles 3D du clitoris, livres ("le petit manuel de sex education") et podcasts pour faciliter la conversation.

      Actions de prévention systématiques :Vidéo "La tasse de thé" : Diffusée "systématiquement lors des rentrées" pour expliquer le consentement de manière claire et non violente.

      "Si vous comprenez à quel point il est ridicule de forcer quelqu'un à boire du thé quand il n'en veut pas et que vous êtes capable de comprendre quand quelqu'un ne veut pas de thé, alors pourquoi est-il si difficile de le comprendre quand on parle de sexe ? Qu'il s'agisse de thé ou de sexe, le consentement est tout ce qui compte."

      Pièce interactive "Le procès de King Kong" : Créée pour les écoles d'ingénieurs pour aborder les violences sexuelles en milieu étudiant et encourager l'intelligence collective.

      Forums de santé sexuelle : Organisés sur les campus et dans les "villes d'équilibre" (Albi, Castres, Montauban, Tarbes, Cahors, Rodez), regroupant divers partenaires associatifs et institutionnels, permettant aux étudiants de s'informer de stand en stand.

      Consultations en visio : Disponibles pour les étudiants éloignés de Toulouse.

      Implication des pairs :Étudiants Relais Santé (ERS) : Environ 20 étudiants sont formés chaque année à la prévention sur toutes les thématiques de santé étudiante, y compris la santé sexuelle. Ils "nous aident à mettre en place des actions qui soient adaptées au public dans le langage du public dans les us et coutumes du public". Ils créent des quizz et des concours de dessins (ex: le tyrannosaure avec le préservatif).

      Cafés Sexo : Des moments d'échanges animés par le Dr Faget à la demande des associations étudiantes ou des BDE, abordant des sujets comme le consentement, l'identité de genre, l'orientation sexuelle, la pornographie, le désir et le plaisir. L'objectif est de parler de "sexualité et non de sa sexualité", créant un espace de "participation" et de "respect".

      Diffusion de ressources :Podcasts sur Campus FM : Enregistrements de 10 minutes sur des thèmes variés (les premières fois, le consentement, etc.), accessibles en ligne.

      Outils visuels : Affiches comme le post d'Hélène Pouille sur le consentement ("être à l'écoute de ce qu'on ressent et demander à l'autre", "une seule hésitation, c'est non") et "la Licorne du genre" pour expliquer le sexe assigné à la naissance, l'identité de genre, l'expression du genre et l'attirance, afin de lutter contre l'homophobie et la transphobie.

      Formation des professionnels : Information des collègues (médecins, psychologues, infirmiers, assistants sociaux) sur la légitimité à parler de sexualité avec les jeunes et l'utilisation d'outils, afin que le sujet ne soit "plus un tabou au SIMS de Toulouse".

      Service Sanitaire en Santé : Participation à la formation des étudiants en santé (médecine, pharmacie, sage-femme, infirmier) au sein de ce dispositif pour les préparer à ouvrir le dialogue sur la santé sexuelle.

      Alignement avec la Charte d'Ottawa : Les actions du SIMS s'inscrivent dans une approche globale de promotion de la santé, visant à "réorienter les services de santé" vers la promotion, "créer des milieux favorables" (gratuité des préservatifs et dépistages), "développer les aptitudes personnelles" (cafés sexo), "renforcer l'action communautaire" (ERS) et contribuer à "établir des politiques publiques saines".

      4. Formation des personnels de l'Éducation Nationale (Ingrid Desplat - Infirmière conseillère technique auprès du recteur de l'académie de Toulouse)

      L'Académie de Toulouse s'engage dans la formation des personnels à l'éducation à la sexualité, soulignant que cette éducation est un "droit" pour les élèves (trois séances par an et par groupe d'âge homogène, fixées par la circulaire de 2018).

      Formateurs : L'académie compte huit formateurs aux profils variés (infirmiers, CPE, professeurs des écoles, professeurs spécialisés), certains ayant des diplômes universitaires en sexologie ou éducation à la sexualité, d'autres une grande expérience de terrain.

      Public formé : Environ 200 à 250 personnels volontaires sont formés chaque année. Parcours de formation : Un parcours structuré est mis en place :

      Niveau 1 (3 jours) : Abord généraliste, circulaire de 2018, compétences psychosociales, homosexualité, orientation sexuelle, et surtout "les besoins des adolescents" pour comprendre certains comportements (ex: masturbation en classe) et "apporter des éléments de réponse". L'accent est mis sur la posture de l'intervenant.

      Niveau 2 (3 jours) : Approfondissement sur des sujets plus complexes comme le genre, qui "suscites le plus d'émotion" et "questionne le plus les adultes formés".

      Un an d'écart est recommandé entre les deux niveaux pour permettre une "réflexion" personnelle sur la posture.

      Approche pédagogique : L'éducation à la sexualité doit être une "approche globale, positive et bienveillante".

      Elle doit intégrer des éléments "psycho-émotionnels", "juridiques et sociaux", et "biologiques" (ce qui marque un changement par rapport aux approches antérieures centrées uniquement sur la biologie et la prévention des IST/grossesses).

      Compétences des intervenants : La formation vise à développer des compétences telles que la capacité à "réguler la parole", "savoir rebondir", "prendre en compte les représentations culturelles", "respecter le silence", adopter des "attitudes chaleureuses" et une "posture non moralisatrice", être "à l'aise avec la sexualité" et "s'adresser aux filles et aux garçons".

      Protection des jeunes : L'éducation à la sexualité est un moyen de "protéger les jeunes", notamment face aux violences intrafamiliales et à l'inceste. "Si on parle jamais sexualité, le jeune qui en est victime, à qui se confie ?"

      Modalités d'accès à la formation : Les personnels volontaires peuvent s'inscrire via le Plan Académique de Formation (PRAF) dans la rubrique "second degré". Des formations d'initiative locale sont également possibles à la demande des chefs d'établissement.

      Réticences : Face aux réticences (souvent liées à l'idée que la sexualité est "du domaine de l'intime"), l'Académie rappelle que des règles sociales comme le consentement sexuel doivent être enseignées pour "éviter les violences sexuelles".

      Le personnel formé est légitime à intervenir sur ces sujets, dans un cadre réglementaire qui permet une intervention sereine.

      5. Thèmes transversaux et idées fortes

      Plusieurs idées clés émergent de l'ensemble des interventions :

      Approche Positive et Globale : La santé sexuelle est bien plus que la prévention des risques. Elle englobe le bien-être physique, émotionnel, mental et social, le plaisir, les relations positives, le consentement, et les identités de genre. Il s'agit de promouvoir une sexualité "épanouie".

      Importance du Consentement : Le consentement est un pilier fondamental de l'éducation sexuelle, expliqué de manière claire et adaptée (ex: vidéo "La tasse de thé", post d'Hélène Pouille). Il doit être "clair, libre, éclairé, actualisé".

      Participation et Implication des Jeunes : Essentielle pour des actions pertinentes. Les jeunes sont co-concepteurs des contenus (projet Sexpert) et acteurs de la prévention (Étudiants Relais Santé). Leurs préoccupations et leurs manières de s'informer doivent être prises en compte.

      Rôle des Pairs : Les discussions entre pairs et la possibilité de se reconnaître en l'autre sont cruciales pour les jeunes (ex: Jonathan sur la recherche d'autres personnes gay, les cafés sexo).

      Lever les Tabous et la Gêne : La difficulté à formuler des questions et la gêne sont des obstacles majeurs. Les professionnels doivent oser poser les questions et créer un climat de confiance pour libérer la parole.

      Diversité des Besoins et des Publics : Les actions doivent être adaptées à la "diversité des préoccupations des jeunes", incluant les identités de genre et les orientations sexuelles, et toucher les publics minorisés (personnes en situation de handicap, de maladie chronique).

      Accès à l'Information Validée et Crédible : Les jeunes recherchent des informations fiables, non "trop institutionnelles". Les outils numériques (podcasts, plateformes interactives) sont des compléments aux actions de terrain.

      Formation et Posture des Professionnels : Cruciales pour une éducation sexuelle efficace. Les intervenants doivent être à l'aise avec le sujet, adopter une posture non moralisatrice, et être formés pour aborder les dimensions psycho-émotionnelles, juridiques et biologiques.

      La légitimité de parler de sexualité doit être affirmée.

      Partenariats et Rôle des Réseaux : La collaboration entre différentes structures (IREPS, INSERM, universités, associations, Éducation Nationale) est essentielle pour une approche globale et cohérente sur l'ensemble du territoire, y compris dans les zones éloignées.

      Les ressources géolocalisées facilitent l'accès aux services.

      Au-delà de la Connaissance Scientifique : Les besoins des jeunes vont au-delà de la simple information biologique et incluent des aspects relationnels, émotionnels et de communication.

    1. Note de synthèse : Promotion des bonnes pratiques solaires

      Cette note de synthèse a pour objectif de résumer les principaux thèmes, idées et faits importants concernant la promotion des bonnes pratiques solaires, en se basant sur les extraits de la "Matinale du Drapps : Promouvoir des bonnes pratiques solaires - Enjeux et pistes d’actions".

      Elle inclura des citations pertinentes issues des sources originales.

      Introduction :

      Contexte et enjeux de la prévention solaire La Direction Générale de la Santé a souligné en 2020 la nécessité de recommandations sanitaires pour les indices UV, en particulier pour les populations à risque.

      Malgré les effets positifs du soleil (notamment la synthèse de vitamine D), une exposition excessive aux UV est nocive et peut entraîner des cancers de la peau et un vieillissement prématuré.

      Il est crucial de trouver un équilibre entre une exposition optimale pour la vitamine D et une protection adéquate.

      Chiffres clés et impacts sur la santé :

      80% des dommages liés aux UV sont provoqués avant 18 ans, les enfants étant plus exposés que les adultes. Un cancer sur trois est un cancer de la peau. Le coût de traitement du mélanome est estimé à 225 millions d'euros par l'INCA.

      20 millions de personnes sont aveugles dans le monde à cause de la cataracte, l'exposition solaire étant un facteur de risque majeur.

      Les effets sur la santé se manifestent à court, moyen et long terme :

      • Court/Moyen terme : Brûlures, coups de soleil, atteintes aux yeux (photokératites, photoconjonctivites), allergies cutanées. Le bronzage lui-même est une réaction de défense de la peau, signalant une agression.
      • Long terme : Cataracte, vieillissement prématuré de la peau (photo-vieillissement avec rides et taches), et cancers de la peau.
      • Carcinomes : Environ 90% des cancers de la peau, très fréquents (130 000 à 230 000 cas/an, en augmentation). Leur pronostic est généralement bon, mais ils sont liés à une exposition prolongée (par exemple, professionnelle) et nécessitent de nombreuses chirurgies coûteuses.
      • Mélanomes : 10% des cancers de la peau, plus rares mais plus graves (environ 18 000 cas/an et 2 000 décès). 83% d'entre eux sont liés à des expositions aux UV, notamment des expositions intenses et intermittentes, souvent durant l'enfance ou les vacances estivales. Ces cancers sont donc majoritairement évitables par une meilleure protection solaire.

      Recommandations de protection solaire

      Les recommandations actuelles de l'Institut National du Cancer (INCK) sont claires :

      • Rechercher l'ombre au maximum, notamment entre 12h et 16h, période de rayonnement maximal.
      • Privilégier la protection vestimentaire (t-shirt à manches, chapeau à large bord, lunettes de soleil). Ces moyens sont prioritaires sur la crème solaire.
      • La crème solaire est un complément, à utiliser sur les zones découvertes. Il est souligné que "trop souvent la crème solaire est utilisée pour justement enlever les vêtements et pour augmenter son exposition et c'est quelque chose qui peut être assez néfaste."
      • Se protéger même par temps nuageux, car le rayonnement UV n'est pas toujours associé à la chaleur.
      • Le rayonnement est amplifié par la réverbération (eau, montagne).
      • Vigilance maximale avec les enfants : limiter leur exposition au maximum, ne pas exposer un enfant de moins d'un an, et leur apprendre les bons réflexes.
      • L'indice UV (disponible sur Météo France) est un outil éducatif. La protection est nécessaire à partir d'un indice 3, et doit être renforcée à partir de 8.
      • Évolution de la représentation sociale du bronzage et comportements des Français

      Historiquement, le bronzage a connu une inversion de sa signification sociale :

      • Jusqu'à la fin du 19e siècle : Signe de prolétariat (travailleurs agricoles), la peau blanche étant associée à la noblesse.
      • Début 20e siècle : Le bronzage est de moins en moins associé à la pauvreté.
      • Années 30 (premiers congés payés) : Le bronzage devient "synonyme de succès, d'aisances financière, de loisirs."
      • Années 80-90 : Apogée de la mode du bronzage, avec l'explosion des cabines UV et une forte médiatisation. Les premières recommandations sanitaires apparaissent à cette période.
      • Aujourd'hui : Les dangers sont bien connus, mais la protection reste insuffisante. Le bronzage est toujours associé à la "bonne santé, de bien-être, de bonne mine, de beauté", véhiculant une image positive. Il y a une confusion avec la synthèse de vitamine D, nécessitant en réalité seulement "environ 15 minutes par jour" d'exposition, bien moins que le temps passé à bronzer.

      Comportements des Français (Baromètre Cancer 2005, 2010, 2015) : * * Les moyens de protection sont insuffisamment utilisés, notamment la protection vestimentaire, en diminution. * Différenciation des comportements :Les femmes se protègent globalement mieux, utilisant plus l'ombre, la crème solaire et les lunettes. Les hommes privilégient les t-shirts et chapeaux. * Protection insuffisante chez les 15-24 ans (population sous-protégée et surexposée). * Un gradient social existe : les personnes moins diplômées sont globalement moins protégées. * Les phototypes plus foncés se protègent moins, bien que les lunettes de soleil restent indispensables pour tous. * Les résidents du nord ont moins le réflexe de se protéger aux heures critiques. * La protection des enfants s'est améliorée, les parents protégeant mieux leurs enfants qu'eux-mêmes. * Les connaissances augmentent, mais les fausses croyances persistent, notamment sur les conséquences des coups de soleil dans l'enfance. * Actions de prévention solaire : Exemples et initiatives * Plusieurs niveaux d'actions sont mis en œuvre :

      1. Niveau International :

      • Programme InterSun (OMS) : Vise à informer sur les effets des UV, encourager les pays à réduire les risques et fournir des conseils pratiques. Axes clés : surveillance et prédiction des risques (liés aux changements environnementaux et comportementaux), promotion de l'indice UV comme outil éducatif, et protection solaire des enfants via programmes éducatifs scolaires.
      • Programme SunSmart (Australie) : Référence mondiale en prévention du cancer de la peau, pays à l'incidence très élevée. Objectifs : réduire l'incidence, éduquer le public via campagnes (notamment l'emblématique "Slip, Slop, Slap, Seek and Slide"), et mettre en œuvre des politiques de protection (écoles, lieux de travail).
      • Impact : Environ 300 000 cancers de la peau évités, 1 000 vies sauvées, diminution de l'incidence chez les plus jeunes. Impact économique positif : "pour 1 dollar dépensé il y a eu un gain de 8,70 dans les 20 prochaines années."

      2. Niveau National (France) :

      • Campagne nationale annuelle (INCK) : Au printemps, informe la population sur les risques et conseils de prévention (ex: "l'ombre, c'est l'endroit le plus cool de l'été").
      • Programmes d'éducation : "Vivre avec le soleil" (Sécurité Solaire), programme probant pour les écoles maternelles et primaires, basé sur une approche expérientielle et intégrable aux programmes scolaires (sciences).

      3. Niveau Local/Régional :

      • Projets d'urbanisme et de végétalisation : Visent à créer des zones d'ombre, réduisant les îlots de chaleur et l'exposition aux UV (ex: cours oasis dans les écoles). Ces projets peuvent bénéficier d'appels à projet comme "Zéro Expo" de l'INCK.
      • Actions ciblées d'éducation à la santé :Étude PRISME (Santé Publique France Occitanie) : Recherche interventionnelle menée auprès de touristes en Occitanie (2019).
      • Constat : Forte exposition intentionnelle ("sunbathing"), utilisation prioritaire de la crème solaire au détriment d'autres moyens, coups de soleil fréquents. Le littoral Occitan (200km, fort rayonnement UV, 8 millions de touristes/an) est un contexte à risque.
      • Objectifs : Identifier les déterminants de la protection solaire (incluant les déterminants sociaux) et évaluer l'efficacité de deux interventions : une basée sur les messages d'apparence physique (photo-vieillissement) et une sur les messages sanitaires (cancer, yeux).
      • Résultats : Protection insuffisante, notamment le port du t-shirt. 3/4 des touristes passent du temps à bronzer.
      • Populations sous-protégées : 15-24 ans (et 12-14 ans pour les lunettes), hommes (crème solaire, lunettes), femmes (chapeau, t-shirt), peaux mates/moins sensibles, personnes à faible niveau d'étude, résidents du nord. Les connaissances et les fausses croyances, l'attirance pour le bronzage et le manque d'encouragement de l'entourage sont des déterminants.
      • Efficacité des interventions :Intervention sanitaire : Augmente la protection à court terme, agit sur crème solaire et lunettes, touche les peaux sensibles et les niveaux d'études supérieurs.
      • Intervention basée sur l'apparence physique : Augmente la protection à court et long terme, diminue l'exposition (évitement 12h-16h), touche les peaux sensibles et les niveaux d'études moins élevés (jusqu'au bac).
      • Perspectives : Renouveler les campagnes, cibler les 15-24 ans et femmes exposées intentionnellement, les personnes socialement moins favorisées. Intégrer des messages sur le photo-vieillissement, apporter des connaissances, dénormaliser le bronzage, déployer des interventions dans divers milieux (scolaire, travail, touristique, sportif) et via différents canaux. Encourager les actions locales (zones d'ombre, accès aux moyens de protection, adaptation des horaires d'activités, sensibilisation des professionnels du tourisme, affichage de l'indice UV).
      • Semaine des Épidories (Épidor, Institut du Cancer de Montpellier) : Programme éducatif pour enfants de 7 à 11 ans, basé sur le modèle COM-B (Capacité, Opportunité, Motivation, Comportement).
      • Contenu : Quatre séances animées par les enseignants, abordant les effets du soleil, la sensibilité de la peau (phototype), les rayons UV et l'indice UV, et les moyens de protection (avec une montre UV). Des prolongements sont proposés en famille.
      • Étude de faisabilité : Impact significatif (faible à important) sur le comportement de protection solaire, les attitudes des enfants et leur niveau de connaissance. Des analyses plus poussées et une évaluation à plus grande échelle et à long terme sont envisagées.
      • Chiffres (2024) : 200 classes, 4569 élèves du CP au CM2.
      • Journée des Épidories : Journée récompense pour 4 classes tirées au sort, avec des ateliers ludiques (professeur dermatologue, jeu de l'ombre, four solaire, carte du monde des protections, jeu de l'oie, constitution de sac à dos pour randonnée).
      • Autres actions : Animations sur l'espace ludo-éducatif pour maternelles (3-6 ans), ateliers parents-enfants, formations et conférences pour étudiants et professionnels de la petite enfance.
      • Déterminants structurels : L'approche COM-B permet de les considérer, mais les intervenants reconnaissent un impact limité sur ces déterminants, malgré une volonté de les prendre en compte (ex: projets de végétalisation des cours d'école).
      • Tournée "Bon été, bon réflexe" (ARS Occitanie, C2DS, Primum non Nocere) : Opération itinérante de sensibilisation aux dangers estivaux depuis 2021.
      • Objectifs : Diffuser des messages de prévention sur les dangers estivaux de manière positive, adapter le discours aux publics et aux spécificités territoriales (littoral vs. intérieur des terres), et former des "animateurs relais" pour démultiplier les actions.
      • Thématiques des ateliers (participatifs et ludiques) : Prévention solaire, baignade sécurisée, consommation de sucre, moustiques tigres/tiques, sport et santé.
      • Moyens : Matériel repérable (arche, tables, barnums, véhicule siglé), espace informatif, goodies (casquettes, chapeaux), deux animateurs dédiés. Des fiches "bons gestes" sont distribuées.
      • Bilan (2024) : Plus de 2900 personnes touchées (+25% vs 2023). Les interventions ont lieu sur les marchés, zones de baignade (mers, lacs, rivières), parcs de loisirs, villes touristiques. Les animateurs relais ont démultiplié 59 ateliers, sensibilisant plus de 3500 personnes.
      • Atelier soleil : Utilise une "nappe des dangers du soleil" interactive, permettant d'échanger sur les UV, l'indice UV, les effets à court et long terme. Adaptation du discours à l'âge du public. Interroge sur les situations de protection de personnages (incluant différents phototypes). Met en évidence l'exposition lors d'activités quotidiennes (promenade, vélo). Utilise un totem pour rappeler les messages clés (règle ABCDE pour les mélanomes).
      • Discussion et perspectives
      • Difficulté d'accès aux dermatologues : Soulignée comme un frein majeur au dépistage des mélanomes. Il est suggéré de passer par le médecin traitant et de pratiquer l'auto-diagnostic (règle ABCDE).
      • Composition des crèmes solaires : Sujet de débat constant. Bien que certaines compositions aient été controversées (octocrylène), il est noté que les crèmes sont "plus propres aujourd'hui qu'elles ne l'étaient auparavant". La crème solaire reste un complément aux protections physiques, et son choix doit se faire sur sa capacité à protéger (SPF, UVA/UVB, résistance à l'eau) et sa composition environnementale.
      • Impact de l'alimentation et autres comportements : Une carence en vitamine D peut provenir de l'alimentation, et l'exposition solaire n'est pas la seule solution.
      • Réverbération des UV : Très importante sur le sable (+15%), l'écume de l'eau (+25%), et surtout la neige (+80%), amplifiant significativement l'exposition même à l'ombre ou dans l'eau.
      • Rayonnement des écrans : Non abordé, mais pourrait faire l'objet de futures discussions.
      • Pollution des crèmes solaires : La question de l'impact environnemental des crèmes solaires sur les milieux aquatiques est soulevée, et il est conseillé de choisir des produits avec des logos spécifiques.
      • L'équilibre des moyens de protection : Il est complexe de jongler entre l'ombre, les vêtements et la crème solaire, mais en se tenant aux bases (ombre 12h-16h, vêtements, crème pour les zones découvertes), la protection devient plus simple.

      En conclusion, la promotion des bonnes pratiques solaires est un enjeu de santé publique majeur, nécessitant une approche multiforme et adaptée aux différentes populations, environnements et représentations sociales.

      Les initiatives présentées, qu'elles soient de recherche ou de terrain, montrent la volonté de cultiver une "culture commune [...] plus saine de nos pratiques solaires".

    1. The problems we face fall in one of three areas: direct control (problems involving ourown behavior); indirect control (problems involving other people's behavior); or nocontrol (problems we can do nothing about, such as our past or situational realities). Theproactive approach puts the first step in the solution of all three kinds of problems withinour present Circle of Influence.Direct control problems are solved by working on our habits. They are obviously withinour Circle of Influence. These are the "Private Victories" of Habits 1, 2, and 3.Indirect control problems are solved by changing our methods of influence. These are the"Public Victories" of Habits 4, 5, and 6. I have personally identified over 30 separatemethods of human influence -- as separate as empathy is from confrontation, as separateas example is from persuasion. Most people have only three or four of these methods intheir repertoire, starting usually with reasoning, and, if that doesn't work, moving toflight or fight. How liberating it is to accept the idea that I can learn new methods ofhuman influence instead of constantly trying to use old ineffective methods to "shape up"someone else!No control problems involve taking the responsibility to change the line on the bottom onour face -- to smile, to genuinely and peacefully accept these problems and learn to livewith them, even though we don't like them. In this way, we do not empower theseproblems to control us. We share in the spirit embodied in the Alcoholics Anonymousprayer, "Lord, give me the courage to change the things which can and ought to bechanged, the serenity to accept the things which cannot be changed, and the wisdom toknow the difference."

      1) direct control - problems involving our own behavior; solved by working on our habits; within circle of influence 2) indirect control - problems involving other people's behavior; solved by changing our methods of influence 3) no control - problems outside our control; accept the problems and learn to live with them

    1. Reviewer #2 (Public review):

      Summary:

      The current paper consists of two parts. The first part is the rigorous feature optimization of the MEG signal to decode individual finger identity performed in a sequence (4-1-3-2-4; 1~4 corresponds to little~index fingers of the left hand). By optimizing various parameters for the MEG signal, in terms of (i) reconstructed source activity in voxel- and parcel-level resolution and their combination, (ii) frequency bands, and (iii) time window relative to press onset for each finger movement, as well as the choice of decoders, the resultant "hybrid decoder" achieved extremely high decoding accuracy (~95%).

      In the second part of the paper, armed with the successful 'hybrid decoder,' the authors asked how neural representation of individual finger movement that is embedded in a sequence, changes during a very early period of skill learning and whether and how such representational change can predict skill learning. They assessed the difference in MEG feature patterns between the first and the last press 4 in sequence 41324 at each training trial and found that the pattern differentiation progressively increased over the course of early learning trials. Additionally, they found that this pattern differentiation specifically occurred during the rest period rather than during the practice trial. With a significant correlation between the trial-by-trial profile of this pattern differentiation and that for accumulation of offline learning, the authors argue that such "contextualization" of finger movement in a sequence (e.g., what-where association) underlies the early improvement of sequential skill. This is an important and timely topic for the field of motor learning and beyond.

      Strengths:

      The use of temporally rich neural information (MEG signal) has a significant advantage over previous studies testing sequential representations using fMRI. This allowed the authors to examine the earliest period (= the first few minutes of training) of skill learning with finer temporal resolution. Through the optimization of MEG feature extraction, the current study achieved extremely high decoding accuracy (approx. 94%) compared to previous works. The finding of the early "contextualization" of the finger movement in a sequence and its correlation to early (offline) skill improvement is interesting and important. The comparison between "online" and "offline" pattern distance is a neat idea.

      Weaknesses:

      One potential weakness, in terms of the generality, is that the study assessed the single sequence, the "41324" across all participants. Future confirmation test of using different sequences would be important.

    2. Reviewer #3 (Public review):

      Summary:

      One goal of this paper is to introduce a new approach for highly accurate decoding of finger movements from human magnetoencephalography data via dimension reduction of a "multi-scale, hybrid" feature space. Following this decoding approach, the authors aim to show that early skill learning involves "contextualization" of the neural coding of individual movements, relative to their position in a sequence of consecutive movements. Furthermore, they aim to show that this "contextualization" develops primarily during short rest periods interspersed with skill training, and correlates with a performance metric which the authors interpret as an indicator of offline learning.

      Strengths:

      A strength of the paper is the innovative decoding approach, which achieves impressive decoding accuracies via dimension reduction of a "multi-scale, hybrid space". This hybrid-space approach follows the neurobiologically plausible idea of concurrent distribution of neural coding across local circuits as well as large-scale networks.

      Weaknesses:

      A clear weakness of the paper lies in the authors' conclusions regarding "contextualization". Several potential confounds, which partly arise from the experimental design, and which are described below, question the neurobiological implications proposed by the authors, and offer a simpler explanation of the results. Furthermore, the paper follows the assumption that short breaks result in offline skill learning, while recent evidence casts doubt on this assumption.

      Specifically:

      The authors interpret the ordinal position information captured by their decoding approach as a reflection of neural coding dedicated to the local context of a movement (Figure 4). One way to dissociate ordinal position information from information about the moving effectors is to train a classifier on one sequence, and test the classifier on other sequences that require the same movements, but in different positions (Kornysheva et al., Neuron 2019). In the present study, however, participants trained to repeat a single sequence (4-1-3-2-4). As a result, ordinal position information is potentially confounded by the fixed finger transitions around each of the two critical positions (first and fifth press). Across consecutive correct sequences, the first keypress in a given sequence was always preceded by a movement of the index finger (=last movement of the preceding sequence), and followed by a little finger movement. The last keypress, on the other hand, was always preceded by a ring finger movement, and followed by an index finger movement (=first movement of the next sequence). Figure 3 - supplement 5 shows that finger identity can be decoded with high accuracy (>70%) across a large time window around the time of the keypress, up to at least {plus minus}100 ms (and likely beyond, given that decoding accuracy is still high at the boundaries of the window depicted in that figure). This time window approaches the keypress transition times in this study. Given that distinct finger transitions characterized the first and fifth keypress, the classifier could thus rely on persistent (or "lingering") information from the preceding finger movement, and/or "preparatory" information about the subsequent finger movement, in order to dissociate the first and fifth keypress. Currently, the manuscript provides little evidence that the context information captured by the decoding approach is more than a by-product of temporally extended, and therefore overlapping, but independent neural representations of consecutive keypresses that are executed in close temporal proximity - rather than a neural representation dedicated to context.

      During the review process, the authors pointed out that a "mixing" of temporally overlapping information from consecutive keypresses, as described above, should result in systematic misclassifications and therefore be detectable in the confusion matrices in Figures 3C and 4B, which indeed do not provide any evidence that consecutive keypresses are systematically confused. However, such absence of evidence (of systematic misclassification) should be interpreted with caution. The authors also reported that there was only a weak relation between inter-press intervals and "online contextualization" (Figure 5 - figure supplement 6), however, their analysis suprisingly includes a keypress transition that is shared between OP1 and OP5 ("4-4"), rather than focusing solely on the two distinctive transitions ("2-4" and "4-1").

      Such temporal overlap of consecutive, independent finger representations may also account for the dynamics of "ordinal coding"/"contextualization", i.e., the increase in 2-class decoding accuracy, across Day 1 (Figure 4C). As learning progresses, both tapping speed and the consistency of keypress transition times increase (Figure 1), i.e., consecutive keypresses are closer in time, and more consistently so. As a result, information related to a given keypress is increasingly overlapping in time with information related to the preceding and subsequent keypresses. Furthermore, learning should increase the number of (consecutively) correct sequences, and, thus, the consistency of finger transitions. Therefore, the increase in 2-class decoding accuracy may simply reflect an increasing overlap in time of increasingly consistent information from consecutive keypresses, which allows the classifier to dissociate the first and fifth keypress more reliably as learning progresses, simply based on the characteristic finger transitions associated with each. In other words, given that the physical context of a given keypress changes as learning progresses - keypresses move closer together in time, and are more consistently correct - it seems problematic to conclude that the mental representation of that context changes. During the review process, authors pointed at absence of evidence of a relation between tapping speed and "ordinal coding" (Figure 5 - figure supplement 7). However, a rigorous test of the idea that the mental representation of context changes would require a task design in which the physical context remains constant.

      A similar difference in physical context may explain why neural representation distances ("differentiation") differ between rest and practice (Figure 5). The authors define "offline differentiation" by comparing the hybrid space features of the last index finger movement of a trial (ordinal position 5) and the first index finger movement of the next trial (ordinal position 1). However, the latter is not only the first movement in the sequence, but also the very first movement in that trial (at least in trials that started with a correct sequence), i.e., not preceded by any recent movement. In contrast, the last index finger of the last correct sequence in the preceding trial includes the characteristic finger transition from the fourth to the fifth movement. Thus, there is more overlapping information arising from the consistent, neighbouring keypresses for the last index finger movement, compared to the first index finger movement of the next trial. A strong difference (larger neural representation distance) between these two movements is, therefore, not surprising, given the task design, and this difference is also expected to increase with learning, given the increase in tapping speed, and the consequent stronger overlap in representations for consecutive keypresses.

      A further complication in interpreting the results stems from the visual feedback that participants received during the task. Each keypress generated an asterisk shown above the string on the screen. It is not clear why the authors introduced this complicating visual feedback in their task, besides consistency with their previous studies. The resulting systematic link between the pattern of visual stimulation (the number of asterisks on the screen) and the ordinal position of a keypress makes the interpretation of "contextual information" that differentiates between ordinal positions difficult. While the authors report the surprising finding that their eye-tracking data could not predict asterisk position on the task display above chance level, the mean gaze position seemed to vary systematically as a function of ordinal position of a movement - see Figure 4 - figure supplement 3.

      The authors report a significant correlation between "offline differentiation" and cumulative micro-offline gains. However, to reach the conclusion that "the degree of representational differentiation -particularly prominent over rest intervals - correlated with skill gains.", the critical question is rather whether "offline differentiation" correlates with micro-offline gains (not with cumulative micro-offline gains). That is, does the degree to which representations differentiate "during" a given rest period correlate with the degree to which performance improves from before to after the same rest period (not: does "offline differentiation" in a given rest period correlate with the degree to which performance has improved "during" all rest periods up to the current rest period - but this is what Figure 5 - figure supplements 1 and 4 show).

      The authors follow the assumption that micro-offline gains reflect offline learning. However, there is no compelling evidence in the literature, and no evidence in the present manuscript, that micro-offline gains (during any training phase) reflect offline learning. Instead, emerging evidence in the literature indicates that they do not (Das et al., bioRxiv 2024), and instead reflect transient performance benefits when participants train with breaks, compared to participants who train without breaks, however, these benefits vanish within seconds after training if both groups of participants perform under comparable conditions (Das et al., bioRxiv 2024). During the review process, the authors argued that differences in the design between Das et al. (2024) on the one hand (Experiments 1 and 2), and the study by Bönstrup et al. (2019) on the other hand, may have prevented Das et al. (2024) from finding the assumed (lasting) learning benefit by micro-offline consolidation. However, the Supplementary Material of Das et al. (2024) includes an experiment (Experiment S1) whose design closely follows the early learning phase of Bönstrup et al. (2019), and which, nevertheless, demonstrates that there is no lasting benefit of taking breaks for the acquired skill level, despite the presence of micro-offline gains.

      Along these lines, the authors argue that their practice schedule "minimizes reactive inhibition effects", in particular their short practice periods of 10 seconds each. However, 10 seconds are sufficient to result in motor slowing, as report in Bächinger et al., elife 2019, or Rodrigues et al., Exp Brain Res 2009.

      An important conceptual problem with the current study is that the authors conclude that performance improves, and representation manifolds differentiate, "during" rest periods. However, micro-offline gains (as well as offline contextualization) are computed from data obtained during practice, not rest, and may, thus, just as well reflect a change that occurs "online", e.g., at the very onset of practice (like pre-planning) or throughout practice (like fatigue, or reactive inhibition).

      The authors' conclusion that "low-frequency oscillations (LFOs) result in higher decoding accuracy compared to other narrow-band activity" should be taken with caution, given that the critical decoding analysis for this conclusion was based on data averaged across a time window of 200 ms (Figure 2), essentially smoothing out higher frequency components.

    1. weaning

      weaning

      Sure! Let's delve into the term "weaning."

      English Explanation

      Weaning is the process of gradually introducing an infant or young animal to a more diverse diet while reducing dependence on breast milk or formula. This process typically occurs when the infant is around six months old, although the exact timing can vary. The primary goal of weaning is to transition the baby from exclusive breastfeeding to eating solid foods.

      There are several important aspects to consider during weaning:

      1. Timing: Weaning usually begins between four to six months, depending on the child’s readiness and pediatrician advice. Signs of readiness may include the ability to sit up without support, showing interest in food, and developing the ability to chew.

      2. Food Introduction: When weaning, it is usually advisable to start with single-grain cereals, pureed fruits, and vegetables. Gradually introducing different food groups helps the child to develop tastes for various flavors and textures.

      3. Emotional Aspects: Weaning can also be an emotional process for both the child and the caregiver. It requires patience and can sometimes lead to resistance as the child adjusts to the change.

      4. Health Considerations: During weaning, caregivers should ensure that the child still receives adequate nutrition, particularly if breastfeeding is significantly decreased. Parents often consult healthcare providers to discuss suitable food options and any necessary dietary adjustments.

      In summary, weaning is a significant developmental milestone that helps transition infants to a mixed diet, supporting their growth and development.


      Chinese Explanation (中文解释)

      断奶是逐渐引导婴儿或幼动物接受更为多样化饮食的过程,同时减少对母乳或配方奶的依赖。这个过程通常在婴儿大约六个月大时开始,尽管具体的时间可能会有所不同。断奶的主要目标是将宝宝从专注于母乳喂养过渡到吃固体食物。

      在断奶过程中,有几个重要的方面需要考虑:

      1. 时机: 断奶通常在四到六个月之间开始,这取决于孩子的准备情况和儿科医生的建议。准备的迹象包括能够独立坐起、对食物表现出兴趣,以及发展咀嚼能力。

      2. 食物引入: 在断奶时,通常建议从单一谷物的谷物、泥状水果和蔬菜开始。逐渐引入不同的食物群体能够帮助孩子培养对各种味道和质地的喜好。

      3. 情感方面: 断奶对孩子和看护者来说也可能是一个情感上的过程。需要耐心,有时孩子在适应这个变化时会表现出抵触。

      4. 健康考量: 在断奶期间,看护者应确保孩子仍获得足够的营养,特别是在母乳喂养显著减少的情况下。父母通常会咨询医疗提供者,以讨论适合的食物选择和必要的饮食调整。

      总之,断奶是一个重要的发展里程碑,帮助婴儿过渡到混合饮食,支持他们的生长与发展。

    2. sire

      sire

      The term "sire" has several meanings, primarily used in formal or historical contexts. Here's a thorough explanation in both English and Chinese:

      English Explanation:

      1. Definition: The word "sire" is traditionally used as a title of respect for a king or lord. It serves as a way to address or refer to someone of higher status or authority.

      2. Origin: The term originates from Middle English, derived from the Old French "sire," which means "lord," and is related to the Latin "senior," meaning "older" or "elder."

      3. Use in Royalty: In monarchies, subjects might address their king or queen as "Sire" to show respect and deference. It conveys a sense of reverence and acknowledges the noble status of the individual.

      4. Use in Animal Breeding: In zoology, particularly in horse or canine breeding, "sire" refers to the male parent. For example, a stallion that contributes to the gene pool of offspring may be called the sire.

      5. Broader Usage: Although its usage as a title has diminished in modern times, it might still be found in literature, historical texts, or in formal ceremonies.

      中文解释:

      1. 定义: “sire”( sire,父亲、尊敬的称谓)这个词主要在正式或历史背景中使用,通常用作对国王或领主的尊称。这是一种对高尚身份或权威人物的称呼。

      2. 起源: 该词源自中世纪英语,来自古法语“sire”,意为“领主”,与拉丁语“senior”相关,意指“年长”或“长者”。

      3. 在王室中的使用: 在君主制国家,臣民可能会称呼他们的国王或女王为“Sire”,以示尊重和敬意。这个词传达了一种崇敬的感觉,并承认了该个体的贵族地位。

      4. 在动物繁殖中的用途: 在动物学上,尤其是马或犬的繁殖中,“sire”用来指代雄性父母。例如,参与后代基因组合的种马可以被称为sire。

      5. 更广泛的用法: 尽管在现代用作称号的使用已减少,但在文学、历史文献或正式仪式中仍然可以找到。

      This thorough explanation covers the nuances of the term "sire" in both languages! If you need further details or specific examples related to this term, feel free to ask.

  2. Jun 2025
    1. devour

      devour

      Sure! Below is a thorough explanation of the word "devour" in both English and Chinese.

      English Explanation

      The word "devour" is a verb that typically means to eat something eagerly and in large amounts. It is often used to describe the act of consuming food with great enthusiasm or hunger. However, "devour" can also have metaphorical meanings, such as being consumed by emotions or being engrossed in an activity, like reading a book.

      1. Etymology: The word "devour" comes from the Latin word "devorare," which means "to swallow down." This reflects the intense and often voracious way in which something is consumed.

      2. Uses in Sentences:

      3. Literal Use: "After the long hike, I was so hungry that I devoured the sandwich in just a few bites."
      4. Metaphorical Use: "She devoured the novel, staying up all night to finish it."

      5. Synonyms: Some synonyms for "devour" include "gobble," "consume," "feast on," and "ingest."

      6. Related Forms: The noun form is "devourer," which refers to someone who devours, and there is also the adjective "devouring," which describes the intense action of consuming something.

      中文解释

      “devour” 是一个动词,通常意味着贪婪地和大量地吃东西。它常用来描述用极大的热情或饥饿感来消耗食物的行为。然而,“devour” 也可以有比喻意义,比如被情感吞噬或沉醉于某项活动,如阅读一本书。

      1. 词源: “devour” 这个词源自拉丁语“devorare”,意为“吞下去”。这反映了以强烈和通常是贪婪的方式消耗某物的方式。

      2. 句子中的使用

      3. 字面意思: “长途徒步旅行后,我非常饿,以至于在几口之内就devoured了三明治。”
      4. 比喻用法: “她devoured了那本小说,通宵达旦地阅读完。”

      5. 同义词: “devour”的一些同义词包括“gobble”(狼吞虎咽)、“consume”(消耗)、“feast on”(大吃特吃)和“ingest”(摄入)。

      6. 相关形式: 名词形式是“devourer”,指的是一个贪吃的人,还有形容词“devouring”,用于描述强烈的消耗某物的行为。

      Feel free to ask if you need more specific examples or further information!

    2. holly berries

      holly berries

      English Explanation

      Holly Berries are the bright red, berry-like fruits produced by holly plants, particularly from species such as Ilex aquifolium (English holly) and Ilex opaca (American holly). These berries are typically small, round, and very distinctive due to their vibrant color, which contrasts strikingly with the glossy, dark green leaves of the holly plant.

      1. Botanical Characteristics: The holly plant is a member of the Aquifoliaceae family and is known for its evergreen nature, meaning it retains its leaves throughout the year. The berries grow in clusters and are often enjoyed by various wildlife, including birds, which help in dispersing the seeds.

      2. Cultural Significance: Holly berries are commonly associated with Christmas and winter holidays. They are often used in decorations, wreaths, and garlands due to their festive color and seasonal availability.

      3. Toxicity: It's important to note that while holly berries are visually appealing, they can be toxic if ingested by humans. They contain compounds that can cause nausea, vomiting, and diarrhea. Therefore, one should be cautious and avoid consuming them.

      4. Symbolism: In addition to their ornamental use, holly and its berries have been deeply embedded in cultural traditions and symbolism. They are often seen as a symbol of protection and a representation of the winter solstice.

      中文解释 (Chinese Explanation)

      冬青果是冬青植物所产生的明亮红色的果实,特别是来自某些种类,如 Ilex aquifolium(英冬青)和 Ilex opaca(美冬青)。这些果实通常小而圆,因其鲜艳的色彩而显得非常独特,这种色彩与冬青植物光滑的深绿色叶子形成了鲜明的对比。

      1. 植物特征: 冬青植物是冬青科的一员,以其常青的特性而闻名,意味着它的叶子在全年保持绿色。果实成簇生长,常常受到各种野生动物的喜爱,包括鸟类,它们有助于种子的传播。

      2. 文化意义: 冬青果通常与圣诞节和冬季假期相关联。由于其节日的颜色和季节性特点,它们常常用于装饰、花圈和花环中。

      3. 毒性: 值得注意的是,尽管冬青果外观迷人,但如果人类食用,它们可能是有毒的。它们包含能引起恶心、呕吐和腹泻的化合物。因此,人们在接触到冬青果时应谨慎,避免食用。

      4. 象征意义: 除了作为装饰外,冬青及其果实还深深植根于文化传统和象征主义中。它们常被视为保护的象征,以及冬至的代表。

    3. bumper

      bumper

      Sure! The term "bumper" can have several meanings depending on the context in which it is used. Below, I will discuss its various meanings in both English and Chinese.

      English Explanation:

      1. Automobile Component:
      2. A bumper is a component located at both the front and rear ends of a vehicle. Its primary purpose is to absorb impact during a collision. Bumpers are designed to protect the vehicle's body and frame, as well as the occupants inside. In many countries, vehicles are required to have bumpers for safety reasons.

      3. Bumper Crop:

      4. In agriculture, a "bumper crop" refers to an unusually large harvest of a particular crop. This term is often used to indicate a season where farming conditions were particularly favorable, leading to greater yields than usual.

      5. Bumper Sticker:

      6. A bumper sticker is a type of sticker or label that is affixed to a vehicle's bumper. These stickers often display messages, slogans, or advertisements. They can be used for political campaigns, personal expressions, or promotions.

      7. Bumper (Entertainment Context):

      8. In television or radio, a "bumper" is a short clip or segment used to transition between content, such as moving from a commercial to a show. It often helps maintain viewer interest and provides a smooth flow of programming.

      Chinese Explanation (中文解释):

      1. 汽车部分:
      2. 保险杠是位于车辆前后两端的一个组件。其主要功能是在碰撞中吸收冲击。保险杠旨在保护车辆的车身和框架,以及车内的乘客。在许多国家,车辆被要求配备保险杠以确保安全。

      3. 丰收:

      4. 在农业中,“丰收”指的是某种农作物的异常丰收。这个术语通常用来表示一个特别有利的季节,导致的产量比平常高得多。

      5. 汽车贴纸:

      6. 汽车贴纸是一种贴在汽车保险杠上的贴纸或标签。这些贴纸通常显示消息、口号或广告。它们可以用于政治活动、个人表达或促销。

      7. 电视或广播中的过渡段:

      8. 在电视或广播中,“过渡段”是一个短小的片段,用于在内容之间过渡,比如从广告转到节目。它通常有助于保持观众的兴趣,并提供节目流畅的过渡。

      Summary

      The word "bumper" has multiple meanings and applications in English, ranging from automotive components to agricultural terms, and also in entertainment contexts. Understanding its various interpretations can help in grasping the full range of its use in different scenarios.

      总结

      “保险杠”这个词在英语中有多种含义和应用,从汽车部件到农业术语,甚至在娱乐环境中都有涉及。理解它的各种解释可以帮助我们在不同场景中充分掌握它的用法。

    4. Starlings roost together in huge numbers.

      Starlings roost together in huge numbers.

      English Explanation:

      The excerpt "Starlings roost together in huge numbers" refers to the behavior of starlings, a type of bird known for their social nature. Here’s a breakdown of the key elements:

      1. Starlings: These are medium-sized passerine birds, often noted for their iridescent feathers and remarkable flocking abilities. They belong to the family Sturnidae.

      2. Roost: This term means to settle or gather in a particular place to rest or sleep. Birds often roost together for safety and comfort, as there is strength in numbers.

      3. Together: This indicates that starlings do not roost in isolation; instead, they congregate in groups, which can sometimes number in the thousands.

      4. Huge numbers: This phrase emphasizes that the gatherings can be particularly large, which is a common sight in the evenings when starlings come together to roost in specific locations, such as trees or other structures.

      In summary, the excerpt highlights an interesting aspect of starlings' social behavior, showcasing how they gather in large, communal groups for resting purposes, which can create breathtaking aerial displays during the roosting period.

      Chinese Explanation:

      这句话“星鸲成群栖息”描述了星鸲(一种鸟类)的一种行为特征。下面是几个关键要素的分析:

      1. 星鸲(Starlings):这些是中等大小的鸣禽,通常以其五光十色的羽毛和卓越的集体飞行能力而著称。它们属于雀科(Sturnidae)家族。

      2. 栖息(Roost):这个词的意思是在特定的地方安静休息或睡觉。鸟类经常成群栖息,以获得安全感和舒适感,因为数量多有其优势。

      3. 成群(Together):这表明星鸲不是单独栖息,而是聚集在一起,聚集的数量有时可以达到上千只。

      4. 庞大的数量(Huge numbers):这个短语强调了这样的聚集可以非常大,这在傍晚时分尤为常见,星鸲会在特定地点(如树木或其他结构)聚集栖息。

      总之,这段话突显了星鸲的社会行为特点,展示了它们如何成群结队进行栖息,这在栖息期间可能会形成令人叹为观止的飞行表演。

    5. outcasts

      outcasts

      Certainly! The term "outcasts" refers to individuals or groups who are rejected or ostracized by society or a particular community. They often face social isolation, discrimination, or exclusion due to various reasons, which may include their beliefs, behaviors, appearances, or backgrounds. Outcasts can be seen in different contexts, such as in literature, where characters are often portrayed as outsiders struggling to find acceptance, or in real life, where people may be marginalized due to factors like poverty, mental illness, or differing sexual orientations.

      Detailed Explanation in English:

      1. Definition: Outcasts are people who have been excluded from a society or group.
      2. Causes for Being an Outcast: There are many reasons a person may be labeled as an outcast. This can stem from their lifestyle choices, social behaviors, physical appearance, or any characteristic that deviates from the norm.
      3. Social Implications: Being an outcast can lead to feelings of loneliness, depression, and a sense of not belonging. Societally, it can create divisions between “insiders” and “outsiders.”
      4. Representations in Literature: Outcasts are often prominent figures in stories, highlighting themes of rejection, the search for identity, and the quest for acceptance.
      5. Real-World Examples: Outcast experiences can be seen in various communities where individuals face stigma or discrimination, such as the LGBTQ+ community, individuals with mental health challenges, etc.

      Detailed Explanation in Chinese:

      1. 定义: "被排斥者"是指被一个社会或群体排除的人。
      2. 成为被排斥者的原因: 人们被标记为被排斥者的原因有很多。这可能源于他们的生活方式选择、社交行为、外貌或任何与常规有所偏离的特征。
      3. 社会影响: 成为被排斥者可能导致孤独感、抑郁和无归属感。在社会层面上,这可能造成“内部人”和“外部人”之间的分裂。
      4. 文艺作品中的表现: 在文学中,被排斥者通常是显著的人物,强调拒绝、寻求身份和寻求接受的主题。
      5. 现实生活中的例子: 被排斥的经历可以在各种社区中看到,例如面临污名化或歧视的群体,如LGBTQ+社区、有心理健康问题的人等。

      This term encapsulates important social issues related to acceptance, belonging, and the human experience.

    6. surplus

      surplus

      English Explanation

      The term "surplus" refers to an amount that exceeds what is needed or required. It can apply to various contexts, including economics, business, and everyday situations. Here are some key points regarding surplus:

      1. Economic Context: In economics, surplus often refers to excess production or supply. For example, if a company produces more goods than consumers can buy, the excess goods are considered a surplus. Similarly, a government may have a budget surplus if its revenues exceed its expenditures.

      2. Types of Surplus:

      3. Budget Surplus: When income exceeds expenditures in a budget (often refers to government finance).
      4. Trade Surplus: Occurs when a country exports more goods and services than it imports.
      5. Capital Surplus: Refers to the excess amount raised from the sale of a company's stock over its par value.

      6. Impact of Surplus: A surplus can have both positive and negative effects. For instance, a budget surplus may allow a government to save for future projects or pay down debt. However, persistent surpluses in certain areas may also indicate inefficiencies, such as overproduction.

      7. Everyday Use: In everyday language, surplus can refer to anything that is extra or additional, such as leftovers from a meal or materials that are not immediately needed.

      中文解释

      “盈余”一词指的是超过所需或要求的数量。它可以应用于经济、商业和日常生活等各种背景。以下是关于盈余的一些关键点:

      1. 经济背景:在经济学中,盈余通常指多余的生产或供应。例如,如果一家公司的生产量超过了消费者的购买力,那么这部分多余的商品就被称为盈余。同样,如果一个政府的收入超过了支出,就会形成预算盈余。

      2. 盈余的类型

      3. 预算盈余:指在预算中收入超过支出的情况(通常指政府财政)。
      4. 贸易盈余:当一个国家的出口超过进口时发生。
      5. 资本盈余:是指公司股票出售所得超过其面值的金额。

      6. 盈余的影响:盈余可能产生积极或消极的影响。例如,预算盈余可能使政府能够为未来的项目储蓄或减少债务。然而,在某些领域持续存在盈余也可能暗示效率低下,例如过度生产。

      7. 日常用法:在日常语言中,盈余可以指任何额外或附加的内容,例如餐后剩余的食物或当前不需要的材料。

    7. lion pride

      lion pride

      Explanation in English:

      The term "lion pride" refers to a social group consisting of lions, typically composed of related females, their offspring, and a coalition of males. A pride usually consists of about 10 to 15 lions but can vary in size.

      Key Characteristics:

      1. Social Structure: Lion prides have a complex social hierarchy. Females typically stay in their natal pride, while males may leave to form coalitions with other males or to start their own pride once they reach maturity.

      2. Hunting and Feeding: Members of a pride often hunt collectively, which improves their chances of taking down larger prey. This cooperative hunting is crucial because it allows them to take on animals that are much larger than individual lions can handle alone.

      3. Territorial Behavior: Prides are territorial and will defend their hunting grounds from intruding lions or other predators. Males play a significant role in protecting the territory.

      4. Cubs and Rearing: In a pride, females may all share the responsibilities of raising the cubs, allowing for a higher chance of cub survival.

      5. Communication and Bonding: Lions communicate through vocalizations, body language, and grooming behaviors, which help strengthen social bonds within the pride.

      Overall, lion prides are fascinating examples of social behavior and cooperation among animals.


      中文解释:

      “狮群”术语指的是由狮子组成的社会群体,通常包括相关的雌性及其后代,以及一组雄性。一个狮群通常由约10到15只狮子组成,但大小可能会有所不同。

      主要特征:

      1. 社会结构:狮群具有复杂的社会等级。雌性通常留在出生的狮群中,而雄性到达成熟后,可能会离开以与其他雄性形成联合或建立自己的狮群。

      2. 狩猎与进食:狮群成员通常会集体狩猎,这提高了他们捕捉大型猎物的机会。这种合作狩猎至关重要,因为它使他们能够捕食比单只狮子能够单独处理的动物大得多的猎物。

      3. 领土行为:狮群是有领土意识的,通常会保护自己的猎场不受其他狮子或掠食者的侵扰。雄性在保护领土方面发挥着重要作用。

      4. 幼崽和抚养:在狮群中,雌性可能会共同承担抚养幼崽的责任,这样能够提高幼崽的存活机会。

      5. 交流与联系:狮子通过声音、身体语言和梳理行为进行交流,这有助于增强狮群内部的社会联系。

      总体而言,狮群是动物之间社会行为和合作的迷人例子。

    8. clutches

      clutches

      Explanation in English:

      The term "clutches" can have different meanings depending on the context in which it is used. Here are some of the primary interpretations:

      1. Mechanical Clutches: In mechanical contexts, clutches refer to devices that connect and disconnect two elements of a machine. For example, in vehicles, a clutch connects the engine to the transmission, allowing the driver to change gears.

      2. Animal Behavior: In biological contexts, "clutches" can refer to a group of eggs laid by birds or reptiles. For example, a bird might lay a clutch of eggs in a single nesting period.

      3. Emotional Usage: The word can also be used figuratively, such as in the phrase "in the clutches of," which means being in a grip or control of something, often with a negative connotation, such as fear or a difficult situation.

      4. Grasping: Lastly, "clutches" can refer to the act of gripping or holding something tightly with one’s hands.

      The meaning can greatly depend on the surrounding text or conversation, so context is crucial for the correct interpretation.

      Explanation in Chinese:

      "clutches"这个词可以根据使用的上下文有不同的含义。以下是一些主要的解释:

      1. 机械离合器:在机械方面,clutches指的是连接和断开机器两个部件的装置。例如,在车辆中,离合器将发动机和变速器连接起来,使驾驶员可以换挡。

      2. 动物行为:在生物学上下文中,"clutches"可以指鸟类或爬行动物产下的一组蛋。例如,一只鸟可能在一次筑巢期间下一个蛋窝(clutch)。

      3. 情感用法:这个词也可以比喻使用,如在短语"在…的掌控之中"(in the clutches of)中,意思是处于某种事物的控制之中,通常带有负面含义,例如恐惧或困难的情境。

      4. 抓住:最后,“clutches”也可以指用手紧紧握住或抓住某样东西的行为。

      这个词的意义在很大程度上取决于周围的文本或对话,因此上下文对于正确理解至关重要。

    9. underwriters

      underwriters

      Certainly! Let's break down the term "underwriters" in both English and Chinese.

      English Explanation

      Underwriters are individuals or organizations, typically in the financial services sector, that assess and assume the risk of insuring a client or group of clients. Their primary roles include:

      1. Risk Assessment: They evaluate the potential risks involved in insuring people or businesses. This involves analyzing various factors, including health records, financial statements, and market conditions.

      2. Insurance Policy Issuance: Based on the risk assessment, underwriters determine the terms of the insurance policy and the premium that needs to be paid by the insured.

      3. Financial Securities: In the context of investment banking, underwriters may also refer to entities that help companies issue new shares of stock or bonds. They assess the value of the offering and help set the pricing before the securities are sold to investors.

      4. Regulatory Compliance: Underwriters ensure that all transactions comply with relevant regulations and guidelines, protecting both the insurer and the insured.

      Overall, underwriters play a critical role in the insurance and financial markets, as they help manage risk and ensure that financial transactions are carried out smoothly and according to established standards.


      中文解释

      承保人(underwriters) 是指在金融服务行业中,评估和承担承保客户或客户群体风险的个人或组织。其主要职能包括:

      1. 风险评估:他们评估承保个人或企业所涉及的潜在风险。这包括分析各种因素,例如健康记录、财务报表以及市场状况。

      2. 保险政策的签发:根据风险评估,承保人决定保险政策的条款和被保险人需要支付的保费。

      3. 金融证券:在投资银行的背景下,承保人也可以指帮助公司发行新股票或债券的实体。他们评估发行的价值,并在证券出售给投资者之前帮助设定价格。

      4. 法规遵从:承保人确保所有交易遵循相关法规和指南,以保护保险公司和被保险人。

      总的来说,承保人在保险和金融市场中扮演着重要的角色,因为他们帮助管理风险,并确保金融交易的顺利进行以及遵守既定标准。

    10. incestuous mating

      incestuous mating

      Explanation in English

      Incestuous Mating refers to the practice of breeding between closely related individuals, such as siblings, parent and offspring, or first cousins. This concept is significant in various fields, including biology, genetics, and animal breeding.

      1. Genetic Implications: Incestuous mating can lead to a higher chance of offspring inheriting genetic disorders. This is because closely related individuals are more likely to carry the same recessive genes that may cause hereditary diseases. Inbreeding increases homozygosity (the presence of the same allele at a gene locus on both chromosomes), which can decrease genetic diversity and lead to inbreeding depression, where the fitness and vitality of the population declines.

      2. Evolutionary Perspective: From an evolutionary standpoint, incestuous mating can pose dangers to a species. Limited genetic diversity makes a population more susceptible to diseases and environmental changes, lessening its ability to adapt over time.

      3. Social and Ethical Considerations: In human societies, incestuous relationships are often taboo and sometimes illegal, as they can lead to ethical concerns related to power dynamics and consent, particularly in cases of coercion or abuse within families.

      4. Animal Breeding: In controlled animal breeding scenarios, while some inbreeding might be done to preserve desirable traits, it is typically moderated to prevent the negative effects mentioned above. Breeders often implement various strategies to maintain genetic health and diversity.

      Explanation in Chinese

      近亲交配 指的是在密切相关个体之间进行繁殖的做法,例如兄弟姐妹、父母与子女或一等表亲之间。这个概念在生物学、遗传学和动物繁殖等多个领域都是重要的。

      1. 遗传影响:近亲交配会导致后代遗传疾病的几率增高。这是因为密切相关的个体更可能携带相同的隐性基因,这些基因可能导致遗传病。近亲繁殖会增加同质性(即在染色体上同一基因位点存在相同等位基因的现象),这可能导致遗传多样性的减少和近亲繁殖抑制,即种群的适应性和活力下降。

      2. 进化视角:从进化的角度看,近亲交配会对物种构成危险。有限的遗传多样性使种群更易受到疾病和环境变化的影响,降低了其适应能力。

      3. 社会和伦理考量:在人的社会中,近亲关系通常被视为禁忌,有时也可能是非法的,因为这些关系可能引发与权力动态和同意相关的伦理问题,尤其是在家庭内部存在强迫或虐待的情况下。

      4. 动物繁殖:在控制的动物繁殖场景中,虽然有时会进行一些近亲繁殖以保留理想特征,但通常会加以限制以防止上述负面影响。饲养员通常会实施各种策略以维护遗传健康和多样性。

    11. carnivorous

      carnivorous

      English Explanation

      The term "carnivorous" refers to organisms that primarily consume meat as their main source of food. This classification is often used in the context of animals, but it can also apply to certain plants.

      1. Definition:
      2. The word "carnivorous" comes from the Latin words "caro," meaning "flesh," and "vorare," meaning "to devour." Thus, it literally means "flesh-eating."

      3. Examples:

      4. Common examples of carnivorous animals include lions, tigers, sharks, and eagles.
      5. Some plants, known as carnivorous plants, obtain nutrients by trapping and digesting insects and other small animals. Examples include the Venus flytrap and the pitcher plant.

      6. Ecological Role:

      7. Carnivorous organisms play a crucial role in their ecosystems by helping to control populations of herbivores (plant-eating animals) and maintaining balance within food webs.

      8. Adaptations:

      9. Many carnivorous animals possess specialized adaptations that aid in hunting and consuming prey. For example, sharp teeth, keen senses, and stealthy movements are common traits among carnivores.

      中文解释

      “肉食性”一词指的是主要以肉类为主要食物来源的生物。这一分类通常用于动物,但有时也适用于某些植物。

      1. 定义
      2. “肉食性”这个词来源于拉丁语,"caro"意为“肉”,"vorare"意为“吞食”。因此,它的字面意思是“食肉的”。

      3. 例子

      4. 常见的肉食动物包括狮子、老虎、鲨鱼和鹰。
      5. 一些植物被称为肉食性植物,通过捕捉和消化昆虫及其他小动物来获取养分。例子包括捕蝇草和瓢虫草。

      6. 生态角色

      7. 肉食生物在其生态系统中发挥着至关重要的角色,它们通过帮助控制草食动物(以植物为食的动物)种群,维护食物链的平衡。

      8. 适应性

      9. 许多肉食动物具有专门的适应性,帮助它们捕猎和消费猎物。例如,锋利的牙齿、敏锐的感官和隐蔽的运动方式是肉食动物的常见特征。
    12. I have a hunch that we may come to look back on the invention ofthe ESS concept as one of the most important advances in evolution-ary theory since Darwin.

      I have a hunch that we may come to look back on the invention of the ESS concept as one of the most important advances in evolution- ary theory since Darwin.

      English Explanation

      The excerpt expresses a personal intuition or feeling (hunch) that the concept of ESS (Evolutionarily Stable Strategy) will be regarded as a significant milestone in the history of evolutionary theory, comparable in importance to Charles Darwin's contributions.

      1. Hunch: This indicates that the author is sharing a personal belief or a preliminary sense about the future significance of the ESS concept without definitive evidence at this moment.

      2. ESS (Evolutionarily Stable Strategy): This term refers to a specific strategy in evolutionary biology that, if adopted by a population, cannot be invaded by any alternative strategy due to its inherent stability. In other words, it is a strategy that, once it becomes common in a population, provides a stable balance against any competing strategies.

      3. Looking back: The author predicts that future generations or researchers might reflect on this concept as a crucial turning point or advancement in understanding how evolutionary processes work.

      4. Important advances in evolutionary theory since Darwin: This implies that Darwin's theory of natural selection has been foundational but suggests that the addition of the ESS concept could be equally transformative in how we understand biological evolution.

      Overall, the excerpt conveys optimism and foresight regarding the impact of the ESS concept on the field of evolutionary biology.

      Chinese Explanation

      该摘录表达了作者对ESS(进化稳定策略)概念未来可能被认为是达尔文以来进化理论中最重要的进展之一的个人直觉或感受(灵感)。

      1. 灵感(hunch):这表明作者在分享一种个人信念或对ESS概念未来重要性的初步感觉,而此时的证据并不充分。

      2. ESS(进化稳定策略):这个术语指的是进化生物学中的一种特定策略,如果它被一个种群采纳,任何其他替代策略都无法入侵,因为它具有固有的稳定性。换句话说,ESS是一种一旦在种群中普遍存在,就可以对任何竞争策略提供稳定平衡的策略。

      3. 回顾(looking back):作者预测未来一代人或研究人员可能会认为这一概念是理解进化过程的关键转折点或进展。

      4. 自达尔文以来进化理论的重要进展:这意味着达尔文的自然选择理论是基础性的,但作者提示ESS概念的加入可能在我们理解生物进化方面同样具有变革性。

      总体而言,这段摘录传达了对ESS概念在进化生物学领域影响的乐观与前瞻性。

    13. darts

      darts

      Certainly! The excerpt "darts" can refer to several different concepts, depending on the context. Below, I will explain its meanings in detail in both English and Chinese.

      English Explanation:

      1. Darts as a Sport: Darts is a popular game typically played in pubs or recreational settings where players throw small, pointed missiles (called darts) at a circular board (the dartboard) that is divided into numbered sections. The objective is to score points by hitting specific areas of the board. The game can be played in various formats, including singles and doubles, and often involves strategies regarding which areas to target to maximize scores. The most well-known type of play is “501,” where players start with 501 points and aim to reduce their score to zero.

      2. Darts as Projectiles: Darts can also refer to the actual projectiles used in the game. These typically consist of a metal tip, a barrel (which players grip) made of materials like tungsten or brass, and often have a flight attached to the back to stabilize the throw.

      3. Figurative Use: The term "darts" can also be used metaphorically to describe piercing or rapid movements, or to indicate something that hurtful has been said, much like someone might describe words as "darting" towards someone.

      4. Dart as a Verb: The verb "to dart" means to move quickly and suddenly. For example, one might say "the cat darted across the street" to indicate a fast, sudden movement.

      Chinese Explanation (中文解释):

      1. 飞镖作为一种运动: 飞镖是一项受欢迎的游戏,通常在酒吧或休闲场所进行,玩家将小型尖头的飞镖(称为飞镖)投射向一个圆形的靶子(飞镖盘),飞镖盘被分成多个编号的区域。目标是通过击中特定区域来得分。这项游戏有多种玩法形式,包括单人和双人,通常涉及有关目标选择的策略,以最大化得分。最常见的玩法是“501”,玩家从501分开始,目标是将分数减少到零。

      2. 飞镖作为投射物: 飞镖也可以指在游戏中使用的实际投射物。这些通常由一个金属尖端、一个用钨或黄铜等材料制成的瓶身(玩家握持的部分)以及通常在背部附带的一个飞行器组成,以稳定投掷。

      3. 比喻用法: “飞镖”一词还可以用于比喻,描述刺痛或快速的动作,或表示某些伤人的话就像飞镖一样朝某人刺去。

      4. 动词“dart”: 动词“dart”意味着迅速而突然地移动。例如,人们可能会说“猫突然冲过街道”,以表示快速的、突发的移动。

      This dual explanation aims to provide a comprehensive understanding of the term "darts" in both English and Chinese.

    14. savage

      savage

      Certainly! The term "savage" can have multiple meanings and connotations depending on the context in which it is used. Below, I will explain the word "savage" thoroughly in both English and Chinese.

      English Explanation

      1. Definition:
      2. The word "savage" is an adjective that typically describes someone or something that is fierce, violent, and untamed. It can refer to behavior, attitudes, or even creatures that are wild and unpredictable.

      3. Contextual Usage:

      4. Animal Context: In terms of animals, a "savage" beast would mean a wild animal that displays aggressive or brutal behavior, such as a lion during a hunt.
      5. Human Behavior: In relation to people, calling someone "savage" might imply that they are brutal or cruel, but it can also have a more colloquial sense, where it means to be bold and unapologetic, especially in a humorous or sharp manner.
      6. Cultural Connotation: Historically, the term has been used to describe Indigenous peoples or cultures in a derogatory way, painting them as primitive. This usage is considered offensive and reflects a colonial mindset.

      7. Related Forms:

      8. Noun: "savage" can also be a noun referring to a person regarded as fierce or uncivilized.
      9. Verb: As a verb, "to savage" means to attack someone or something violently or with intense criticism.

      10. Contemporary Use: In modern slang, particularly on social media, the term "savage" can denote someone who is exceptionally ruthless or witty, often in a funny and engaging way. For example, someone might refer to a cutting remark made by a friend as "savage," implying it was bold and striking.

      中文解释 (Chinese Explanation)

      1. 定义:
      2. “savage”是一个形容词,通常用来描述某人或某物凶猛、暴力和未驯化。它可以指行为、态度,甚至是野生和不可预测的生物。

      3. 语境用法:

      4. 动物语境: 在动物方面,“savage”动物指的是一种显示出攻击性或残酷行为的野生动物,比如狮子在捕猎时的表现。
      5. 人类行为: 当提到人时,称某人为“savage”可能暗示他是残忍的或冷酷的,但在口语中也会有更俏皮的意思,指某人非常大胆和毫不忏悔,尤其在幽默或尖锐的方式上。
      6. 文化内涵: 从历史上看,这个词常被用于以贬义的方式描述土著人民或文化,描绘他们为原始的。这种用法被认为是冒犯性的,反映了殖民的思维定势。

      7. 相关形式:

      8. 名词:“savage”还可以作名词,指被视为凶猛或不文明的人。
      9. 动词:“to savage”意味着以猛烈或激烈的批评攻击某人或某物。

      10. 现代用法: 在现代俚语中,尤其是在社交媒体上,“savage”可以表示某人极为无情或者机智,通常以有趣和引人入胜的方式。例如,有人可能会讲一个朋友说的尖锐评论是“savage”,意味着这种表述大胆且令人印象深刻。

      This comprehensive explanation highlights the versatility of the word "savage" across different contexts and cultures.

    15. pact

      pact

      Certainly! The term "pact" refers to a formal agreement or treaty between two or more parties. It carries significant implications depending on the context in which it is used, typically relating to agreements in international relations, business deals, or personal commitments.

      In English:

      1. Definition: A pact is an agreement that is usually binding and involves mutual promises between the parties involved. It may pertain to a variety of contexts such as diplomatic treaties, business contracts, or personal promises.

      2. Nature of Pacts: Pacts are often formal and may involve legal obligations. They can cover a wide range of subjects, including trade agreements, peace treaties, alliances, or specific commitments in various fields.

      3. Examples:

      4. International Relations: The North Atlantic Treaty Organization (NATO) can be considered a pact among member countries to provide mutual defense.
      5. Social Commitments: Friends may enter into a personal pact to support one another through difficult times.
      6. Business: Companies may form a pact to collaborate on a project or share resources.

      7. Importance: The purpose of a pact is to establish clear guidelines and responsibilities among the participants, ensuring cooperation and mutual benefit.

      8. Implications: Breaking a pact can lead to serious consequences, such as diplomatic disputes or loss of trust among parties involved.

      In Chinese (中文):

      1. 定义:pact(契约或协议)是指两个或两个以上当事方之间的正式协议。它通常涉及相互承诺,具有约束力。

      2. 契约的性质:契约通常是正式的,并可能涉及法律义务。它可以涵盖各种主题,包括贸易协议、和平条约、联盟或在各个领域的特定承诺。

      3. 例子

      4. 国际关系:北大西洋公约组织(NATO)可以认为是成员国之间的一种契约,提供相互防御。
      5. 社会承诺:朋友之间可能会达成个人契约,在困难时期相互支持。
      6. 商业:公司之间可能会形成契约,共同合作项目或共享资源。

      7. 重要性:契约的目的在于在参与者之间建立明确的指导方针和责任,确保合作与互惠。

      8. 影响:违反契约可能导致严重后果,例如外交争端或当事方之间信任的丧失。

      In summary, a "pact" is an essential means of formalizing relationships and responsibilities in various contexts, reinforcing trust and collaboration among involved parties.

      总而言之,“契约”是正式化各种背景下关系与责任的重要手段,加强了当事方之间的信任与合作。

    16. ethologists

      ethologists

      Explanation in English

      Ethologists are scientists who study animal behavior in natural environments. The field of ethology emerged from the observation and analysis of animal behaviors, focusing primarily on how these behaviors have evolved and how they serve the survival and reproductive success of species. Ethologists observe animals in their natural habitats rather than in controlled laboratory settings, which allows them to understand behavior in the context of ecological and evolutionary pressures.

      Key aspects of ethology include:

      1. Innate Behavior: Ethologists study instinctual behaviors that are often hardwired into an animal's genetics. These behaviors are typically performed without prior experience and include things like mating rituals and parental care.

      2. Learning and Adaptation: Ethologists also examine how animals learn from their environment, adapt to challenges, and develop social structures within their species.

      3. Communication: The field involves understanding how animals communicate with each other, using vocalizations, body language, and other signals.

      4. Field Studies: Ethologists often conduct field observations to gather data on animals acting in their natural settings, providing insights that may be missed in laboratory studies.

      5. Interdisciplinary Approach: Ethology intersects with various fields, including psychology, ecology, and evolutionary biology, each contributing to a fuller understanding of animal behavior.

      The study of ethology has contributed significantly to our understanding of animal behavior, leading to insights that can also be applicable to human behavior and psychology.

      Explanation in Chinese

      动物行为学家是研究动物在自然环境中行为的科学家。动物行为学的领域源于对动物行为的观察和分析,主要关注这些行为是如何演化以及它们如何促进物种的生存和繁殖成功。动物行为学家会在动物的自然栖息地进行观察,而不是在控制的实验室环境中,从而能够理解行为在生态和进化压力下的背景。

      动物行为学的一些关键方面包括:

      1. 先天行为:动物行为学家研究那些通常与动物的基因密切相关的本能行为。这些行为通常在没有先前经验的情况下进行,包括交配仪式和亲代照护。

      2. 学习与适应:动物行为学家还研究动物如何从环境中学习、适应挑战,以及在其物种内发展社会结构。

      3. 交流:这一领域涉及理解动物之间如何沟通,使用声音、肢体语言和其他信号。

      4. 野外研究:动物行为学家通常进行野外观察,以收集在自然环境中活动的动物的数据,这提供了在实验室研究中可能被忽视的洞见。

      5. 跨学科方法:动物行为学与多种领域交叉,包括心理学、生态学和进化生物学,各自贡献于对动物行为的更全面理解。

      动物行为学的研究极大地促进了我们对动物行为的理解,得出的见解也可以适用于人类行为和心理学。

    17. pollination

      pollination

      English Explanation

      Pollination is the biological process through which pollen from the male reproductive organs of flowers (anthers) is transferred to the female reproductive organs (stigmas) of the same or different flowers. This process is essential for the reproduction of flowering plants and plays a crucial role in the production of fruits and seeds.

      Pollination can occur in various ways, including:

      1. Wind Pollination (Anemophily): Pollen is carried from one flower to another by the wind. Many grasses and trees rely on this method.

      2. Insect Pollination (Entomophily): Insects, such as bees, butterflies, and moths, visit flowers to collect nectar and inadvertently transfer pollen from one flower to another. This is the most common form of pollination and is vital for the reproduction of many flowering plants.

      3. Animal Pollination: Besides insects, other animals, including birds (like hummingbirds) and bats, can also assist in pollinating flowers.

      4. Self-Pollination: Some plants can fertilize themselves when pollen from the same flower or plant reaches the stigma.

      The process of pollination is essential not only for plant reproduction but also has significant implications for agriculture, as many crops depend on pollinators for fruit and seed production. The decline in pollinator populations, such as bees, poses a serious threat to food security and biodiversity.

      Chinese Explanation

      授粉是一个生物过程,花朵雄性生殖器官(花药)的花粉被转移到同一朵或不同花朵的雌性生殖器官(柱头)。这一过程对开花植物的繁殖至关重要,并在果实和种子的生产中发挥着关键作用。

      授粉可以通过多种方式发生,包括:

      1. 风授粉(风媒授粉):花粉通过风从一朵花传播到另一朵花。许多草类和树木依赖这种方法。

      2. 昆虫授粉(昆虫媒介授粉):昆虫如蜜蜂、蝴蝶和飞蛾等访问花朵以采集花蜜,并无意间将花粉从一朵花转移到另一朵花。这是最常见的授粉形式,且对许多开花植物的繁殖至关重要。

      3. 动物授粉:除了昆虫外,其他动物,如鸟类(如蜂鸟)和蝙蝠,也可以帮助授粉。

      4. 自我授粉:一些植物可以通过自身的花粉来进行授粉,当同一朵花或植物的花粉到达柱头时,便可实现。

      授粉过程不仅对植物的繁殖至关重要,对农业亦有重大影响,因为许多作物依赖授粉者来进行果实和种子的生产。授粉者数量的减少(如蜜蜂的减少)对粮食安全和生物多样性构成了严重威胁。

    18. burrow

      burrow

      English Explanation

      The term "burrow" can be defined in several contexts, primarily in relation to animals and the environment:

      1. Definition: A burrow is a sheltered tunnel or hole in the ground that various animals create for living, sleeping, or hiding. Burrows can vary in size and complexity, depending on the species.

      2. Animal Behavior: Many mammals, such as rabbits, foxes, and rodents, dig burrows to provide protection from predators, store food, and raise their young. These underground homes help them maintain a stable environment, protecting them from extreme weather conditions and allowing for a degree of privacy.

      3. Ecological Role: Burrows play a significant role in the ecosystem. They improve soil aeration and promote the hydration of surrounding areas due to the movement of air and water. Burrows can also serve as habitats for other organisms, including various insects and plants.

      4. Human Use: In some cases, humans may also create burrows or tunnels for various purposes, such as irrigation or drainage systems, mining, and even as temporary shelters in emergencies.

      In summary, a burrow is an important biological and ecological structure that provides shelter and serves multiple functions for both wildlife and the environment.


      Chinese Explanation

      “burrow”(地洞)这个词在多个上下文中可以定义,主要与动物和环境有关:

      1. 定义:burrow 是一种动物在地下挖掘的隧道或洞穴,用于栖息、睡觉或躲藏。根据物种的不同,burrow 的大小和复杂程度各异。

      2. 动物行为:许多哺乳动物,如兔子、狐狸和啮齿动物,挖掘 burrows 以保护自己免受掠食者的攻击、储存食物和抚养幼崽。这些地下居所帮助它们维持稳定的环境,让它们免受极端天气的影响,并提供一定程度的隐私。

      3. 生态作用:burrows 在生态系统中扮演着重要的角色。由于空气和水的流动,它们改善了土壤的通气性,并促进了周围地区的水分渗透。burrows 也可以作为其他生物的栖息地,包括各种昆虫和植物。

      4. 人类用途:在某些情况下,人类也可能会挖掘 burrows 或隧道,用于灌溉或排水系统、采矿,甚至在紧急情况下作为临时庇护所。

      总之,burrow 是一个重要的生物和生态结构,为野生动物和环境提供庇护,并发挥多种功能。

    19. squeaks

      squeaks

      The term "squeaks" refers to a type of sound that is often high-pitched and short in duration. It can be created by various sources, including animals, machinery, or even human actions. Here are some key points about "squeaks":

      1. Animal Sounds: Many small animals, including mice, chipmunks, and some birds, make squeaking sounds. These sounds can serve as communication among species or alerts to potential dangers.

      2. Mechanical Noises: In machinery or equipment, squeaks often indicate friction or a need for lubrication. For example, a squeaky door might need some oil on its hinges to operate smoothly.

      3. Human Sounds: People can also produce squeaky sounds, whether through vocal expressions, playful activities, or by using certain objects, like squeaky toys.

      4. Expressions: The term can also carry metaphorical meanings, such as "squeaky clean," which suggests something is extremely clean, or "squeaking by," which means managing to succeed or survive with difficulty.

      In summary, squeaks are brief, high-pitched sounds that can indicate various meanings depending on their context, including animal communication, mechanical issues, or playful sounds.


      中文解释:

      “squeaks”是指一种声音,通常是高音调且持续时间短。这种声音可以由多种来源产生,包括动物、机械,甚至是人的行为。以下是关于“squeaks”的一些关键点:

      1. 动物声音:许多小动物,包括老鼠、花栗鼠和一些鸟类,会发出吱吱声。这些声音可以作为物种之间的交流,或是对潜在危险的警报。

      2. 机械噪音:在机械设备中,吱吱声通常表示摩擦或需要润滑。例如,吱吱作响的门可能需要在铰链上加油,以便顺畅运作。

      3. 人类发出的声音:人类也可以发出吱吱声,无论是通过声音表达、玩耍活动,还是使用某些物品,如发出吱吱声的玩具。

      4. 比喻意义:该术语还可以具有比喻意义,例如“squeaky clean”,意味着某物极其干净,或“squeaking by”,意指困难地成功或生存。

      总之,吱吱声是简短的高音调声音,其含义可以根据上下文而有所不同,包括动物交流、机械问题或玩乐声音。

    20. antecedent

      antecedent

      English Explanation:

      The term "antecedent" has several meanings depending on the context in which it is used. Here are the main interpretations:

      1. Linguistics: In grammar, an antecedent refers to the noun or pronoun that a subsequent pronoun refers back to. For example, in the sentence "The cat lost its toy," the word "cat" is the antecedent of the pronoun "its."

      2. Logic and Mathematics: In logical propositions, an antecedent is the first part of a conditional statement, usually expressed in the "if... then..." format. For instance, in the statement "If it rains, then the ground gets wet," "it rains" is the antecedent.

      3. General Usage: The term can generally refer to something that precedes something else in time, order, or causation. For example, historical events can be considered antecedents to current situations.

      4. Psychology: In behavioral psychology, an antecedent is a stimulus or event that occurs before a behavior. For example, a cue or trigger that leads to a specific response.

      Chinese Explanation:

      “前因”这个词在不同的上下文中有几种含义,以下是主要的解释:

      1. 语言学: 在语法中,前因指的是一个名词或代词,随后出现的代词会指回这个名词或代词。例如,在句子“猫丢了它的玩具”中,“猫”是代词“它”的前因。

      2. 逻辑和数学: 在逻辑命题中,前因是条件语句的第一部分,通常以“如果……那么……”的格式表达。例如,在句子“如果下雨,那么地面会湿”中,“下雨”是前因。

      3. 一般用法: 这个词通常指时间、顺序或因果关系上在某事物之前的某事物。例如,历史事件可以被视为当前情况的前因。

      4. 心理学: 在行为心理学中,前因是发生在某行为之前的刺激或事件。例如,一个提示或触发因素会导致特定的反应。

    21. strains

      strains

      Certainly! The term "strains" can refer to different concepts depending on the context in which it is used. Here's a detailed explanation of the term in both English and Chinese:

      English Explanation:

      1. Biological Context: In biology, "strains" usually refer to genetic variants or subtypes of microorganisms, such as bacteria or viruses. For example, various strains of the influenza virus can have different properties, levels of virulence, and responses to vaccines.

      2. Medical Context: In medicine, "strains" can refer to injuries that involve the overstretching or tearing of muscles or tendons. A strain can cause pain, swelling, and reduced flexibility in the affected area.

      3. Mechanical Context: In engineering or physics, "strain" refers to the measure of deformation representing the displacement between particles in a material body. It is a dimensionless quantity that describes how much a material is stretched or compressed under stress.

      4. Linguistic Context: In linguistics, "strain" can also refer to distinct variants or dialects within a language, such as different strains of English spoken in various regions (e.g., American English, British English).

      5. General Usage: The word "strain" can also refer to a difficulty or pressure that someone faces, such as emotional or psychological strain resulting from stress or workload.

      中文解释:

      1. 生物学背景:在生物学中,“菌株”通常指微生物的遗传变体或亚型,比如细菌或病毒。例如,流感病毒的不同菌株可以具有不同的特性、毒性水平和对疫苗的反应。

      2. 医学背景:在医学中,“拉伤”可以指涉及肌肉或腱的过度拉伸或撕裂的伤害。拉伤可能导致受影响部位出现疼痛、肿胀和灵活性降低。

      3. 机械背景:在工程或物理学中,“应变”指的是表示材料体内颗粒之间位移的变形度量。它是一个无量纲量,描述材料在压力下被拉伸或压缩的程度。

      4. 语言学背景:在语言学中,“变体”可以指语言中的不同方言或变种,例如在不同地区说的英语变体(如美式英语、英式英语)。

      5. 一般用法: “拉紧”一词也可以指个人所面临的困难或压力,例如由于压力或工作量大而产生的情感或心理上的紧张。

      Summary:

      The term "strains" has multiple meanings across different fields, including biology, medicine, engineering, and general usage. Understanding the context in which it is used is essential for grasping its specific significance.

      总结:

      “菌株”一词在不同领域有多种含义,包括生物学、医学、工程学和一般用法。理解其使用的上下文对于掌握其具体意义至关重要。

    22. differentialsurvival of genes

      differential survival of genes

      English Explanation

      The phrase "differential survival of genes" refers to the concept that not all genes or genetic variations within a population have the same likelihood of being passed on to subsequent generations. This concept is closely related to natural selection and evolutionary biology.

      Key Points:

      1. Differences in Survival: Some genes provide advantages or adaptations that enhance an organism’s chances of survival and reproduction in a given environment. These genes are more likely to be retained and passed on to offspring.

      2. Natural Selection: This process is a mechanism of evolution where individuals with favorable traits (which may be due to certain genes) are more likely to survive and reproduce. Over time, this can lead to changes in the genetic makeup of a population.

      3. Genetic Variability: Within any population, there is a variety of genetic traits. Some may be beneficial, while others can be neutral or harmful. The differential survival of genes emphasizes that the success of these various genes can vary based on environmental pressures.

      4. Implications for Evolution: Understanding the differential survival of genes helps explain how populations evolve. Traits that improve survival will become more common, while those that do not contribute positively may diminish in frequency or disappear.

      Overall, this concept is fundamental to understanding evolutionary processes, genetic diversity, and the development of species over time.

      Chinese Explanation

      “基因的差异生存”这个短语指的是并非所有基因或种群中的遗传变异在被传递到后代时都有相同的可能性。这个概念与自然选择和进化生物学紧密相关。

      关键点:

      1. 生存差异: 一些基因提供了优势或适应性,使得生物体在特定环境中的生存和繁殖几率更高。这些基因更有可能被保留并传递给后代。

      2. 自然选择: 这一过程是进化的一种机制,其中具有有利特征的个体(这可能是由某些基因引起的)更可能生存和繁殖。随着时间的推移,这可以导致一个种群的基因组成发生变化。

      3. 遗传变异: 在任何种群中,存在各种各样的遗传特征。有些可能是有益的,而另一些可能是中性的或有害的。基因的差异生存强调了这些不同基因的成功程度会根据环境压力而变化。

      4. 对进化的影响: 理解基因的差异生存有助于解释种群如何进化。改善生存的性状将变得更为常见,而那些没有积极贡献的则可能在频率上减少或消失。

      总体而言,这一概念是理解进化过程、遗传多样性以及物种随时间发展所必不可少的。

    23. servo-control

      servo-control

      English Explanation

      Servo-Control refers to a control system that uses feedback to achieve precise control of a mechanism or process. It typically involves a servo mechanism—an electromechanical device that can accurately turn, position, or move machinery in response to signals or commands.

      In a servo-control system, several components work together:

      1. Servo Motor: This is a small electric motor that allows precise motion control. It can rotate to a specific angle or move a certain distance based on control signals.

      2. Feedback Device: This component, often a sensor, measures the output of the servo motor and sends feedback to the control system to inform it of the current position or speed. Common devices include encoders and potentiometers.

      3. Controller: The heart of the system, the controller processes the input signals and compares them to the desired output. It then adjusts the command sent to the servo motor to minimize any difference between these two signals.

      4. Control Loop: This is the continuous process of measurement, comparison, and adjustment that defines servo-control. The system constantly checks how well the output matches the desired result and fine-tunes the operation.

      Servo-control systems are widely used in robotics, industrial automation, aerospace, and wherever precise movement is essential, such as in camera focusing mechanisms or CNC machinery.

      Chinese Explanation

      伺服控制 是一种利用反馈实现机制或过程精确控制的控制系统。它通常涉及到一个伺服机构——一种电机械装置,能够根据信号或指令精确地转动、定位或移动机械。

      在伺服控制系统中,多个组件共同协作:

      1. 伺服电机:这是一个小型电动机,允许精确的运动控制。它可以根据控制信号旋转到特定角度或移动一定距离。

      2. 反馈装置:这个组件通常是传感器,用于测量伺服电机的输出,并将反馈信息发送给控制系统,以告知其当前的位置或速度。常见的设备包括编码器和电位器。

      3. 控制器:系统的核心,控制器处理输入信号并将其与期望输出进行比较。然后,它调整发送给伺服电机的命令,以最小化这两个信号之间的差距。

      4. 控制循环:这是测量、比较和调整的连续过程,定义了伺服控制。该系统不断检查输出与期望结果的匹配程度,并微调操作。

      伺服控制系统广泛应用于机器人技术、工业自动化、航空航天以及任何需要精确运动的地方,比如相机对焦机制或数控机械。

    24. die parabolic reflector

      die parabolic reflector

      Certainly! Let's break down the term "die parabolic reflector" and then provide a thorough explanation in both English and Chinese.

      English Explanation

      The phrase "die parabolic reflector" appears to be a combination of English and German. "Die" is the German definite article meaning "the," while "parabolic reflector" is an English term.

      A parabolic reflector is a device that uses the geometric shape of a parabola to reflect light, sound, or other waves. This type of reflector is commonly used in various applications, such as:

      1. Satellite Dishes: Satellite dishes are parabolic reflectors that focus signals from satellites onto a receiver, allowing for the reception of satellite television and internet.

      2. Flashlights: The reflector behind the bulb in many flashlights is often parabolic, which helps concentrate the light into a beam.

      3. Solar Cookers: Parabolic solar cookers use the sun’s rays, which are reflected to a focal point, to heat food or liquids.

      4. Acoustic Devices: In sound technology, parabolic microphones utilize the shape of a parabolic dish to capture sound from a specific direction while minimizing noise from other directions.

      The properties of a parabola ensure that parallel rays of light or sound are reflected to a single focal point, thereby enhancing the efficiency of the devices that use this principle.

      Chinese Explanation

      “die parabolic reflector” 这个短语似乎是英语和德语的结合。“die” 是德语的定冠词,意思是“这个”,而“parabolic reflector”是一个英语术语。

      抛物面反射器是一种利用抛物线的几何形状来反射光线、声音或其他波动的装置。这种类型的反射器在各种应用中非常常见,例如:

      1. 卫星天线:卫星天线是抛物面反射器,能够将来自卫星的信号集中到接收器上,从而接收卫星电视和互联网信号。

      2. 手电筒:许多手电筒中灯泡后面的反射器通常是抛物面的,这有助于将光线集中成一束光。

      3. 太阳能炉:抛物面太阳能炉利用太阳光的反射,将光线集中到焦点上以加热食物或液体。

      4. 声学设备:在声音技术中,抛物面麦克风利用抛物面盘的形状从特定方向捕捉声音,同时减少来自其他方向的噪音。

      抛物线的特性确保平行的光线或声音被反射到一个焦点,从而提高了使用这一原理的设备的效率。

      If you need further elaboration or have specific questions about this term, feel free to ask!

    25. speculative

      speculative

      Certainly! Here’s a thorough explanation of the term "speculative" in both English and Chinese.

      English Explanation:

      The term "speculative" can be used in various contexts, primarily involving uncertainty, hypothesis, or risk.

      1. General Definition: In a general sense, "speculative" refers to ideas, thoughts, or actions that are based on conjecture rather than firm evidence. It often indicates a lack of certainty about the outcome.

      2. Finance and Investment: In the finance world, speculative investments are those that carry a high level of risk. Investors make speculative investments with the expectation of significant returns, understanding that there is a chance of losing their capital. Examples include penny stocks, derivatives, or cryptocurrencies.

      3. Philosophy and Theory: In philosophical discussions, "speculative" may refer to theories or ideas that are not grounded in empirical evidence or practical application. This might involve abstract reasoning or exploring hypothetical concepts.

      4. Literature and Art: In literature and art, "speculative fiction" refers to genres like science fiction and fantasy that explore imaginative and futuristic ideas, often asking "what if" questions.

      Overall, the term "speculative" connotes an element of guesswork and risk-taking, whether in finance, intellectual exploration, or creative endeavors.

      中文解释 (Chinese Explanation):

      "speculative" 这个词在不同的语境中有多种含义,主要与不确定性、假设或风险相关。

      1. 一般定义:一般来说,“speculative”指的是基于推测而非确凿证据的想法、思考或行为。这通常暗示着对结果缺乏确定性。

      2. 金融与投资:在金融领域,投机性投资是指那些风险水平较高的投资。投资者进行投机性投资时,期望获得显著回报,同时也明白可能会失去其资本。例子包括便士股票、衍生品或加密货币。

      3. 哲学与理论:在哲学讨论中,“speculative”可能指的是没有实证依据或实际应用的理论或想法。这可能涉及抽象推理或探索假设概念。

      4. 文学与艺术:在文学和艺术中,“speculative fiction”指的是探索想象和未来主义想法的文体,如科幻小说和奇幻小说,常常提出“如果……会怎样”的问题。

      总体而言,“speculative”这个词暗示了在金融、智力探索或创作努力中,存在着猜测和冒险的成分。

    26. time-lag

      time-lag

      English Explanation

      The term "time-lag" refers to a delay or interval between two events or phenomena. It can occur in various contexts, such as in physics, economics, psychology, and everyday life.

      1. Physics: In physics, time-lag can refer to the delay in the response of a system to an external stimulus. For example, if you push a swing, there is a time-lag before the swing actually begins to move.

      2. Economics: In economics, time-lag is often used when discussing the effects of policy changes or economic shocks. For instance, if a government implements a new tax policy, there may be a time-lag before the economic effects of that policy are felt by individuals and businesses.

      3. Psychology: In psychology, time-lag can relate to the delay between an individual's perception of an event and their reaction to it. For instance, it might refer to the response time of a person realizing they need to move out of the way of an oncoming car.

      4. Everyday Life: In daily life, time-lag might refer to the delay that occurs in communication (e.g., online messaging), where there might be a gap between sending a message and receiving a reply.

      In summary, time-lag indicates that there is often a delay between cause and effect, and understanding this concept is important in analyzing time-dependent relationships in various fields.


      Chinese Explanation

      “时间延迟”(time-lag)指的是两个事件或现象之间的延迟或间隔。它可以出现在多种情境中,比如物理学、经济学、心理学和日常生活中。

      1. 物理学:在物理学中,时间延迟可以指一个系统对外部刺激反应的延迟。例如,当你推动秋千时,秋千实际开始移动之前会有一个时间延迟。

      2. 经济学:在经济学中,时间延迟通常用来讨论政策变化或经济冲击的影响。例如,如果政府实施新的税收政策,可能会在个人和企业实际感受到该政策经济影响之前,有一段时间的延迟。

      3. 心理学:在心理学中,时间延迟可以与个体对事件的感知和反应之间的延迟有关。例如,它可能指一个人意识到需要移动以避开来车的反应时间。

      4. 日常生活:在日常生活中,时间延迟可能是指沟通中发生的延迟(例如在线消息),即发送消息和收到回复之间可能存在的间隔。

      总之,时间延迟表明原因与结果之间通常存在延迟,理解这一概念在分析各个领域中与时间相关的关系时非常重要。

    27. multi-stranded

      multi-stranded

      Certainly! Let's break down the term "multi-stranded" in detail in both English and Chinese.

      English Explanation

      The term "multi-stranded" is an adjective that describes something composed of multiple strands, threads, or components. It is often used in various contexts such as:

      1. Textiles and Materials: In the textile industry, "multi-stranded" refers to fabrics or ropes made from intertwining several threads or fibers. This can enhance strength, flexibility, and durability.

      2. Biology: In molecular biology, it can refer to structures such as DNA, which is typically described as a double helix, where the strands represent the two long chains of nucleotides.

      3. Complex Systems: In a more abstract sense, the term can describe systems or concepts that involve multiple interconnected elements. For example, a "multi-stranded narrative" in literature could refer to a story told from various perspectives or involving multiple subplots.

      4. Technology: In technology, "multi-stranded" might refer to communication systems, such as fiber optic cables that consist of multiple strands to increase data transmission capacity.

      Overall, the key idea is that something described as "multi-stranded" has several components or layers that contribute to its overall function or structure.

      Chinese Explanation

      “multi-stranded” (多 strands的)是一个形容词,用于描述由多个“strand”(纤维、线)或组成部分构成的事物。它通常在不同的上下文中使用,比如:

      1. 纺织物和材料:在纺织行业中,“多 strands的”指的是由多根线或纤维交织而成的面料或绳索。这可以增强材料的强度、柔韧性和耐久性。

      2. 生物学:在分子生物学中,它可以指如DNA这样的结构,通常被描述为双螺旋结构,其中“strands”代表两条长链核苷酸。

      3. 复杂系统:在更抽象的意义上,这个词可以描述涉及多个互相关联元素的系统或概念。例如,文学中的“多 strands叙事”可能指的是从多个视角讲述的故事,或涉及多个子情节的情节。

      4. 技术:在技术领域,“多 strands的”可能指的是通信系统,例如由多根光纤组成的光纤电缆,以增加数据传输能力。

      总体来说,被描述为“多 strands的”事物具有多个组成部分或层次,这些部分共同影响其整体功能或结构。

    28. axon

      axon

      English Explanation

      Axon: An axon is a long, slender projection of a nerve cell (neuron) that conducts electrical impulses away from the cell body. It is a critical component of the nervous system and plays a key role in transmitting information throughout the body.

      1. Structure: An axon typically arises from a part of the neuron called the axon hillock, which is situated at the junction of the cell body and the axon. The axon is usually covered in a fatty layer known as myelin, which helps speed up the transmission of impulses along the axon.

      2. Function: The primary function of an axon is to transmit signals, known as action potentials, to other neurons, muscles, or glands. This transmission is essential for everything from reflexes to complex responses in the body.

      3. Types: Axons can vary in length and diameter. Some can extend just a few millimeters, while others can be over a meter long, such as the axons that run from the spinal cord to the toes.

      4. Communication: When an electrical impulse reaches the end of an axon, it triggers the release of neurotransmitters, which then cross the synapse (the gap between neurons) and initiate a response in the next neuron or cell.

      Chinese Explanation

      轴突:轴突是神经细胞(神经元)的一种长而细的突起,负责将电信号从细胞体传导出去。它是神经系统的一个重要组成部分,在信息传递中起着关键作用。

      1. 结构:轴突通常从神经元的一部分——轴突丘(axonal hillock)开始,轴突丘位于细胞体与轴突的交界处。轴突通常被称为髓鞘的脂肪层包裹,这有助于加速沿轴突的冲动传导。

      2. 功能:轴突的主要功能是将信号(称为动作电位)传递给其他神经元、肌肉或腺体。这种传输对身体的反射动作和复杂反应至关重要。

      3. 类型:轴突的长度和直径可以有所不同。有些可以延伸仅几毫米,而另一些可能长达一米,例如,从脊髓延伸到脚趾的轴突。

      4. 交流:当电冲动到达轴突末端时,它会触发神经递质的释放,这些神经递质随后穿越突触(神经元之间的间隙),并在下一个神经元或细胞中引发反应。

    29. cam

      cam

      It seems like you've provided a very short excerpt consisting solely of the word "cam." To ensure that I can provide a thorough explanation, I'll interpret "cam" in a couple of different contexts. Please let me know if you meant something specific!

      In English: 1. Camera (Cam): - "Cam" is often used as a shorthand term for "camera." This could refer to a variety of cameras, including traditional film cameras, digital cameras, or more specifically, webcams or security cameras. Cameras capture images or videos, serving many purposes in photography, videography, surveillance, and communication.

      1. Camshaft (Cam):
      2. In the context of engineering, particularly in automotive mechanics, "cam" can refer to a camshaft, which is a crucial component in an internal combustion engine. The camshaft controls the timing of the engine's valves, playing a key role in how efficiently an engine operates.

      3. Cam in Computing:

      4. In the realm of computing, "cam" can also refer to "computer-aided manufacturing" (CAM), which involves software used to control machine tools and related machinery in the manufacturing of workpieces.

      5. Slang Usage:

      6. "Cam" is sometimes used in slang to refer to "camera" in social media or live streaming contexts, particularly where individuals may stream live video from their camera.

      In Chinese (中文): 1. 相机 (Cam): - “Cam” 常常是指“相机”的简写。这可以指各种相机,包括传统胶卷相机、数码相机,或更具体的摄像头、监控摄像机等。相机用于拍摄图像或视频,服务于摄影、摄像、监控和交流等多种目的。

      1. 凸轮轴 (Cam):
      2. 在工程领域,特别是在汽车机械中,“cam”可以指“凸轮轴”,这是内部燃烧发动机中的关键部件。凸轮轴控制发动机气门的时机,在发动机的高效运行中起着重要作用。

      3. 计算机辅助制造 (Cam):

      4. 在计算机领域,“cam” 还可以指“计算机辅助制造”(CAM),这涉及用于控制机床和相关机械的软 件,应用于工件的制造。

      5. 俚语用法:

      6. “Cam” 有时在社交媒体或直播上下文中作为俚语,用来指代“摄像头”,特别是个人可能从摄像头进行直播的视频。

      If you have a specific context or intended meaning for "cam," please provide additional details so I can tailor the explanation accordingly!

    30. cords

      cords

      Certainly! The term "cords" can refer to various concepts depending on the context. Below, I'll provide a detailed explanation in both English and Chinese.

      English Explanation:

      1. Definition:
      2. "Cords" generally refers to long, flexible lengths of material, often used for tying, hanging, or binding. They can be made from various materials such as cotton, nylon, or wire.

      3. Types:

      4. There are various types of cords, including:

        • Rope: A thicker cord used for heavy-duty tasks, often made from fibers like jute or polyester.
        • String: A thinner cord used for lighter tasks like tying packages.
        • Electrical cords: Used to transmit electricity, often found in appliances and gadgets.
        • Sewn cords: Used in clothing or upholstery for structural support or decoration.
      5. Uses:

      6. Cords have numerous applications in daily life:

        • Household: Used for hanging items, tying up boxes, crafting, etc.
        • Technology: Chargers and power cables for electronic devices.
        • Outdoor: Tents and hammocks often use sturdy cords for support.
      7. Cultural Significance:

      8. In various cultures, cords can symbolize connection, binding relationships, or even spiritual beliefs, reminiscent of “the ties that bind.”

      中文解释:

      1. 定义
      2. “绳索”通常指的是长而灵活的材料,常用于绑、挂或束缚。它们可以由多种材料制成,例如棉花、尼龙或金属线。

      3. 类型

      4. 有多种类型的绳索,包括:

        • 绳子:较粗的绳索,通常用于重载任务,由黄麻或聚酯等纤维制成。
        • 线:较细的绳索,通常用于轻型任务,如打包。
        • 电源线:用于传输电力,常见于电器和设备中。
        • 缝纫绳:用于服装或家具的结构支撑或装饰。
      5. 用途

      6. 绳索在日常生活中有许多应用:

        • 家庭:用于悬挂物品、捆绑箱子、手工艺等。
        • 科技:电子设备的充电器和电源线。
        • 户外:帐篷和吊床通常使用坚固的绳索提供支撑。
      7. 文化意义

      8. 在各种文化中,绳索可以象征联系、绑定关系,甚至是精神信仰,提醒我们“将人们结合在一起的纽带”。

      If you have a specific context in mind regarding "cords," please let me know, and I can tailor the explanation further!

    31. premium

      premium

      English Explanation

      The term "premium" can have several meanings depending on the context in which it is used. Here are the most common usages:

      1. Insurance: In the insurance industry, a "premium" refers to the amount of money that an individual or business pays to an insurance company in exchange for coverage. This payment can be made on a monthly, quarterly, or annual basis. The premium is determined based on various factors, including the type of insurance, the amount of coverage, the risk involved, and the policyholder's history.

      2. Financial and Investment Context: In finance, a "premium" often refers to the amount by which the price of a bond or stock exceeds its face value or intrinsic value. For example, if a bond with a face value of $1,000 is sold for $1,050, the $50 difference is considered the premium.

      3. Product Marketing: In marketing, a "premium" may refer to a higher-quality product that is sold at a higher price compared to standard options. This can also include promotional items offered for free or at a reduced price as an incentive to purchase a particular product.

      4. Economic Context: The term can also refer to the additional amount paid for a good or service due to its perceived scarcity or desirability.

      Overall, the concept of a "premium" generally implies an additional charge or cost above the basic level, often associated with enhanced value or quality.

      Chinese Explanation

      "Premium" 这个词根据其使用的上下文可以有几种不同的含义。以下是最常见的几种用法:

      1. 保险:在保险行业中,"premium" 指的是个人或企业为获得保险保障而支付给保险公司的金额。这笔费用可以按月、季度或年度支付。保险费的确定基于各种因素,包括保险的类型、保障的金额、风险及投保人的历史。

      2. 金融和投资环境:在金融领域,"premium" 通常指的是债券或股票的价格超过其面值或内在价值的部分。例如,如果一只面值为1000美元的债券以1050美元的价格出售,那么50美元的差额被称为溢价。

      3. 产品营销:在营销中,"premium" 可以指以高于标准选项的价格销售的高品质产品。这也包括作为购买特定产品的激励,免费或低价提供的促销商品。

      4. 经济背景:这个词还可以指由于某种商品或服务的稀缺性或吸引力而多支付的额外金额。

      总体而言,"premium" 的概念通常意味着在基本水平之上的额外收费或成本,通常与增强的价值或质量相关联。

    32. colony

      colony

      Certainly! Let’s explain the term "colony."

      English Explanation:

      A "colony" refers to a territory or area that is under the political control of a foreign state or another entity. Colonies are often established through conquest, settlement, or economic dominance, and they may be governed by a different set of laws and regulations than those that apply to the state from which they originated.

      There are several types of colonies:

      1. Settlement Colonies: These are territories where people from the colonizing country move in and establish communities, often leading to the displacement of native populations. An example is the United States during the 17th and 18th centuries.

      2. Exploitation Colonies: These are established primarily for economic benefit, where the colonizer extracts resources and wealth, often using the indigenous population for labor without providing them rights or support.

      3. Plantation Colonies: These focus on agriculture and are often characterized by large farms or plantations, where cash crops are grown, typically using slave or indentured labor. Many colonies in the Caribbean and southern United States fit this description.

      4. Dependent Colonies: These are territories that are administered by a foreign power but do not have a significant number of settlers from that power. The local population might remain in charge of daily affairs, but ultimate authority rests with the colonizing country.

      Colonies have had significant impacts on history, culture, economics, and international relations, often leading to conflicts and changes in the social dynamics of the regions involved.


      Chinese Explanation (中文解释):

      “殖民地”是指一个地区或区域,受外国国家或其他实体的政治控制。殖民地通常通过征服、定居或经济控制建立,可能受到与其原始国家不同的法律和规章的治理。

      殖民地通常有以下几种类型:

      1. 定居殖民地:这是殖民国家的人们迁入并建立社区的地区,往往导致本土人口的流离失所。一个例子是美国在17和18世纪的殖民时期。

      2. 开发殖民地:这些殖民地主要是为了经济利益而建立,殖民者会提取资源和财富,通常利用当地人口进行劳动,而不给予他们权利或支持。

      3. 种植园殖民地:这些殖民地侧重农业,通常具有大型农场或种植园,种植经济作物,通常使用奴隶或契约劳工。加勒比海和美国南部的许多殖民地符合这一描述。

      4. 依赖殖民地:这些地区由外国势力管理,但并没有大量来自该国的定居者。当地人口可能仍然负责日常事务,但最终的权力仍然归殖民国家。

      殖民地对历史、文化、经济和国际关系产生了重大影响,通常导致冲突和涉及地区社会动态的变化。

    33. receptacles

      receptacles

      English Explanation:

      The term "receptacles" refers to containers or devices that are used to hold or store something. In various contexts, receptacles can have different meanings:

      1. General Use: In everyday language, receptacles can refer to any object that receives and contains items, such as bins, boxes, or cups.

      2. Electrical Context: In electricity, a receptacle typically refers to an electrical outlet where plugs can be inserted to create a power connection for appliances and devices.

      3. Biological Context: In biology, "receptacles" can refer to structures that receive and hold reproductive cells or organs, such as in the case of plants.

      4. Waste Management: In terms of waste management, receptacles include trash cans or recycling bins designed to hold waste materials.

      In all these uses, receptacles serve the primary function of receiving and holding materials temporarily or permanently for a particular purpose.

      Chinese Explanation:

      “容器”(receptacles)这个词指的是用于承载或存储某物的容器或装置。在不同的上下文中,容器可以有不同的含义:

      1. 一般用法:在日常语言中,容器可以指任何能够接收和容纳物品的物体,例如垃圾桶、箱子或杯子。

      2. 电气环境:在电气领域,容器通常指电源插座,用户可以将插头插入其中,以便为电器和设备提供电力连接。

      3. 生物学环境:在生物学中,“容器”可以指接收和容纳生殖细胞或器官的结构,例如植物中的某些部分。

      4. 废物管理:在废物管理方面,容器包括垃圾箱或回收箱,旨在存放废弃物材料。

      在所有这些用法中,容器的主要功能是临时或永久地接收和存放材料,以满足特定的目的。

    34. hitching

      hitching

      The term "hitching" can refer to several concepts depending on the context in which it is used. Below is a thorough explanation in both English and Chinese.

      English Explanation

      "Hitching" generally relates to the act of attaching or securing one object to another, often in a way that allows it to be pulled or to move together. Here are some contexts where "hitching" might be applicable:

      1. Transportation: In the context of vehicles, it can refer to connecting a trailer to a car or truck. When someone is "hitching" a trailer, they are typically using a hitching mechanism that locks the trailer to the towing vehicle for safe transport.

      2. Personal Transportation: "Hitching a ride" is a colloquial phrase meaning to get a lift from someone else. This can involve standing by the side of a road and signaling to passing vehicles, hoping that a driver will stop and offer a ride.

      3. Agriculture: In farming, hitching can refer to the attachment of farm equipment like plows or harvesters to tractors.

      4. Social Context: The term can also be used informally to describe forming a connection or relationship with someone, often in a light or casual manner.

      In general, "hitching" implies a connection, whether it’s physical or metaphorical, and suggests a movement or journey together.

      Chinese Explanation

      “hitching” 这个词根据使用的上下文可以指代多个概念。以下是这个词的详尽解释:

      1. 交通运输:在交通工具的背景下,它指的是将一个拖车连接到汽车或卡车上。当有人在“hitching”一个拖车时,他们通常在使用一种可以将拖车锁定到牵引车辆上的钩接装置,以便安全运输。

      2. 个人交通:“hitching a ride” 是一个口语化的短语,意思是从别人那里搭便车。这可以涉及站在路边并向过往车辆示意,希望司机能够停车并提供搭载。

      3. 农业:在农业中,hitching 可以指将农具,例如犁或收割机,连接到拖拉机上。

      4. 社交背景:这个词也可以非正式地用来描述与某人的连接或关系的建立,通常以轻松或随意的方式进行。

      总体而言,“hitching”暗示了某种连接,无论是物理上的还是隐喻上的,并暗示着一起的移动或旅程。

    35. parasite

      parasite

      English Explanation

      The term "parasite" refers to an organism that lives on or within another organism (the host) and benefits at the host's expense. Parasites can be found in various forms, including:

      1. Types of Parasites:
      2. Ectoparasites: These live on the exterior of the host. Examples include fleas, ticks, and lice.
      3. Endoparasites: These live inside the host’s body. Examples include tapeworms, roundworms, and certain protozoa.

      4. Life Cycle: Parasites often have complex life cycles involving different stages and sometimes different hosts. For instance, some parasites may require a secondary host to complete their life cycle.

      5. Infection and Disease: Parasites can cause infections and diseases in their hosts, leading to various health issues. Common symptoms may include fatigue, abdominal pain, or malnutrition, depending on the type of parasite and the extent of the infestation.

      6. Ecological Role: In ecological terms, parasites play a significant role in regulating host populations and maintaining biodiversity. They are part of the food web and can influence the evolution of their hosts.

      7. Treatment and Prevention: Preventing parasitic infections often involves maintaining good hygiene, proper sanitation, and avoiding contact with contaminated food and water. Treatment may include medication specifically targeting the type of parasite.

      In summary, parasites are organisms that exploit their hosts for nourishment and can have significant impacts on health, ecology, and evolutionary processes.

      中文解释

      “寄生虫”这个术语指的是一种生活在另一个生物体(宿主)内或宿主表面上,并以宿主为代价获利的生物体。寄生虫可见于多种形式,包括:

      1. 寄生虫的类型
      2. 外寄生虫:这些寄生生活在宿主的表面上。例子包括跳蚤、蜱虫和虱子。
      3. 内寄生虫:这些寄生生活在宿主体内。例子包括绦虫、线虫和某些原生动物。

      4. 生命周期:寄生虫通常具有复杂的生命周期,涉及不同的阶段,有时甚至需要不同的宿主来完成生命周期。例如,有些寄生虫可能需要第二宿主来完成其生命周期。

      5. 感染和疾病:寄生虫可以在宿主体内引起感染和疾病,导致各种健康问题。根据寄生虫的类型和感染程度,常见的症状可能包括疲劳、腹痛或营养不良。

      6. 生态角色:在生态上,寄生虫在调节宿主种群和维持生物多样性方面起着重要作用。它们是食物链的一部分,并可以影响宿主的进化过程。

      7. 治疗和预防:预防寄生虫感染通常涉及保持良好的卫生、适当的卫生设施以及避免接触受污染的食物和水。治疗可能包括针对特定类型寄生虫的药物。

      总之,寄生虫是利用其宿主获取养分的生物体,对健康、生态和进化过程有着重要影响。

    36. mitotic

      mitotic

      English Explanation

      The term "mitotic" refers to processes or events related to mitosis, which is a type of cell division. Mitosis is critical for growth, repair, and reproduction in multicellular organisms, allowing a single cell to divide and produce two identical daughter cells, each with the same number of chromosomes as the original cell. The process of mitosis is divided into several phases, which include:

      1. Prophase: The chromatin condenses into visible chromosomes, and the nuclear envelope begins to break down.
      2. Metaphase: The chromosomes align at the cell's equatorial plane, and spindle fibers attach to their centromeres.
      3. Anaphase: The sister chromatids are pulled apart to opposite poles of the cell.
      4. Telophase: The separated chromatids reach the opposite poles, the nuclear envelope re-forms around each set of chromosomes, and the chromosomes start to de-condense.
      5. Cytokinesis: This is the final step where the cytoplasm divides, resulting in two distinct daughter cells.

      Understanding mitotic processes is essential in fields such as biology, medicine, and genetics, as errors in mitosis can lead to conditions such as cancer.

      Chinese Explanation

      “有丝分裂”(mitotic) 这个术语指的是与有丝分裂相关的过程或事件。 有丝分裂是一种细胞分裂类型,对于多细胞生物的生长、修复和繁殖至关重要,它允许一个细胞分裂并产生两个相同的子细胞,每个子细胞拥有与原始细胞相同数量的染色体。有丝分裂的过程分为几个阶段,包括:

      1. 前期 (Prophase):染色质凝聚成可见的染色体,核膜开始破裂。
      2. 中期 (Metaphase):染色体在细胞的赤道面上排列,纺锤丝附着到它们的着丝粒上。
      3. 后期 (Anaphase):姐妹染色单体被拉向细胞的相对极。
      4. 末期 (Telophase):分开的染色单体到达相对极,核膜重新在每组染色体周围形成,染色体开始解凝聚。
      5. 细胞质分裂 (Cytokinesis):这是最后一步,细胞质分裂,形成两个不同的子细胞。

      理解有丝分裂过程在生物学、医学和遗传学等领域是至关重要的,因为有丝分裂中的错误可能导致癌症等疾病。

    37. cues

      cues

      Certainly! The term "cues" refers to signals or prompts that guide behavior or convey information. In various contexts, cues can take many forms, including verbal, non-verbal, environmental, or even internal stimuli.

      1. In Psychology: Cues often serve as triggers for memory recall, prompting individuals to remember certain information or events when they encounter specific stimuli. For example, the smell of a particular perfume might cue memories of a loved one.

      2. In Communication: Cues can be both verbal (like tone of voice or choice of words) and non-verbal (like body language or facial expressions). These cues help convey emotions, intentions, and responses during interactions.

      3. In Behavior: Cues are critical in learning and conditioning. Animals (including humans) can learn to associate cues with certain behaviors or outcomes. For instance, a dog might respond to the cue "sit" because it knows that sitting will result in a treat.

      4. In Performance Arts: Cues guide performers on stage. For example, in theater, a cue might be a specific line of dialogue or a sound effect signaling an actor when to act.

      Now, in Chinese:

      “线索”指的是指引行为或传达信息的信号或提示。在不同的情境中,线索可以采取多种形式,包括语言、非语言、环境,甚至是内在刺激。

      1. 在心理学中:线索常常作为记忆回忆的触发因素,当人们遇到特定的刺激时,可以促使他们想起某些信息或事件。例如,某种香水的气味可能会唤起对某个亲人的回忆。

      2. 在沟通中:线索可以是语言(如语调或用词选择)和非语言(如肢体语言或面部表情)。这些线索有助于在互动中传达情感、意图和反应。

      3. 在行为中:线索在学习和条件反射中至关重要。动物(包括人类)可以学会将线索与特定的行为或结果联系起来。例如,一只狗可能会因为知道坐下会得到奖励而对“坐下”这个线索作出反应。

      4. 在表演艺术中:线索指导舞台上的表演者。例如,在戏剧中,线索可能是特定的台词或音效,提示演员何时行动。

      This comprehensive explanation should clarify the meaning of "cues" in both English and Chinese.

    38. cox

      cox

      It seems like the excerpt you provided is just the word "cox." To give you a thorough explanation, I will consider its possible meanings and contexts in both English and Chinese.

      English Explanation

      1. Cox as a Surname: "Cox" is a common surname in English-speaking countries. It can refer to many notable people, including athletes, authors, and politicians.

      2. Cox in Anatomy: In some contexts, "cox" can refer to the hip joint in anatomy, as in "coxofemoral," which pertains to the hip.

      3. Cox as a Verb: In rowing, a "cox" (short for coxswain) is a person responsible for steering the boat and motivating the rowers. The verb form, "to cox," means to guide or lead in this context.

      4. Cox Communications: It could also refer to Cox Communications, a major telecommunications company in the United States, providing cable television, internet, and home phone services.

      5. Cox in Popular Culture: It might be used in branding or as part of a cultural reference, such as in literature or entertainment.

      Given the ambiguity, if you had a specific context in mind for "cox," please provide it for a more tailored explanation.

      Chinese Explanation

      1. Cox作为姓氏:在英语国家,“Cox”是一个常见的姓氏,可以指很多知名人士,包括运动员、作家和政治家等。

      2. Cox在解剖学中的意义:在某些上下文中,“cox”可以指解剖学中的髋关节,例如“coxofemoral”,即与髋部相关的。

      3. Cox作为动词:在划船中,“cox”(来自“coxswain”)是指负责掌舵和鼓舞划桨者的人。动词形式“to cox”在这个上下文中意味着指导或领导。

      4. Cox通讯:它也可能指Cox通讯,这是一家美国主要的电信公司,提供有线电视、互联网和家庭电话服务。

      5. Cox在流行文化中的用法:它可能在品牌中或作为文化参考出现在文学或娱乐作品中。

      由于“cox”的含义模糊不清,如果你有特定的上下文,请提供更多信息,以便我进行更具体的解释。

    39. mole

      mole

      Sure! The term "mole" can have several meanings depending on the context in which it is used. Here’s a thorough explanation in both English and Chinese:

      English Explanation:

      1. In Chemistry: A mole is a fundamental unit in chemistry that measures the amount of a substance. One mole is defined as exactly \(6.022 \times 10^{23}\) entities (atoms, molecules, ions, etc.), which is known as Avogadro's number. This is used to facilitate calculations in chemical reactions and stoichiometry.

      2. In Biology: A mole can refer to a small burrowing mammal known for its velvety fur, small eyes, and spade-like hands, adapted for digging. Moles are known for creating tunnels in gardens and fields.

      3. In Medicine: A mole (or nevus) is a common type of skin growth that usually appears as a brown or black spot on the skin. While most moles are benign, any changes in their appearance can indicate potential skin issues, including skin cancer.

      4. In Espionage: A mole can refer to a spy who infiltrates an organization, often working undercover to gather information for a rival or enemy.

      Chinese Explanation:

      1. 在化学中:摩尔是化学中的一个基本单位,用于衡量物质的数量。一个摩尔被定义为恰好 \(6.022 \times 10^{23}\) 个实体(原子、分子、离子等),这个数字称为阿伏伽德罗常数。这个单位在化学反应和化学计量中非常重要。

      2. 在生物学中:鼹鼠是一种小型的挖掘哺乳动物,以其柔软的皮毛、小眼睛和铲状的手而闻名,适合挖掘。鼹鼠以在花园和田野中创造隧道而著称。

      3. 在医学中:痣(或称为痦子)是一种常见的皮肤生长,通常表现为皮肤上棕色或黑色的斑点。尽管大多数痣是良性的,但如果痣的外观发生变化,可能会指示皮肤问题,包括皮肤癌。

      4. 在间谍活动中:鼹鼠可以指渗透到一个组织中的间谍,通常是在秘密工作,以收集敌对或竞争对手的信息。

      Summary:

      The word "mole" holds diverse meanings across different fields such as chemistry, biology, medicine, and espionage. Understanding the context is crucial to grasp its intended meaning.

      总结:

      "摩尔" 这个词在化学、生物学、医学和间谍活动等不同领域中具有多种含义。了解上下文对把握其意图至关重要。

    40. permanence

      permanence

      English Explanation:

      "Perpetuity" refers to the state of lasting indefinitely or enduring permanently. It suggests an absence of change over time and is often associated with concepts of stability, continuity, and constancy. In various contexts, such as philosophy, art, nature, and even in financial terms, permanence can hold different meanings:

      1. Philosophical Context: In philosophy, permanence often raises questions about the nature of existence and reality. Philosophers may explore what it means for something to exist perpetually and how temporary phenomena relate to this idea.

      2. Art: In art, permanence can refer to works that are designed to last, like sculptures or architecture, which can withstand the test of time, versus ephemeral art forms that are temporary, like sand sculptures or performance art.

      3. Nature: In nature, permanence might pertain to geological formations or ecosystems that exist for extended periods as opposed to seasonal changes which are temporary.

      4. Finance: In financial terms, "permanence" may refer to structures such as perpetual bonds, which pay interest indefinitely but do not have a maturity date, representing a long-term obligation.

      Chinese Explanation (中文解释):

      “永恒”指的是一种持续存在或永久性的状态。它暗示着时间的变化缺失,通常与稳定性、连续性和恒常性概念相关联。在哲学、艺术、自然及金融等多个领域,“永恒”可以有不同的含义:

      1. 哲学背景:在哲学中,永恒常常引发有关存在和现实本质的问题。哲学家可能会探讨某物持续存在的意义,以及临时现象与这一思想的关系。

      2. 艺术:在艺术中,永恒可以指那些设计用于长久保存的作品,比如雕塑或建筑,它们能够经受时间的考验,而与之相对的是如沙雕或表演艺术这样短暂的艺术形式。

      3. 自然:在自然界中,永恒可能涉及持续存在的地质构造或生态系统,相对于季节性变化而言,这些更为持久。

      4. 金融:在金融术语中,“永恒”可能涉及像永久债券这样的结构,这些债券无限期支付利息,但没有到期日,代表长期的义务。

      Conclusion

      Understanding "permanence" requires looking beyond a single definition and recognizing its implications across various domains.

    41. mimicry

      mimicry

      English Explanation

      Mimicry refers to the phenomenon where one organism evolves to resemble another organism or object in order to gain some advantage, such as protection from predators, increased reproductive success, or improved foraging opportunities. This adaptation can take many forms, including visual similarities, sounds, behaviors, or even chemical signals.

      There are several types of mimicry:

      1. Batesian Mimicry: This occurs when a harmless species mimics the appearance of a harmful or unpalatable species to avoid predation. For example, certain non-venomous snakes mimic the coloration of venomous snakes.

      2. Müllerian Mimicry: This happens when two or more unpalatable species evolve to resemble each other, reinforcing the avoidance behavior of predators since they learn to avoid them all. An example includes various species of toxic butterflies that share similar warning colors.

      3. Aggressive Mimicry: In this type, a predator or parasite mimics a harmless or beneficial organism to deceive its prey or host. For instance, some anglerfish have a lure that resembles prey to attract fish.

      4. Automimicry: This involves an organism mimicking parts of its own body or other individuals of its species to gain an advantage, such as a butterfly with wing patterns that confuse predators.

      Through these adaptations, mimicry plays a vital role in ecological interactions and the survival of species.

      Chinese Explanation

      拟态(mimicry)是指一种生物演化出与另一种生物或物体相似的现象,以获得某种优势,例如保护自己不受捕食者的攻击、增加繁殖成功率或改善觅食机会。这种适应可以有多种形式,包括视觉相似性、声音、行为甚至化学信号。

      拟态有几种类型:

      1. 贝茨拟态(Batesian Mimicry):当一种无害的物种模仿一种有害或难以食用的物种的外观,以避免被捕食时,该现象被称为贝茨拟态。例如,有些无毒蛇模仿有毒蛇的颜色。

      2. 穆勒拟态(Müllerian Mimicry):当两个或多个不可口味的物种进化出相似的特征,以增强捕食者的回避行为,这种现象称为穆勒拟态。一个例子是不同种类的有毒蝴蝶共享类似的警告色。

      3. 攻击性拟态(Aggressive Mimicry):在这种类型中,一种捕食者或寄生虫模仿无害或有益的生物,以欺骗其猎物或宿主。例如,一些琵琶鱼有一个像猎物的诱饵,以吸引鱼类。

      4. 自拟态(Automimicry):这是指一种生物模仿其自身身体的某些部分或其物种的其他个体,以获得优势,例如蝴蝶的翅膀图案可以混淆捕食者。

      通过这些适应,拟态在生态相互作用和物种的生存中发挥着重要作用。

    42. mosaic

      mosaic

      English Explanation

      The term "mosaic" has several meanings, depending on the context in which it is used:

      1. Artistic Definition: In the realm of art, a mosaic refers to a decorative technique where small pieces of colored glass, stone, or other materials are arranged to create a larger image or pattern. This technique has been used since ancient times, often seen in the flooring and wall decorations of Roman and Byzantine architecture.

      2. Biological Definition: In biology, mosaic can refer to an organism or a matter composed of genetically different cells. An example of this is a "mosaic" organism, which has cells that have different genetic makeups, such as in certain cases of chimerism where two embryos merge into one.

      3. Cultural Definition: In a cultural or social context, the term "mosaic" can describe a society that is composed of diverse groups and cultures, each contributing to the larger identity of the community. This is often used to describe societies that embrace multiculturalism and diversity, as opposed to a "melting pot" where distinct identities blend into one.

      4. Data Visualization: In data visualization, a mosaic plot (or mosaic diagram) is a graphic representation of data that shows the relationships between two or more categorical variables in a structured way, often using rectangles to indicate proportions.

      Chinese Explanation

      “马赛克”这个词根据其使用的不同上下文,有几种含义:

      1. 艺术定义:在艺术领域,马赛克指的是一种装饰技术,利用小块彩色玻璃、石头或其他材料来排列成一个更大的图像或图案。这种技术自古以来就被使用,常见于罗马和拜占庭建筑中的地板和墙壁装饰。

      2. 生物学定义:在生物学中,马赛克可以指由基因不同的细胞组成的生物体。例如,“马赛克”生物体,其中的细胞具有不同的基因组成,比如在某些嵌合体的情况下,两个胚胎合并成一个。

      3. 文化定义:在文化或社会背景下,“马赛克”可以描述一个由多样化群体和文化组成的社会,每个群体都对整个社区的身份贡献力量。这通常用于形容一个拥抱多元文化和多样性的社会,相对于“熔炉”概念,在熔炉中,各种身份融为一体。

      4. 数据可视化:在数据可视化中,马赛克图(或马赛克图表)是一种图形表示数据的方法,显示两个或多个分类变量之间的关系,通常使用矩形表示比例。

      In summary, the word "mosaic" is versatile and rich in meaning, spanning across various fields such as art, biology, cultural studies, and data representation. The concept of bringing together various elements—whether materials, cells, cultural identities, or data representations—is central to all these definitions.

    43. crossing over

      crossing over

      English Explanation:

      "Crossing over" is a term that can have different meanings depending on the context in which it is used:

      1. In Genetics: Crossing over refers to the process during meiosis (a type of cell division) where homologous chromosomes exchange segments of their genetic material. This process increases genetic diversity among offspring and is a critical mechanism in evolution. It typically occurs during prophase I of meiosis when the chromosomes are paired up.

      2. In Literature and Communication: Crossing over may refer to the act of transitioning between different genres, styles, or forms of expression. This can also apply to storytelling where a narrative combines elements from various traditions or cultural stories.

      3. In Everyday Language: It can refer to moving from one side to another, such as when someone crosses a street or a boundary, indicating a physical movement or a change in situation.

      4. In Psychology: It could also signify the crossing from one mental state or phase of life to another, such as overcoming obstacles or transitions in personal development.

      Each of these interpretations highlights a different aspect of the concept, emphasizing the idea of exchange, transition, or transformation.

      Chinese Explanation:

      “交叉”这个术语在不同的上下文中可以有不同的含义:

      1. 在遗传学中:交叉指的是在减数分裂(细胞分裂的一种)过程中,同源染色体交换其遗传物质的片段。这个过程增加了后代的遗传多样性,是进化中的一个重要机制。通常发生在减数分裂的前期 I,当时染色体成对存在。

      2. 在文学和沟通中:交叉可能指的是在不同的体裁、风格或表现形式之间的过渡。这也可以应用于讲故事的方式,其中一个叙事结合了来自各种传统或文化故事的元素。

      3. 在日常语言中:它可以指从一侧移动到另一侧,比如当某人过马路或越过边界时,表示一种物理运动或情况的变化。

      4. 在心理学中:它也可以表示从一种心理状态或人生阶段过渡到另一种状态,例如克服障碍或个人发展的转变。

      每种解释突出了这个概念的不同方面,强调了交流、过渡或转变的思想。

    44. mitosis

      mitosis

      English Explanation:

      Mitosis is a type of cell division that results in two genetically identical daughter cells from a single parent cell. It is essential for growth, tissue repair, and asexual reproduction in organisms. The process of mitosis is divided into several stages:

      1. Prophase: The chromosomes condense and become visible, the nuclear envelope breaks down, and the spindle apparatus forms.

      2. Metaphase: The chromosomes align along the middle of the cell, known as the metaphase plate.

      3. Anaphase: The sister chromatids are pulled apart to opposite poles of the cell.

      4. Telophase: The chromosomes begin to de-condense, the nuclear envelope reforms around each set of chromosomes, and the spindle apparatus disassembles.

      Finally, after mitosis is complete, cytokinesis occurs, which is the division of the cytoplasm, resulting in two separate daughter cells. Mitosis is crucial because it ensures that each daughter cell receives an exact copy of the parent cell's DNA, maintaining genetic consistency.


      中文解释:

      有丝分裂(mitosis)是一种细胞分裂的方式,它使一个母细胞分裂成两个基因组完全相同的子细胞。这一过程对于生长、组织修复和无性繁殖至关重要。有丝分裂过程可以分为几个阶段:

      1. 前期(Prophase):染色体开始凝缩并变得可见,核膜破裂,纺锤体装置形成。

      2. 中期(Metaphase):染色体沿着细胞中间对齐,形成中期板。

      3. 后期(Anaphase):姐妹染色单体被拉向细胞的两极。

      4. 末期(Telophase):染色体开始解凝缩,核膜重新在每组染色体周围形成,纺锤体装置解体。

      最后,在有丝分裂完成后,还会发生细胞质分裂(cytokinesis),即细胞质的分裂,最终形成两个独立的子细胞。有丝分裂非常重要,因为它确保每个子细胞都获得母细胞DNA的精确副本,从而维持遗传的一致性。

    45. geneticists

      geneticists

      Certainly! Here’s a thorough explanation of the term "geneticists" in both English and Chinese.

      English Explanation

      Geneticists are scientists who specialize in the study of genes, genetic variation, and heredity in living organisms. Their work involves understanding how traits are inherited and how genetic information is passed from one generation to the next. Geneticists employ various techniques and methodologies to analyze DNA, RNA, and proteins to explore the underlying principles of genetics.

      They may work in various fields, including:

      1. Medical Genetics: Studying genetic disorders and exploring potential treatments.
      2. Molecular Genetics: Investigating the molecular mechanisms that govern gene expression and regulation.
      3. Population Genetics: Analyzing the distribution and changes of gene variants in populations over time.
      4. Plant and Animal Breeding: Applying genetic principles to enhance desirable traits in crops and livestock.

      Geneticists often collaborate with other scientists and healthcare professionals to develop new therapies, conduct research, and contribute to our understanding of biology, evolution, and medicine.

      Chinese Explanation

      遗传学家(geneticists)是专门研究基因、基因变异和生物体遗传特征的科学家。他们的工作涉及理解特征如何被遗传以及基因信息如何从一代传承到下一代。遗传学家运用各种技术和方法来分析DNA、RNA和蛋白质,以探索遗传学的基本原理。

      他们可能在多个领域工作,包括:

      1. 医学遗传学:研究遗传性疾病并探索潜在的治疗方法。
      2. 分子遗传学:研究控制基因表达和调控的分子机制。
      3. 种群遗传学:分析基因变异在种群中的分布和随时间的变化。
      4. 植物和动物育种:应用遗传学原理来增强作物和家畜中的优良特性。

      遗传学家通常与其他科学家和医疗专业人员合作,开发新疗法、进行研究,并为我们对生物学、进化和医学的理解做出贡献。

    46. allele

      allele

      English Explanation:

      An allele is a variant form of a gene that is located at a specific position on a specific chromosome. Genes, which are segments of DNA, are responsible for the hereditary traits of an organism, and alleles determine the variations of those traits. For example, in humans, the gene for eye color has multiple alleles, such as those that code for brown, blue, or green eyes.

      Alleles can be classified as:

      1. Dominant Alleles: These are expressed in the phenotype even if only one copy is present. For example, if the allele for brown eyes is dominant, a person with one brown eye allele and one blue eye allele will have brown eyes.

      2. Recessive Alleles: These require two copies to be expressed in the phenotype. Using the same example, a person with two blue eye alleles will have blue eyes only if they do not have a dominant brown eye allele.

      3. Homozygous: An individual with two identical alleles for a trait (e.g., two brown eye alleles).

      4. Heterozygous: An individual with two different alleles for a trait (e.g., one brown eye allele and one blue eye allele).

      Alleles play a crucial role in genetics and evolution as they contribute to the diversity of traits in populations and can affect the likelihood of certain traits being passed down to future generations.


      中文解释:

      等位基因是位于特定染色体上特定位置的基因变体。基因是DNA的片段,负责有机体的遗传特征,而等位基因决定了这些特征的变异。例如,在人类中,负责眼睛颜色的基因有多种等位基因,例如编码棕色、蓝色或绿色眼睛的基因。

      等位基因可以分类为:

      1. 显性等位基因: 这些等位基因即使只有一个副本存在,也会在表现型中表达出来。例如,如果棕色眼睛的等位基因是显性的,那么一个有一个棕色眼睛等位基因和一个蓝色眼睛等位基因的人会有棕色眼睛。

      2. 隐性等位基因: 这些等位基因需要两个副本才能在表现型中表达出来。以同样的例子,一个有两个蓝色眼睛等位基因的人只有在没有显性棕色眼睛等位基因的情况下才会有蓝色眼睛。

      3. 同型合子: 对于某一特征,一个个体有两个相同的等位基因(例如,两个棕色眼睛等位基因)。

      4. 异型合子: 对于某一特征,一个个体有两个不同的等位基因(例如,一个棕色眼睛等位基因和一个蓝色眼睛等位基因)。

      等位基因在遗传学和进化中扮演着重要角色,因为它们有助于种群特征的多样性,并可能影响特定特征被传递给后代的可能性。

    47. snail

      snail

      Certainly! Let's break down the word "snail" and explore its meanings and contextual uses thoroughly in both English and Chinese.

      English Explanation:

      Definition:

      A "snail" is a common name for a gastropod mollusk, a type of animal that typically has a coiled shell and a soft, unsegmented body. Snails can be found in various environments, including gardens, forests, and aquatic habitats.

      Characteristics:

      1. Physical Appearance: Snails usually have a spiraled shell that can provide protection from predators and harsh environmental conditions. Their bodies are often slimy due to the secretion of mucus, which helps them move smoothly over surfaces.

      2. Movement: Snails are known for their slow movement, which is facilitated by a muscular foot that glides along surfaces with the help of mucus.

      3. Habitat: They can be terrestrial (land snails), aquatic (water snails), or even arboreal (tree snails). Each species has adapted to its surroundings in unique ways.

      4. Diet: Most snails are herbivores and feed on a variety of plant materials, though some are omnivores or carnivores.

      5. Reproduction: Many snails are hermaphrodites, meaning they possess both male and female reproductive organs, allowing them to mate with any other individual of their species.

      Cultural Significance:

      In various cultures, snails have been symbolic of slow progress or patience. They are also sometimes featured in literature, art, and cuisine—especially in French cooking, where "escargots" (snails) are considered a delicacy.

      Chinese Explanation (中文解释):

      定义:

      蜗牛是胃足纲软体动物的通称,一种通常具有螺旋状壳和柔软、无分节身体的动物。蜗牛可以在多个环境中找到,包括花园、森林和水生栖息地。

      特征:

      1. 外观:蜗牛通常具有螺旋形的壳,可以保护自己免受捕食者和恶劣环境的侵害。它们的身体因分泌粘液而常常显得湿滑,这有助于它们在表面上平稳移动。

      2. 运动:蜗牛以缓慢移动而闻名,运动是通过一块肌肉足和粘液的作用来实现的。

      3. 栖息地:它们可以是陆生(陆地蜗牛)、水生(水蜗牛)或甚至是树生(树蜗牛)的。每种物种都以独特的方式适应其环境。

      4. 饮食:大多数蜗牛是草食性,主要以各种植物材料为食,虽然有些也是杂食性或食肉性。

      5. 繁殖:许多蜗牛是雌雄同体的,意味着它们同时具有雄性和雌性生殖器官,可以与同种的任何个体交配。

      文化意义:

      在各种文化中,蜗牛常常象征着缓慢的进展或耐心。在文学、艺术和烹饪中,蜗牛时常被作为题材,尤其在法式烹饪中,“蜗牛”(escargots)被视为一种美味佳肴。

      This summary of the word "snail" highlights its biological, ecological, and cultural aspects in both English and Chinese.

    48. strung

      strung

      The term "strung" can have different meanings depending on the context in which it is used. Below is a thorough explanation of the word in both English and Chinese:

      English Explanation:

      "Strung" is the past participle of the verb "string." To "string" means to thread something through a line or cord, or to arrange objects in a series or line. Here are a few different contexts in which "strung" might be used:

      1. Physical Meaning: In the most literal sense, "strung" can refer to fitting items like beads, lights, or other objects onto a string or rope. For example, "The beads were strung together to make a necklace."

      2. Figurative Meaning: In a metaphorical sense, "strung" can describe a situation where someone is under a lot of stress or emotional tension. For example, "He was feeling strung out after weeks of working long hours." Here, it implies that the person is stretched thin, similar to a tightly pulled string.

      3. Musical Context: In music, "strung" may refer to the setup of instruments that have strings, such as guitars, violins, etc. For example, "The violin was strung with new strings for the concert."

      4. Cultural Idioms: The phrase "strung up" can also refer to someone being punished or put in a difficult situation. For instance, "After the investigation, he felt like he was being strung up by the media."

      Chinese Explanation:

      "Strung" 是动词 "string" 的过去分词。 "String" 的意思是将某物通过线或绳子穿起来,或者将物体排列成一系列或一条线。以下是 "strung" 可能在不同语境中使用的几个例子:

      1. 物理意义: 在最直接的意义上,"strung" 可以指将珠子、灯光或其他物体串在绳子或线上的动作。例如,"珠子被串在一起做成项链。"

      2. 比喻意义: 在比喻意义上,"strung" 可以描述一个人处于很大的压力或情绪紧张的状态。例如,"经过几周的长时间工作,他感到非常紧张。" 在这里,表示这个人被拉得很紧,就像被拉紧的绳子。

      3. 音乐上下文: 在音乐中,"strung" 可能指那些有弦的乐器的设置,比如吉他、小提琴等。例如,"为了音乐会,小提琴换上了新弦。"

      4. 文化习语: 短语 "strung up" 也可以指某人受到惩罚或陷入困难境地。例如,"调查后,他感觉自己像是被媒体绳之以法。"

      Overall, the understanding of "strung" requires an awareness of the context in which it appears, as its meaning can vary significantly. <br /> 总的来说,"strung" 的理解需要对出现的语境有一定的认识,因为它的意义可能会有很大的不同。

    49. mats

      mats

      The excerpt provided is simply the word "mats." Since this word can have multiple meanings, I will explain it thoroughly in both English and Chinese.

      English Explanation:

      The term "mats" refers to plural forms of "mat." A mat is typically a piece of fabric or material that is used to cover a floor or ground surface. Mats are often used for various purposes, including:

      1. Doormats: Placed at the entrance of homes to trap dirt and moisture from shoes.
      2. Yoga Mats: Used during yoga exercises to provide cushioning and support for the body.
      3. Area Rugs: Decorative mats that enhance the aesthetic appeal of a room.
      4. Exercise Mats: Used for performing workouts, providing protection and support during physical activities.
      5. Car Mats: Protect the floor of a vehicle from dirt, mud, and wear.

      In summary, "mats" can refer to various kinds of mats used in domestic, recreational, and professional contexts.

      Chinese Explanation (中文解释):

      “mats”这个词是“mat”的复数形式。“mat”通常指的是一种用于覆盖地板或地面表面的织物或材料。垫子通常用于多种用途,包括:

      1. 门垫:放置在家庭入口处,以捕捉鞋子上的污垢和水分。
      2. 瑜伽垫:在瑜伽练习中使用,以提供身体的缓冲和支持。
      3. 区域地毯:装饰性垫子,增强房间的美观。
      4. 运动垫:用于进行锻炼,提供保护和支持,以便进行身体活动。
      5. 汽车垫:保护车辆的地板免受污垢、泥土和磨损。

      总之,“mats”可以指各种用于家庭、娱乐和专业场合的垫子。

      If you have a specific context in which you want to understand the word "mats," please provide more details, and I can give you a more tailored explanation!

    50. contingent

      contingent

      The term "contingent" has several meanings and uses, depending on the context in which it is applied. Here’s a thorough explanation in both English and Chinese:

      English Explanation:

      1. General Definition: The word "contingent" generally refers to something that is dependent on certain conditions or circumstances. It implies that one event or situation is conditional upon the occurrence of another.

      2. In Logic and Philosophy: In logic, a contingent proposition is one that is neither necessarily true nor necessarily false. Its truth value can change depending on circumstances.

      3. In Business and Law: In a business or legal context, "contingent" often describes obligations or events that are set to occur only if certain conditions are met. For example, a contingent liability is a potential obligation that may arise, depending on the outcome of a future event, like a lawsuit.

      4. As a Noun: As a noun, "contingent" can refer to a group of people who represent a larger organization, usually in a specific context like a meeting, event, or gathering.

      Chinese Explanation (中文解释):

      1. 一般定义: “contingent”这个词通常指的是依赖于特定条件或情况的事物。它暗示一个事件或情况是基于另一个事件的发生而存在的。

      2. 在逻辑和哲学中: 在逻辑学中,contingent命题是指既不是必然真实,也不是必然虚假的命题。它的真实性随着情况的变化而变化。

      3. 在商业和法律中: 在商业或法律的上下文中,“contingent”通常描述的是只有在某些条件满足的情况下才会发生的义务或事件。例如,contingent liability(或称或有负债)是指可能出现的潜在义务,其发生依赖于未来事件的结果,例如诉讼。

      4. 作为名词: 作为名词,“contingent”可以指代表一个更大组织的一组人,通常在某个特定的场合,如会议、活动或聚会上。

      Summary:

      The concept of "contingent" highlights the importance of conditions and dependence on various factors, whether in logic, business, or general use. In both English and Chinese, it underscores the intricate relationships between events and conditions that define their outcomes.

      总结:“contingent” 的概念强调了条件的重要性和对各种因素的依赖,无论是在逻辑、商业还是一般用法中。在英语和中文中,它突出了事件和条件之间复杂的关系,这决定了它们的结果。

    51. affinity

      affinity

      English Explanation

      The term "affinity" generally refers to a natural liking, attraction, or relationship between two entities. It can be used in various contexts, such as:

      1. Biology and Chemistry: Affinity describes the degree to which two substances are attracted to each other. For example, in biochemistry, it can refer to how strongly an enzyme binds to its substrate.

      2. Social Context: In social interactions, "affinity" may refer to the emotional bond or connection between people. For instance, two individuals may feel an affinity for each other due to shared interests or values.

      3. Literature and Art: The term can also refer to the harmonious or appealing connection between different elements in art or literature. For example, a writer might express an affinity for a particular literary style.

      4. General Use: More broadly, affinity can signify any type of attraction or similarity between individuals or objects, such as "affinity for nature" or "affinity for a particular genre of music."

      In each of these contexts, the concept of affinity encompasses ideas of connection, relationship, and attraction based on inherent qualities or shared characteristics.

      中文解释

      “亲和力”(affinity)一词通常指两个实体之间的自然喜好、吸引力或关系。它可以在各种上下文中使用,例如:

      1. 生物学和化学:亲和力描述了两种物质相互吸引的程度。例如,在生物化学中,它可能指酶与其底物结合的强度。

      2. 社会交往:在社会互动中,“亲和力”可以指人们之间的情感纽带或联系。例如,由于共同的兴趣或价值观,两个人可能会感到相互之间有亲和力。

      3. 文学和艺术:这个术语也可以指艺术或文学中不同元素之间的和谐或吸引人的联系。例如,一个作家可能会对某种特定的文学风格表现出亲和力。

      4. 一般用法:更广泛来说,亲和力可以表示个人或物体之间任何类型的吸引或相似性,例如“对自然的亲和力”或“对特定音乐风格的亲和力”。

      在这些上下文中,亲和力的概念涵盖了基于内在特质或共享特征的连接、关系和吸引力的思想。

    52. coupons

      coupons

      English Explanation

      The term "coupons" generally refers to vouchers or documents that provide a discount or a special offer when purchasing goods or services. They can be physical printouts or digital codes that a consumer can apply at checkout, either in-store or online. Coupons are widely used in retail and marketing as a strategy to attract customers, encourage product trials, and increase sales.

      1. Types of Coupons:
      2. Discount Coupons: Offer a specific percentage or amount off the purchase price.
      3. Free Shipping Coupons: Waive shipping costs for online purchases.
      4. Buy One Get One Free (BOGO): Offers customers an additional product for free when they buy a specified item.
      5. Cashback Coupons: Reimburse a portion of the purchase price after the transaction.

      6. Usage: Coupons can be found in newspapers, magazines, online platforms, through email newsletters, or even on social media. Consumers are encouraged to use coupons to save money or obtain products at a reduced price.

      7. Strategies for Retailers: Businesses use coupons to:

      8. Attract new customers.
      9. Promote seasonal sales or new products.
      10. Retain existing customers by offering incentives.

      11. Expiration and Conditions: Most coupons come with expiration dates and specific conditions for use, such as minimum purchase requirements or applicable products.

      中文解释

      “优惠券”(coupons)通常是指在购买商品或服务时提供折扣或特别优惠的凭证或文件。它们可以是实体的纸质凭证或数字代码,消费者在结账时可以使用,无论是在实体店还是在线。优惠券在零售和营销中被广泛使用,作为吸引顾客、鼓励产品试用和增加销售的一种策略。

      1. 优惠券的类型
      2. 折扣优惠券:提供特定的百分比或金额的购买折扣。
      3. 免邮优惠券:在线购买时免除运费。
      4. 买一赠一(BOGO):当顾客购买特定商品时,免费赠送额外商品。
      5. 返现优惠券:在交易后返还一部分购买价格。

      6. 使用方式:优惠券可以在报纸、杂志、在线平台、电子邮件通讯,甚至社交媒体上找到。消费者被鼓励使用优惠券以节省开支或以较低价格获得产品。

      7. 零售商的策略:商家使用优惠券来:

      8. 吸引新顾客。
      9. 促销季节性商品或新产品。
      10. 通过提供激励保留现有顾客。

      11. 有效期和使用条件:大多数优惠券都有有效期和特定的使用条件,例如最低购买要求或适用产品。

      Overall, coupons serve as a valuable tool for both consumers seeking savings and retailers aiming to drive sales.

    53. ammonia:

      ammonia:

      English Explanation

      Ammonia is a colorless gas with a distinct pungent smell, primarily composed of nitrogen and hydrogen, and its chemical formula is NH₃. It is produced naturally by the decomposition of organic matter and is extensively used in various industries.

      In nature, ammonia is generated through processes such as the breakdown of nitrogenous organic materials, making it a vital component in the nitrogen cycle, which is essential for plant and animal life. In industrial settings, ammonia is commonly synthesized via the Haber-Bosch process, which combines nitrogen from the air with hydrogen derived from fossil fuels.

      Ammonia serves several purposes, including:

      1. Fertilizer Production: It is a key ingredient in nitrogenous fertilizers, promoting plant growth.
      2. Cleaning Agents: Due to its high alkalinity, ammonia is used in various cleaning products for its ability to cut through grease and stains.
      3. Refrigeration: Ammonia is used as a refrigerant in large-scale cooling systems due to its efficient heat absorption properties.
      4. Manufacturing: It’s utilized in the production of plastics, explosives, and other chemicals.

      However, ammonia can be toxic at high concentrations and requires careful handling to prevent potential health hazards.

      中文解释

      是一种无色气体,具有明显刺鼻的气味,主要由氮和氢组成,其化学式为NH₃。氨是通过有机物分解自然生成的,并在各个行业中被广泛使用。

      在自然界中,氨是通过氮含量有机物料的分解过程产生的,因而它在氮循环中扮演着重要角色,这一过程对植物和动物生命至关重要。在工业环境中,氨通常是通过哈柏-博施法合成的,该方法将空气中的氮与来自化石燃料的氢结合。

      氨的用途包括:

      1. 肥料生产:它是氮肥的主要成分,促进植物生长。
      2. 清洁剂:由于其高碱性,氨被用于各种清洁产品中,能够有效去除油脂和污渍。
      3. 制冷剂:氨被用于大规模制冷系统中,因为它在热量吸收方面非常有效。
      4. 制造业:它在塑料、炸药和其他化学品的生产中被广泛应用。

      然而,氨在高浓度下可能具有毒性,因此需要小心处理,以防止潜在的健康危害。

    54. globule

      The term "globule" generally refers to a small spherical body or droplet. It can be used in various scientific contexts, such as:

      1. Biology: In biology, globules can refer to small spherical structures, such as fat globules found in emulsions or blood globules (like red and white blood cells).

      2. Chemistry: In chemistry, it may describe small droplets of liquid, often within a different liquid (like oil globules in water).

      3. Physics: In physics, globules may refer to small particles that behave as if they were solid bodies under certain conditions.

      4. Astrophysics: The term can also be used to describe small, dense clouds of gas or dust in space, such as globules of gas within nebulae.

      If you need more specific information or context related to "globule," feel free to ask!

    55. springing

      It seems like you're looking for information or context related to the word "springing." The term can have multiple meanings depending on the context:

      1. Physical Movement: "Springing" often refers to a quick or sudden movement, such as leaping or jumping. For example, "The athlete is springing off the blocks at the start of the race."

      2. Bouncing or Resilience: It can also describe an object returning to its original shape after being compressed or stretched, such as a spring in machinery or a mattress.

      3. Emergence: In a more metaphorical sense, "springing" can refer to the sudden emergence of something, such as ideas that spring to mind or flowers that spring up in springtime.

      4. Literal Spring Season: It could also simply evoke the feelings and events of spring, such as renewal, growth, and the beauty of nature.

      If there’s a specific context you're interested in, please provide more details!

    56. pests

      It seems like you're looking for information about pests. Pests can refer to various organisms that are considered undesirable or harmful in certain contexts, such as agriculture, gardening, or even in homes. Here’s a brief overview of different types of pests:

      Types of Pests

      1. Insects:
      2. Agricultural Pests: Aphids, beetles, caterpillars, and locusts can damage crops.
      3. Household Pests: Ants, cockroaches, termites, and bed bugs can invade homes.

      4. Rodents:

      5. Rats and mice are common pests that can cause damage to structures and spread diseases.

      6. Weeds:

      7. Unwanted plants that compete with cultivated crops for nutrients, water, and sunlight.

      8. Fungi:

      9. Some species can be harmful to crops, leading to diseases in plants.

      10. Birds:

      11. Certain birds can be pests when they feed on crops or invade structures.

      Control and Management

      1. Cultural Controls:
      2. Crop rotation, intercropping, and maintaining healthy soil can help prevent pest infestations.

      3. Biological Controls:

      4. Introducing natural predators or parasites to control pest populations.

      5. Chemical Controls:

      6. Pesticides and herbicides can be used, but they should be applied carefully to minimize environmental impact.

      7. Physical Controls:

      8. Barriers, traps, and handpicking can effectively manage pests without chemicals.

      9. Integrated Pest Management (IPM):

      10. A holistic approach combining multiple methods for effective pest management.

      Prevention Tips

      • Keep areas clean and free of food debris.
      • Seal cracks and holes in buildings to prevent rodent entry.
      • Regularly inspect plants for early signs of pests.
      • Use native or pest-resistant plant varieties in landscaping.

      If you have specific pests in mind or need information on a certain aspect of pest control, feel free to ask!

    57. unionism

      Unionism is a political and social movement that advocates for the unification of communities, regions, or countries. The term can be understood in various contexts, including:

      1. Labor Unionism: In this context, unionism refers to the organization of workers into unions to collectively negotiate with employers over wages, working conditions, and other labor rights. Labor unions seek to protect the interests of workers and advocate for their rights in the workplace.

      2. Political Unionism: This refers to the political movement that promotes the union of separate entities into a single political unit. For example, in the context of the United Kingdom, unionism often relates to the desire to maintain the political union of England, Scotland, Wales, and Northern Ireland, opposing movements for independence.

      3. Nationalism and Ethnic Unionism: Some movements advocate for the unification of people based on shared national or ethnic identities. This form of unionism can be seen in the context of historical struggles for independence or self-determination.

      4. Social Unionism: This aspect of unionism focuses on building solidarity among various social groups, advocating for rights and justice, and fostering community engagement.

      Overall, unionism has various interpretations and implications depending on the historical, cultural, and political context in which it is applied.

    58. thrust

      The term "thrust" can have several meanings depending on the context:

      1. Physics and Engineering: In the context of mechanics, thrust refers to the force exerted by engines or propellers to propel an object, such as an aircraft or rocket. It is typically measured in newtons (N) or pounds (lb).

      2. Literature and Rhetoric: Thrust can refer to the main point or central idea of an argument, narrative, or piece of writing.

      3. Martial Arts: In martial arts and fighting techniques, a thrust refers to a quick, forward motion, typically with a weapon like a sword or spear, aimed at an opponent.

      4. General Usage: More broadly, the word can mean to push or drive something with force in a particular direction.

      If you have a specific context in which you're interested in the term "thrust," feel free to ask!

    59. limps

      The term "limps" can refer to a few different contexts. Here are some possible interpretations:

      1. Physical Condition: In a medical or physical context, "limps" generally refers to an alteration in the way a person or animal walks due to pain, injury, or deformity in a limb. It can be a temporary condition resulting from injury or a chronic condition due to illness or structural problems.

      2. Music: In a musical context, "limps" could be a misinterpretation of "lips" as in "limp" or "lilting" in performance or rhythm, though it's less common.

      3. Slang or Colloquial Use: "Limps" may also be used informally to describe something that is weak, flaccid, or lacking in strength or vitality.

      4. Mathematics: In mathematical discussions, "limp" or "limps" might refer to the concept of limits, although it is not a standard term.

      If you meant something specific by "limps," please provide more context so I can assist you better!

    60. hawk

      The word "hawk" can refer to several different things, depending on the context:

      1. Bird of Prey: Hawks are birds known for their keen eyesight, strong talons, and hunting skills. They belong to the family Accipitridae and are often found in various habitats around the world.

      2. Military Term: In political context, a "hawk" refers to someone who advocates for aggressive or warlike policies, particularly in foreign relations. This is in contrast to a "dove," who typically favors diplomacy and peace.

      3. Slang: In some contexts, "hawk" can also be used to describe someone who sells goods or services aggressively, or in a more negative sense, it can refer to someone who preys on the vulnerable.

      4. Sports: The term is also used in sports, such as the "Chicago Blackhawks," an NHL team.

      If you have a specific context in mind, feel free to share!

    61. inhibitory

      The term "inhibitory" generally refers to something that prevents, restricts, or slows down a process or activity. It is commonly used in various contexts, including:

      1. Biology/Pharmacology: Inhibitory refers to substances or mechanisms that decrease the activity of enzymes, neurotransmitters, or physiological processes. For instance, inhibitory neurotransmitters like gamma-aminobutyric acid (GABA) reduce neuronal excitability.

      2. Psychology: Inhibitory control is a cognitive process that allows individuals to regulate their thoughts, actions, and impulses. It is crucial for decision-making and self-regulation.

      3. Chemistry: Inhibitory compounds can refer to molecules that impede chemical reactions or disrupt biochemical pathways.

      4. Education: Inhibitory experiences can include negative feedback or restrictive policies that limit students' creativity or engagement.

      If you have a specific context in mind for "inhibitory," please provide more details, and I can elaborate further!

    62. stride

      The term "stride" can refer to several different concepts depending on the context. Here are a few interpretations:

      1. Walking or Running: A stride is the length of a person's step while walking or running. It can refer to the distance covered when one leg moves forward or the overall pattern of movement.

      2. Figurative Use: Metaphorically, "to take something in stride" means to accept or deal with a situation calmly and without panic.

      3. Stride in Computing: In computer science, particularly in array processing and memory, stride refers to the distance in memory between elements of an array. It indicates how far apart array elements are located in memory.

      4. Stride in Music: In music theory, it may refer to the interval between notes or the regular movement between pitches.

      If you have a specific context in mind for "stride," please provide more details!

    63. suppress

      It seems like you're looking for information or a definition related to the term "suppress." The word "suppress" can have various meanings depending on the context:

      1. To put down by force: It can refer to the act of restraining or preventing something from happening, such as suppressing a rebellion or a protest.

      2. To keep something from being expressed: This can relate to emotions or thoughts, such as suppressing anger or fear.

      3. In scientific contexts: It can refer to inhibiting a process, such as suppressing the growth of bacteria in microbiology.

      4. In psychology: It may refer to the act of consciously or unconsciously blocking out painful thoughts or memories.

      If you have a specific context in mind or need more detailed information, please let me know!

    64. baboons

      Baboons are primates belonging to the genus Papio, which are part of the family Cercopithecidae, also known as Old World monkeys. There are five species of baboons: the olive baboon (Papio anubis), yellow baboon (Papio cynocephalus), chacma baboon (Papio ursinus), redeared baboon (Papio angusticeps), and hamadryas baboon (Papio hamadryas).

      Here are some key characteristics and behaviors of baboons:

      1. Social Structure: Baboons live in large, complex social groups known as troops, which can consist of a few dozen to several hundred individuals. These troops have a hierarchical structure governed by dominance and social relationships.

      2. Diet: Baboons are omnivorous and will eat a varied diet that includes fruits, seeds, roots, insects, and sometimes small animals. Their ability to adapt their diet is one of the factors contributing to their success in various habitats.

      3. Habitat: They are primarily found in Africa, inhabiting savannas, woodlands, and even some urban areas. The hamadryas baboon is also found in the Arabian Peninsula.

      4. Communication: Baboons are known for their vocalizations, body language, and facial expressions, which they use to communicate with one another about food, threats, and social interactions.

      5. Intelligence: Baboons are considered to be highly intelligent and exhibit problem-solving skills, tool use, and social learning. They can adapt to changing environments and often show complex social behaviors.

      6. Conservation: While some baboon species are relatively common and widespread, others face threats due to habitat loss, hunting, and human-wildlife conflict.

      If you have specific questions about baboons or would like more detailed information, feel free to ask!

    65. fallacy

      A fallacy is an error in reasoning or logic that undermines the validity of an argument. Fallacies can be formal, where the flaw lies in the structure of the argument, or informal, where the flaw lies in the content or context of the argument.

      Here are a few common types of fallacies:

      1. Ad Hominem: Attacking the person making the argument rather than the argument itself.
      2. Straw Man: Misrepresenting an opponent’s argument to make it easier to attack.
      3. Appeal to Authority: Relying on the opinion of someone deemed an expert, rather than providing solid evidence.
      4. False Dichotomy: Presenting only two options in a situation where more options exist.
      5. Slippery Slope: Arguing that a relatively small first step will lead to a chain of related events culminating in a significant impact.

      Understanding fallacies is important for evaluating arguments critically and engaging in more effective reasoning.

    66. nasty

      “Nasty” is an English adjective (and occasionally noun) with several related senses:

      1. Very unpleasant or disagreeable

      2. She got a nasty headache after the trip.

      3. The smell in that alley was absolutely nasty.

      4. Malicious or spiteful

      5. He said some really nasty things about her behind her back.

      6. That was a nasty trick to play on your friend.

      7. Dangerous or severe (informal)

      8. They got caught in a nasty storm at sea.

      9. Be careful—that cut looks nasty and might get infected.

      10. Sexually explicit or lewd (slang)

      11. He made a few nasty jokes at the party.

      12. They were swapping nasty stories.

      As a noun, “a nasty” can mean something (or someone) that’s offensive or unpleasant:

      Watch out for the wasps—they can be real nasties.


      Synonyms

      • Unpleasant: disagreeable, distasteful
      • Malicious: spiteful, mean, vindictive
      • Severe/Dangerous: fierce, brutal
      • Lewd: bawdy, ribald

      Translation into Chinese

      • 讨厌的 (tǎoyàn de) – unpleasant, annoying
      • 恶意的 (è yì de) – malicious, spiteful
      • 严重的 (yánzhòng de) – severe, nasty (e.g., injury)
      • 下流的 (xiàliú de) – lewd, dirty

      Usage notes

      • Context is key: calling someone “nasty” in casual conversation usually means they’re rude or unkind; in medical or weather contexts it often means severe or dangerous.
      • Tone can range from mild (“that sandwich was nasty”) to strong condemnation (“that was a nasty betrayal”).

      Feel free to let me know if you’d like example sentences in another context or more on its history and etymology!

    1. Note: This response was posted by the corresponding author to Review Commons. The content has not been altered except for formatting.

      Learn more at Review Commons


      Reply to the reviewers

      Reviewer #1 (Evidence, reproducibility and clarity (Required)):

      Comments for the authors of Review Commons Manuscript RC-2024-02804:

      The author of the Review Commons manuscript "Antigen flexibility supports the avidity of hemagglutinin-specific antibodies at low antigen densities", present their recent work evaluating hemagglutinin interactions with cellular receptors and antibodies. This manuscript focuses specifically on the avidity of the hemagglutinin using a fluorescence-based assay to measure dissociation kinetics and steady-state binding of antibodies to virions. Their findings confirm that bivalent interactions can offset weak monovalent affinity and that HA ectodomain flexibility is an additional determinant of antibody avidity. These findings are key for our understanding of neutralizing antibodies. Below are some comments that I would like the authors to address as they revise the manuscript.

      Comments:

      1. Can the authors provide justification for the two influenza viruses that they used.

      We selected the lab-adapted IAV strains A/WSN/1933 (H1N1) and A/Hong Kong/1968 (H3N2) for this work because they are well-studied, including in the context of the antibodies used here, S139/1 and C05. While both antibodies bind to more contemporary H3N2 strains, they no not bind to HA from pandemic H1N1. Another feature of these strains is that their HAs have high enough affinity to both antibodies to enable strong signal in our imaging assays. This context for our strain selection has been added in lines 85-88.

      1. The use of filamentous particles is a strength, but authors should detail the role of filamentous vs. spherical in nature and lab settings. This will help researchers that plan to repeat these assays.

      We have revised the text (lines 336-339) to include more context on the biology of filamentous and spherical influenza viruses. In our experiments, HK68 naturally produces filaments in cell culture whereas WSN33 does not. To produce filaments artificially, we replace the M1 sequence from WSN33 with that of M1 from A/Udorn/1972, an H3N2 strain that is closely related to HK68.

      1. Did the authors add the Udorn M1 to the HK68 as well?

      Since HK68 naturally forms filaments, we did not introduce Udorn M1 into this strain. We note that the amino acid sequences of Udorn M1 and HK68 M1 differ only at position 167 (Alanine in Udorn, Threonine in HK68), and that this residue has previously been found to not correlate with virus morphology (10.1016/j.virol.2003.12.009).

      Reviewer #1 (Significance (Required)):

      This manuscript focuses specifically on the avidity of the hemagglutinin using a fluorescence-based assay to measure dissociation kinetics and steady-state binding of antibodies to virions. Thie findings confirm that bivalent interactions can offset weak monovalent affinity and that HA ectodomain flexibility is an additional determinant of antibody avidity. These findings are key for our understanding of neutralizing antibodies.

      Reviewer #2 (Evidence, reproducibility and clarity (Required)):

      Summary

      In this study, Benegal et al. investigate the binding kinetics of HA-head-specific antibodies (S139/1 and C05) to intact influenza virus particles using a fluorescence microscopy-based technique to measure the dissociation rate (koff) of the antibodies. By applying their proposed equilibrium model for bivalent antibody binding to HA, the authors calculated the crosslinking rate (kx), which represents the rate at which a single-bound antibody crosslinks to an additional HA molecule. Their experiments revealed that antigen crosslinking significantly slows koff, reducing it by up to two orders of magnitude. The authors further utilized streptavidin-coated beads conjugated with biotinylated HA or biotinylated BSA at varying concentrations to control HA surface density. Their results demonstrated that the two tested HA-head-specific antibodies retained the ability to crosslink HAs even at ~10-fold lower HA surface densities. In a complementary experiment, they employed an HA-anchor-specific antibody to restrict HA flexibility, which led to reduced binding of S139/1 and C05 IgGs but not their Fab fragments. This finding suggests that HA flexibility, rather than density, is the primary determinant of antibody crosslinking and avidity. Overall, the authors present an innovative approach to elucidating the dissociation and crosslinking kinetics of antibodies targeting intact virions or nanoparticles. The study is well-designed, with alternative interpretations of the results carefully considered and addressed throughout. I have only a few minor comments and suggestions for clarification.

      Minor comments:

      1. In Figure 1, does the grey color of each IgG in panel C indicate the Fc domain? If so, please add the description of the colors to the figure legend. In fact, it may be better to explain all the colors used here (for HA1, HA2, Fab heavy chain, light chain, etc.).

      We have included this information in panel C and the caption for Figure 1.

      1. Under the section," Bivalent binding of S139/1 and C05 persists after ~10-fold reductions in HA surface densities", the beginning of the second paragraph writes, "For both S139/1 and C05 Fab, binding increases linearly with HA density, as expected for a monovalent interaction dictated by absolute HA availability rather than density (Fig. 3D). Interestingly, the same relationship is observed for S139/1 IgG."

      Visually, I think the same relationship also seems to hold for C05 IgG. Would it be better to perform some linear regression and report the R2 value for the fitting so that this assessment can be quantitative?

      We agree with the reviewer's point. In Figure 3 of the revised manuscript, we include the results from a linear regression analysis to make this assessment more quantitative.

      1. At the end of the same page, in the same paragraph, the authors mentioned, "In contrast to the IgG, Fab binding measured at twice the molar concentration of the IgG is nearly undetectable under these conditions, confirming the IgG binding is not occurring through monovalent interactions (Fig. S2E)." What are the conditions you are referring to? In Fig. S2E, there is only the Ab intensity for the Ab binding at 100% HA (and not the other percentages). For the Ab intensity of S139/1 Fab, what is the concentration of the Fab used in Figure 3D? Why could the intensity in this experiment for S139/1 Fab reach ~100,000, whereas that of the 8 nM in Fig. S2E can only reach ~20,000?

      To clarify this point, we have updated Figure 3 to include the antibody concentration used for each experiment. The experiments in Fig 3 are conducted approximately around the respective KD of each IgG or Fab to ensure both consistency and strong signal-to-noise. For S139/1, we use 4nM of IgG, and 25nM of Fab. In Fig S2E, we use a concentration of Fab fragments double to that of the IgG, to reach an equivalent concentration of binding sites and confirm that the IgG binding we see is indeed due to bivalent binding. In this case, we use 4nM of IgG and 8nM of Fab.

      1. Under the section, "Tilting of HA about its membrane anchor contributes to C05 and S139/1 avidity", in the second paragraph, the authors wrote, "If this is correct, we reasoned that avidity could be reduced by constraining tilting of the HA ectodomain. To test this hypothesis, we used FISW84, an antibody that binds to the HA anchor epitope and biases the ectodomain into a tilted conformation (Fig. 4B)."

      Can you use some computational models (maybe the same one you used for Figure 4A) to show that when an HA trimer is bounded by FISW84 Fabs, the tilting of HA is constrained? I think this will help substantiate the assertion above.

      This is an important point. The model that we employ in Figure 4A is suited to predicting the angles sampled by HAs when they are bound by an IgG antibody, but it does not take into consideration clashes with the viral membrane. It is these clashes that we predict based on published structures (reference 35 in the revised manuscript) will constrain HA tilting when FISW84 binds to the HA anchor. We have revised the text (Lines 247-249) to clarify these points.

      1. It would be good if you could mention the strain of HA used in the experiments in Figure 4 in the actual Figure as well (as supposed to just in the figure legend).

      We have added this information to Figure 4 in the revised manuscript.

      1. I do not see a method section for the structure-based model you used in Figure 4. In the text, you cited your previous study (ref 28) for the model, but it would be good to write about this briefly (and how you specifically apply the model in this study) in this current manuscript.

      We have updated the methods to include a subsection ("Geometric Model for Preferred Crosslinking Geometry") on how the structure-based model was set up, along with a corresponding visual in Fig S3 of the angles of freedom given.

      1. In Figure S1 panel D, what is the unit of the antibody concentration? Could you please add it to the graph legend?

      We have updated the figure (S1E in the revised manuscript) to include this information.

      Reviewer #2 (Significance (Required)):

      Previously, this group utilized the same fluorescence-based method to investigate the potency of anti-HA IgG1 antibodies in preventing viral entry versus egress, as well as the tendency of antibodies targeting different HA epitopes to crosslink two HA trimers in cis or in trans (He et al., J Virol, 2024). In this study, they extend their work by evaluating, in-depth, how the density and flexibility of hemagglutinin (HA) on the viral surface influence the binding avidity of anti-HA antibodies. Using two human IgG1 antibodies targeting the HA head, the authors demonstrate that these antibodies can crosslink two HA trimers in cis, even when the trimers are further apart than adjacent HAs. Notably, the study reveals that HA flexibility, rather than density, is the key determinant modulating antibody crosslinking. Even at a 10-fold reduced HA density compared to the original, the antibodies retained their ability to crosslink trimers.

      This study provides critical insights into the relationship between HA density, flexibility, and antibody function, adding to the broader understanding of antibody crosslinking-a topic frequently discussed in the field of influenza research. These findings could have significant implications for vaccine design, particularly for strategies involving the display of the HA ectodomain on nanoparticles, potentially guiding the development of more effective influenza vaccines. Furthermore, the broader relevance of these findings may extend to other viruses with similar structural and immunological properties.

      My expertise lies in the structural determination of antibody-antigen complexes in influenza and other pathogens. While I may not have sufficient expertise to evaluate specific technical details of the fluorescence-based methods employed, the authors have convincingly demonstrated the robustness of their experimental design and interpretation, supported by appropriate controls.

      Reviewer #3 (Evidence, reproducibility and clarity (Required)):

      SUMMARY In "Antigen flexibility supports the avidity of hemagglutinin-specific antibodies at low antigen densities", Benegal et al. develop a microscopy-based assay to measure dissociation of HA head-binding antibodies from intact virions. This assay allows the authors to explore the contribution of IgG bivalent avidity to antibody interaction with native virions, which is not accessible using other methods such as BLI. Using this assay, the authors further explore the effect of HA density on IgG avidity with engineered low-HA virions and then with artificial HA-coated microspheres. In addition to measuring antibody dissociation, the authors perform structural analyses to predict the conformational preferences of many HA IgGs from published structures. The authors conclude that low HA densities (down to ~10%) still support high avidity binding for the 2 IgGs tested, and thus there would be little evolutionary pressure for IAV to reduce the HA density as a strategy to evade immune recognition.

      MAJOR COMMENTS

      The data presented are generally convincing for the two antibodies tested, with some caveats listed below. I believe the microscopy technique is valuable and provides a significant contribution to the field, and I believe that the finding that avidity persists at low densities for IAV is compelling and worth communicating to other virologists. Overall, with the incorporation of the suggested major revisions, this manuscript represents a significant advancement in the field.

      A major limitation of the current study is the small number of antibodies tested. Two antibodies are quite few, particularly since this work attempts to generalize these observations with structural predictions of dozens or hundreds of HA antibodies. While I believe that the resilience of IgG binding to lower epitope densities is likely common to many HA antibodies (or antibodies in general), this work alone does not support this. To this end, the authors should acknowledge their limited sample size in the text or discussion and that the generalization to other antibodies is speculative. Alternatively, the authors could demonstrate with additional antibodies (such as F045-092 which is pointed out in Fig S3A and perhaps group 'i' antibodies according to Fig S3A).

      This is an important point, and we more explicitly acknowledge this limitation in lines 277-278.

      It seems to me lateral diffusion of HA in the viral membrane is an important discussion point that was missed in this manuscript. The authors should comment on what is known about the lateral mobility of HA on virions, and how this could impact the ability of an IgG to crosslink. The authors should comment about whether long range diffusion and/or short range "shuffling" of glycoproteins could contribute to crosslinking preferences of antibodies in addition to the tilt, which is the only movement discussed. As appropriate, the authors should then comment on how this may affect their interpretation of experiments using beads. In experiments on beads, there is certainly no lateral mobility of the HA trimers; what are the consequences of this on the analysis?

      We agree that this is an important consideration, and we have revised the manuscript (lines 296-298) to address these points. Briefly, we have previously performed fluorescence recovery after photobleaching of covalently labeled HA and NA on the surface of filamentous influenza particles (10.7554/eLife.43764; see Figure 1B of this reference for a representative example). This data indicates that long range diffusion does not seem to be occurring on the virion surface. Short range diffusion, or shuffling, has not been observed, but cannot be ruled out, and may increase conformations favorable to bivalent binding.

      Should the authors qualify the limitations in the scope of their experimental results and the system of choice (beads vs. virions) as described in my previous comments, I suggest three experiments that I believe are essential to support the authors' claims. Alternative to qualifying the limitations, two optional experiments are also listed that could support the authors' claims as they are - those require a more extensive experimental undertaking and are thus labeled [OPTIONAL].

      1) The photobleaching experiment shown in Figure S1A. I am concerned that measuring photobleaching in steady state conditions does not properly control for the experimental conditions. In steady state, bleached antibody could unbind and be replaced by fluorescent antibody that has diffused into the field of view. This should be more thoroughly controlled by irreversibly capturing antibody (such as with biotin) and imaging after excess antibody is washed away, or by some other method such as capturing and imaging virus that has been directly labeled with AF555. This should be possible using reagents and techniques already demonstrated by the authors.

      We have updated the supplemental information with a more rigorous control for photobleaching; the revised figures are shown in Fig S1A. In this experiment, fluorescent S139/1 IgG was bound to HK68 virions. The antibody was washed away, and the loss of fluorescence signal was imaged separately under two conditions: 1) Dissociation only; an image was collected at 0s and one at 60s. 2) Dissociation and photobleaching; an image was collected at a rate of 1 frame per second for 60 seconds. The difference between the endpoint intensities from both conditions is not statistically significant. This supports our conclusion that, in the absence of antibodies in solution that can exchange with those bound to virions, photobleaching does not make a detectable contribution to the loss of signal we observe in our antibody dissociation experiments.

      2) In imaging, the authors analyzed only filamentous virions because they exhibit the best signal to noise ratio, which is a reasonable technical simplification. However, this relies on the assumption that glycoprotein presentation is relatively constant between virions of different sizes. It would be helpful to perform some analysis of small virions in any movie where there is sufficient signal. This would support the assumption that rates for small virions are comparable to those of filaments in the same experiment. This should be possible by performing additional analysis on existing data, without requiring additional experiments.

      Thank you for calling our attention to a point that needs clarification. The analysis that was restricted to filaments was for the SEP-HA binding experiments (shown in Fig 3A&B). This was done in order to select only those particles that were not diffraction-limited, so that we could control for any systematic differences in size between the two populations by measuring HA signal per unit particle length. For the dissociation experiments (Fig 2), data was taken from all virions in the fields of view. For this analysis, the normalized dissociation curves were averaged in two ways to account for the potential discrepancy that the reviewer points out. In the first method, the average was taken with each virion equally weighted, while in the second method, the entire field of view was masked and normalized together. Both curves look very similar, suggesting that any potential differences between smaller virions and filaments are not enough to make a quantifiable difference in dissociation rate. A representative dissociation curve with both analyses shown side-by-side has been added in Figure S1B.

      3) In figure 3, C05 fab binding is used to assay HA content of the SEP HA virions. An additional method of confirming HA content that is more independent from the imaging assay would be beneficial, such as a Western blot to quantify HA relative to NP, NA, or M1 etc.

      We have used western blotting to quantify the amount of HA contained relative to M1 in each population. This new data is discussed in lines 163-168 of the revised manuscript and shown in Figure S2C. As noted in the revised text, western blot analysis suggests that the density of native HA is decreased to ~31% its normal level in SEP-HA virions, lower than the ~75% value determined via fluorescence microscopy. One possible reason for this disparity is the presence of virus-like particles in the SEP-HA sample that completely lack wildtype HA. These would be excluded from our imaging analysis but captured by the western blot.

      4) [OPTIONAL] In figure 4, it is depicted that FISW84 biases HA in a tilted conformation, and the authors reasonably propose the reduced flexibility discourages crosslinking by IgGs. From the modeling summarized in Figure S3A, are there any antibodies predicted to prefer crosslinking HA at the same angle FISW84 tilts the ectodomain? Would FISW84 enhance crosslinking by such an antibody?

      This is an interesting suggestion, and we have revised the manuscript (lines 247-249) to clarify our thinking on this point. Based on the structure of the FISW84 Fab (PDB ID 6HJQ), we conclude that binding of a single Fab fragment does not necessarily actively tilt the HA ectodomain in a specific direction. Rather, it restricts tilting in the direction that would cause a steric clash between the Fab and the membrane. As a result, HA can still sample a range of angles, but this range is no longer symmetrical about the ectodomain axis. By reducing the likelihood that two HA ectodomains would tilt towards each other at a favorable angle, we would expect all antibodies to be disadvantaged to some degree. A possible exception could be if three FISW84 Fab fragments manage to bind to a single HA trimer. In this case, the HA ectodomain would be forced to remain perpendicular to the membrane to accommodate them all. This would favor antibodies that prefer binding to HAs where the ectodomains are parallel to each other. In our analysis in Figure S3A, this includes primarily antibodies that bind to the HA central stalk, such as 31.b.09. However, we note that these antibodies may encounter barriers to bivalent binding that we do not consider here, including proximity to the FISW84 epitope and the high density of HA in the membrane.

      5) [OPTIONAL] In figure S3A, the authors display theoretical tilt and spacing preferences for many HA antibodies based on published structures. Interestingly, their group iii antibody is predicted to prefer greater spacing and tilt, and likewise the authors observe increased binding at lower densities (in figure 3E). It would be beneficial to the work to test group i antibodies (base binding) in the dissociation experiments. The behavior of a base binding antibody, particularly at low densities could reinforce the modeling performed for this work.

      This is an excellent suggestion which we are not currently able to pursue for technical reasons. In particular, it would be difficult to distinguish between increased binding of these antibodies at low antigen densities that is due to bivalent attachment (and thus reduced dissociation) versus increased accessibility of the epitope, which may be occluded at higher HA densities.

      The experiments are well explained and supported by methods that would enable reproducibility.

      The authors state "The statistical tests and the number of replicates used in specific cases are described in the figure legends" yet in many cases this information is absent. For the k values in fig 2D, some indication of error or confidence interval would be helpful.

      We have ensured that this information is included in each of the captions. Regarding the k values, formal error propagation is challenging due to the way the k values were derived. Specifically, these values were calculated by fitting the average of the three initial dissociation traces, rather than fitting each replicate individually and then averaging the rate constants. As a result, the usual methods for estimating confidence intervals or standard error of the mean are not directly applicable.

      MINOR COMMENTS

      o Some of the small details in fig 1A and fig S1 are lost due to small figure size - such as the sialic acid residues and lipid bilayer.

      We have resized the figure components.

      o Although described in the text, it could be helpful to incorporate into figure 2 why the BLI data is shown for S129 fab. Perhaps indicate in 2C that that curve is "too fast to accurately measure" and perhaps near the table in 2D indicate the blue data is from Lee et al. It may be fine to simply remove the BLI results from the figure and refer to them only in the discussion of the experiments. Even with the measured data, the difference between fab and IgG is striking enough to support the paper, and the BLI data may be more confusing in the figure than it adds.

      We have updated the caption for Figure 2D to clarify that binding between the S139/1 Fab and A/WSN/1933 HA is approaching the limit of detection in our assay, and that the additional rates are from Lee et al. We have also updated the table to make the presentation of the kinetic parameters more clear.

      o In figure 3A, better describe the fluorescent components in the fluorescent images in the legend.

      We have updated the caption for Figure 3A to describe the fluorescent components shown in the image. Specifically, the panel labeled 'HA' shows signal from a fluorescent FI6v3 scFv, while the panel labeled 'decoy' shows signal from the SEP-HA construct.

      o From personal experience, the flexibility of HA ectodomain can be significantly affected by how much of the membrane proximal linker region is retained or removed. Could the authors comment on how they chose the cutoff for their HA ectodomain used in the bead experiments and their rationale?

      This is an important point, and while the precise impact of the linker on HA flexibility remains uncertain, we agree that it may increase the freedom of motion of the ectodomain relative to the HA membrane anchor. We mention this caveat in the revised text (lines 188-191) and we have added an AlphaFold2 prediction of how our recombinant HA might look to Figure S2D.

      o In Figure S1B, if I understand correctly: black dashed line "IgG equivalent dissociation rate" is the experimental data, magenta "Crosslinking model fit" is the theoretically total antibody bound as described by the mathematical model. Then the gray lines "Double- /singly- bound antibodies plot the theoretical amount of antibody bound once and bound twice. If this is correct, I believe it would be clearer if the singly- and doubly- bound were plotted in separate colors, and that this is explained more clearly in the legend.

      We have revised the figure to show doubly- and singly-bound curves using different line styles.

      o Related to an earlier comment, if lateral diffusion may play a role, how might this differ between different types of antibodies?

      As mentioned in our previous response, we do not anticipate that lateral diffusion makes a significant contribution to antibody binding to the surface of virions, although it may be important on the cell surface.

      o Could the authors comment in the discussion on how their results on virions may translate to the surface of the infected cell, which is also decorated in viral glycoproteins? Early time points of infection could be an in vivo example of low-density HA. What extent may antibody binding and crosslinking affect viral proteins on the cell surface or the immune response?

      This is a very interesting point. Antibody binding to the infected cell surface has been shown to alter viral release and morphology, presumably at lower HA densities than those observed the viral surface. We have added a brief discussion of this point (lines 291-295) to the revised manuscript.

      o The github link in the methods is incorrect or not yet available.

      Thank you for noting this. We have updated the link.

      o Reference 1 has an incorrect or expired link.

      These references have been updated.

      Reviewer #3 (Significance (Required)):

      • This work represents a conceptual advance in our understanding of antibody action on viral pathogens. The authors adapt existing microscopy methodologies to measure antibody avidity in a new way that is better representative of in vivo conditions.

      • To my knowledge, this is the first instance of direct measurement of antibody off-rates from intact virus particles, instead of immobilized protein as in BLI, SPR, or interferometry.

      • This work should be of interest to virologist and biophysicists interested in the cooperative binding of antibodies and the relation of virus structural organization to antibody recognition. Immunologist may also be influenced by this work. This work may be followed up by other researchers similarly measuring the association and dissociation rates of antibodies with single virions, or otherwise comparing fab to IgG binding to gain insight into when crosslinking is or is not occurring.

      • Reviewer expertise: Single-virion imaging, protein complexes, biochemistry, influenza A.

      • I do not have sufficient expertise to evaluate the mathematical models and differential equations for modeling the k-on and k-off rates.

    2. Note: This preprint has been reviewed by subject experts for Review Commons. Content has not been altered except for formatting.

      Learn more at Review Commons


      Referee #3

      Evidence, reproducibility and clarity

      Summary

      In "Antigen flexibility supports the avidity of hemagglutinin-specific antibodies at low antigen densities", Benegal et al. develop a microscopy-based assay to measure dissociation of HA head-binding antibodies from intact virions. This assay allows the authors to explore the contribution of IgG bivalent avidity to antibody interaction with native virions, which is not accessible using other methods such as BLI. Using this assay, the authors further explore the effect of HA density on IgG avidity with engineered low-HA virions and then with artificial HA-coated microspheres. In addition to measuring antibody dissociation, the authors perform structural analyses to predict the conformational preferences of many HA IgGs from published structures. The authors conclude that low HA densities (down to ~10%) still support high avidity binding for the 2 IgGs tested, and thus there would be little evolutionary pressure for IAV to reduce the HA density as a strategy to evade immune recognition.

      Major comments

      The data presented are generally convincing for the two antibodies tested, with some caveats listed below. I believe the microscopy technique is valuable and provides a significant contribution to the field, and I believe that the finding that avidity persists at low densities for IAV is compelling and worth communicating to other virologists. Overall, with the incorporation of the suggested major revisions, this manuscript represents a significant advancement in the field.

      A major limitation of the current study is the small number of antibodies tested. Two antibodies are quite few, particularly since this work attempts to generalize these observations with structural predictions of dozens or hundreds of HA antibodies. While I believe that the resilience of IgG binding to lower epitope densities is likely common to many HA antibodies (or antibodies in general), this work alone does not support this. To this end, the authors should acknowledge their limited sample size in the text or discussion and that the generalization to other antibodies is speculative.

      Alternatively, the authors could demonstrate with additional antibodies (such as F045-092 which is pointed out in Fig S3A and perhaps group 'i' antibodies according to Fig S3A).

      It seems to me lateral diffusion of HA in the viral membrane is an important discussion point that was missed in this manuscript. The authors should comment on what is known about the lateral mobility of HA on virions, and how this could impact the ability of an IgG to crosslink. The authors should comment about whether long range diffusion and/or short range "shuffling" of glycoproteins could contribute to crosslinking preferences of antibodies in addition to the tilt, which is the only movement discussed. As appropriate, the authors should then comment on how this may affect their interpretation of experiments using beads. In experiments on beads, there is certainly no lateral mobility of the HA trimers; what are the consequences of this on the analysis?

      Should the authors qualify the limitations in the scope of their experimental results and the system of choice (beads vs. virions) as described in my previous comments, I suggest three experiments that I believe are essential to support the authors' claims. Alternative to qualifying the limitations, two optional experiments are also listed that could support the authors' claims as they are - those require a more extensive experimental undertaking and are thus labeled [OPTIONAL].

      1. The photobleaching experiment shown in Figure S1A. I am concerned that measuring photobleaching in steady state conditions does not properly control for the experimental conditions. In steady state, bleached antibody could unbind and be replaced by fluorescent antibody that has diffused into the field of view. This should be more thoroughly controlled by irreversibly capturing antibody (such as with biotin) and imaging after excess antibody is washed away, or by some other method such as capturing and imaging virus that has been directly labeled with AF555. This should be possible using reagents and techniques already demonstrated by the authors.
      2. In imaging, the authors analyzed only filamentous virions because they exhibit the best signal to noise ratio, which is a reasonable technical simplification. However, this relies on the assumption that glycoprotein presentation is relatively constant between virions of different sizes. It would be helpful to perform some analysis of small virions in any movie where there is sufficient signal. This would support the assumption that rates for small virions are comparable to those of filaments in the same experiment. This should be possible by performing additional analysis on existing data, without requiring additional experiments.
      3. In figure 3, C05 fab binding is used to assay HA content of the SEP HA virions. An additional method of confirming HA content that is more independent from the imaging assay would be beneficial, such as a Western blot to quantify HA relative to NP, NA, or M1 etc.
      4. [OPTIONAL] In figure 4, it is depicted that FISW84 biases HA in a tilted conformation, and the authors reasonably propose the reduced flexibility discourages crosslinking by IgGs. From the modeling summarized in Figure S3A, are there any antibodies predicted to prefer crosslinking HA at the same angle FISW84 tilts the ectodomain? Would FISW84 enhance crosslinking by such an antibody?
      5. [OPTIONAL] In figure S3A, the authors display theoretical tilt and spacing preferences for many HA antibodies based on published structures. Interestingly, their group iii antibody is predicted to prefer greater spacing and tilt, and likewise the authors observe increased binding at lower densities (in figure 3E). It would be beneficial to the work to test group i antibodies (base binding) in the dissociation experiments. The behavior of a base binding antibody, particularly at low densities could reinforce the modeling performed for this work.

      The experiments are well explained and supported by methods that would enable reproducibility.

      The authors state "The statistical tests and the number of replicates used in specific cases are described in the figure legends" yet in many cases this information is absent. For the k values in fig 2D, some indication of error or confidence interval would be helpful.

      Minor Comments

      • Some of the small details in fig 1A and fig S1 are lost due to small figure size - such as the sialic acid residues and lipid bilayer.
      • Although described in the text, it could be helpful to incorporate into figure 2 why the BLI data is shown for S129 fab. Perhaps indicate in 2C that that curve is "too fast to accurately measure" and perhaps near the table in 2D indicate the blue data is from Lee et al. It may be fine to simply remove the BLI results from the figure and refer to them only in the discussion of the experiments. Even with the measured data, the difference between fab and IgG is striking enough to support the paper, and the BLI data may be more confusing in the figure than it adds.
      • In figure 3A, better describe the fluorescent components in the fluorescent images in the legend.
      • From personal experience, the flexibility of HA ectodomain can be significantly affected by how much of the membrane proximal linker region is retained or removed. Could the authors comment on how they chose the cutoff for their HA ectodomain used in the bead experiments and their rationale?
      • In Figure S1B, if I understand correctly: black dashed line "IgG equivalent dissociation rate" is the experimental data, magenta "Crosslinking model fit" is the theoretically total antibody bound as described by the mathematical model. Then the gray lines "Double-/singly- bound antibodies plot the theoretical amount of antibody bound once and bound twice. If this is correct, I believe it would be clearer if the singly- and doubly-bound were plotted in separate colors, and that this is explained more clearly in the legend.
      • Related to an earlier comment, if lateral diffusion may play a role, how might this differ between different types of antibodies?
      • Could the authors comment in the discussion on how their results on virions may translate to the surface of the infected cell, which is also decorated in viral glycoproteins? Early time points of infection could be an in vivo example of low-density HA. What extent may antibody binding and crosslinking affect viral proteins on the cell surface or the immune response?
      • The github link in the methods is incorrect or not yet available.
      • Reference 1 has an incorrect or expired link.

      Significance

      • This work represents a conceptual advance in our understanding of antibody action on viral pathogens. The authors adapt existing microscopy methodologies to measure antibody avidity in a new way that is better representative of in vivo conditions.
      • To my knowledge, this is the first instance of direct measurement of antibody off-rates from intact virus particles, instead of immobilized protein as in BLI, SPR, or interferometry.
      • This work should be of interest to virologist and biophysicists interested in the cooperative binding of antibodies and the relation of virus structural organization to antibody recognition. Immunologist may also be influenced by this work. This work may be followed up by other researchers similarly measuring the association and dissociation rates of antibodies with single virions, or otherwise comparing fab to IgG binding to gain insight into when crosslinking is or is not occurring.
      • Reviewer expertise: Single-virion imaging, protein complexes, biochemistry, influenza A.
      • I do not have sufficient expertise to evaluate the mathematical models and differential equations for modeling the k-on and k-off rates.
    3. Note: This preprint has been reviewed by subject experts for Review Commons. Content has not been altered except for formatting.

      Learn more at Review Commons


      Referee #2

      Evidence, reproducibility and clarity

      Summary

      In this study, Benegal et al. investigate the binding kinetics of HA-head-specific antibodies (S139/1 and C05) to intact influenza virus particles using a fluorescence microscopy-based technique to measure the dissociation rate (koff) of the antibodies. By applying their proposed equilibrium model for bivalent antibody binding to HA, the authors calculated the crosslinking rate (kx), which represents the rate at which a single-bound antibody crosslinks to an additional HA molecule. Their experiments revealed that antigen crosslinking significantly slows koff, reducing it by up to two orders of magnitude.

      The authors further utilized streptavidin-coated beads conjugated with biotinylated HA or biotinylated BSA at varying concentrations to control HA surface density. Their results demonstrated that the two tested HA-head-specific antibodies retained the ability to crosslink HAs even at ~10-fold lower HA surface densities. In a complementary experiment, they employed an HA-anchor-specific antibody to restrict HA flexibility, which led to reduced binding of S139/1 and C05 IgGs but not their Fab fragments. This finding suggests that HA flexibility, rather than density, is the primary determinant of antibody crosslinking and avidity.

      Overall, the authors present an innovative approach to elucidating the dissociation and crosslinking kinetics of antibodies targeting intact virions or nanoparticles. The study is well-designed, with alternative interpretations of the results carefully considered and addressed throughout. I have only a few minor comments and suggestions for clarification.

      Minor comments:

      1. In Figure 1, does the grey color of each IgG in panel C indicate the Fc domain? If so, please add the description of the colors to the figure legend. In fact, it may be better to explain all the colors used here (for HA1, HA2, Fab heavy chain, light chain, etc.).
      2. Under the section," Bivalent binding of S139/1 and C05 persists after ~10-fold reductions in HA surface densities", the beginning of the second paragraph writes, "For both S139/1 and C05 Fab, binding increases linearly with HA density, as expected for a monovalent interaction dictated by absolute HA availability rather than density (Fig. 3D). Interestingly, the same relationship is observed for S139/1 IgG."

      Visually, I think the same relationship also seems to hold for C05 IgG. Would it be better to perform some linear regression and report the R2 value for the fitting so that this assessment can be quantitative? 3. At the end of the same page, in the same paragraph, the authors mentioned, "In contrast to the IgG, Fab binding measured at twice the molar concentration of the IgG is nearly undetectable under these conditions, confirming the IgG binding is not occurring through monovalent interactions (Fig. S2E)." What are the conditions you are referring to? In Fig. S2E, there is only the Ab intensity for the Ab binding at 100% HA (and not the other percentages). For the Ab intensity of S139/1 Fab, what is the concentration of the Fab used in Figure 3D? Why could the intensity in this experiment for S139/1 Fab reach ~100,000, whereas that of the 8 nM in Fig. S2E can only reach ~20,000? 4. Under the section, "Tilting of HA about its membrane anchor contributes to C05 and S139/1 avidity", in the second paragraph, the authors wrote, "If this is correct, we reasoned that avidity could be reduced by constraining tilting of the HA ectodomain. To test this hypothesis, we used FISW84, an antibody that binds to the HA anchor epitope and biases the ectodomain into a tilted conformation (Fig. 4B)."

      Can you use some computational models (maybe the same one you used for Figure 4A) to show that when an HA trimer is bounded by FISW84 Fabs, the tilting of HA is constrained? I think this will help substantiate the assertion above. 5. It would be good if you could mention the strain of HA used in the experiments in Figure 4 in the actual Figure as well (as supposed to just in the figure legend). 6. I do not see a method section for the structure-based model you used in Figure 4. In the text, you cited your previous study (ref 28) for the model, but it would be good to write about this briefly (and how you specifically apply the model in this study) in this current manuscript. 7. In Figure S1 panel D, what is the unit of the antibody concentration? Could you please add it to the graph legend?

      Significance

      Previously, this group utilized the same fluorescence-based method to investigate the potency of anti-HA IgG1 antibodies in preventing viral entry versus egress, as well as the tendency of antibodies targeting different HA epitopes to crosslink two HA trimers in cis or in trans (He et al., J Virol, 2024). In this study, they extend their work by evaluating, in-depth, how the density and flexibility of hemagglutinin (HA) on the viral surface influence the binding avidity of anti-HA antibodies. Using two human IgG1 antibodies targeting the HA head, the authors demonstrate that these antibodies can crosslink two HA trimers in cis, even when the trimers are further apart than adjacent HAs. Notably, the study reveals that HA flexibility, rather than density, is the key determinant modulating antibody crosslinking. Even at a 10-fold reduced HA density compared to the original, the antibodies retained their ability to crosslink trimers.

      This study provides critical insights into the relationship between HA density, flexibility, and antibody function, adding to the broader understanding of antibody crosslinking-a topic frequently discussed in the field of influenza research. These findings could have significant implications for vaccine design, particularly for strategies involving the display of the HA ectodomain on nanoparticles, potentially guiding the development of more effective influenza vaccines. Furthermore, the broader relevance of these findings may extend to other viruses with similar structural and immunological properties.

      My expertise lies in the structural determination of antibody-antigen complexes in influenza and other pathogens. While I may not have sufficient expertise to evaluate specific technical details of the fluorescence-based methods employed, the authors have convincingly demonstrated the robustness of their experimental design and interpretation, supported by appropriate controls.

    1. La variable puede tomar 5 valores plausibles a partir del puntaje logrado por los estudiantes: Bajo del nivel 1 (menos de 407 puntos), Nivel 1 (desde 407 hasta 491 puntos), Nivel 2 (desde 492 hasta 576 puntos), Nivel 3 (desde 557 hasta 661 puntos) y el Nivel 4 (sobre 661 puntos).

      en esta descripción es confuso si la variable es ordinal o continua

    1. Applying strict scrutiny to the case at hand, the Policy fails. OSU lacks a compelling state interest.While the nation and Olympus do have a history of sex discrimination, more of the same will notsolve that problem – one that is in the rear window. We have or have had female judges andjustices, governors, mayors, cabinet secretaries, a speaker of the house (twice), and a vicepresident. Rather than solving a problem, the School has created new problems. Even if the Schoolproffered a compelled interest, which it has not, its means do not advance that interest in a mannerthat is narrowly tailored. Put simply, OSU could have pursued a course of action that was lessrestrictive. There are many ways to attract female students beyond the discriminatory practicesemployed here. The School, for instance, might utilize enhanced recruitment techniques, advertisein female dominated media markets, or aggressively recruit female candidates, to name but afew. Such methods might accomplish similar results. The existence of such alternatives undercutsthe argument that the Policy is least restrictive and thus not narrowly tailored.

      14A questions-- 1) scruitiny level? 2) level of restriveness? 3) state interest? 4) narrowly tailored?

    1. Author response:

      The following is the authors’ response to the original reviews

      Public Reviews: 

      Reviewer #1 (Public review): 

      Summary: 

      Walton et al. set out to isolate new phages targeting the opportunistic pathogen Pseudomonas aeruginosa. Using a double ∆fliF ∆pilA mutant strain, they were able to isolate 4 new phages, CLEW-1. -3, -6, and -10, which were unable to infect the parental PAO1F Wt strain. Further experiments showed that the 4 phages were only able to infect a ∆fliF strain, indicating a role of the MS-protein in the flagellum complex. Through further mutational analysis of the flagellum apparatus, the authors were able to identify the involvement of c-di-GMP in phage infection. Depletion of c-di-GMP levels by an inducible phosphodiesterase renders the bacteria resistant to phage infection, while elevation of c-di-GMP through the Wsp system made the cells sensitive to infection by CLEW-1. Using TnSeq, the authors were able to not only reaffirm the involvement of c-di-GMP in phage infection but also able to identify the exopolysaccharide PSL as a downstream target for CLEW-1. C-di-GMP is a known regulator of PSL biosynthesis. The authors show that CLEW-1 binds directly to PSL on the cell surface and that deletion of the pslC gene resulted in complete phage resistance. The authors also provide evidence that the phage-PSL interaction happens during the biofilm mode of growth and that the addition of the CLEW-1 phage specifically resulted in a significant loss of biofilm biomass. Lastly, the authors set out to test if CLEW-1 could be used to resolve a biofilm infection using a mouse keratitis model. Unfortunately, while the authors noted a reduction in bacterial load assessed by GFP fluorescence, the keratitis did not resolve under the tested parameters. 

      Strengths: 

      The experiments carried out in this manuscript are thoughtful and rational and sufficient explanation is provided for why the authors chose each specific set of experiments. The data presented strongly supports their conclusions and they give present compelling explanations for any deviation. The authors have not only developed a new technique for screening for phages targeting P. aeruginosa, but also highlight the importance of looking for phages during the biofilm mode of growth, as opposed to the more standard techniques involving planktonic cultures. 

      Weaknesses: 

      While the paper is strong, I do feel that further discussions could have gone into the decision to focus on CLEW-1 for the majority of the paper. The paper also doesn't provide any detailed information on the genetic composition of the phages. It is unclear if the phages isolated are temperate or virulent. Many temperate phages enter the lytic cycle in response to QS signalling, and while the data as it is doesn't suggest that is the case, perhaps the paper would be strengthened by further elimination of this possibility. At the very least it might be worth mentioning in the discussion section. 

      Thank you for your review. The genomes of all Clew phages and Ocp-2 have been uploaded [Genbank accession# PQ790658.1, PQ790659.1, PQ790660.1, PQ790661.1, and PQ790662.1]. It turns out that the Clew phage are highly related, which is highlighted by the genomic comparison in the supplementary figure S1. It therefore made sense to focus our in-depth analysis on one of the phage. We have included a supplementary figure (S1A), demonstrating that the other Clew phage also require an intact psl locus for infection, to make that logic clearer. The phage are virulent (there is apparently a bit of a debate about this with regard to Bruynogheviruses, but we have not been able to isolate lysogens). This is now mentioned in the discussion.  

      Reviewer #2 (Public review): 

      This manuscript by Walton et al. suggests that they have identified a new bacteriophage that uses the exopolysaccharide Psl from Pseudomonas aeruginosa (PA) as a receptor. As Psl is an important component in biofilms, the authors suggest that this phage (and others similarly isolated) may be able to specifically target biofilm-growing bacteria. While an interesting suggestion, the manner in which this paper is written makes it difficult to draw this conclusion. Also, some of the results do not directly follow from the data as presented and some relevant controls seem to be missing. 

      Thank you for your review. We would argue that the combination of demonstrating Psl-dependent binding of Clew-1 to P. aeruginosa, as well as demonstration of direct binding of Clew-1 to affinity-purified Psl, indicates that the phage binds directly to Psl and uses it as a receptor. In looking at the recommendations, it appears that the remark about controls refers to not using the ∆pslC mutant alone (as opposed to the ∆fliF2 ∆pslC double mutant) as a control for some of the binding experiments. However, since the ∆fliF2 mutant is more permissive for phage infection, analyzing the effect of deleting pslC in the context of the ∆fliF2 mutant background is the more stringent test. 

      Recommendations for the authors:

      Reviewer #1 (Recommendations for the authors): 

      First off, I would like to congratulate the authors on this study and manuscript. It is very well executed and the writing and flow of the paper are excellent. The findings are intriguing and I believe the paper will be very well received by both the phage, Pseudomonas, and biofilm communities. 

      Thank you for your kind review of our work!

      I have very little to critique about the paper but I have listed a few suggestions that I believe could strengthen the paper if corrected: 

      Comments and suggestions: 

      (1) The paper initially describes 4 isolated phages but no rationale is given for why they chose to continue with CLEW-1, as opposed to CLEW-3, -6, and -10. The paper would benefit from going into more detail with phage genomics and perhaps characterize the phage receptor binding to PSL. 

      Clew-1, -3, -6, and -10 are actually quite similar to one another. The genomes are now uploaded to Genbank [accession# PQ790658.1, PQ790659.1, PQ790660.1, and PQ790661.1]. They all require an intact Psl locus for infection, we have updated Fig. S1 to show this for the remaining Clew phage. In the end, it made sense to focus on one of these related phage and characterize it in depth.

      (2) PA14 was used in some experiments but not listed in the strain table. 

      Thank you, this has been added in the resubmission.

      (3) Would have been good to see more strains/isolates used.

      We are currently characterizing the host range of Clew-1. It appears to be pretty limited, but this will likely be included in another paper that will focus on host range, not only of Clew-1, but other biofilm-tropic phage that we have isolated since then.

      (4) Could purified PSL be added to make non-PSL strain (like PA14) susceptible? 

      We have tried adding purified Psl to a psl mutant strain, but this does not result phage sensitivity. Further characterization of the Psl receptor, is something we are currently working on, but will likely be a much bigger story than can be easily accommodated in a revised manuscript.

      (5) No data on resistance development. 

      We have not done this as yet.

      (6) Alternative biofilm models. Both in vitro and in vivo. 

      We agree that exploring the interaction of Clew-1 with biofilms in greater detail is a logical next step. The revised manuscript does have data on the viability of P. aeruginosa biofilm bacteria after Clew-1 infection using either a bead biofilm model or LIVE/DEAD staining of static biofilms. However, expanding on this further (setting up flow-cell biofilms, developing reporters to monitor phage infection, etc.) is beyond the scope of this initial report and characterization of Clew-1.

      (7) There is a mistake in at least one reference. An unknown author is listed in reference 48. DA Garsin is not part of the paper. Might be worth looking into further mistakes in the reference list as I suspect this might be an issue related to the citation software.

      Thank you. Yes, odd how that extra author got snuck in. This has been corrected.

      (8) I don't seem to be able to locate a Genbank file or accession number. If it wasn't performed how was evolutionary relatedness data generated?

      The genomes of all Clew phages and Ocp-2 have been uploaded [Genbank accession# PQ790658.1, PQ790659.1, PQ790660.1, PQ790661.1, and PQ790662.1]

      (9) No genomic information about the isolated phages. Are they temperate or virulent? This would be important information as only strictly lytic phages are currently deemed appropriate for phage therapy. 

      These phage are virulent. We have only been able to isolate resistant bacteria from plaques, but they do not harbor the phage (as detected by PCR). This matches what other researchers have found for Bruynogheviruses.

      Reviewer #2 (Recommendations for the authors): 

      Others have used different PA mutants lacking known phage receptors to pan for new phages. However, it is not totally clear how the screen here was selected for the Psl-specific phage. The authors used flagella and pili mutants and found Clew-1, -3, -6, and -10. These were all Bruynogheviruses. They also isolated a phage that uses the O antigen as a receptor. The family of this latter phage and how it is known to use this as a receptor is not described. 

      Phage Ocp-2 is a Pbunavirus. We added new supplementary figure S3, addressing the O-antigen receptor.

      The authors focused on Clew-1, but the receptor for these other Clew phages is not presented. For Clew-1 the phage could plaque on the fliF deletion mutant but not the wild-type strain. The reason for this never appears to be addressed. The authors leap to consider the involvement of c-di-GMP, but how this relates to fliF appears to be lacking. 

      We have included a supplementary figure demonstrating that all the Clew phage require Psl for infection (Fig. S1A). As noted above, we have uploaded the genomic data that underpins the comparison in our supplementary figure. The phage are all closely related. It therefore made sense to focus on one of the phage for the analysis.  

      It is particularly unclear why this phage doesn't plaque on PAO1 as this strain does make Psl. Related to this, it actually looks like something is happening to PAO1 in Figure S4 (although what units are on the x-axis is not entirely clear).

      We hypothesize that the fraction of susceptible cells in the population dictates whether the phage can make overt plaques. The supplementary figure S4 indicates that a subpopulation of the wild-type culture is susceptible and this is borne out by the fraction of wild type cells that the phage can bind to (~50%). The fliF mutation increases this frequency of susceptible cells to 80-90% (Fig. 3).

      The Tnseq screen to identify receptors is clever and identifies additional phosphodiesterase genes, the deletion of which makes PAO1 susceptible. And the screen to find resistant fliF mutants identified genes involved in Psl. However, the link between the phosphodiesterase mutants and the amount of Psl produced never appears to be established. And the statement that Psl is required for infection (line 130) is never actually tested.

      The link between c-di-GMP and Psl production is well-established in the literature. I think the requirement for Psl in infection is demonstrated multiple ways, including lack of plaque formation on psl mutant strains and lack of phage binding to strains that do not produce Psl, direct binding of the phage to affinity purified Psl.

      Figure 2C describes using a ∆fliF2 strain but how this is different (or if it is different) from ∆fliF described in the text is never explained.

      The difference in the deletions is explained in table S1, in the description for the deletion constructs used in their construction, pEXG2-∆fliF and pEXG2-∆fliF2 (∆fliF2 is smaller than ∆fliF and can be complemented completely with our complementing plasmid, pP37-fliF, which is the reason why we used the ∆fliF2 mutation going forward, rather than the ∆fliF mutation on which the phage was originally isolated).

      Similarly, there is a sentence (line 138) that "Attachment of Clew-1 is Psl-dependent" but this would appear to have no context.

      The relevant figure, Fig. 3, is cited in the next sentence and is the subject of the remaining paragraphs in this section of the manuscript.

      For Figure 3B, why wasn't the single ∆pslC mutant visualized in this analysis? Similar questions relate to the data in Figure 4.

      Analyzing the effect of the pslC deletion in the context of the ∆fliF2 mutant background, which is more permissive for phage infection, is the more stringent test.  

      The efficacy of Clew-1 in the mouse keratitis model is intriguing but it is unclear why the CFU/eye are so variable. The description of how the experiment was actually carried out is not clear. Was only one eye scratched or both? Were controls included with a scratch and no bacteria ({plus minus} phage)?

      One eye was infected. We did not conduct a no-bacteria control (just scratching the cornea is not sufficient to cause disease). The revised manuscript has an updated animal experiment in which we carried the infection forward to 72h with two phage treatments. Following this regiment, there is a significant decrease in CFU, as well as corneal opacity (disease). Variability of the data is a fairly common feature in animal experiments. There are a number of factors, such as does the mouse blink and remove some of the inoculum shortly after deposition of the bacteria or the phage after each treatment that could explain this variability.

    1. Author response:

      The following is the authors’ response to the current reviews.

      Public Reviews:

      Reviewer #1 (Public review):

      Weaknesses:

      The revised manuscript has gained much clarity and consistency. One previous criticism, however, has in my opinion not been properly addressed. I think the problem boils down to not clearly distinguishing between orthologs and paralogs/homologs. As this problem affects a main conclusion - the prevalence of deletions over insertions in the MTBC - it should be addressed, if not through additional analyses, then at least in the discussion.

      Insertions and deletions are now distinguished in the following way: "Accessory regions were further classified as a deletion if present in over 50% of the 192 sub-lineages or an insertion/duplication if present in less than 50% of sub-lineages." The outcome of this classification is suspicious: not a single accessory region was classified as an insertion/duplication. As a check of sanity, I'd expect at least some insertions of IS6110 to show up, which has produced lineage- or sublineage-specific insertions (Roychowdhury et al. 2015, Shitikov et al. 2019). Why, for example, wouldn't IS6110 insertions in the single L8 strain show up here?

      In a fully clonal organism, any insertion/duplication will be an insertion/duplication of an existing sequence, and thus produce a paralog. If I'm correctly understanding your methods section, paralogs are systematically excluded in the pangraph analysis. Genomic blocks are summarized at the sublineage levels as follows (l.184 ): "The DNA sequences from genomic blocks present in at least one sub-lineage but completely absent in others were extracted to look for long-term evolution patterns in the pangenome." I presume this is done using blastn, as in other steps of the analysis.

      So a sublineage-specific copy of IS6110 would be excluded here, because IS6110 is present somewhere in the genome in all sublineages. However, the appropriate category of comparison, at least for the discussion of genome reduction, is orthology rather than homology: is the same, orthologous copy of IS6110, at the same position in the genome, present or absent in other sublineages? The same considerations apply to potential sublineage-specific duplicates of PE, PPE, and Esx genes. These gene families play important roles in host-pathogen interactions, so I'd argue that the neglect of paralogs is not a finicky detail, but could be of broader biological relevance.

      Within the analysis we undertook we did look at paralogous blocks in pangraph, based on copy number per genome. However, this could have been clearer in the text and we will rectify this. We also focussed on duplicated/deleted blocks that were present in two of more sub-lineages. This is noted in figure 4 legend but we will make this clearer in other sections of the manuscript.

      We agree that indeed the way paralogs are handled could still be optimised, and that gene duplicates of some genes could have biological importance. The reviewer is suggesting that a synteny analysis between genomes would be best for finding specific regions that are duplicated/deleted within a genome, and if those sections are duplicated/deleted in the same regions of the genome. Since Pangraph does not give such information readily, a larger amount of analysis would be required to confirm such genome position-specific duplications. While this is indeed important, we deem this to be out of scope for the current publication, but will note this as a limitation in the discussion. However, this does not fundamentally change the main conclusions of our analysis.


      The following is the authors’ response to the original reviews.

      Public Reviews:

      Reviewer #1 (Public Review):

      Summary:

      In this paper, Behruznia and colleagues use long-read sequencing data for 335 strains of the Mycobacterium tuberculosis complex to study genome evolution in this clonal bacterial pathogen. They use both a "classical" pangenome approach that looks at the presence and absence of genes, and a more general pangenome graph approach to investigate structural variants also in non-coding regions. The two main results of the study are that (1) the MTBC has a small pangenome with few accessory genes, and that (2) pangenome evolution is driven by deletions in sublineage-specific regions of difference. Combining the gene-based approach with a pangenome graph is innovative, and the former analysis is largely sound apart from a lack of information about the data set used. The graph part, however, requires more work and currently fails to support the second main result. Problems include the omission of important information and the confusing analysis of structural variants in terms of "regions of difference", which unnecessarily introduces reference bias. Overall, I very much like the direction taken in this article, but think that it needs more work: on the one hand by simply telling the reader what exactly was done, on the other by taking advantage of the information contained in the pangenome graph.

      Strengths:

      The authors put together a large data set of long-read assemblies representing most lineages of the Mycobacterium tuberculosis context, covering a large geographic area. State-of-the-art methods are used to analyze gene presence-absence polymorphisms (Panaroo) and to construct a pangenome graph (PanGraph). Additional analysis steps are performed to address known problems with misannotated or misassembled genes in pangenome analysis.

      Weaknesses:

      The study does not quite live up to the expectations raised in the introduction. Firstly, while the importance of using a curated data set is emphasized, little information is given about the data set apart from the geographic origin of the samples (Figure 1). A BUSCO analysis is conducted to filter for assembly quality, but no results are reported. It is also not clear whether the authors assembled genomes themselves in the cases where, according to Supplementary Table 1, only the reads were published but not the assemblies. In the end, we simply have to trust that single-contig assemblies based on long-reads are reliable.

      We have now added a robust overview of the dataset to supplementary file 1. This is split into 3 sections: public genomes, which were assembled by others; sequenced genomes, which were created and assembled by us; the BUSCO information for all the genomes together. We did not assemble any public data ourselves but retrieved these from elsewhere. We have modified the text to be more specific on this (Line 114 onwards) and the supplementary file is updated to better outline the data.

      One issue with long read assemblies could be that high rates of sequencing errors result in artificial indels when coverage is low, which in turn could affect gene annotation and pangenome inference (e.g. Watson & Warr 2019, https://doi.org/10.1038/s41587-018-0004-z). Some of the older long-read data used by the authors could well be problematic (PacBio RSII), but also their own Nanopore assemblies, six of which have a mean coverage below 50 (Wick et al. 2023 recommend 200x for ONT, https://doi.org/ 10.1371/journal.pcbi.1010905). Could the results be affected by such assembly errors? Are there lineages, for example, for which there is an increased proportion of RSII data? Given the large heterogeneity in data quality on the NCBI, I think more information about the reads and the assemblies should be provided.

      We have now included an analysis where we looked to see if the sequencing platform influenced the resulting accessory genome size and the pseudogene count. The details of this are included in lines 207-219, and the results are outlined in lines 251-258. Essentially, we found no correlation between sequencing platform and genome characteristics, although less stringent cut-offs did suggest that PacBio SMRT-only assembled genomes may have larger accessory genomes. We do not believe this is enough to influence our larger inferences from this data. It should be noted that complete genomes, in general, give a better indication of pangenome size compared to draft genomes, as has been shown previously (e.g. Marin et al., 2024). Even with some small potential bias, this makes our analysis more robust than any previously published.

      In relation to the sequencing depth of our own data, all genomes had coverage above 30x, which Sanderson et al. (2024) has shown to be sufficient for highly accurate sequence recovery. We fixed an issue with the L9 isolate from the previous submission, which resulted in a better BUSCO score and overall quality of that isolate and the overall dataset.

      The part of the paper I struggled most with is the pangenome graph analysis and the interpretation of structural variants in terms of "regions of difference". To start with, the method section states that "multiple whole genomes were aligned into a graph using PanGraph" (l.159/160), without stating which genomes were for what reason. From Figure 5 I understand that you included all genomes, and that Figure 6 summarizes the information at the sublineage level. This should be stated clearly, at present the reader has to figure out what was done. It was also not clear to me why the authors focus on the sublineage level: a minority of accessory genes (107 of 506) are "specific to certain lineages or sublineages" (l. 240), so why conclude that the pangenome is "driven by sublineage-specific regions of difference", as the title states? What does "driven by" mean? Instead of cutting the phylogeny arbitrarily at the sublineage level, polymorphisms could be described more generally by their frequencies.

      We apologise for the ambiguity in the methodology. All the isolates were inputted to Pangraph to create the pangenome using this method. This is now made clearer in lines 175-177. Standard pangenome statistics (size, genome fluidity, etc.) derived from this Pangraph output are now present in the results section as well (lines 301-320).

      We then only looked at regions of difference at the sub-lineage level, meaning we grouped genomes by sub-lineage within the resulting graph and looked for blocks common between isolates of the same sub-lineage but absent from one or more other sub-lineages. We did this from both the Panaroo output and the Pangraph output and then retained only blocks found by both. The results of this are now outlined in lines 351-383.

      We focussed on these sub-lineage-specific regions to focus on long-term evolution patterns and not be influenced by single-genome short-term changes. We do not have enough genomes of closely related isolates to truly look at very recent evolution, although the small accessory genome indicates this is not substantial in terms of gene presence/absence. We also did not want potential mis-annotations in a single genome to heavily influence our findings due to the potential issues pointed out by the reviewer above. We state this more clearly in the introduction (lines 106-108), methods (lines 184-186) and results (345-347), and we indicate the limitations in the Discussion, lines 452-457 and 471-473. We also changed the title to ‘shaped’ instead of ‘driven by’.

      I fully agree that pangenome graphs are the way to go and that the non-coding part of the genome deserves as much attention as the coding part, as stated in the introduction. Here, however, the analysis of the pangenome graph consists of extracting variants from the graph and blasting them against the reference genome H37Rv in order to identify genes and "regions of difference" (RDs) that are variable. It is not clear what the authors do with structural variants that yield no blast hit against H37Rv. Are they ignored? Are they included as new "regions of difference"? How many of them are there? etc. The key advantage of pangenome graphs is that they allow a reference-free, full representation of genetic variation in a sample. Here reference bias is reintroduced in the first analysis step.

      We apologise for the confusion here as indeed the RDs terminology is very MTBC-specific. Current RDs are always relevant to H37Rv, as that is how original discovery of these regions was done and that is how RDScan works. We clarify this in the introduction (lines 67-68). If we found a large sequence polymorphism (e.g. by Pangraph) and searched for known RDs using RDScan, we then assigned a current RD name to this LSP. This uses H37Rv as a reference. If we did not find a known RD, we then classified the LSP as a new RD if it is present in H37Rv, or left the designation as an LSP if not in H37Rv, thus expanding the analysis beyond the H37Rv-centric approaches used by others previously. This is hopefully now made clearer in the methods, lines 187-194.

      Along similar lines, I find the interpretation of structural variants in terms of "regions of difference" confusing, and probably many people outside the TB field will do so. For one thing, it is not clear where these RDs and their names come from. Did the authors use an annotation of RDs in the reference genome H37Rv from previously published work (e.g. Bespiatykh et al. 2021)? This is important basic information, its lack makes it difficult to judge the validity of the results. The Bespiatykh et al. study uses a large short-read data (721 strains) set to characterize diversity in RDs and specifically focuses on the sublineage-specific variants. While the authors cite the paper, it would be relevant to compare the results of the two studies in more detail.

      We have amended the introduction to explain this terminology better (lines 67-68). Naming of the RDs here came from using RDScan to assign current names to any accessory regions we found and if such a region was not a known RD, we gave it a lineage-related name, allowing for proper RD naming later (lines 187-194). Because the Bespiatyk paper is the basis for RDScan, our work implicitly compares to this throughout, as any RDs we find which were not picked up by RDScan are thus novel compared to that paper.

      As far as I understand, "regions of difference" have been used in the tuberculosis field to describe structural variants relative to the reference genome H37Rv. Colloquially, regions present in H37Rv but absent in another strain have been called "deletions". Whether these polymorphisms have indeed originated through deletion or through insertion in H37Rv or its ancestors requires a comparison with additional strains. While the pangenome graph does contain this information, the authors do not attempt to categorize structural variants into insertions and deletions but simply seem to assume that "regions of difference" are deletions. This, as well as the neglect of paralogs in the "classical" pangenome analysis, puts a question mark behind their conclusion that deletion drives pangenome evolution in the MTBC.

      We have now amended the analysis to specifically designate a structural variant as a deletion if present in the majority of strains and absent in a minority, or an insertion/duplication if present in a minority and absent in a majority (lines 191-192). We also ran Panaroo without merging paralogs to examine duplication in this output; Pangraph implicitly includes paralogs already.

      From all these analyses we did not find any structural variants classed as insertions/duplications and did not find paralogs to be a major feature at the sub-lineage level (lines 377-383). While these features could be important on shorter timescales, we do not have enough closed genomes to confidently state this (limitation outlined in lines 452-457). Therefore, our assertion that deletions are a primary force shaping the long-term evolution in this group still holds.

      Reviewer #2 (Public Review):

      Summary:

      The authors attempted to investigate the pangenome of MTBC by using a selection of state-of-the-art bioinformatic tools to analyse 324 complete and 11 new genomes representing all known lineages and sublineages. The aim of their work was to describe the total diversity of the MTBC and to investigate the driving evolutionary force. By using long read and hybrid approaches for genome assembly, an important attempt was made to understand why the MTBC pangenome size was reported to vary in size by previous reports.

      Strengths:

      A stand-out feature of this work is the inclusion of non-coding regions as opposed to only coding regions which was a focus of previous papers and analyses which investigated the MTBC pangenome. A unique feature of this work is that it highlights sublineage-specific regions of difference (RDs) that were previously unknown. Another major strength is the utilisation of long-read whole genomes sequences, in combination with short-read sequences when available. It is known that using only short reads for genome assembly has several pitfalls. The parallel approach of utilizing both Panaroo and Pangraph for pangenomic reconstruction illuminated the limitations of both tools while highlighting genomic features identified by both. This is important for any future work and perhaps alludes to the need for more MTBC-specific tools to be developed.

      Weaknesses:

      The only major weakness was the limited number of isolates from certain lineages and the over-representation others, which was also acknowledged by the authors. However, since the case is made that the MTBC has a closed pangenome, the inclusion of additional genomes would not result in the identification of any new genes. This is a strong statement without an illustration/statistical analysis to support this.

      We have included a Heaps law and genome fluidity calculation for each pangenome estimation to demonstrate that the pangenome is closed. This is detailed in lines 225-228 with results shown in lines 274-278 and 316- 320 and Supplementary Figure 2. We agree that more closely related genomes would benefit a future version of this analysis and indicate we indicate the limitations in the Discussion, lines 452-457 and 471-473.

      Recommendations for the authors:

      Reviewer #1 (Recommendations For The Authors):

      Abstract

      l. 24, "with distinct genomic features". I'm not sure what you are referring to here.

      We refer to the differences in accessory genome and related functional profiles but did not want to bloat the abstract with such additional details

      Introduction

      l. 40, "L1 to L9". A lineage 10 has been described recently: https://doi.org/10.3201/eid3003.231466.

      We have updated the text and the reference. Unfortunately, no closed genome for this lineage exists so we have not included it in the analyses. We note this in the results, like 232

      l.62/3, "caused by the absence of horizontal gene transfer, plasmids, and recombination". Recombination is not absent in the MTBC, only horizontal gene transfer seems to be, which is what the cited studies show. Indeed a few sentences later homologous recombination is mentioned as a cause of deletions.

      This has now been removed from the introduction

      l. 67, "within lineage diversity is thought to be mostly driven by SNPs". Again I'm not sure what is meant here with "driven by". Point mutations are probably the most common mutational events, but duplications, insertions, deletions, and gene conversion also occur and can affect large regions and possibly important genes, as shown in a recent preprint (https://doi.org/10.1101/2024.03.08.584093).

      We have changed the text to say ‘mostly composed of’. While indeed other SNVs may be contributing, the prevailing thought at lineage level is that SNPs are the primary source of diversity. The linked pre-print is looking at within transmission clusters and this has not been described at the lineage level, which could be done in a future work.

      l. 100/1. "that can account for variations in virulence, metabolism, and antibiotic resistance". I would phrase this conservatively since the functional inferences in this study are speculative.

      This has now been tempered to be less specific.

      Methods

      l. 108. That an assembly has a single contig does not mean that it is "closed". Many single contig assemblies on NCBI are reference-guided short-read assemblies, that is, fragments patched together rather than closed assemblies. The same could be true for long-read assemblies.

      We specifically chose those listed as closed on NCBI so rely on their checks to ensure this is true. We have stated this better in the paper, line 117.

      l. 111. From Supplementary Table 1 understand that for many genomes only the reads were available (no ASM number). Did you assemble these genomes? If yes, how? The assembly method is not indicated in the supplement, contrary to what is written here.

      All public genomes were downloaded in their assembled forms from the various sources. This is specified better in the text (line 118) and the supplementary table 1 now lists the accessions for all the assemblies.

      l. 113. How many assemblies passed this threshold? And is BUSCO actually useful to assess assembly quality in the MTBC? I assume the dynamic, repetitive gene families that cause problems for assembly and mapping in TB (PE, PPE, ESX) do not figure in the BUSCO list of single-copy orthologs.

      All assemblies passed the BUSCO thresholds for high-quality genomes as laid out in Supplementary Table 1. While indeed this does not include multi-copy genes such as PE/PPE we focussed on regions of difference at the sub-lineage level where two or more genomes represent that sub-lineage. This means any assembly issues in a single genome would need to be exactly the same in another of the same sub-lineage to be included in our results. Through this, we aimed to buffer out issues in individual assemblies.

      l. 147: Why is Panaroo used with -merge-paralogs? I understand that near-identical genes may not be too interesting from a functional perspective, but if the aim of the analysis is to make broad claims about processes driving genome evolution, paralogs should be considered.

      We chose to do so with merged paralogs to look for larger patterns of diversity beyond within-genome paralogs. Additionally, this was required to build the core phylogenetic tree. However, as the reviewer points out, this may bias our findings towards deletions and away from duplications as a primary evolutionary force.

      We repeated this without the merged paralogs option and indeed found a larger pangenome, as outlined in Table 1. However, at the sub-lineage level, this did not result in any new presence/absence patterns (lines 381-383). This means the paralogs tended to be in single genomes only. This still indicates that deletions are the primary force in the longer-term evolution of the complex but indeed on shorter spans this may be different.

      l. 153: remove the comment in brackets.

      This has been fixed and the proper URL placed in instead.

      l. 159: which genomes, and why those?

      This is now clarified to state all genomes were used for this analysis.

      l. 161, "gene blocks": since this analysis is introduced as capturing the non-coding part of the genome, maybe just call them "blocks"?

      All references to gene blocks are now changed to genomic blocks to be more specific.

      l. 162: what happens with blocks that yield no hits against RvD1, TbD1, and H37Rv?

      We named these with lineage-specific names (supplementary table 4) but did not assign RD names specifically.

      l. 164: where does the information about the regions of difference come from? How exactly were these regions determined?

      Awe have expanded this section to be more specific on the use of RDScan and new naming, along with how we determine if something is an RD/LSP.

      Results

      l. 185ff: This paragraph gives many details about the geographic origin of the samples, but what I'd expect here is a short description of assembly qualities, for example, the results of the BUSCO analysis, a description of your own Nanopore assemblies, or a small analysis of the number of indels/pseudogenes relative to sequencing technology or coverage (see comment in the public review).

      This section (lines 231-258) has been expanded considerably to give a better overview of the dataset and any potential biases. Supplementary table 1 has also been expanded to include more information on each strain.

      l. 187, "324 genomes published previously": 322 according to the methods section.

      The number has been fixed throughout to the proper total of public genomes (329).

      l. 201: define the soft core, shell, and cloud genes.

      This is now defined on line 262

      l. 228, "defined primarily by RD105 and RD207 deletions": this claim seems to come from the analysis of variable importance (Factoextra), which should be made clear here.

      This has been clarified on line 333.

      l. 237, "L8, serving as the ancestor of the MTBC": this is incorrect, equivalent to saying that the Chimpanzee is the ancestor of Homo sapiens.

      We have changed this to basal to align with how it is described in the original paper.

      l. 239, "The accessory genome of the MTBC". It is a bit confusing that the same term, 'accessory genome', is used here for the graph-based analysis, which is presented as a way to look at the non-coding part of the genome.

      We have clarified the terminology on line 347 and improved consistency throughout.

      l. 240/1, "specific to certain lineages and sublineages". What exactly do you mean by "specific" to? Present only in members of a certain lineage/sublineage? In all members of a certain lineage/sublineage? Maybe an additional panel in Figure 5, showing examples of lineage- and sublineage-specific variants, would help the reader grasp this key concept.

      We have clarified this on line 349 and the legend of what is now figure 4.

      l. 241/2, "82 lineage and sublineage-specific genomic regions ranging from 270 bp to 9.8 kb". Were "gene blocks" filtered for a minimum size, or why are there no variants smaller than 270 bp? A short description of all the blocks identified in the graph could be informative (their sizes, frequencies ...).

      Yes, a minimum of 250bp was set for the blocks to only look at larger polymorphisms. This is clarified on line 177 and 304.

      A second point: It is not entirely clear to me what Figure 6 is showing. Are you showing here a single representative strain per sublineage? Or have you somehow summarized the regions of difference shown in Figure 5 at the sublineage level? What is the tree on the left? This should be made clear in the legend and maybe also in the methods/results.

      In figure 4 (which was figure 6), because each RD is common to all members of the same sub-lineage, we have placed a single branch for each sub-lineage. This is has been clarified in the legend.

      l. 254, "this gene was classified as being in the core genome": why should a partially deleted gene not be in the core genome?

      You are correct, we have removed that statement.

      l. 258/259, "The Pangraph alignment approach identified partial gene deletion and non-coding regions of the DNA that were impacted by genomic deletion". I do not understand how you classify a structural variant identified in the pangenome graph as a deletion or an insertion.

      This has been clarified as relative to H37Rv, as this is standard practice for RDs and general evolutionary analyses in MTBC, as outlined above.

      l. 262/263 , "the accessory genome of the MTBC is small and is acquired vertically from a common ancestor within the lineage". If deletion is the main process involved here, "acquired" seems a bit strange.

      We agree and changed the header to better reflect the discussion on mis-annotation issues

      Figure 1: Good to know, but not directly relevant for the rest of the paper. Maybe move it to the supplement?

      This has been moved to Supplementary figure 1

      Figure 2: the y-axis is labeled 'Variable genome size', but from the text and the legend I figure it should be 'Number of accessory genes'?

      This has been changed to ‘accessory genes’ in Figure 1 (which was figure 2 in previous version).

      Figure 4: too small.

      We will endeavour to ensure this is as large as possible in the final version.

      Discussion

      l. 271, "MTBC accessory genome is ... acquired vertically". See above.

      Changed, as outlined above.

      l. 292, "appeared to be fragmented genes caused by misassemblies". Is there a way to distinguish "true" pseudogenes from misassemblies? This could be a relevant issue for low-coverage long-read assemblies (see public review).

      Not that we are currently aware of, but we do know other groups which are working on this issue.

      l. 300/1, "the whole-genome approach could capture higher genetic variations". Do you mean the graph approach? I'm not sure that comparing the two approaches here makes sense, as they serve different purposes. A pangenome graph is a summary of all genetic variation, while the purpose of Panaroo is to study gene absence/presence. So by definition, the graph should capture more genetic variation.

      This statement was specifically to state that much genetic variation in MTBC is outside the coding genes and so traditional “pangenome’ analyses are actually not looking at the full genomic variation.

      l. 302/3, "this method identified non-coding regions of the genome that were affected by genomic deletions". See the comments above regarding deletions versus insertions. I'd say this method identifies coding and non-coding regions that were affected by genomic deletions and insertions.

      We have undertaken additional analyses to be sure these are likely deletions, as outlined above.

      l. 305: what are "lineage-independent deletions"?

      We labelled these as convergent evolution, now clarified on line 443.

      l. 329: How is RD105 "caused" by the insertion of IS6110? I did not find RD105 mentioned in the Alonso et al. paper. Similarly below, l. 331, how is RD207 "linked" to IS6110?

      The RD105 connection was misattributed as IS6110 insertion is related to RD152, not RD105. This has now been removed.

      RD207 is linked to IS6110 as its deletion is due to recombination between two such elements. This is now clarified on line 486.

      l. 345, "the growth advantage gene group": not quite sure what this is.

      We have fixed this on line 499 to state they are genes which confer growth advantages.

      l. 373ff: The role of genetic drift in the evolution of the MTBC is an open question, other studies have come to different conclusions than Hershberg et al. (this has been recently reviewed: https://doi.org/10.24072/pcjournal.322).

      We have outlined this debate better in lines 527-531

      l. 375/6, "Gene loss, driven by genetic drift, is likely to be a key contributor to the observed genetic diversity within the MTBC." This sentence would need some elaboration to be intelligible. How does genetic drift drive gene loss?

      We have removed this.

      l. 395/6, "... predominantly driven by genome reduction. This observation underlines the importance of genomic deletions in the evolution of the MTBC." See comments above regarding deletions. I'm not convinced that your study really shows this, as it completely ignores paralogs and the processes counteracting reductive genome evolution: duplication and gene amplification.

      As outlined above, we have undertaken additional analyses to more strongly support this statement.

      l. 399, "the accessory genome of MTBC is a product of gene deletions, which can be classified into lineage-specific and independent deletions". Again, I'm not sure what is meant by lineage-independent deletions.

      We have better defined this in the text, line 443, to be related to convergent evolution.

      Reviewer #2 (Recommendations For The Authors):

      Suggestions for improved or additional experiments, data, or analyses.

      In lines 120-121, it is mentioned that TB-profiler v4.4.2 was used for lineage classification, but this version was released in February 2023. As I understand there have been some changes (inclusion/exclusion) of certain lineage markers. Would it not be appropriate to repeat lineage classification with a more recent version? This would of course require extensive re-analysis, so could the lineage marker database perhaps also be cited.

      We have rerun all the genomes through TB-Profiler v6.5 and updated the text to state this; the exact database used is also now stated.

      Could the authors perhaps include the sequencing summary or quality of the nanopore sequences? The L9 (Mtb8) sample had a relatively lower depth and resulted in two contigs. Yet one contig was the initial inclusion criteria. It is unclear whether these samples were excluded from some of the analyses. Mtb6 also has relatively low coverage. Was the sequencing quality adequate to accurately identify all the lineage markers, in particular those with a lower depth of coverage? Could a hybrid approach be an inexpensive way to polish these assemblies?

      We reanalysed the L9 sample and, with some better cleaning, got it to a single contig with better depth and overall score. This is outlined in the Supplementary table 1 sheets. While depth is average, it is still above the recommended 30x, which is needed for good sequence recovery (Sanderson et al., 2024). We did indeed recover all lineage markers from these assemblies.

      Recommendations for improving the writing and presentation.

      The introduction is well-written and recent MTBC pangenomic studies have been incorporated, but I am curious as to why this paper was not referred to: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6922483/ I believe this was the first attempt to study the pangenome, albeit with a different research question. Nearly all previous analyses largely focused on utilizing the pangenome to investigate transmission.

      Indeed this study did look at a pangenome of sorts, but specifically SNPs and not genes or regions. Since the latter is the main basis for pangenome work these days, we chose not to include this paper.

      Minor corrections to the text and figures.

      In line 129, it is explained that DNA was extracted to be suitable for PacBio sequencing, but ONT sequencing was used for the 11 new sequences. Is this a minor oversight or do the authors feel that DNA extracted for PacBio would be suitable for ONT sequencing? It is a fair assumption.

      We apologise, this is a long-read extraction approach and not specific to PacBio. We have amended the text to state this.

      In line 153, this should be removed: (Conor, could you please add the script to your GitHub page?).

      This has been fixed now.

    1. Note de synthèse détaillée : Collaboration et accompagnement des élèves en milieu éducatif

      Introduction

      Ce document de synthèse présente les thèmes principaux et les idées essentielles extraites de la table ronde "Journée d’étude CPE 2025".

      Il met en lumière le rôle crucial de la collaboration entre les différents acteurs de l'éducation nationale et les partenaires extérieurs pour la réussite, l'épanouissement et l'insertion professionnelle des élèves, en particulier ceux à besoins éducatifs particuliers.

      Les intervenants partagent leurs expériences et leurs perspectives sur les défis, les leviers et les recommandations pour favoriser un travail collaboratif efficace.

      1. Missions des professionnels de l'éducation et de l'accompagnement Plusieurs intervenants ont détaillé leurs missions, soulignant la diversité des rôles et la complexité de l'écosystème éducatif :

      2. Laura Renault (CPE en collège REP) : Les missions du CPE sont multiples et incluent l'organisation de l'espace et du temps de la vie scolaire, la gestion du service (recrutement et management des AED), la contribution à la réussite et au bien-être des élèves (accueil, accompagnement des projets personnels, orientation), et la participation à la politique de l'établissement comme conseiller du chef d'établissement.

      Elle souligne l'importance de "l'organisation du service donc on pense au recrutement des assistants d'éducation aux objectifs aussi du service et à l'ambition qu'on veut pour notre service".

      • Ludovique Brel (Directeur de l'IME Lérange) : En tant que directeur d'un IME accueillant des jeunes avec déficience intellectuelle et TSA, ses missions englobent la gestion RH, budgétaire, le projet d'établissement, et les relations avec les partenaires et les tutelles.

      Il met en avant l'ouverture récente d'une unité d'autorégulation collège pour les jeunes avec troubles du neurodéveloppement (TND), qui vise à travailler sur les problématiques émotionnelles en collaboration avec les professionnels du collège.

      Il précise que ces jeunes "sont dans leur classe d'âge leur classe de niveau c'est-à-dire qu'on parle pas de jeunes qui ont des particularités cognitives ou quoi que ce soit ce sont vraiment des jeunes qui sont en capacité classique".

      • Nathalie Yayaten (Proviseure des lycées des métiers de l'automobile) : Ses fonctions consistent à administrer l'établissement, représenter l'État, et "lancer, impulser, animer le projet d'établissement qui amène une forme de gouvernance et de grandes de grands objectifs sur la conduite de la politique éducative et pédagogique de l'établissement".

      Son expérience en collège REP et en cité éducative lui confère une perspective large sur les collaborations.

      • Lise MERIS (Coordinatrice ULIS Lycée Professionnel et service école inclusive du rectorat) : Ses missions se concentrent sur la sécurisation du parcours des jeunes en situation de handicap, leur accompagnement vers le monde professionnel, et le développement de partenariats internes et externes (monde de l'entreprise, médico-social). Au rectorat, elle soutient la scolarité réussie et l'insertion professionnelle des jeunes, notamment lors des transitions entre le premier et le second degré.

      Elle vise à "rendre l'élève acteur de son projet professionnel de l'accompagner du mieux possible au regard de ses points forts et de ses points d'effort".

      • Stéphane Copman (Éducateur à l'IME Mermose) : Il accompagne 14 jeunes déficients intellectuels au collège, veillant à leur sécurité et à la réussite de leur projet de socialisation.

      Contrairement aux enseignants, il n'a "aucune obligation de résultat" et s'adapte aux capacités de chaque jeune pour éviter l'échec scolaire.

      Sa mission inclut également "de veiller à la circulation de l'information au sein du collège et en lien également avec mon établissement et les familles".

      2. Le travail collaboratif : un impératif pour la réussite de l'élève

      Les intervenants s'accordent sur l'importance fondamentale du travail collaboratif, non seulement au sein de l'établissement mais aussi avec l'environnement extérieur.

      L'EPLE comme entité locale et ouverte : Nathalie Yayaten insiste sur le "L" de "Local" dans EPLE (Établissement Public Local d'Enseignement).

      L'établissement ne doit pas se fermer à son environnement et doit s'adapter aux problématiques territoriales.

      "L'établissement doit évoluer par rapport à son public doit s'adapter et doit aussi être très en en écoute et en réponse des problématiques territoriales sur lequel il est ancré".

      Le CPE au carrefour des relations : Le CPE est perçu comme un pivot, "au carrefour des relations entre les différents collaborateurs au sein d'établissement", mais aussi "au carrefour de toutes ses relations à l'extérieur de l'établissement", ce qui "fait la richesse du métier".

      Cohérence des discours et des actions : Pour que le jeune grandisse bien, il est essentiel que tous les acteurs (école, famille, clubs de sport, centres sociaux, professionnels paramédicaux) se connaissent et surtout "parlent d'une même voix ou où est en tout cas un discours très cohérent".

      Les discours contradictoires, par exemple entre collège et centre social sur les devoirs, fragilisent le jeune et sa famille.

      Exemples de collaborations réussies :

      Dispositif "Devoirs faits" avec les centres sociaux : Permet aux enseignants d'expliquer des méthodes d'apprentissage et montre aux familles une collaboration "main dans la main".

      Partenariat avec le PRE (Programme de Réussite Éducative) : Accueil des élèves exclus temporairement, offrant un lien et un accompagnement aux familles en difficulté.

      Unités d'autorégulation (UAR) : Projet co-porté par le SMS (Service Médico-Social) et le collège, avec des décisions prises d'un commun accord entre les directions.

      La formation commune de toutes les équipes (enseignants, CPE, infirmière) est un point clé pour créer une "culture commune" et dépasser les tensions liées aux différentes portes d'entrée professionnelles (enseigner vs prendre le jeune dans sa globalité).

      Collaboration pour l'orientation professionnelle : Les entreprises sont invitées à présenter les métiers, offrant aux jeunes d'autres perspectives et sources d'information.

      3. Les freins et les leviers du travail collaboratif

      Malgré la volonté de collaborer, des difficultés peuvent apparaître. Les intervenants mettent l'accent sur les leviers pour les surmonter.

      • Frustrations des CPE et des enseignants : Le CPE doit gérer des situations de décrochage ou de conflit dont il n'est pas à l'origine. Les enseignants sont confrontés à des publics hétérogènes et se sentent parfois démunis face aux "élèves à besoins éducatifs particuliers", pouvant s'épuiser.
      • Lever les freins par la collaboration : La collaboration apporte un "autre regard" et permet de débloquer des situations complexes. Un éducateur parlant à un professeur, ou l'inverse, peut faire "s'ouvrir les chakras" et envisager d'autres approches.
      • Le CPE comme levier central : Laura Renault affirme que "vous [les CPE] êtes le levier". Grâce à leur position transversale et leur liberté d'action, les CPE peuvent "créer ces collaborations qui vont permettre à un tel et un tel de poser un autre regard sur la situation".
      • Importance des espaces d'échange formels : Les cellules de veille et les GPDs (Groupes de Prévention du Décrochage Scolaire) sont des moments clés pour le "regard croisé et d'échange et de partage d'information". Il est crucial de transmettre les informations nécessaires en respectant "l'éthique de travail" et la confiance du jeune et de sa famille.
      • Patience et détermination : Ludovique Brel insiste sur ces deux qualités pour mener à bien les projets collaboratifs, reconnaissant que les choses ne se règlent pas du jour au lendemain. L'exemple de l'autorégulation montre une augmentation significative de la participation des enseignants à la formation, signe d'une "réelle volonté" de travailler ensemble.
      • Le jeune au centre : L'objectif ultime est que "le jeune soit l'élément central". L'équipe SMS apporte un soutien par sa connaissance des problématiques spécifiques du jeune (ex: TND), permettant de faire converger la compétence pédagogique et la compétence médico-sociale pour le bien-être de l'élève.

      4. Recommandations pour un travail collaboratif efficace

      Plusieurs précautions et recommandations sont formulées pour favoriser des collaborations fructueuses :

      • Chacun à sa place, dans le respect des missions : Lise MERIS souligne l'importance que "chacun reste à sa place" et "sache quelle est sa place". Il faut connaître les missions et les compétences de chacun pour savoir "qui fait quoi, à quel moment" et ainsi respecter les champs d'expertise.
      • Non-jugement et bienveillance : Adopter une posture de non-jugement et de bienveillance envers le travail de l'autre est essentiel pour construire une collaboration "très horizontale".
      • Postures d'ouverture avec les parents : Accueillir les parents "dans cette posture d'ouverture de collaboration" permet de changer la dynamique, de les faire baisser la garde et de construire des solutions avec eux, et non à leur place ou contre eux. "Le parent comprend que vous êtes en train de vous triturer l'esprit avec vos collègues à essayer de trouver une solution pour son jeune".
      • Anticipation : La collaboration "s'anticipe". Il faut initier des démarches en amont pour être capable de travailler ensemble lorsque des difficultés surgissent.
      • Valoriser les réussites : Ne pas se concentrer uniquement sur les situations de tension, mais aussi reconnaître les moments où "ça se passe bien" et les jeunes qui vont bien. "Il faut aussi se donner à notre travail une légitimité se dire que oui il y a quand même des choses qui vont et il faut aussi voilà se viscéralement en tous les cas y croire".
      • Ne pas perdre la confiance du jeune et de la famille : La centralité du jeune et de sa confiance est primordiale. Il est important d'expliquer, de rassurer les familles et les jeunes.
      • Vulgariser le langage : Face à l'abondance de sigles et de jargons professionnels, il est recommandé de "vulgariser au maximum" pour rendre les informations accessibles à tous, y compris aux familles et aux jeunes.

      Un "glossaire" des sigles peut être utile.

      Conclusion La table ronde a clairement démontré que la réussite de tous les élèves, notamment ceux à besoins éducatifs particuliers, repose sur une collaboration forte et structurée.

      Le CPE, par sa position charnière, est un acteur clé de cette dynamique, en favorisant les échanges internes et externes.

      Les défis liés aux cultures professionnelles différentes peuvent être surmontés par la patience, la détermination, la formation commune, le respect mutuel des compétences et une posture d'ouverture centrée sur le bien-être et la réussite du jeune.

    1. Compte Rendu Détaillé : Le Conseiller Principal d'Éducation Accompagnant

      Ce document explore le rôle du Conseiller Principal d'Éducation (CPE) en tant qu'accompagnant au sein de l'établissement scolaire, en insistant sur la dimension individuelle et collective de son travail.

      Il s'appuie sur une approche socio-historique, praxéologique et didactique pour problématiser la question de l'accompagnement et de la collaboration.

      1. Le Contexte Socio-Historique et la Problématique du Rôle du CPE

      Le rôle du CPE en France, particulièrement dans le secondaire, est marqué par une dichotomie historique entre "l'instruction et l'éducation".

      Les enseignants sont perçus comme détenteurs de l'instruction, tandis que les CPE, bien qu'ayant une mission éducative et pédagogique, souffrent d'un manque de légitimité à cet égard depuis leur création en 1970.

      Cette tension persiste, et les CPE se battent toujours pour être reconnus comme pédagogues.

      Dans un contexte de démocratisation scolaire ayant renforcé les inégalités, les CPE sont fortement attendus pour "accueillir [et] suivre les élèves de manière à pallier les insuffisances du système [et] les difficultés que connaissent les élèves".

      Leur défi éducatif fondamental est d'"aider l'élève à se construire en tant que personne".

      Cependant, ils sont également vus comme des garants de l'action pédagogique et de la régulation des désordres scolaires, un rôle souvent associé à la discipline plutôt qu'à l'éducation et à l'accompagnement.

      La critique de l'autorité au XXe siècle, ou son "érosion" (Prerra), complexifie davantage le rôle du CPE, qui doit faire face à une confusion entre autoritarisme et autorité éducative nécessaire à la médiation entre l'individu et le collectif.

      La "division du travail éducatif" (Tardif et Levasseur, Payet) est également une problématique majeure, le CPE se situant entre le cognitif/enseignement (enseignants) et le comportemental (personnels spécialisés comme les AESH).

      Il est à la fois celui qui "aide les enseignants à enseigner, il aide les élèves à apprendre et en même temps il est très attendu pour réguler tous les désordres scolaires".

      2. Les Missions du CPE et la Place de la Dimension Pédagogique

      Les missions de la vie scolaire visent à placer les adolescents dans les meilleures conditions de vie individuelles et collectives, de réussite scolaire (depuis la circulaire de 2015) et d'épanouissement personnel.

      La vie scolaire, selon Jean-Pierre Aubin, n'est pas la vie hors la classe, mais "l'ensemble des événements de la vie collective et puis aussi tout ce qui concerne la normalisation de la vie collective".

      Le CPE, bien qu'en lien fort avec le pôle éducatif (problèmes sociaux et affectifs), est aussi connecté au pôle instruction.

      La dimension pédagogique de son rôle est "très importante" car il est celui qui gère les problèmes personnels ou collectifs des élèves et qui consacre un temps significatif à l'accueil de la parole des élèves, notamment lors des entretiens.

      Or, cette dimension est "assez peu connue encore" par de nombreux enseignants, sauf si elle fait partie de la culture de l'établissement.

      Les textes officiels (circulaire de 2015, référentiel de 2013) légitiment le travail en équipe des CPE :

      Promotion de la citoyenneté participative : Accompagnement des élèves dans leurs "apprentissages sociaux et citoyens". Suivi des élèves : Construction du parcours de l'élève sur les plans "pédagogiques et éducatifs", impliquant un travail individuel (entretiens) en lien avec les familles et le personnel d'éducation nationale. Organisation de la vie scolaire : L'équipe de vie scolaire, incluant les Assistants d'Éducation (AED), contribue également à l'accompagnement individuel et collectif.

      3. L'Accompagnement comme Activité Pilier du Métier de CPE

      L'entretien est l'"activité pilier du métier" de CPE, constituant la part la plus importante de leur temps et de leur activité, comme l'a montré une étude du CREC en 2007.

      Cependant, les CPE ressentent souvent une "frustration" due à la "tyrannie de l'urgence" (Sylvie Condette) ou au "tourbillon professionnel" (Christine Fauquenois Simonet), qui les pousse à privilégier la gestion du collectif au détriment du suivi individuel et de la collaboration.

      L'accompagnement est un "travail de l'ombre qui n'est pas quantifiable et surtout pas dans l'immédiat".

      Les résultats ne sont pas instantanés, ce qui contraste avec les "attentes [d'un] coup de baguette magique" de la part des collègues ou de la direction.

      C'est un processus de "coconstruction, un cheminement" sur le long terme, où le CPE doit être une "personne de confiance" pour l'élève.

      L'accompagnement est défini comme une "activité" (et non un simple dispositif institutionnel) qui sous-tend des pratiques et une posture.

      Il a une "dimension constructiviste", visant à aider l'élève à "construire son propre parcours" et à "se décider à agir, à s'assumer", sans agir à sa place.

      Cela implique un "étayage" de "nature dialogique", une "médiation sociale" pour que l'élève se projette dans sa vie scolaire et sociale.

      C'est une "relation disymétrique" mais "éducative" et "temporaire".

      Le CPE doit concilier cette relation de confiance individuelle avec le travail collectif, car il "ne peut pas accompagner seul". L'information doit être échangée et le travail collaboratif mis en place.

      L'accompagnement implique une "éthique de l'accompagnement" et de la "responsabilité" (méta-responsabilité), où le CPE, par son "autorité éducative" (au sens d'«augmenter l'autre»), permet à l'élève de grandir et de devenir autonome.

      Ce rôle demande un "principe de retenue" et le "principe du doute", évitant de donner des solutions toutes faites.

      Selon les travaux de Frédérique Lherbé Serini, l'accompagnant adopte trois figures posturales entremêlées :

      Le Compagnon : À l'écoute, soucieux du bien-être de l'autre, proche de l'éthique du caresse, attentif à ce qui va bien et ce qui ne va pas. L'Accompagnateur : Dans la coconstruction, le cheminement avec l'élève. Le Guide : Intervient pour dire "stop" lorsque l'élève se met en danger ou que la construction n'est plus possible.

      Les CPE ne sont pas uniquement des guides, mais adoptent majoritairement les postures de compagnon et d'accompagnateur.

      4. Le Travail Collaboratif du CPE au sein de l'Établissement

      Le travail coopératif est "prescrit" et est une "compétence partagée" entre enseignants et CPE. Cependant, sa réalité sur le terrain est peu documentée. Des facteurs de contexte peuvent défavoriser la collaboration :

      L'intégration croissante des CPE dans "l'équipe de direction élargie" peut renforcer leur image administrative et créer des obstacles à la coopération avec les enseignants.

      L'"intensification [et la] complexification" du métier d'enseignant, la remise en question des savoirs et la judiciarisation de l'institution peuvent générer des crispations entre les corps enseignants et les CPE.

      Malgré cela, la collaboration CPE-enseignant a toujours été une constante dans les textes, évoluant de l'"échange d'information" (1982) à des "savoirs partagés [et une] collaboration étroite" (2015).

      Les "collectifs de travail" se forment soit par "initiative libre" (besoins partagés face à des difficultés), soit par "assignation" (appartenance à une équipe prédéfinie, ex: équipe pédagogique d'un niveau).

      Des "groupes de projets spécifiques" (devoir fait, café des parents) sont aussi des espaces de collaboration.

      Le contexte de l'établissement (proximité des bureaux, culture d'établissement) et l'institutionnalisation de certains temps (heure de vie de classe) sont des facteurs clés pour la facilitation de la collaboration.

      Le "pouvoir d'agir" du CPE, par ses initiatives, est important.

      Un véritable collectif de travail, au-delà d'un simple groupe de professionnels, est caractérisé par :

      L'adhésion à des "valeurs partagées".

      L'élaboration commune de "règles de fonctionnement" et d'objectifs.

      L'engagement volontaire et autonome des membres, conduisant à la création de "groupes de veille éducative" par exemple, qui s'inscrivent progressivement dans une "culture d'établissement".

      Les pratiques de collaboration varient :

      "Pratiques de collaboration minimum" : Échanges informels dans les couloirs ou à la salle des professeurs.

      Le CPE doit organiser ces informations éparses.

      Le "rayonnement d'un CPE" dans un établissement est lié à sa capacité à aller vers les autres et à initier ces rencontres.

      5. Modalités de Travail du CPE et Collaboration

      La "approche multidimensionnelle" est une compétence clé du CPE, lui permettant d'avoir une "vision globale et complexe" de la vie de l'élève (loisirs, difficultés, etc.) et de croiser les regards pour le bien-être et l'épanouissement de chacun.

      Les CPE travaillent en étroite collaboration avec :

      Les personnels d'éducation (AED) : Considérés comme une "mine d'or" d'informations grâce à leur proximité avec les élèves. Les réunions de service régulières sont cruciales pour la remontée de ces informations.

      Les enseignants : Plus de 80% des CPE échangent régulièrement sur les entretiens avec les élèves, montrant que l'accompagnement ne se fait pas en vase clos.

      La collaboration est souvent initiée par le CPE, ou par sollicitation d'autres membres de la communauté éducative, y compris les élèves eux-mêmes.

      Le partage de savoirs sur les élèves et leurs difficultés permet au CPE d'"entrer dans la classe" différemment.

      L'"éthique des collectifs de travail" est primordiale :

      La plupart des CPE informent l'élève avant ou après le partage d'informations avec d'autres professionnels (professeur principal, infirmière, médecin scolaire), et un tiers le fait systématiquement avant.

      C'est un "principe" pour certains CPE pour ne pas rompre la relation de confiance.

      Le partage d'informations se fait avec "tact", en ne dévoilant pas tout le contenu de l'entretien mais uniquement ce qui est pertinent pour le suivi.

      La question du "secret" (professionnel ou non) et du partage est récurrente et nécessite un travail important en formation initiale.

      Les "entretiens tripartites" (avec l'élève, le CPE et un autre collègue) sont une pratique importante, permettant de confirmer une "cohérence" et une "cohésion d'équipe".

      C'est une "prise de risque", car le résultat peut être inattendu, mais elle est jugée nécessaire car les CPE "ne peuvent pas travailler seul en entretien avec l'élève".

      Le CPE sait aussi "relayer" l'accompagnement à une autre personne lorsque ses propres limites d'éducateur sont atteintes. C'est une compétence difficile mais essentielle, nécessitant de ne pas donner l'impression à l'élève d'être "abandonné".

      Le CPE est souvent un "médiateur" entre les élèves et les adultes de l'établissement (enseignants, infirmière, etc.) lorsque la relation est coupée.

      En Réseau d'Éducation Prioritaire (REP+), il existe une "culture commune de la manière d'accompagner les élèves" entre CPE, directeurs d'école et directeurs de SEGPA, avec une forte volonté de travailler sur la continuité école-collège concernant les savoirs sociaux et citoyens, et un travail commun sur les "rituels pour faire adhérer les élèves à la règle".

      Conclusion

      Le processus d'accompagnement par le CPE est caractérisé par des "effets très forts d'inter et de co et de rétroaction" entre les élèves et les CPE, qui s'étendent en "cercles concentriques" avec la formation de collectifs autour de la relation duale.

      Ce travail en équipe nécessite une "vraie éthique", notamment le "tact", car les élèves sont sensibles à un "sentiment de loyauté".

      Enfin, l'"expérience collective nourrit la reconnaissance individuelle", soulignant l'importance de développer des expériences de travail collaboratif dès la formation initiale des CPE et des enseignants.

    1. Reviewer #1 (Public review):

      This paper describes technically-impressive measurements of calcium signals near synaptic ribbons in goldfish bipolar cells. The data presented provides high spatial and temporal resolution information about calcium concentrations along the ribbon at various distances from the site of entry at the plasma membrane. This is important information. Important gaps in the data presented mean that the evidence for the main conclusions is currently inadequate.

      Strengths

      • The technical aspects of the measurements are impressive. The authors use calcium indicators bound to the ribbon and high speed line scans to resolve changes with a spatial resolution of ~250 nm and temporal resolution of less than 10 ms. These spatial and temporal scales are much closer to those relevant for vesicle release than previous measurements.

      • The use of calcium indicators with very different affinities and of different intracellular calcium buffers helps provide confirmation of key results.

      Weaknesses

      • Multiple key points of the paper lack a statistical test or summary data from populations of cells. For example, the text states that the proximal and distal calcium kinetics in Figure 2A differ. This is not clear from the inset to Figure 2A - where the traces look like scaled versions of each other. Values for time to half-maximal peak fluorescence are given for one example cell but no statistics or summary are provided. Figure 8 shows examples from one cell with no summary data. This issue comes up in other places as well.

      • The rise time measurements in Figure 2 are very different for low and high affinity indicators, but no explanation is given for this difference. Similarly, the measurements of peak calcium concentration in Figure 4 are very different with the two indicators. That might suggest that the high affinity indicator is strongly saturated, which raises concerns about whether that is impacting the kinetic measurements.

    2. Reviewer #2 (Public review):

      Summary:

      The study introduces new tools for measuring intracellular Ca2+ concentration gradients around retinal rod bipolar cell (rbc) synaptic ribbons. This is done by comparing the Ca2+ profiles measured with mobile Ca2+ indicator dyes versus ribbon-tethered (immobile) Ca2+ indicator dyes. The Ca2+ imaging results provide a straightforward demonstration of Ca2+ gradients around the ribbon and validate their experimental strategy. This experimental work is complemented by a coherent, open-source, computational model that successfully describes changes in Ca2+ domains as a function of Ca2+ buffering. In addition, the authors try to demonstrate that there is heterogeneity among synaptic ribbons within an individual rbc terminal.

      Strengths:

      The study introduces a new set of tools for estimating Ca2+ concentration gradients at ribbon AZs, and the experimental results are accompanied by an open-source, computational model that nicely describes Ca2+ buffering at the rbc synaptic ribbon. In addition, the dissociated retinal preparation remains a valuable approach for studying ribbon synapses. Lastly, excellent EM.

      Comments on revisions:

      Specific minor comments:

      (1) Rewrite the final sentence of the Abstract. It is difficult to understand.

      (2) Add a definition in the Introduction (and revisit in the Discussion) that delineates between micro- and nano-domain. A practical approach would be to round up and round down. If you round up from 0.6 um, then it is microdomain which means ~ 1 um or higher. Likewise, round down from 0.3 um to nanodomain? If you are using confocal, or even STED, the resolution for Ca imaging will be in the 100 to 300 nm range. The point of your study is that your new immobile Ca2-ribbon indicator may actually be operating on a tens of nm scale: nanophysiology. The Results are clearly written in a way that acknowledges this point but maybe make such a "definition" comment in the intro/discussion in order to: 1) demonstrate the power of the new Ca2+ indicator to resolve signals at the base of the ribbon (effectively nano), and 2) (Discussion) to acknowledge that some are achieving nanoscopic resolution (50 to 100nm?) with light microscopy (as you ref'd Neef et al., 2018 Nat Comm).

      (3) Suggested reference: Grabner et al. 2022 (Sci Adv, Supp video 13, and Fig S5). Here rod Cav channels are shown to be expressed on both sides the ribbon, at its base, and they are within nanometers from other AZ proteins. This agrees with the conclusions from your imaging work.

      (4) In the Discussion, add a little more context to what is known about synaptic transmission in the outer and inner retina.. First, state that the postsynaptic receptors (for example: mGluR6-OnBCs vs KARs-Off-BCs, vs. AMPAR-HCs), and possibly the synaptic cleft (ground squirrel), are known to have a significant impact on signaling in the outer retina. In the inner retina, there are many more unknowns. For example, when I think of the pioneering Palmer JPhysio study, which you sight, I think of NMDAR vs AMPAR, and uncertainty in what type postsynaptic cell was patched (GC or AC....). Once you have informed the reader that the postsynapse is known to have a significant impact on signaling, then promote your experimental work that addresses presynaptic processes: "...the new tool and results allow us to explore release heterogeneity, ribbon by ribbon in dissociated preps, which we eventually plan to use at ribbon synapses within slices......to better understand how the presynapse shapes signaling......".

    1. Reviewer #1 (Public review):

      Summary:

      In this manuscript, the authors attempt to reconstitute some active zone properties by introducing synaptic ribbon proteins into HEK cells. This "ground-up" approach can be valuable for assessing the necessity of specfic proteins in synaptic function. Here, the authors co-transfect a membrane-targeted bassoon, RBP2, calcium channel subunits and Ribeye to generate what they call "synthetic ribbons". The resultant structures show an ability to cluster calcium channels (Figure 4B) and a modest ability to concentrate calcium entry locations (figure 7J). At the light level, the ribeye aggregates look spherical and localize to the membrane through its interaction with the membrane-targeted bassoon and at the EM level the structures resemble those observed when Ribeye is overexpressed alone. It is a nice proof-of-principle in establishing a useful experimental system for studying calcium channel localization and with expression of other proteins perhaps a means to understanding structure and function of the ribbon. The paper does establish that previously described protein-interactions can be reconstituted in a heterologous system to and that the addition of Ribeye can increase the size of calcium channel patches via indirect interactions.

      Strengths:

      (1) The authors establish a new experimental system for the study of calcium channel localization to active zones.<br /> (2) The clustering of calcium channels to bassoon via RBP2 is a nice confirmation of a previously-described interaction between bassoon and calcium channels in a cell-based system<br /> (3) The "ground-up" approach is an attractive one and theoretically allows one learn a lot about the essential interactions for building a ribbon structure.<br /> (4) The finding that introducing Ribeye can enhance the size of calcium channel patches is a novel finding that is interesting.

      Weaknesses:

      (1) The addition of EM is welcome, but the structures seem to resemble those created by overexpression of Ribeye alone, albeit at the membrane. It is unclear to me whether the interaction with Bsn or indirect interactions with other proteins has any effect on these structures. Also, while the abstract mentions that the size and shape are similar to ribbons, the EM seems to show that the size and shape are quite variable.<br /> (2) The clustering of channels is accomplished by taking advantage of previously described interactions between RBP2, Ca channels and bassoon. While it is nice to see that it can be reconstituted in a naive cell, the interactions were previously described. The localization of Ribeye to bassoon takes advantage of a previously described interaction between the two and the membrane localization of the complexes required introduction of a membrane-anchoring motif. These factors limit the novelty of the findings.<br /> (3) The difference in Ca imaging between SyRibbons and other locations is subtle. While there are reasonable explanations for why this could be the case, it may limit the utility of this system for studying Ca-channel-ribbon dynamics moving forward.

    2. Reviewer #2 (Public review):

      Summary:

      The authors show that co-expression of bassoon, RIBEYE, Cav1.3-alpha1, Cav-beta3, Cav-alpha2delta1, and RBP2 in a heterologus system (HEK293 cells) is sufficient to generate a protein complex resembling a presyanptic ribbon-type active zone both in morphology and in function (in clustering voltage-gated Ca channels and creating sites for localized Ca2+ entry). If the 3 separate Cav gene products are taken as a single protein (i.e. a Ca channel), the conclusion is that the core of a ribbon synapse comprises 4 proteins: bassoon holds the RIBEYE-containing ribbon to the plasma membrane, and RPB2 binds to bassoon and Ca channels, tethering the Ca channels to the presynaptic active zone.

      Strengths:

      (1) Good use of a heterologous system with generally appropriate controls provides convincing evidence that a presynaptic ribbon-type active zone (without the ability to support exocytosis), with the ability to support localized Ca2+ entry (a key feature of ribbon-type pre-synapses) can be assembled from a few proteins.<br /> (2) In the revised manuscript, the authors do a good job of addressing the limitations of their cultured cell-system.

      Weaknesses:

      (1) Relies on over-expression, which almost certainly diminishes the experimentally-measured parameters (e.g. pre-synapse clustering, localization of Ca2+ entry).<br /> (2) Are HEK cells the best model? HEK cells secrete substances and have a studied-endocytitic pathway, but they do not create neurosecretory vesicles. Initially, I asked why didn't the authors did not try to reconstitute a ribbon synapse in a cell that makes neurosecretory vesicles like a PC12 cell, and the authors addressed this question in their revision.<br /> (3) Related to 1 and 2: the Ca channel localization observed is significant but not so striking given the presence of Cav protein and measurements of Ca2+ influx distributed across the membrane. Presumably, this is the result of overexpression and an absence of pathways for pre-synaptic targeting of Ca channels. But, still, it was surprising that Ca channel localization was so diffuse. I suppose that the authors tried to reduce the effect of over-expression by using an inducible Cav1.3? Even so, the accessory subunits were constitutively over-expressed.

    3. Author response:

      The following is the authors’ response to the original reviews

      Life Assessment

      The authors use a synthetic approach to introduce synaptic ribbon proteins into HEK cells and analyze the ability of the resulting assemblies to cluster calcium channels at the active zone. The use of this ground-up approach is valuable as it establishes a system to study molecular interactions at the active zone. The work relies on a solid combination of super-resolution microscopy and electrophysiology, but would benefit from: (i) additional ultrastructural analysis to establish ribbon formation (in the absence of which the claim of these being synthetic ribbons might not be supported; (ii) data quantification (to confirm colocalization of different proteins); (iii) stronger validation of impact on Ca2+ function; (iv) in depth discussion of problems derived from the use of an over-expression approach.

      We thank the editors and the reviewers for the constructive comments and appreciation of our work. Please find a detailed point-to-point response below. In response to the critique received, we have now (i) included an ultrastructural analysis of the SyRibbons using correlative light microscopy and cryo-electron tomography, (ii) performed quantifications to confirm the colocalisation of the various proteins, (iii) discussed and carefully rephrased our interpretation of the role of the ribbon in modulating Ca<sup>2+</sup> channel function and (iv) discussed concerns regarding the use of an overexpression system. 

      Public Reviews:

      Reviewer #1 (Public Review):

      We would like to thank the reviewer for the comments and advice to further improve our manuscript. We have completely overhauled the manuscript taking the suggestions of the reviewer into account.

      (1) Are these truly "synthetic ribbons". The ribbon synapse is traditionally defined by its morphology at the EM level. To what extent these structures recapitulate ribbons is not shown. It has been previously shown that Ribeye forms aggregates on its own. Do these structures look any more ribbonlike than ribeye aggregates in the absence of its binding partners?

      We thank reviewer 1 for their constructive feedback and critique of the work. 

      We agree that traditionally, ribbon synapses have always been defined by the distinct morphology observed at the EM level. However, since the discovery of the core-components of ribbons (RIBEYE and Piccolino) confocal and super-resolution imaging of immunofluorescently labelled ribbons have gained importance for analysing ribbon synapses. A correspondence of RIBEYE immunofluorescent structures at the active zone to electron microscopy observations of ribbons has been established in numerous studies (Wong et al, 2014; Michanski et al, 2019, 2023; Maxeiner et al, 2016; Jean et al, 2018) even though direct correlative approaches have yet to be performed to our knowledge. We have now analysed SyRibbons using cryo-correlative electron-light microscopy. We observe that GFPpositive RIBEYE spots corresponded well with electron-dense structures, as is characteristic for synaptic ribbons (Robertis & Franchi, 1956; Smith & Sjöstrand, 1961; Matthews & Fuchs, 2010). We could also observe SyRibbons within 100 nm of the plasma membrane (see Fig. 3). We have now added this qualitative ultrastructural analysis of SyRibbons in the main manuscript (lines 272 - 294, Fig. 3 and Supplementary Fig. 3).

      (2) No new biology is discovered here. The clustering of channels is accomplished by taking advantage of previously described interactions between RBP2, Ca channels and bassoon. The localization of Ribeye to bassoon takes advantage of a previously described interaction between the two. Even the membrane localization of the complexes required the introduction of a membraneanchoring motif.

      We respectfully disagree with the overall assessment. Our study emphasizes the synthetic establishment of protein assemblies that mimic key aspects of ribbon-type active zone, defining minimum molecular requirements. Numerous previous studies have described the role of the synaptic ribbon in organising the spatial arrangement of Ca<sup>2+</sup> channels, regulating their abundance and possibly also modulating their physiological properties (Maxeiner et al, 2016; Frank et al, 2010; Jean et al, 2018; Wong et al, 2014; Grabner & Moser, 2021; Lv et al, 2016). We would like to highlight that there remain major gaps between existing in vitro and in vivo data; for instance, no evidence for direct or indirect interactions between Ca<sup>2+</sup> channels and RIBEYE have been demonstrated so far. While we do indeed take advantage of previously known interactions between RIBEYE and Bassoon (tom Dieck et al, 2005); between Bassoon, RBP2 and P/Q-type Ca<sup>2+</sup> channels (Davydova et al, 2014); and between RBP2 and Ltype Ca<sup>2+</sup> channels (Hibino et al, 2002), our study tries to bridge these gaps by establishing the indirect link between the synaptic ribbon (RIBEYE) and L-type CaV1.3 Ca<sup>2+</sup> channels using a bottom-up approach, which has previously just been speculative. Our data shows how even in a synapse-naive heterologous expression system, ribbon synapse components assemble Ca<sup>2+</sup> channel clusters and even show a partial localisation of Ca<sup>2+</sup> signal. Moreover, we argue that the established reconstitution approach provides other interesting insights such as laying ground-up evidence supporting the anchoring of the synaptic ribbon by Bassoon. Finally, we expect that the established system will serve future studies aimed at deciphering the role of putative CaV1.3 or CaV1.4 interacting proteins in regulating Ca<sup>2+</sup> channels of ribbon synapses by providing a more realistic Ca<sup>2+</sup> channel assembly that has been available in heterologous expression systems used so far. In response to the reviewers comment we have augmented the discussion accordingly.  

      (3) The only thing ribbon-specific about these "syn-ribbons" is the expression of ribeye and ribeye does not seem to participate in the localization of other proteins in these complexes. Bsn, Cav1.3 and RBP2 can be found in other neurons.

      The synaptic ribbon made of RIBEYE is the key molecular difference in the molecular AZ ultrastructure of ribbon synapses in the eye and the ear. We hypothesize the ribbon to act as a superscaffold that enables AZ with large Ca<sup>2+</sup> channel assemblies and readily releasable pools. In further support of this hypothesis, the present study on synthetic ribbons shows that CaV1.3 Ca<sup>2+</sup> channel clusters are larger in the presence of SyRibbons compared to SyRibbon-less CaV1.3 Ca<sup>2+</sup> channel clusters in tetratransfected HEK cells (Ca<sup>2+</sup> channels, RBP, membrane-anchored Bassoon, and RIBEYE, Fig. 6). In response to the reviewers comment we now added an analysis of triple-transfected HEK cells (Ca<sup>2+</sup> channels, RBP, membrane-anchored Bassoon), in which CaV1.3 Ca<sup>2+</sup> channel clusters again are significantly smaller than at the SyRibbons and indistinguishable from SyRibbon-less CaV1.3 Ca<sup>2+</sup> channel clusters (Fig. 6E, F).

      (4) As the authors point out, RBP2 is not necessary for some Ca channel clustering in hair cells, yet seems to be essential for clustering to bassoon here.

      Here we would like to clarify that RBP2 is indeed important in inner hair cells for promoting a larger complement of CaV1.3 and RBP2 KO mice show smaller CaV1.3 channel clusters and reduced whole cell and single-AZ Ca<sup>2+</sup> influx amplitudes (Krinner et al, 2017). However, a key point of difference we emphasize on is that even though CaV1.3 clusters appeared smaller, they did not appear broken or fragmented as they do upon genetic perturbation of Bassoon (Frank et al, 2010), RIBEYE (Jean et al, 2018) or Piccolino (Michanski et al, 2023). This highlights how there may be a hierarchy in the spatial assembly of CaV1.3 channels at the inner hair cell ribbon synapse (also described in the discussion section “insights into presynaptic Ca<sup>2+</sup> channel clustering and function”) with proteins like RBP2 regulating abundance of CaV1.3 channels at the synapse and organising them into smaller clusters – what we have termed as “nanoclustering”; while Bassoon and RIBEYE may serve as super-scaffolds further organizing these CaV1.3 nanoclusters into “microclusters”. Observations of fragmented Ca<sup>2+</sup> channel clusters and broader spread of Ca<sup>2+</sup> signal seen upon Ca<sup>2+</sup> imaging in RIBEYE and Bassoon mutants (Jean et al, 2018; Frank et al, 2010; Neef et al, 2018), and the absence of such a phenotype in RBP2 mutants (Krinner et al, 2017) may be explained by such a differential role of these proteins in organising Ca<sup>2+</sup> channel spatial assembly. The data of the present study on reconstituted ribbon containing AZs are in line with these observations in inner hair cells: RBP2 appears important to tether Ca<sup>2+</sup> channels to Bassoon and these AZ-like assemblies are organised to their full extent by the presence of RIBEYE. As mentioned in the response to point 3 of the reviewer, we have now further strengthened this point by adding the analysis of SyRibbon-less CaV1.3 Ca<sup>2+</sup> channel clusters in tripletransfected HEK cells (Ca<sup>2+</sup> channels, RBP, membrane-anchored Bassoon, Fig. 6E, F). Moreover, we have revised the discussion accordingly. 

      (5) The difference in Ca imaging between SyRibbons and other locations is extremely subtle.

      We agree with the reviewer on the modest increase in Ca<sup>2+</sup> signal amplitude seen in the presence of  SyRibbons and provide the following reasoning for this observation: 

      (i) It is plausible that due to the overexpression approach, Ca<sup>2+</sup> channels (along with RBP2 and PalmBassoon) still show considerably high expression throughout the membrane even in regions where SyRibbons are not localised. Indeed, this is evident in the images shown in the lower panel in Fig. 6B, where Ca<sup>2+</sup> channel immunofluorescence is distributed across the plasma membrane with larger clusters formed underneath SyRibbons (for an opposing scenario, please see the cell in Fig. 6B upper panel with very localised CaV1.3 distribution underneath SyRibbons). This would of course diminish the difference in the Ca<sup>2+</sup> signals between membrane regions with and without SyRibbons. We note that while the contrast is greater for native synapses, extrasynaptic Ca<sup>2+</sup> channels have been described in numerous studies alone for hair cells (Roberts et al, 1990; Brandt, 2005; Zampini et al, 2010; Wong et al, 2014).

      (ii) Nevertheless, we do not expect a remarkably big difference in Ca<sup>2+</sup> influx due to the presence of SyRibbons in the first place. Ribbon-less AZs in inner hair cells of RIBEYE KO mice showed normal Ca<sup>2+</sup> current amplitudes at the whole-cell and the single-AZ level (Jean et al, 2018). However, it was the spatial spread of the Ca2+ signal at the single-AZ level which appeared to be broader and more diffuse in these mutants in the absence of the ribbon, in contrast to the more confined Ca2+ hotspots seen in the wild-type controls. 

      So, in agreement with these published observations – it appears that presence of SyRibbons helps in spatially confining the Ca<sup>2+</sup> signal by super scaffolding nanoclusters into microclusters (see also our response to points 3 and 4 of the reviewer): this is evident from seeing some spatial confinement of Ca<sup>2+</sup> signals near SyRibbons on top of the diffuse Ca<sup>2+</sup> signal across the rest of the membrane as a result of overexpression in HEK cells. 

      We have now carefully rephrased our interpretation throughout the manuscript and added further explanation in the discussion section.   

      (6) The effect of the expression of palm-Bsn, RBP2 and the combination of the two on Ca-current is ambiguous. It appears that while the combination is larger than the control, it probably isn't significantly different from either of the other two alone (Fig 5). Moreover, expression of Ribeye + the other two showed no effect on Ca current (Figure 7). Also, why is the IV curve right shifted in Figure 7 vs Figure 5?

      We agree with the reviewer that co-expression of palm-Bassoon and RBP2 seems to augment Ca<sup>2+</sup> currents, while the additional expression of RIBEYE results in no change when compared to wild-type controls. We currently do not have an explanation for this observation and would refrain from making any claims without concrete evidence. As the reviewer also correctly pointed out, while the expression of the combination of palm-Bassoon and RBP2 raises Ca<sup>2+</sup> currents, current amplitudes are not significantly different when compared to the individual expression of the two proteins (P > 0.05, Kruskal-Wallis test). In light of this, we have now carefully rephrased our MS. Moreover, we would like to thank reviewer 1 for pointing out the right shift in the IV curve which was due to an error in the values plotted on the x-axis. This has been corrected in the updated version of the manuscript. 

      (7) While some of the IHC is quantified, some of it is simply shown as single images. EV2, EV3 and Figure 4a in particular (4b looks convincing enough on its own, but could also benefit from a larger sample size and quantification)

      We have now added quantifications for the colocalisations of the various transfection combinations depicted in the above-mentioned figures collectively in Supplementary Figure 7 and added the corresponding results and methods accordingly. 

      Reviewer #2 (Public Review):

      We would like to thank the reviewer for the comments and advice to further improve our manuscript.

      (1) Relies on over-expression, which almost certainly diminishes the experimentally-measured parameters (e.g. pre-synapse clustering, localization of Ca2+ entry).

      We acknowledge this limitation highlighted by the reviewer arising from the use of an overexpression system and have carefully rephrased our interpretation and discussed possible caveats in the discussion section. 

      (2) Are HEK cells the best model? HEK cells secrete substances and have a studied-endocytitic pathway, but they do not create neurosecretory vesicles. Why didn't the authors try to reconstitute a ribbon synapse in a cell that makes neurosecretory vesicles like a PC12 cell?

      This is a valid point for discussion that we also had here extensively. We indeed did consider pheochromocytoma cells (PC12 cells) for reconstitution of ribbon-type AZs and also performed initial experiments with these in the initial stages of the project. PC12 cells offer the advantage of providing synaptic-like microvesicles and also endogenously express several components of the presynaptic machinery such as Bassoon, RIM2, ELKS etc (Inoue et al, 2006) such that overexpression of exogenous AZ proteins would have to be limited to RIBEYE only. 

      However, a major drawback of PC12 cells as a model is the complex molecular background of these cells. We have also briefly described this in the discussion section (line 615 – 619). Naïve, undifferentiated PC12 cells show highly heterogeneous expression of various CaV channel types (Janigro et al, 1989); however, CaV1.3, the predominant type in ribbon synapses of the ear, does not seem to express in these cells (Liu et al, 1996). Furthermore, our attempts at performing immunostainings against CaV1.3 and at overexpressing CaV1.3 in PC12 cells did not prove successful and we decided on refraining from pursuing this further (data not shown). 

      On the contrary, HEK293 cells being “synapse-naïve” provide the advantage of serving as a “blank canvas” for performing such reconstitutions, e.g. they lack voltage-gated Ca<sup>2+</sup> channels and multidomain proteins of the active zone. Moreover, an important practical aspect for our choice was the availability of the HEK293 cell line with stable (and inducible) expression of the CaV1.3 Ca<sup>2+</sup> channel complex. Finally, as described in lines 613 – 614 of the discussion section, even though HEK293 cells lack SVs and the molecular machinery required for their release, our work paves way for future studies which could employ delivery of SV machinery via co-expression (Park et al, 2021) which could then be analyzed by the correlative light and electron microscopy workflow we worked out and added during revision. 

      (3) Related to 1 and 2: the Ca channel localization observed is significant but not so striking given the presence of Cav protein and measurements of Ca2+ influx distributed across the membrane. Presumably, this is the result of overexpression and an absence of pathways for pre-synaptic targeting of Ca channels. But, still, it was surprising that Ca channel localization was so diffuse. I suppose that the authors tried to reduce the effect of over-expression by using an inducible Cav1.3? Even so, the accessory subunits were constitutively over-expressed.

      We agree with the reviewer on the modest increase in Ca<sup>2+</sup> signal amplitude seen in the presence of SyRibbons. Yes, we employed inducible expression of the CaV1.3a subunit and tried to reduce the effect of overexpression by testing different induction times. However, we did not observe any major differences in expression and observed large variability in CaV1.3 expression across cells irrespective of induction duration. At all time points, there were cells with diffuse CaV1.3 localisation also in regions without SyRibbons which likely reduced the contrast of the Ca<sup>2+</sup> signal we observe. We provide the following reasoning for this observation: 

      (i) It is plausible that due to the overexpression approach, Ca<sup>2+</sup> channels (along with RBP2 and PalmBassoon) still show considerable expression along the membrane also in regions where SyRibbons are not localised. Indeed, this is evident in the images shown in the lower panel in Fig. 6B where Ca<sup>2+</sup> channel immunofluorescence is distributed across the plasma membrane with larger clusters formed underneath SyRibbons. This would of course diminish the difference in the Ca<sup>2+</sup> signals between membrane regions with and without SyRibbons. We note that while the contrast is greater for native synapses, extrasynaptic Ca<sup>2+</sup> channels have been described in numerous studies alone for hair cells (Roberts et al, 1990; Brandt, 2005; Zampini et al, 2010; Wong et al, 2014).

      (ii) Nevertheless, we do not expect a striking difference in Ca<sup>2+</sup> influx amplitude due to the presence of SyRibbons in the first place. Ribbon-less AZs in inner hair cells of RIBEYE KO mice showed normal Ca<sup>2+</sup> current amplitudes at the whole-cell and the single-AZ level (Jean et al, 2018). Instead, it was the spatial spread of the Ca<sup>2+</sup> signal at the single-AZ level which appeared to be broader and more diffuse in these mutants in the absence of the ribbon, in contrast to the more confined Ca<sup>2+</sup> hotspots seen in the wildtype controls. 

      So, in agreement with these published observations – it appears that presence of SyRibbons helps in spatially confining the Ca<sup>2+</sup> signal by super scaffolding nanoclusters into microclusters: this is evident from seeing some spatial confinement of Ca<sup>2+</sup> signals near SyRibbons on top of the diffuse Ca<sup>2+</sup> signal across the rest of the membrane as a result of overexpression in HEK cells. 

      We have now carefully rephrased our interpretation throughout the manuscript and added further explanation in the discussion section.   

      Reviewer #3 (Public Review):

      We would like to thank the reviewer for the comments and advice to further improve our manuscript.

      (1) The results obtained in a heterologous system (HEK293 cells) need to be interpreted with caution. They will importantly speed the generation of models and hypothesis that will, however, require in vivo validation.

      We acknowledge this limitation highlighted by Reviewer 3 arising from the use of an overexpression system and have carefully rephrased our interpretation and discussed possible caveats in the discussion section. We employed inducible expression of the CaV1.3a subunit and tried to reduce the effect of overexpression by testing different induction times. However, we did not observe any major differences in expression and observed large variability in CaV1.3 expression across cells irrespective of induction duration. At all time points, there were cells with diffuse CaV1.3 localisation, even in regions without SyRibbons and this could reduce the contrast of the Ca<sup>2+</sup> signal we observe. We provide the following reasoning for this observation: 

      (i) It is plausible that due to the overexpression approach, Ca<sup>2+</sup> channels (along with RBP2 and PalmBassoon) still show considerable expression along the membrane also in regions where SyRibbons are not localised. Indeed, this is evident in the images shown in the lower panel in Fig. 6B where Ca<sup>2+</sup> channel immunofluorescence is distributed across the plasma membrane with larger clusters formed underneath SyRibbons. This would of course diminish the difference in the Ca<sup>2+</sup> signals between membrane regions with and without SyRibbons. We note that while the contrast is greater for native synapses, extrasynaptic Ca<sup>2+</sup> channels have been described in numerous studies alone for hair cells (Roberts et al, 1990; Brandt, 2005; Zampini et al, 2010; Wong et al, 2014).

      (ii) Nevertheless, we do not expect a striking difference in Ca<sup>2+</sup> influx amplitude due to the presence of SyRibbons in the first place. Ribbon-less AZs in inner hair cells of RIBEYE KO mice showed normal Ca<sup>2+</sup> current amplitudes at the whole-cell and the single-AZ level (Jean et al, 2018). Instead, it was the spatial spread of the Ca<sup>2+</sup> signal at the single-AZ level which appeared to be broader and more diffuse in these mutants in the absence of the ribbon, in contrast to the more confined Ca<sup>2+</sup> hotspots seen in the wildtype controls. 

      So, in agreement with these published observations – it appears that presence of SyRibbons helps in spatially confining the Ca<sup>2+</sup> signal by super scaffolding nanoclusters into microclusters: this is evident from seeing some spatial confinement of Ca<sup>2+</sup> signals near SyRibbons on top of the diffuse Ca<sup>2+</sup> signal across the rest of the membrane as a result of overexpression in HEK cells. 

      (2) The authors analyzed the distribution of RIBEYE clusters in different membrane compartments and correctly conclude that RIBEYE clusters are not trapped in any of those compartments, but it is soluble instead. The authors, however, did not carry out a similar analysis for Palm-Bassoon. It is therefore unknown if Palm-Bassoon binds to other membrane compartments besides the plasma membrane. That could occur because in non-neuronal cells GAP43 has been described to be in internal membrane compartments. This should be investigated to document the existence of ectopic internal Synribbons beyond the plasma membrane because it might have implications for interpreting functional data in case Ca2+-channels become part of those internal Synribbons.

      In response to this valid concern, we have now included the suggested experiment in Supplementary Figure 1. We investigated the subcellular localisation of Palm-Bassoon and did not find Palm-Bassoon puncta to colocalise with ER, Golgi, or lysosomal markers, suggesting against a possible binding with membrane compartments inside the cell. We have added the following sentence in the results section, line 145 : “Palm-Bassoon does not appear to localize in the ER, Golgi apparatus or lysosomes (Supplementary Fig 1 D, E and F).”

      (3) The co-expression of RBP2 and Palm-Bassoon induces a rather minor but significant increase in Ca2+-currents (Figure 5). Such an increase does not occur upon expression of (1) Palm-Bassoon alone, (2) RBP2 alone or (3) RIBEYE alone (Figure 5). Intriguingly, the concomitant expression of PalmBassoon, RBP2 and RIBEYE does not translate into an increase of Ca2+-currents either (Figure 7).

      We agree with the reviewer that co-expression of palm-Bassoon and RBP2 seems to augment Ca<sup>2+</sup> currents, while the additional expression of RIBEYE results in no change when compared to wild-type controls. We currently do not have an explanation for this observation and would refrain from making any claims without concrete evidence. We also highlight that, while the expression of the combination of palm-Bassoon and RBP2 raises Ca<sup>2+</sup> currents, current amplitudes are not significantly different when compared to the individual expression of the two proteins (P > 0.05, Kruskal-Wallis test). In light of this, we have now carefully rephrased our MS. 

      (4) The authors claim that Ca2+-imaging reveals increased CA2+-signal intensity at synthetic ribbontype AZs. That claim is a subject of concern because the increase is rather small and it does not correlate with an increase in Ca2+-currents.

      Thanks for the comment: please see our response to your first comment and the lines 585 – 610 in the discussion section.

      Recommendations for the authors:  

      Reviewer #2 (Recommendations For The Authors):

      (1) The authors should have a better discussion of problems derived from over-expression.

      Done. Please see above. 

      (2) Ideally, the authors would repeat the study using a secretory cell line, but this is of course not possible. The idea could be brought forth, though.

      As described above in our response to the public review of reviewer 2, we have discussed this idea in the discussion section (refer to lines 615 – 619), emphasizing on both the advantages and the limitations of using a secretory cell line (e.g. PC12 cells) instead of HEK293 cells as a model for performing such reconstitutions. 

      Reviewer #3 (Recommendations For The Authors):

      (1) There are several figures in which colocalization between different proteins is studied only displaying images but without any quantitative data. This should be corrected by providing such a quantitative analysis.

      We have now added quantifications for the colocalisations of the various transfection combinations depicted in the above-mentioned figures collectively in Supplementary Figure 7 and added the corresponding results and methods accordingly. 

      (2) The little increase in Ca2+-currents and Ca2+-influx associated to the clustering of Ca2+-channels to Synribbons is a concern. The authors should discuss if such a minor increase (found only when Palm-Bassoon and RBP2 ae co-expressed) would have or not physiological consequences in an actual synapse. They might discuss the comparison of those results and compare with results obtained in genetically modified mice in which Ca2+-currents are affected upon the removal of AZs proteins. On the other hand, they should explain why Ca2+-currents do not increase when the Synribbons are formed by RIBEYE, Palm-Bassoon and RBP2.

      Done. Please see above. 

      (3) The description of the patch-clamp experiments should be enriched by including representative currents. Did the authors measure tail currents?

      We would like to thank the reviewer for the valuable suggestion and have now added representative currents to the figures (see Supplementary Figure 5B). We agree with the reviewer on the importance of further characterizing the Ca<sup>2+</sup> currents in the presence and absence of SyRibbons by analysis of tail currents for counting the number of Ca<sup>2+</sup> channels by non-stationary fluctuation analysis but consider this to be out of scope of the current study and an objective for future studies. 

      (4) The current displayed in Figure 7 E should be explained better.

      Previous studies have shown that Ca<sup>2+</sup>-binding proteins (CaBPs) compete with Calmodulin to reduce Ca<sup>2+</sup>-dependent inactivation (CDI) and promote sustained Ca<sup>2+</sup> influx in Inner Hair Cells (Cui et al, 2007; Picher et al, 2017). In the absence of CaBPs, CaV1.3-mediated Ca<sup>2+</sup> currents show more rapid CDI as in the case here upon heterologous expression in HEK cells ((Koschak et al, 2001), see also Picher et al 2017 where co-expression of CaBP2 with CaV1.3 inhibits CDI in HEK293 cells). The inactivation kinetics of CaV1.3 are also regulated by the subunit composition (Cui et al, 2007) along with the modulation via interaction partners and given the reconstitution here we do not find the currents very surprising. 

      (5) Is the difference in Ca2+-influx still significantly higher upon the removal of the maximum value measured in positive Syribbons spots (Figure 7, panel K)?

      Yes, on removing the maximum value, the P value increases from 0.01 to 0.03 but remains statistically significant. 

      (6) In summary, although the approach pioneered by the authors is exciting and provides relevant results, there is a major concern regarding the interpretation of the modulation of Ca2+ channels.

      We have now carefully rephrased our interpretation on the modulation of Ca<sup>2+</sup> channels.  

      References

      Brandt A (2005) Few CaV1.3 Channels Regulate the Exocytosis of a Synaptic Vesicle at the Hair Cell Ribbon Synapse. Journal of Neuroscience 25: 11577–11585

      Cui G, Meyer AC, Calin-Jageman I, Neef J, Haeseleer F, Moser T & Lee A (2007) Ca2+-binding proteins tune Ca2+-feedback to Cav1. 3 channels in mouse auditory hair cells. The Journal of Physiology 585: 791–803

      Davydova D, Marini C, King C, Klueva J, Bischof F, Romorini S, Montenegro-Venegas C, Heine M, Schneider R, Schröder MS, et al (2014) Bassoon specifically controls presynaptic P/Q-type Ca(2+) channels via RIM-binding protein. Neuron 82: 181–194

      tom Dieck S, Altrock WD, Kessels MM, Qualmann B, Regus H, Brauner D, Fejtová A, Bracko O, Gundelfinger ED & Brandstätter JH (2005) Molecular dissection of the photoreceptor ribbon synapse: physical interaction of Bassoon and RIBEYE is essential for the assembly of the ribbon complex. J Cell Biol 168: 825–836

      Frank T, Rutherford MA, Strenzke N, Neef A, Pangršič T, Khimich D, Fejtova A, Gundelfinger ED, Liberman MC, Harke B, et al (2010) Bassoon and the synaptic ribbon organize Ca2+ channels and vesicles to add release sites and promote refilling. Neuron 68: 724–738

      Grabner CP & Moser T (2021) The mammalian rod synaptic ribbon is essential for Cav channel facilitation and ultrafast synaptic vesicle fusion. eLife 10: e63844

      Hibino H, Pironkova R, Onwumere O, Vologodskaia M, Hudspeth AJ & Lesage F (2002) RIM - binding proteins (RBPs) couple Rab3 - interacting molecules (RIMs) to voltage - gated Ca2+ channels. Neuron 34: 411–423

      Inoue E, Deguchi-Tawarada M, Takao-Rikitsu E, Inoue M, Kitajima I, Ohtsuka T & Takai Y (2006) ELKS, a protein structurally related to the active zone protein CAST, is involved in Ca2+-dependent exocytosis from PC12 cells. Genes to Cells 11: 659–672

      Janigro D, Maccaferri G & Meldolesi J (1989) Calcium channels in undifferentiated PC12 rat pheochromocytoma cells. FEBS Letters 255: 398–400

      Jean P, Morena DL de la, Michanski S, Tobón LMJ, Chakrabarti R, Picher MM, Neef J, Jung S, Gültas M, Maxeiner S, et al (2018) The synaptic ribbon is critical for sound encoding at high rates and with temporal precision. Elife 7: e29275

      Koschak A, Reimer D, Huber I, Grabner M, Glossmann H, Engel J & Striessnig J (2001) alpha 1D (Cav1.3) subunits can form l-type Ca2+ channels activating at negative voltages. J Biol Chem 276: 22100–22106

      Krinner S, Butola T, Jung S, Wichmann C & Moser T (2017) RIM-Binding Protein 2 Promotes a Large Number of CaV1.3 Ca2+-Channels and Contributes to Fast Synaptic Vesicle Replenishment at Hair Cell Active Zones. Front Cell Neurosci 11: 334

      Liu H, Felix R, Gurnett CA, De Waard M, Witcher DR & Campbell KP (1996) Expression and Subunit Interaction of Voltage-Dependent Ca2+ Channels in PC12 Cells. J Neurosci 16: 7557–7565

      Lv C, Stewart WJ, Akanyeti O, Frederick C, Zhu J, Santos-Sacchi J, Sheets L, Liao JC & Zenisek D (2016) Synaptic Ribbons Require Ribeye for Electron Density, Proper Synaptic Localization, and Recruitment of Calcium Channels. Cell Reports 15: 2784–2795

      Matthews G & Fuchs P (2010) The diverse roles of ribbon synapses in sensory neurotransmission. Nat Rev Neurosci 11: 812–822

      Maxeiner S, Luo F, Tan A, Schmitz F & Südhof TC (2016) How to make a synaptic ribbon: RIBEYE deletion abolishes ribbons in retinal synapses and disrupts neurotransmitter release. The EMBO Journal 35: 1098–1114

      Michanski S, Kapoor R, Steyer AM, Möbius W, Früholz I, Ackermann F, Gültas M, Garner CC, Hamra FK, Neef J, et al (2023) Piccolino is required for ribbon architecture at cochlear inner hair cell synapses and for hearing. EMBO Rep 24: e56702

      Michanski S, Smaluch K, Steyer AM, Chakrabarti R, Setz C, Oestreicher D, Fischer C, Möbius W, Moser T, Vogl C, et al (2019) Mapping developmental maturation of inner hair cell ribbon synapses in the apical mouse cochlea. PNAS 116: 6415–6424

      Neef J, Urban NT, Ohn T-L, Frank T, Jean P, Hell SW, Willig KI & Moser T (2018) Quantitative optical nanophysiology of Ca2+ signaling at inner hair cell active zones. Nat Commun 9: 290

      Park D, Wu Y, Lee S-E, Kim G, Jeong S, Milovanovic D, Camilli PD & Chang S (2021) Cooperative function of synaptophysin and synapsin in the generation of synaptic vesicle-like clusters in non-neuronal cells. Nat Commun 12

      Picher MM, Gehrt A, Meese S, Ivanovic A, Predoehl F, Jung S, Schrauwen I, Dragonetti AG, Colombo R, Camp GV, et al (2017) Ca2+-binding protein 2 inhibits Ca2+-channel inactivation in mouse inner hair cells. PNAS 114: E1717–E1726

      Robertis ED & Franchi CM (1956) Electron Microscope Observations on Synaptic Vesicles in Synapses of the Retinal Rods and Cones. J Biophys Biochem Cytol 2: 307–318

      Roberts WM, Jacobs RA & Hudspeth AJ (1990) Colocalization of ion channels involved in frequency selectivity and synaptic transmission at presynaptic active zones of hair cells. J Neurosci 10: 3664–3684

      Smith CA & Sjöstrand FS (1961) A synaptic structure in the hair cells of the guinea pig cochlea. Journal of Ultrastructure Research 5: 184–192

      Wong AB, Rutherford MA, Gabrielaitis M, Pangršič T, Göttfert F, Frank T, Michanski S, Hell S, Wolf F, Wichmann C, et al (2014) Developmental refinement of hair cell synapses tightens the coupling of Ca2+ influx to exocytosis. EMBO J 33: 247–264

      Zampini V, Johnson SL, Franz C, Lawrence ND, Münkner S, Engel J, Knipper M, Magistretti J, Masetto S & Marcotti W (2010) Elementary properties of CaV1.3 Ca(2+) channels expressed in mouse cochlear inner hair cells. J Physiol 588: 187–199

    1. Author response:

      The following is the authors’ response to the original reviews

      Public Reviews:

      Reviewer #1 (Public review):

      Summary:

      The authors, Dalal, et. al., determined cryo-EM structures of open, closed, and desensitized states of the pentameric ligand-gated ion channel ELIC reconstituted in liposomes, and compared them to structures determined in varying nanodisc diameters. They argue that the liposomal reconstitution method is more representative of functional ELIC channels, as they were able to test and recapitulate channel kinetics through stopped-flow thallium flux liposomal assay. The authors and others have described channel interactions with membrane scaffold proteins (MSP), initially thought to be in a size-dependent manner. However, the authors reported that their cryo-EM ELIC structure interacts with the large nanodisc spNW25, contrary to their original hypotheses. This suggests that the channel's interactions with MSPs might alter its structure, possibly not accurately representing/reflecting functional states of the channel.

      Strengths:

      Cryo-EM structural determination from proteoliposomes is a promising methodology within the ion channel field due to their large surface area and lack of MSP or other membrane mimetics that could alter channel structure. Comparing liposomal ELIC to structures in various-sized nanodiscs gives rise to important discussions for other membrane protein structural studies when deciding the best method for individual circumstances.

      Weaknesses:

      The overarching goal of the study was to determine structural differences of ELIC in detergent nanodiscs and liposomes. Including comparisons of the results to the native bacterial lipid environment would provide a more encompassing discussion of how the determined liposome structures might or might not relate to the native receptor in its native environment. The authors stated they determined open, closed, and desensitized states of ELIC reconstituted in liposomes and suggest the desensitization gate is at the 9' region of the pore. However, no functional studies were performed to validate this statement.

      The goal of this study was to determine structures of ELIC in the same lipid environment in which its function is characterized. However, it is also worth noting that phosphatidylethanolamine and phosphatidylglyerol, two lipids used for the liposome formation, are necessary for ELIC function (PMID 36385237) and principal lipid components of gram-negative bacterial membranes in which ELIC is expressed.

      The desensitized structure of ELIC in liposomes shows a pore diameter at the hydrophobic L240 (9’) residue of 3.3 Å, which is anticipated to pose a large energetic barrier to the passage of ions due to the hydrophobic effect. We have included a graphical representation of pore diameters from the HOLE analysis for all liposome structures in Supplementary Figure 6B. While we have not tested the role of L240 in desensitization with functional experiments, it was shown by Gonzalez-Gutierrez and colleagues (PMID 22474383) that the L240A mutation apparently eliminates desensitization in ELIC. This finding is consistent with L240 (9’) being the desensitization gate of ELIC. We have referenced this study when discussing the desensitization gate in the Results.

      Reviewer #2 (Public review):

      Summary

      The report by Dalas and colleagues introduces a significant novelty in the field of pentameric ligand-gated ion channels (pLGICs). Within this family of receptors, numerous structures are available, but a widely recognised problem remains in assigning structures to functional states observed in biological membranes. Here, the authors obtain both structural and functional information of a pLGIC in a liposome environment. The model receptor ELIC is captured in the resting, desensitized, and open states. Structures in large nanodiscs, possibly biased by receptor-scaffold protein interactions, are also reported. Altogether, these results set the stage for the adoption of liposomes as a proxy for the biological membranes, for cryoEM studies of pLGICs and membrane proteins in general.

      Strengths

      The structural data is comprehensive, with structures in liposomes in the 3 main states (and for each, both inward-facing and outward-facing), and an agonist-bound structure in the large spNW25 nanodisc (and a retreatment of previous data obtained in a smaller disc). It adds up to a series of work from the same team that constitutes a much-needed exploration of various types of environment for the transmembrane domain of pLGICs. The structural analysis is thorough.

      The tone of the report is particularly pleasant, in the sense that the authors' claims are not inflated. For instance, a sentence such as "By performing structural and functional characterization under the same reconstitution conditions, we increase our confidence in the functional annotation of these structures." is exemplary.

      Weaknesses

      Core parts of the method are not described and/or discussed in enough detail. While I do believe that liposomes will be, in most cases, better than, say, nanodiscs, the process that leads from the protein in its membrane down to the liposome will play a big role in preserving the native structure, and should be an integral part of the report. Therefore, I strongly felt that biochemistry should be better described and discussed. The results section starts with "Optimal reconstitution of ELIC in liposomes [...] was achieved by dialysis". There is no information on why dialysis is optimal, what it was compared to, the distribution of liposome sizes using different preparation techniques, etc... Reading the title, I would have expected a couple of paragraphs and figure panels on liposome reconstitution. Similarly, potential biochemical challenges are not discussed. The methods section mentions that the sample was "dialyzed [...] over 5-7 days". In such a time window, most of the members of this protein family would aggregate, and it is therefore a protocol that can not be directly generalised. This has to be mentioned explicitly, and a discussion on why this can't be done in two days, what else the authors tested (biobeads? ... ?) would strengthen the manuscript.

      To a lesser extent, the relative lack of both technical details and of a broad discussion also pertains to the cryoEM and thallium flux results. Regarding the cryoEM part, the authors focus their analysis on reconstructions from outward-facing particles on the basis of their better resolutions, yet there was little discussion about it. Is it common for liposome-based structures? Are inward-facing reconstructions worse because of the increased background due to electrons going through two membranes? Are there often impurities inside the liposomes (we see some in the figures)? The influence of the membrane mimetics on conformation could be discussed by referring to other families of proteins where it has been explored (for instance, ABC transporters, but I'm sure there are many other examples). If there are studies in other families of channels in liposomes that were inspirational, those could be mentioned. Regarding thallium flux assays, one argument is that they give access to kinetics and set the stage for time-resolved cryoEM, but if I did not miss it, no comparison of kinetics with other techniques, such as electrophysiology, nor references to eventual pioneer time-resolved studies are provided.

      Altogether, in my view, an updated version would benefit from insisting on every aspect of the methodological development. I may well be wrong, but I see this paper more like a milestone on sample prep for cryoEM imaging than being about the details of the ELIC conformations.

      Additions have been made to the Results and Discussion sections elaborating on the following points: 1) reconstitution of ELIC in liposomes using dialysis, the advantage of this over other methods such as biobeads, and whether the dialysis protocol can be shortened for other less stable proteins; 2) the issue of separating outward- and inward-facing channels; 3) referencing the effect of nanodiscs on ABC transporters, structures of membrane proteins in liposomes, and pioneering time-resolved cryo-EM studies; and 4) comparison of the kinetics of ELIC gating kinetics with electrophysiology measurements. With regards to the first point, it should be noted that all necessary details are provided in the Methods to reproduce the experiments including the reconstitution and stopped-flow thallium flux assay. It is also important to note that the same preparation for making proteoliposomes was used for assessing function using the stopped-flow thallium flux assay and for determining the structure by cryo-EM. This is now stated in the Results.

      Recommendations for the authors:

      Reviewer #1 (Recommendations for the authors):

      Major revisions:

      (1) The authors suggest that the desensitization gate is located at the 9' region within the pore. However, as stated by the authors, the 2' residues function as the desensitization gate in related channels. In a few of their HOLE analyzed structures (e.g. Figure 2B and 4B), there seems to be a constriction also at 2', but this finding is not discussed in the context of desensitization. Further functional testing of mutated 9' and/or 2' gates would bolster the argument for the location of the desensitization gate.

      As stated above, we have included HOLE plots of pore radius in Supplementary Fig. 6B and referenced the study showing that the L240A mutation (9’) in ELIC (PMID 22474383) appears to eliminate desensitization. This result along with the narrow pore diameter at 9’ in the desensitized structure suggests that 9’ is likely a desensitization gate in ELIC. In contrast, mutation of Q233 (2’) to a cysteine in a previous study produced a channel that still desensitizes (PMID 25960405). Since Q233 is a hydrophilic residue in contrast to L240, Q233 probably does not pose the same energetic barrier to ion translocation as L240 based on the structure.

      (2) In discussing functional states of ELIC and ELIC5 in different reconstitution methods, the authors reference constriction sites determined by HOLE analysis software. These constriction sites were key evidence for the authors to determine functional state, however, it is difficult to discern pore sizes based on the figures. Pore diameters and clear color designation (ie, green vs orange) with the figures would greatly aid their discussions.

      HOLE plots are displayed in Supplementary Fig. 6B and pore diameters are not provided in the text.

      (3) The authors had an intriguing finding that ELIC dimers are found in spNW25 scaffolds. Is there any functional evidence to suggest they could be functioning as dimers?

      There is no evidence that the function of ELIC or other pLGICs is altered by the formation of dimers of pentamers. Therefore, while this result is intriguing and likely facilitated by concentrating multiple ELIC pentamers within the nanodisc, it is not clear if these interactions have any functional importance. We have stated this in the Results.

      (4) Thallium flux assay to validate channel function within proteoliposomes. Proteoliposomes are known to be generally very leaky membranes, would be good to have controls without ELIC added to determine baseline changes in fluorescence.

      We have established from multiple previous studies that liposomes composed of 2:1:1 POPC:POPE:POPG (PMID 36385237 and 31724949) do not show significant thallium flux as measured by the stopped-flow assay (PMID 29058195) in the absence of ELIC activity. Furthermore, in the present study, the data in Fig. 1A of WT ELIC shows a low thallium flux rate 60 seconds after exposure to agonist when the ion channel has mostly desensitized. Therefore, this data serves also as a control indicating that the high thallium flux rates in response to agonist (at earlier delay times) are not due to leak, but rather due to ELIC channel activity.

      Minor revisions:

      (1) Abstract and introduction. 'Liganded' should be ligand

      We removed this word and changed it to “agonist-bound” for consistency throughout the manuscript.

      (2) Inconsistent formatting of FSC graphs in Supplemental Figure 4

      The difference is a consequence of the different formatting between cryoSPARC and Relion FSC graphs.

      Reviewer #2 (Recommendations for the authors):

      Minor writing remarks:

      The present report builds on previous work from the same team, and to my eye it would be a plus if this were conveyed more explicitly. I see it as a strength to explore various developments in several papers that complement each other. E.g in the introduction when citing reference 12 (Dalal 2024), later in introducing ref 15 (Petroff 2022), I wish I was reminded of the main findings and how they fit with the new results.

      We have expanded on the Results and Discussion detailing key findings from these studies that are relevant to the current study.

      Suggestions for analysis:

      Data treatment. Maybe I missed it, but I wondered if C1 vs C5 treatment of the liposome data showed any interesting differences? When I think about the biological membrane, I picture it as a very crowded place with lots of neighbouring proteins. I would not be surprised if, similarly to what they do in discs, the receptor would tend to stick to, or bump into, anything present also in liposomes (a neighboring liposome, some undefined density inside the liposome).

      We attempted to perform C1 heterogeneous refinement jobs in cryoSPARC and C1 3D classification in Relion5. For the WT datasets, these did not produce 3D reconstructions that were of sufficient quality for further refinement. For ELIC5 with agonist, the C1 reconstructions were not different than the C5 reconstructions. Furthermore, there was no evidence of dimers of pentamers from the 2D or 3D treatments, unlike what was observed in the spNW25 nanodiscs. This is likely because the density of ELIC pentamers in the liposomes was too low to capture these transient interactions. We have included this information in the Methods.

      In data treatment, we sometimes find only what we're looking for. I wondered if the authors tried to find, for instance, the open and D conformations in the resting dataset during classifications.

      This is an interesting question since some population of ELIC channels could visit a desensitized conformation in the absence of agonist and this would not be detected in our flux assay. After extensive heterogeneous refinement jobs in cryoSPARC and 3D classification jobs in Relion5, we did not detect any unexpected structures such as open/desensitized conformations in the apo dataset.

      In the analysis of the M4 motions, is there info to be gained by looking at how it interacts with the rest of the TMD? For instance, I wondered if the buried surface area between M4 and the rest was changed. Also one could imagine to look at that M4 separately in outward-facing and inward-facing conformations (because the tension due to the bilayer will not be the same in the outer layer in both orientations - intuitively, I'd expect different levels of M4 motions)

      We have expanded our analysis of the structures as recommended. We determined the buried surface area between M4 and the rest of the channel in the liganded WT and ELIC5 structures in liposomes and nanodiscs, as well as the area between the TMD interfaces for these structures. There appears to be a pattern where liposome structures show less buried surface area between M4 and the rest of the channel, and less area at the TMD interfaces. Overall, this suggests that the liposome structures of ELIC in the open-channel or desensitized conformations are more loosely packed in the TMD compared to the nanodisc structures.

      We have also further discussed the issue of separating outward- and inward-facing conformations in the Results. The problem with classifying outward- and inward-facing orientations is that top/down or tilted views of the particles cannot be easily distinguished as coming from channels in one orientation or the other, unless there are conformational differences between outward- and inward-facing channels that would allow for their separation during 3D heterogeneous refinement or 3D classification. Furthermore, since the inward-facing reconstructions are of much lower resolution than the outward-facing reconstructions, we suspect that these particles are more heterogeneous possibly containing junk, multiple conformations, or particles that are both inward- and outward-facing. On the other hand, the outward-facing structures are of good quality, and therefore we are more confident that these come from a more homogeneous set of particles that are likely outward-facing (Note that most particles are outward facing based on side views of the 2D class averages). That said, when examining the conformation of M4 in outward- and inward-facing structures, we do not see any significant differences with the caveat that the inward-facing structures are of poor quality and that inward- and outward-facing particles may not have been well-separated.

  3. notebooksharing.space notebooksharing.space
    1. Findings from Analysis

      Have you mixed the labels of your plot in this analysis? It looks like what you are describing under 1.5°C is shown for 4°C in the plot

    2. 2.7°C Scenario: Both basins show slight 2060 increase, reduced by 2100, suggesting peak water ~2060, less severe than 4°C. 1.5°C Scenario:

      I do not see strong differences between warming levels, regarding peak water (see also my comments above)

    3. Yarla Shampo Basin

      this is not enough, to just give bullet points about the evolution of curves. You should also write your findings down in full sentences (e.g. the seasonal peak runoff for 4°C is reached in ..., where as this peak is shifted for 1.5°C to ... .

    4. closely aligning with their respective targets, especially for 4°C and 2.7°C. The slight positive deviation for the 1.5°C target is minor but notable

      Here it would be good to also add some numbers you have found (e.g. for 4°C the selection has an mean temperature of 4.06°C and a median tempreture of …)

    1. Note: This response was posted by the corresponding author to Review Commons. The content has not been altered except for formatting.

      Learn more at Review Commons


      Reply to the reviewers

      Reviewer #1 (Evidence, reproducibility and clarity (Required)):

      In Morris, M.J. et al., the authors strive to better understand the roles for the microcephaly protein WDR62 in brain growth and function. To accomplish this, an in situ biotinylation assay was performed and identified 42 proteins proximal to WDR62 including the Hsp70 co-chaperone BAG2. Through a series of co-immunoprecipitation assays, the BAG2-WDR62 interaction was shown to be mediated through the structured N-terminal region of WDR62, and it was proposed that common WDR62 mutations disrupt this interaction. In AD293 cells, loss of WRD62 expression resulted in an increase in the expression of BAG2 expression while reducing HPRT expression. Subsequent loss of BAG2 expression by siRNA treatment restored the expression of HPRT suggesting that there is an association between the stability of HPRT and BAG2, likely mediated through its proposed association with Hsp70/90 molecular chaperones. Finally, the authors investigate the subcellular localization and ability of WRD62 to phase separate. WRD62 was shown to form discrete condensates induced by sorbitol-mediated hyperosmotic stress. The formation of WRD62 granules are hypothesized to be driven by cell volume exclusion and macromolecular crowding. These granules appear similar, both in physical appearance and characteristics, to other reported biomolecular condensates such as those reported in metabolism (e.g. purinosomes). WRD62-containing condensates were shown to colocalize with enzymes in de novo purine biosynthesis; however, this association is not required for purinosome formation and/or its stability under both purine-depleted and sorbitol-driven growth conditions. Overall, the manuscript provided a previously unrealized and exciting association between WDR62 and purine metabolism.

      EVIDENCE, REPRODUCIBILITY AND CLARITY Summary: The current manuscript reads as multiple manuscripts with findings that are at times weakly connected (in my opinion). For example, I had a hard time understanding how the BioID results relate to the discovery of WRD62 phase-separation and its colocalization with purinosomes. I would strongly encourage the authors to consider dividing the results into separate manuscripts to strengthen their claims and create a more focused and cohesive manuscript (or series of manuscripts). I believe then several of my reservations associated with the current manuscript will be addressed, and in my opinion, the hard work from the authors will be better received across the scientific community.

      Response: We thank Reviewer #1 for acknowledging the novelty of our work and appreciate the constructive feedback regarding the lack of integration among individual findings. In response, we have removed content related to condensate formation and conducted additional experiments to more thoroughly characterize the mechanisms of WDR62 interaction. These new data, along with revisions to the manuscript text, have strengthened the coherence of our findings. We believe the revised manuscript now presents a more unified narrative, highlighting the complex roles of WDR62 in regulating purine metabolism.

      I would like to commend the authors for all the work that went into the current version of the manuscript. Being part of a biochemistry and cell biology research group, I completely understand how much time and effort must have went into generating these data. That being said, I felt that there were several instances where clarification and additional information is warranted to arrive at the conclusions made by the authors. These points are outlined below.

      Major Comments:

      1. There appears to be a discrepancy between the data presented in Figure 1 and what is stated in the main text. Clarification is necessary to better understand the results:

      • The following statement (and derivatives of it) are repeated throughout the manuscript: "...we found that the WDR62 interactome comprised molecular chaperones such as HSP70, HSP90, and their co-regulators, BAG2, STIP1, and DNAJC7" (lines 91-93, 316-318, 422-425). STIP1 and DNAJC7 were not identified in the list of 42 proximal proteins to WDR62 (Figure 1D). DNAJC7 was included because of a previous report curated in the BioGRID database, and there is no mention of HSP90 in the data produced in Figure 1. Please revise the main text to reflect the data that was generated.

      Response: We thank the reviewer for this valid point and highlighting the instances where our description of results did not accurately reflect the data generated. We have reworded the relevant sections (e.g. lines 105-107) in our revised manuscript to better delineate interactors identified in BioID studies (BAG2) as opposed to those previously reported on protein interaction databases such as BioGRID (DNAJC7).

      Based on the data presented in the Venn Diagrams in Figure 1D, the author's numbers do not seem to be consistent with the sentence on lines 126-128. I count 37 proteins unique to their BioID study, 90 unique to the BioGRID database, and 5 proteins that overlap between the two data sets. This sentence needs to be revised.

      Response: We thank the reviewer for pointing out this inconsistency. There were 95 protein interactors of WDR62 from BioGRID while we identified 42 proteins in our BioID study with 5 proteins overlapping. We have revised the main text (lines 144-146) and Fig. 1D to accurately reflect the protein numbers identified.

      What data were used to generate the interaction map in Figure 1I? Enzymes tied to purine metabolism were not identified from the data presented in Figure 1D but have now appeared. A discussion of this in the main text is warranted.

      Response: We generated the interaction map in Fig. 1I using STRING to visualise WDR62 protein-protein interactions derived from both the BioGRID database and our BioID analysis. As the reviewer correctly points out, purine metabolic enzymes were not direct interactors of WDR62. Purine enzymes are linked to the molecular chaperones which, in turn, associated with WDR62 from our BioID analysis. The links between purine enzymes and chaperones were obtained from the BioGRID database. In response to this feedback, we have revised our manuscript to include a more detailed description of how the interaction map in Fig. 1I was generated, both in the main text (lines 148-157) and the legend for Figure 1. The BioGRID interactions between heat shock proteins and purine enzymes were introduced in the manuscript text at lines 264-266.

      1. This reviewer has several reservations on how the various key players in the manuscript are related to substantiate the conclusions made in the manuscript. For instance, how is HPRT, purinosomes, and WDR62 related? How about HSP90, WRD62, and HPRT? Pairwise connections were made throughout the manuscript; however, trying to tie all three together is difficult with the data presented.

      • The authors tried to connect HPRT, purinosomes, and WDR62 with BAG2; however, this study could greatly improve if we understood how a knockdown of BAG2 impacts purinosome formation and/or WDR62 colocalization with purinosome enzymes.

      Response: We have incorporated additional experiments in our revised manuscript to better connect HPRT, WDR62 and BAG2. Using proximity ligation assays (PLA) we demonstrated endogenous interactions between WDR62 and BAG2 (Fig. 4K), as well as between WDR62/HPRT and BAG2/HPRT (Fig. 6I-J). The interaction between BAG2 and HPRT was decreased in WDR62 KO cells (Fig. 6J), and recent experiments revealed that BAG2 depletion similarly disrupted the WDR62/HPRT interaction. These findings suggest that WDR62 expression, and presumably its interaction with BAG2, is necessary for BAG2-mediated regulation of HPRT.

      Further, we found that the loss of HPRT expression in WDR62 KO cells was reversed by siRNA depletion of BAG2 (Fig. 6K), supporting our model in which elevated BAG2 levels in the absence of WDR62 promote aberrant HPRT degradation. Collectively, our results suggest that proper BAG2 regulation of HPRT requires WDR62.

      To address the reviewer’s suggestion, we also examined WDR62 cytoplasmic localisation following BAG2 depletion and found that BAG2 was not required for WDR62 to form granules in response to osmotic stress. We also show that BAG2 is not responsible for purinosome assembly or for the subcellular distribution/localisation of HPRT.

      Is HPRT a client of HSP90? And how are WRD62 and HSP90 related since they do not associated (based on your BioID data)? These connections would again strengthen the arguments made in the manuscript and help to explain the HSP90 inhibition data presented in Figures 7F and 7G.

      Response: Although our BioID data did not explicitly identify an association between WDR62 and HSP90, we initially focused on HSP90 due to the established role of BAG2 in protein misfolding and degradation through its interaction with HSP90 (doi: 10.7150/thno.78492). We hypothesised that while WDR62 may not directly interact with HSP90, its interaction with BAG2 could provide an indirect link. To strengthen our conclusions and address the limitations of our HSP90 inhibition data (NVP-AUY922), we performed additional experiments using a second HSP90 inhibitor (17-AAG) and an HSP70 inhibitor (MKT-077) across both short (1 h) and long (24 h) treatment durations (Fig 6 and Fig S10). Further details are provided in our response below to minor comment #1.

      Caution is warranted when making conclusions about WDR62 (and its granules) and purinosomes.

      Response: We acknowledge the reviewer’s feedback and have revised our manuscript to focus on the functional characterisation of WDR62 interaction and co-localisation with BAG2 and related HSP co-chaperones. As part of this revision, we removed the FRAP studies and sections discussing WDR62 phase separation and purinosome assembly (further details below). Additionally, we have softened out description of cytoplasmic WDR62 granules as purinosomes. Instead, we describe WDR62 as forming dynamic puncta containing purine enzymes and discuss the possibility that these granules may represent or overlap with bona fide purinosomes.

      The authors describe the association between WDR62 and purinosomes differently throughout the text. I would recommend that the authors come to some conclusion about this and be consistent.

      Response: We thank reviewer #1 for pointing out inconsistencies in our conclusions regarding WDR62 and purinosomes between sections of our manuscript. We have revised our manuscript to ensure our description of these findings are consistent throughout. Specifically, our findings show that WDR62 responds to osmotic and metabolic stress by forming dynamic cytoplasmic granules that share many protein components with purinosomes (Fig. 5). This suggests that WDR62 may be a novel component of bona fide purinosomes or that WDR62 granules substantially overlap with purinosomes both spatially and compositionally. However, the formation of granules by purine enzymes was not perturbed by WDR62 KO (Fig. S6). Thus, we conclude that while WDR62 colocalized with purine enzyme containing granules consistent with purinosomes in response to cell stress, WDR62 was not required for granule formation by purine enzymes such as PFAS and PPAT.

      A. (Lines 339-340) "WDR62 granules represent or overlap substantially with the phase-separated metabolons known as purinosomes". Based on the data presented, it appears that these might still be different entities but either overlap or have similar components. Purinosome localization with mitochondria (approx 60-80%) and microtubules (approx 90-95%) were significantly higher than those reported for WDR62 granules (approx 40%). This comparison would suggest that not all WDR62 granules behave similarly to purinosomes. And from the dot plot in Figure 3G, about half of the characterized WDR62 granules do not align with the previously reported characteristics of purinosomes.

      Response: In Fig. 3G, we measured the diameter and distribution of WDR62 granules and found their size and number per cell closely matched those reported for BAG2 condensates (doi: 10.1038/s41467-022-30751-4). This aligns with our findings that WDR62 interacts with BAG2 and is recruited to similar subcellular compartments. The reviewer correctly notes that WDR62 granules only partially align with previously reported characteristics of purinosomes, suggesting that they may be distinct entities. Our revised manuscript acknowledges this possibility while also emphasising that WDR62 granules share features and colocalise with many purinosome components. To enhance the focus and clarity of the manuscript, we have removed Fig. 3G as the diameter and number of WDR62 granules are already reported in Fig. 3F.

      In the abstract and introduction, the authors state that WDR62 is being recruited to the purinosome and leave out the other possibility. I would recommend that the authors soften this claim in these sections because of the above possibility but also the lack of characterization of the sorbitol-induced "purinosomes". There is little discussion or evidence for how sorbitol induces purinosome formation. Is de novo purine biosynthesis activated upon sorbitol treatment? Are multiple de novo purine biosynthetic enzymes present in the sorbitol-induced "purinosomes"? Further, I agree that there is a tendency for WDR62 to associate with condensates that bear an enzyme within de novo purine biosynthesis; however many of these proteins are known to self-aggregate upon cell stress. Therefore, the entities that are being observing and called purinosomes might not be bone fide purinosomes. Additional care is necessary to make these statements. In my opinion, the current data only suggests that this might be a possibility.

      Response: As indicated, we have softened our claim that stress-induced WDR62 granules represented bona fide purinosomes. Fig. 3 of our revision more precisely describes the characteristics of WDR62 granules while Fig. 4 now reports on the co-localisation of WDR62 granules with protein chaperones and de novo purine synthesis enzymes typically associated with purinosomes. We now conclude that WDR62 may be associated with purinosomes but may also represent distinct entities with shared components and characteristics. Notably, proteins such as BAG2 and PFAS may undergo phase separation in response to stress independently of purinosome assembly.

      In additional work conducted for our revised manuscript, we find that WDR62 loss reduced rates of purine synthesis in cells cultured in the presence of purines (Fig. 5) but was not involved in de novo purine biosynthesis under purine-depleted conditions (Fig. S9). This was consistent with the finding that WDR62 loss did not prevent stress-induced formation of PFAS or PPAT granules (Fig. S6) which are likely to represent purinosomes. We concede that additional investigation is required to determine the functional significance of WDR62 granules in response to stress stimuli and purine depletion.

      (Lines 325-329) The authors reference a previous manuscript demonstrating that co-chaperones co-cluster with purinosomes. Based on this fact, they infer that WDR62 granules might represent purinosomes since WDR62 interacts with these same set of co-chaperones. These co-chaperones interact with a large number of different proteins (in fact, most kinases), so it is uncertain how the authors decided to go down this path to link purine metabolism with WDR62. Discussion of how this connection was made would help elevate the story. What additional insights did they have that lead them down these investigations?

      Response: BAG2 functions as a co-chaperone that regulates the activity of HSP70/90. While the reviewer correctly points out that co-chaperones such as BAG2 have a broad number of clients, numerous studies have established the role of HSP70/90 in purine metabolism (e.g. doi: 10.1016/j.isci.2020.101058, 10.1073/pnas.1300173110) and in neurodevelopment (10.3389/fnins.2018.00821). Moreover, purines are critical for normal brain development and dysregulation is well known to lead to congenital defects including microcephaly. As such, when we identified a role for WDR62 in the chaperone network through interaction with BAG2, it was not a leap to hypothesise that neurometabolic defects stemming from dysregulated purine production or salvage might be involved in WDR62-associated microcephaly.

      Indeed, we show that WDR62 are localised with purine enzymes in response to purine-depletion and that WDR62 depletion leads to metabolic dysregulation. WDR62 has several binding partners with multiple cellular functions, and we do not exclude alternative mechanisms involved in cortical development. However, the mechanistic link with heat shock proteins and purine metabolism is a novel one that would be of broad interest in molecular neurodevelopmental biology. On this feedback, we have revised main text (lines 214-218, lines 260-263, lines 292-295, lines 378-383) to better explain the rationale underlying our experiments and overall study focus.

      If WDR62 is not required for purinosome formation, why would it localize with the purinosome? Is there any hypothesis that could be readily tested to better help understand this observation? Providing a better understanding of this would greatly elevate the work.

      Response: Given the role of HSP70/90 in purinosome assembly and the interaction of WDR62 with BAG2, and purine enzymes PFAS and PPAT, we were initially surprised that WDR62 depletion did not affect stress-induced PFAS and PPAT granule formation (Fig. S6). At the time of writing the original manuscript, we interpreted these granules as purinosomes. However, it remains possible that WDR62 might have a function in purine synthesis or in purinosome assembly that remains unidentified. Indeed, we have not yet tested different cell types or additional conditions that induce purinosome formation or determined the localisation or activity of other purine synthesis enzymes. Thus, we concede our conclusions on WDR62 and purinosome formation were premature.

      As our revised manuscript is now focused on the WDR62-BAG2-HPRT interaction and given the reviewer’s prior comment that PFAS and PPAT colocalization in granules may not represent purinosomes in all contexts, we acknowledge that potential WDR62 functions in purinosomes warrants further investigation beyond this study. In the revised discussion (lines 473-497) we address these limitations and propose alternative interpretations of our findings.

      (OPTIONAL) Please validate that the associations between WDR62 and the purine biosynthetic enzymes occur on the endogenous level (void of transient transfection). Many methods such as immunofluorescence and proximity ligation assays have been used by others to demonstrate protein-purinosome interactions. This result would reduce any concern that the association is a result of overexpression (artifact).

      Response: As suggested, we conducted proximity ligation assays (PLA) to validate endogenous interactions between WDR62 and BAG2, HPRT, and PFAS (Fig. 4K, Fig. 6I-K). Notably, sorbitol treatment increased the interaction between WDR62 and HPRT (Fig. 6H, I), supporting the role of WDR62 in regulating HPRT under cellular stress. Additionally, WDR62 deletion appear to reduce the interaction between BAG2 and HPRT (Fig. 6K), while BAG2 depletion similarly reduces the interaction between WDR62 and HPRT (Fig. 6J). These findings support a model in which WDR62 and BAG2 cooperatively regulate HPRT stability.

      Figures 6F and 6G conclude that nucleosides from purine-depleted growth conditions accumulate while the corresponding monophosphates do not change between WRD62 knock-out and wildtype cells. Given that purine-depleted growth conditions activate de novo purine biosynthesis (uncertain if this has been demonstrated in AD293 cells), could this result simply demonstrate that purine salvage is no longer used and the nucleosides have accumulated and are awaiting degradation (or exportation) rather than a loss of HPRT expression as inferred from the stated conclusions? The conclusions could be better substantiated with the use of a stable isotope incorporation assay.

      Is there a difference in the contribution of de novo purine biosynthesis and purine salvage to the generation of the monophosphates (AMP, GMP) between WDR62 knockout and wildtype AD293 cells? Use of a stable isotope (such as 15N-glutamine) could help to come to the appropriate conclusion.

      __Response: __We thank the reviewer for this helpful suggestion to better characterize WDR62-dependent purine defects in more detail. In our revised manuscript we performed targeted metabolomics experiments and tracked the incorporation of 13C2-glycine and 13C5-hypoxanthine into purine nucleosides to assess purine synthesis and purine salvage flux between WT and WDR62 KO cells (n=5). Indeed, purine nucleotides in KO cells showed a significant loss of incorporation of 13C2 from 13C2-glycine, consistent with impaired de novo synthesis in cells cultured in presence of purines. In contrast, labelling from 13C5-hypoxanthine showed no overt differences between WT and KO cells, suggesting that incorporation via the salvage pathway is not grossly altered under these conditions. We have subsequently added a section to the discussion (lines 498-521) to discuss these results which suggest that the reduced HPRT levels in KO cells may be sufficient to sustain rates of purine salvage which are not altered with WDR62 loss. Thus, the accumulation of nucleosides is most likely due to increase conversion from monophosphates or reduced degradation to uric acid. Nonetheless, we show that WDR62 is required for purine synthesis under basal conditions and has a complex role in regulating purine metabolism.

      (Lines 483-485) If there is a change in de novo purine biosynthesis, are there any detectable changes in AICAR levels that might influence purine metabolism at the transcriptional level?

      __Response: __This remains a possibility. However, we did not detect the AICAR intermediate in our untargeted LC-MS/MS metabolomics analysis perhaps due to low relative abundance and/or low stability. As a result, we were unable to comment on AICAR levels but this would be an interesting research direction to pursue in subsequent follow up studies.

      Are the data and the methods presented in such a way that they can be reproduced? Are the experiments adequately replicated and statistical analysis adequate? 1. For purine-depleted studies (metabolite analyses, microscopy), how long were the cells grown in purine-depleted medium before the analysis? And how was the purine-depleted medium generated? Please reference any source that might have been used.

      __Response: __We removed purines from the cell culture environment by incubating cells for 7 days with DMEM supplemented with FBS dialyzed to remove small molecules such as nucleosides and nucleobases. This important methodological detail was omitted in error in our original submission. Our revised manuscript includes description of how we depleted cells of purines in the Materials & Methods at Lines 636-640 with reference to source materials and prior studies.

      Details describing the BioID experiment are minimal. How many replicates were performed, was label-free or TMT quantitation used for the protein identification. Further the data analysis and mining of the proteins from the BioID study are missing - What database was used to identify the proteins from the peptides? Please include this information in the Materials and Methods section as well as a link to a repository where the LC-MS/MS data generated can be found. Additionally, it would be very helpful to have a spreadsheet or table that lists the biotinylated proteins and expectant or p values for each.

      __Response: __We performed three independent biological replicates (n = 3) for the BioID experiment. We apologise for the omission and have now included this information in the Fig. 1 legend. Label-free quantitation was used for protein identification, and peptides were identified using the ProteinPilot™ Software (v. 4.5) database. As part of our revision, we have updated the Materials and Methods section to include these details and will also provide a spreadsheet listing all biotinylated proteins across replicates, including their p-values. Furthermore, we have submitted our LC-MS/MS data as supplementary files associated with this manuscript.

      Please include information about the streptavidin pulldown presented in Figure 1C.

      __Response: __Streptavidin pulldown followed by immunoblot for known WDR62 interacting proteins is described in our Materials & Methods section at line 753-759. __ __Proteins bound to Streptavidin agarose beads were eluted with Laemmli buffer following washing. Pulldown fractions and total lysates were then resolved on SDS-PAGE, transferred to PVDF and blotted with primary antibodies to detect WDR62 interacting proteins such as CEP170, JNK and AURKA. We also used this method to confirm biotin-labelling and affinity isolation of BAG2 in Fig. 1C.

      Many of the figure legends could benefit from a statistical description.

      Response: As requested, we have updated the legends for all relevant figures and supplementary figures to include statistical descriptions, specifying analyses used and replicate (n) numbers. These additions complement the detailed description of our statistical methods provided in the Materials & Methods section (line 884).

      There seems to be only two data points for Figure S3A. While there is no significant difference observed, it would be ideal to have additional replicates.

      Response: We have completed an additional replicate and updated Fig. S3A for our revised submission. This study which now includes n = 3 independent biological replicates. While we observed a slight increase in the proportion of cells with MAPKBP1 granules in response to sorbitol stress, this change was not statistically significant. In contrast, WDR62 formed granules in a much larger proportion of cells (~90%) in response to stress (Fig. 3E).

      (Figure 5I) Please provide statistical analysis to demonstrate the colocalization between FGAMS and WDR62 is robust in purine-depleted AD293 cells.

      Response: Our revised manuscript now includes three independent replicates assessing WDR62 co-localisation with PFAS in purine-depleted AD293 cells (Fig. 4I in revision). We consistently observed a high degree of co-localisation, as quantified by Pearson’s correlation coefficient (mean = 0.8), which was significantly different from control conditions.

      1. The use of HSP90 inhibitors is a little confusing given the connections being made with BAG2 and other HSP70 co-chaperones in Figure 1.

      • Does the same conclusions hold true with an HSP70 inhibitor or siRNA?

      • (OPTIONAL) There are a lot of discrepancies between Hsp90 inhibitors and effective treatment concentrations. For example, NVP-AUY922 caused purinosomes to disassemble whereas STA9090 cause purinosomes to change morphology and adopt a more aggregated state. Do other Hsp90 inhibitors share the same phenotypic response as NVP-AUY922 in this study.

      • The treatment time (24 h) with NVP-AUY922 is very long. Given that Hsp90 interacts with hundreds of proteins, it is hard to understand whether the effect of Hsp90 inhibition is direct or indirect. Shorter times (1 h or less) would be more insightful.

      __Response: __To address these specific comments on the specificity of effects from HSP90 inhibitor treatment, we have conducted additional experiments using NVP-AUY922, in addition to another HSP90 inhibitor, 17-AAG, and the HSP70 inhibitor, MKT-077, at both 24-hour and 1-hour timepoints.

      Our results demonstrate that NVP-AUY922 can rescue the aggregated HPRT phenotype in WDR62 KO cells even after 1 hour of treatment (Fig. 6F, G). Similarly, 17-AAG exhibits a comparable effect, reinforcing the role of HSP90 inhibition in modulating the spatial distribution of HPRT in the cytosol (Fig. 6F, G). Additionally, we found that MKT-077, a HSP70 inhibitor, also rescues the aggregated HPRT phenotype, with the effect being most pronounced at 24 hours but still evident at 1 hour (Fig. S10A, B). We also utilized BAG2 siRNA but determined that BAG2 depletion rescued WDR62 KO effects on HPRT expression (Fig. 6L) but did not reverse the effect on HPRT spatial distribution (Fig. S10C).

      (OPTIONAL) Does the 2.6-fold increase in BAG2 increase its association with WDR62?

      Response: We observed a ~2.6-fold increase in BAG2 levels following WDR62 deletion (Fig. 6A). However, as WDR62 is not present in KO cells, it is not possible to verify whether there would be an increase association with WDR62 and we did not conduct an experiment to overexpress BAG2 in WT cells. However, we presume that increased cellular levels of BAG2 would lead to increased pulldown with WDR62 by immunoprecipitation for example.

      Is the degradation of HPRT occurring through BAG2-mediated proteasomal degradation? Showing HPRT recovery by treating the cells with MG132 along with CHX would provide meaningful clues as to how BAG2 and HPRT might be related - Is BAG2 concentration increasing to facilitate the enhanced degradation of HPRT?

      __Response: __We thank the reviewer for this useful suggestion. However, our initial experiments with MG132 and chloroquine to inhibit proteosomal and autophagic pathways respectively gave mixed results. Our preliminary findings suggest neither was sufficient to substantially rescue HPRT levels in WDR62 KO cells. However, this needs extensive follow up with more precise dissection of cell degradation pathways with additional inhibitor or genetic targeting of degradation machinery. Thus, we did not include these studies in the revision and will instead include this in a follow up paper once we have completed a more comprehensive investigation.

      Does HPRT colocalize with WDR62 in cells?

      __Response: __ In response to this comment, we have demonstrated that osmotic stress induces the spatial reorganisation of endogenous HPRT into puncta that juxtapose and co-localize with WDR62 granules in a stress-dependent manner (Fig. 6H). This was further validated by examining the endogenous WDR62-HPRT interaction using PLA, which also revealed a stress-induced increase upon sorbitol treatment (Fig. 6I).

      (OPTIONAL) It would be nice to see validation experiments of some of the hits in Figure 1D or 1E in a co-immunoprecipitation experiment conducted similar to Figure 1C.

      __Response: __Our BioID assay, presented in Fig. 1D and E, identified WDR62 interactors, such as AURKA, JNK, CEP170 and MAPKBP1, that have been previously validated by co-IP by our group and others. Among the chaperones identified, we focused on BAG2 in this particularly study and validated BAG2-WDR62 interactions between by coIP (Fig. 2) and by proximity ligation assays (Fig. 4).

      The authors presented the findings that suggest that BAG2 interacts differently with commonly observed WDR62 mutations in MCPH2? How do these mutations affect WDR62 condensation, colocalization with purinosomes, or alter HPRT activity? Tying back the observations to something clinical would help elevate the overall significance of the findings.

      Response: We investigated the condensation of mutant WDR62. Interestingly, R438H mutant, which binds BAG2 (Fig. 2), forms granules constitutively prior to stress treatment while the 3936dupC mutant, which does not bind BAG2 (Fig. 2), did not form granules in response to sorbitol stress treatment. We also find that PFAS is colocalized with R438H granules in the absence of stress, although this requires repeated analysis and quantification. However, WDR62 deletion does not prevent PFAS or PPAT granule formation (Fig. S6) and, given reviewer advice to focus the topic of our revised manuscript, we have not included the effects of WDR62 mutations on granule formation in our revised manuscript.

      However, in response to these comments, we have conducted rescue experiments with patient-identified MCPH mutant variants of WDR62. Expression of the R438H or 3936dupC mutant in WDR62 KO cells did not rescue HPRT to the same extent as full-length WDR62 with wild-type sequence (Fig. 6B). Additionally, attempts to restore BAG2 levels in WDR62 KO cells by expressing mutant WDR62 showed no discernible difference from full-length WDR62. Thus, mutations to WDR62 associated with MCPH alters binding to BAG2 (Fig. 2, increased with R438H and decreased with 3936dupC), this was associated with dysregulated levels of BAG2 and HPRT. In our revised manuscript, we also examined the effect of HPRT depletion on neurodevelopment in vivo (Fig. 7) and included description of these findings at lines 417-442.

      Are the text and figures clear and accurate?

      1. There are many times throughout the manuscript that the wrong figure is being referenced. These mistakes caused significant confusion at many times while reviewing the manuscript. Please double check all in-text references to figures. For example, I believe that you meant to use Figure S1C instead of Figure 2E with the statement on lines 183-185. Again, I believe that correct figure reference on line 501 is Figure 7G not Figure 7E.

      Response: We apologize for this oversight. We have amended the errors indicated by the reviewer. Line 544 (501 in first submission) now refers to the correct figure (Fig. 6F) and lines 204-206 (183-185 in first submission) correctly refers to Fig. S1C in addition to Fig 2E. Each of the authors have also revised the rest of the manuscript to ensure all figures are correctly referenced in the main text.

      The figure legend on Figure S4 does not match the figure and the main text references. Please verify that the text in the figure legends correspond correctly to the figure.

      Response: We apologize for these inconsistencies in the figure legend relating to Fig S4 in our original submission. In the revised manuscript, we have amended the figure legend and the main text referencing Fig. S4 to correctly correspond to order of data panels in this figure.

      Please provide this data for the sentence on lines 399-400 in the supplemental file.

      __Response: __As requested, we have revised the manuscript to include results on HPRT cytoplasmic localisation following osmotic stress. We show that osmotic stress induces the spatial reorganisation of HPRT into puncta that juxtapose and co-localize with WDR62 granules in a stress-dependent manner (Fig. 6H). This was further validated by examining the endogenous WDR62-HPRT interaction using PLA, which also revealed a stress-induced increase upon sorbitol treatment (Fig. 6I).

      I believe that the authors use the phrase "cell proliferation" to describe cell viability in the main text. In the Materials and Methods section, the authors state "The XTT cell proliferation assay enables quantification of cellular redox potential, providing a colorimetric readout of cell viability." Cell proliferation, viability, and cytotoxicity are different measurements, so please revise to reflect the correct experiment that was performed.

      __Response: __The XTT colorimetric assay can be used to determine cell proliferation or loss of cell viability depending on the specific experiment. The reviewer is correct in pointing out that our study using XTT to measure cell numbers in the context of purine-depletion (Figure 5B) is a measure of cell viability. We apologize for the misleading text in our description of the XTT methods in our original submission. In our revised manuscript, we have amended our description of the XTT assay in our methods and in the figure legend to more accurately reflect the experiment performed.

      Other Minor Comments:

      1. Move the sentence "In contrast, despite reduced mRNA..." (lines 387-388) to the last section when a reduction in PFAS expression was first mentioned.

      __Response: __As requested, we have moved this line referring to PFAS protein levels in WDR62 KO cells to the previous section to when a reduction in PFAS mRNA was first mentioned.

      1. Please reference the following in the manuscript: • BioGRID database in the main text and Materials and Methods section • The reported study showing the DNAJC7-WDR62 interaction (as curated from BioGRID) • Fiji in the Materials and Methods section

      __Response: __We have now included references to these in our revised manuscript. References to BioGRID database are in the main text (line 146) and in the Materials and Methods (line 765). The report of DNAJC7-WDR62 interaction (Ref #37) curated from BioGRID was added at line 157 and reference (Ref #82) to Fiji plug-in was indicated at line 690 in Materials & Methods.

      (Line 461-463) The authors state the following: "the loss of WDR62 leads to an increase in BAG2 and vice-versa (Fig. 7A) (Fig. S9B). I am not sure that the vice-versa (i.e. loss of BAG2 increases WDR62) is true. From the data presented in Figure 7H, I do not see a significant change in WDR62 expression upon BAG2 siRNA treatment.

      __Response: __We apologize for the incorrect use of the term “vice versa” in this context. We had meant that while WDR62 loss led to an increase in BAG2, the converse increased expression in WDR62 resulted in a decrease in BAG2 levels. The reviewer is correct that the siRNA knockdown in BAG2 did not substantially alter WDR62 levels. We have amended the text at lines 465-467 to clarify this statement.

      For your BioID study, do you know how many or the proportion of cells that were mitotically arrested with the low dose of nocodazole (200 ng/mL)? Given the small number of unique proteins that were in the mitotic only population, it is curious to know how enriched the cells were and whether WDR62 localization is important in the context of this study.

      __Response: __The overnight treatment with low dose nocodazole results in an enrichment of cells arrested in late prometaphase which we estimate at 50-60% of AD293 cells compared to

      1. Just to clarify, the WDR62-HA lane (third in each set) in Figure 1C is not WDR62-BirA*-HA and that it is only being used as a control.

      Response: This is correct. To improve clarity, we have amended the labels on the WDR62-HA lanes in Figure 1C to say “WDR62-HA only”.

      1. In the Discussion (lines 439-441) "We also show that WDR62 forms dynamic, phase-separated granules that co-localise with chaperones and purine metabolic enzymes, resembling purinosomes." I believe that the authors meant to say co-chaperones instead of chaperones given no microscopy data was presented showing the colocalization of HSP70/90 with WDR62 granules. Please revise.

      __Response: __This sentence (line 473) has been revised as suggested.

      Reviewer #2 (Evidence, reproducibility and clarity (Required)):

      Summary:

      The authors provide evidence to reveal the novel functions of WDR62 protein in maintaining the stability and activity of purine metabolic enzymes and overall purine homeostasis. WDR62 interacted with BAG2, and they are recruited to purinosome. WDR62 loss caused accelerated degradation of purine salvage enzyme HPRT, and led to the accumulation of purine nucleotide intermediates.

      While this study is compelling and significant for the field of neurodevelopmental disorders including microcephaly and purine metabolism, there are several concerns that should be addressed before publication.

      __Response: __We thank reviewer #2 for their constructive criticisms and supportive comments noting the statement reinforcing significance of our study in the field. We have made a meaningful and concerted effort to address the reviewer comments with extensive additional experimental work and substantial revision of our manuscript.

      Major comments:

      Although all experiments are conducted using non-neuronal cultured cells, does this phenomenon also occur in neuronal cells?

      __Response: __To address this comment and reviewer concerns regarding the links between WDR62 and HPRT in a neuronal context, we performed in utero-electroporation to determine the effects of HPRT depletion on formation of neocortex in mouse embryos. We electroporated embryonic day 14 (E14) mouse brains with siRNA targeting Wdr62, and Hprt and assessed neural progenitor proliferation, migration and differentiation using immunofluorescence. We find that the loss of both WDR62 and HPRT leads to a similar precocious delamination of neural progenitors from the apical ventricular surface (Fig. 7). This process is the first step in neural migration and required to generate a diversity of cells, both self-renewed (eg. outer radial glia) and differentiated neurons and glial cells in the developing neocortex (doi.org/10.1146/annurev-cellbio-101011-155801). Interestingly, we also uncovered that HPRT loss promoted the self-renewal of delaminated intermediate progenitors (IPs) which is unlike impaired the self-renewal of neural progrenitors observed following WDR62 depletion (Fig. 7). Thus, brain development is sensitive to HPRT levels and the HPRT depletion phenocopies WDR62 in cell delamination which supports a neural role for WDR62-HPRT. Moreover, our findings suggest WDR62 loss has more severe neurodevelopmental defects with hints at the complex metabolic functions of WDR62 (discussed in lines 563-577).

      What is the interaction between endogenous WDR62 and Bag2? This is because in overexpression systems, multiple chaperones may interact with the target protein during protein folding.

      Is endogenous WDR62 also present in the purinosome in purine depleted or sorbitol condition?

      __Response: __In response to these comments and similar concerns by reviewer #1, we examined interactions between WDR62, BAG2, HPRT, and PFAS at the endogenous level by utilising proximity ligation assays (PLA, Fig. 4+6). We determined a robust interaction between endogenous WDR62 and BAG2 (Fig. 4K), evident by abundant PLA puncta which were nuclear excluded and localised to the cytosol, consistent with our results in overexpression systems (Fig. 4). We also confirmed endogenous WDR62 interactions with purine enzymes PFAS (Fig. 4K) and HPRT (Fig. 6I) in a similar fashion. To determine whether sorbitol stress promotes their interaction, we assessed changes in the per cell numbers of these puncta in response to sorbitol stress. We confirmed that endogenous WDR62 interaction with HPRT was dependent on BAG2 (Fig. 6J). WDR62-HPRT interactions increased with sorbitol stress (Fig. 6I).

      Regarding Fig6 and Fig7, when HPRT decreases and inosine accumulates in WDR62-KO condition, did the levels of hypoxanthine, xanthine, and uric acid change?

      __Response: __ In Fig. 5G we used an untargeted metabolomics approach that relies on identification databases such as MS-DIAL and associated spectral libraries. Unlike targeted approaches, this method does not always allow for the confident identification of all metabolites of interest. As a result, hypoxanthine, xanthine, uric acid, and other purine intermediates (e.g., AICAR) were not positively identified. This is likely due to limitations in database coverage, spectral similarity to other compounds, or constrains related to our extraction method.

      Does HPRT and the three microcephaly-associated WDR62 mutants also recruited in the purinosome in purine depleted or sorbitol condition?

      __Response: __In response to this, and a similar comment by reviewer #1, we examined whether endogenous HPRT co-localised with WDR62 granules induced by sorbitol. We show that hyperosmotic stress induces the spatial reorganisation of HPRT into puncta that juxtapose and co-localize with WDR62 granules in a stress-dependent manner (Fig. 6H). This was further validated by examining the endogenous WDR62-HPRT interaction using PLA, which also revealed a stress-induced increase upon sorbitol treatment (Fig. 6I).

      As to whether mutant WDR62 was recruited to purinosomes, as detailed in our response to reviewer #1 above (minor comment #6), we find that R438H mutant formed condensed granules prior to stress treatment while 3936dupC mutant did not form granules in response to stress. Therefore, MCPH mutations appear to disrupt the stress-induced formation of WDR62 granules in the cytoplasm. Since we also find that WDR62 KO did not prevent stress-induced formation of PFAS and PPAT granules, which may represent or overlap with purinomes, we chose to not include our findings on granule localization of mutant WDR62 localization in our current revised manuscript. We instead focused on rescue of HPRT and BAG2 levels with patient-derived MCPH mutant variants of WDR62. We confirmed that, unlike WT WDR62, mutant WDR62 could not fully return HPRT or BAG2 levels in WDR62 KO cells (Fig. 6B).

      In Fig7C, HPRT/tubulin ratio appears to decrease in WT from 0hr to 24h, but the graph does not show this decrease. Additionally, quantification of PFAS(FGAMS) and BAG2/tubulin should be performed.

      Response: While slight variations in HPRT signals are visible from 0 h to 24 h in the representative blot, quantification across the n = 9 biological replicates do not support a significant decrease, with these variations falling within the SEM shown in the graph. This representative blot was selected for its clarity and since it most clearly depicts the key trend which is the increasing difference in the HPRT/Tubulin ratio between WT and KO cells with increased duration of CHX treatment. Additionally, in response to this comment, we have now quantified PFAS and BAG2/Tubulin and have inserted these data into Fig. 6C.

      Fig7D is problematic. HPRT in WDR62-KO cells seems to localize in the nucleus, possibly due to stronger exposure in KO conditions compared to WT. Also, the line scan is drawn in areas with low signal in WT. The comparison should be performed in areas with high perinuclear signal.

      __Response: __We appreciate the reviewer’s feedback and acknowledge their concern of an apparent differences in fluorescence intensity in WDR62 KO vs WT cells. In the original submission, slight differences in fluorescence intensity between the WT and WDR62 KO panels may have exaggerated differences in HPRT levels in the nucleus. To address this, we have replaced the representative images with those with more consistent fluorescence intensity across conditions and better represent the average population of sampled cells. Regardless, quantified the change in HPRT cytoplasmic redistribution in response to WDR62 loss across multiple independent biological replicates (n=4) and multiple cells (>12 cells per repeat) within each biological replicate to confirm a change in HPRT distribution in KO cells (Fig. 6E+G).

      The localization of HPRT should be compared in WT and WDR62-KO with BAG2 siRNA. It is also possible to confirm whether the phenotypes observed in KO, such as cell proliferation and xanthosine/inosine levels, are rescued.

      __Response: __We conducted a series of immunofluorescence experiments to assess the impact of BAG2 knockdown (siRNA) on the spatial distribution of HPRT in WT and WDR62 KO cells. BAG2 depletion had no effect on HPRT distribution and did not rescue its aggregated-like appearance in WDR62 KO cells (Fig. S10C). Thus, while abnormal HPRT localization in absence of WDR62 was due to excessive of HSP70/90 activity (Fig. 6F), this was not reversed by BAG2 siRNA. However, BAG2 siRNA reduced BAG2 levels to below wild-type cells (Fig. 6I). An imbalance of HSP and co-chaperone levels are known to be involved in aggregation of cytoplasmic proteins. (doi.org/10.1096/fj.202002645R). Therefore, while BAG2 siRNA may have returned HPRT levels, it may not have appropriately corrected the levels of HSP70/90 activity required for normal HPRT localization (lines 407-413 in revision).

      We did not attempt to rescue cell proliferation and xanthosine/inosine levels with BAG2 siRNA in order to prioritize other studies requested by reviewers such as neurodevelopment function of HPRT and flux analysis of purine synthesis/salvage.

      It should be considered that the induction of Bag2 in WDR62-KO might allow purinosome formation to proceed normally due to compensation. The co-localization of WDR62 and purine enzymes during purinosome formation should be compared when BAG2 expression is suppressed. Similarly, any changes in BAG2 localization in WDR62-KO should be examined. Furthermore, the purinosome formation ability should be compared in WDR62KO + Bagl2 siRNA condition.

      __Response: __To address these insightful comments and requests by reviewer #2 response, we have performed additional experiments to assess whether BAG2 facilitates WDR62 granule assembly, purinosome assembly, and the WDR62-HPRT interaction. siRNA-mediated BAG2 depletion did not prevent stress-induced assembly of WDR62 or PFAS granules (Fig. S6D+E). Thus, unlike HSP70/90 activity, purinosome assembly and WDR62 localization to purinosomes did not appear to require BAG2. Rather we demonstrated a role for WDR62-BAG2 in regulating HPRT (Fig. 6, lines 400-411).

      The reduction of HPRT in WDR62-KO should be examined for potential effects of enhanced degradation via the ubiquitin-proteasome system or the autophagy-lysosome system.

      __Response: __See our response to reviewer #1, minor comment #3. Briefly, neither MG132 blockade of proteosomal degradation nor chloroquine inhibition of autophagy was sufficient to return HPRT levels in WDR62 KO cells. However, these studies are not exhaustive and we are currently pursuing alternative and more specific inhibitors of UPS or lysosomal degradation. As this is not essential for the main findings of the current manuscript, we will include delineation of HPRT degradation pathway in a future publication.

      Although it is known that HPRT-KO mice do not exhibit any effects on normal brain development except in some dopaminergic neurons, what are your thoughts on this?

      Response: We thank the author for raising this interesting point. While global HPRT KO mice appear not to exhibit widespread brain development defects (doi: 10.1007/s00018-022-04326-x) this does not preclude a role for impaired HPRT to contribute to specific neurodevelopmental defects in context of WDR62 mutation or loss. In utero electroporation studies, we find that WDR62 or HPRT depletion results in precocious delamination of apical precursors which may trigger premature differentiation. However, while WDR62 depletion led to reduced proliferation of delaminated radial glia ventricular/subventricular zone, we observed increased proliferation with HPRT loss (Fig. 7). Our findings are in good concordance with the study mentioned by reviewer #2, Witteveen et al. 2022 (doi: 10.1007/s00018-022-04326-x), who similarly reported an increase in proliferation and abnormal cell migration patterns which may be attributed to apical delamination of radial glia. The increased proliferation of progenitors in the intermediate zone or outer ventricular/subventricular zone may compensate for premature differentiation of apical progenitors to explain the lack of overall reduction in brain size with HPRT deficiency alone. Thus, our findings indicate that defects in WDR62-HPRT may contribute to the premature apical delamination of radial glia but WDR62 has additional functions that are indispensable for normal brain development. This may include complex functions in regulating purine metabolism independent of HPRT. We have now included the paper by Witteveen et al. 2022 in our revised manuscript and the above was discussed in detail at lines 565-577.

      Minor comments: • Please write the full name before the abbreviation of the gene. • There is no measurement data for Fig7C, and a measurement line is drawn only in one panel of the ROI. • The line 488 "Fig11" looks like a typo.

      __Response: __As requested by the reviewer, we have included the full name of genes before their abbreviation and corrected the typographical error (line 548 in revision). For Fig S7C (Fig. S6B in revision), we have removed the measurement line which was included in error in our original manuscript. This supplementary figure demonstrates that the stress-stimulated granule assembly of ectopically expressed PFAS and PPAT was not altered or appreciably different in WDR62 KO cells. We quantified this for sorbitol treatment (Fig S6A). We performed the purine-depletion experiment twice with identical results. Given this was a negative result we focused our efforts elsewhere.

      The table could not be found.

      __Response: __We apologise for this oversight. The Supplementary Information file containing Tables S1-3 was excluded from the original submission has now been included in our revised submission.

      It is strange that all measurement values for WT or control in Fig2, Fig7, and FigS9 are exactly 1.0 without any variation. Please check the measurement method again.

      __Response: __Our densometric band measurements in western blots within the indicated figures are normalized against WT control cells as a reference condition. This removes variation in arbitrary densitometric values that changes from blot to blot even for identical samples. Thus, values are fold-change in protein levels relative to WT control conditions. Hence values for WT or control cells are 1 (no change relative to itself) as the reference points and there is no variation between replicate experiments. We apologize for not explaining this in our original submission. Our revision now describes this quantification and processing of raw data in methods and materials (lines 668-671).

      Please write the method for purine depleted medium.

      __Response: __Our revised manuscript includes description of how we depleted cells of purines in the Materials & Methods at lines 636-640 with reference to source materials and prior studies.

      Reviewer #3 (Evidence, reproducibility and clarity (Required)):

      Summary:

      In the present work, authors describe a novel role of the microcephaly associated protein WDR62 in purine metabolism under cell stress conditions. In the proposed cellular model (AD293 WDR62 overexpression system), the WDR62 proximity binding partners are firstly identified and categorized according to their functional role in the cell (protein folding, purine metabolism, and stress granules). Among them, authors focus on BAG2 - a HSP70/90 co-chaperone involved in cellular stress responses. After the characterization of the WDR62-BAG2 physical interaction sites, suggested to be disrupted by WDR62 pathogenic mutations, their functional interaction in cellular stress responses is investigated. WDR62-associated granules are extensively characterized for their physical and dynamic properties under different conditions (i.e., hyper-osmotic stress). Further, through the evaluation of N-and C-terminally truncated form of WDR62 authors characterize the protein regions responsible for WDR62-containing granule condensation - suggesting a potential mechanism disruption in the event of pathological WDR62 mutations. Lastly, authors provide evidence that WDR62 condensation does not occur in canonical stress granules but in the so called-purinosomes, where it participates in the regulation of purine metabolic pathway stabilizing HPRT (purine salvage enzyme) via WDR62-BAG2-HSP70/90 axis.

      Major comments:

      Overexpression system and the employed cell line are a major limitation of the study. There is no experimental data on human neural cells and on endogenous WDR62, underestimating the potential difference in cell type-specific metabolism. In light of this consideration, the provided introduction and conclusions on neural development and microcephaly have to be re-formulated. I suggest providing a more general introduction/conclusions on WDR62 role (and alterations) in cell division and cell metabolism (neurodevelopment and cancer share common patterns) since purine homeostasis is not exclusive of neural progenitor cells.

      This reviewer thinks that the structure of the work is a bit convoluted (too many results in main figures that are not substantial). I suggest to re-organize and to prioritize the most relevant results. Further, it would be clinically relevant to add WDR62 mutant constructs in the functional evaluation of purine metabolism to better dissect the physiological role of WDR62 and the impact of the mutations on cellular physiology.

      Response: We are appreciative for this constructive evaluation of our manuscript and frank comments on the limitations of our study from reviewer #3. We have now included extensive new studies that provide evidence supporting endogenous mechanisms and insights into in vivo functions in neurodevelopment. We have also removed and combined several figures relating to the stress-induced purinosome assembly of WDR62 to better focus our manuscript on WDR62 interaction mechanisms and their purine metabolic function.

      Fig. 1: Overexpressed WDR62 fluorescence signal might be artifactual and may hide more detailed localization pattern during interphase. Authors should also provide endogenous WDR62 immunofluorescence panel in AD293 cells. Additionally, the "cytosolic" localization of WDR62 during interphase (indicated in the introduction, lines 88-89) has been re-defined in recent works pointing out that the protein is dynamically associated with the interphasic centrosome, the Golgi apparatus, and spindle poles during mitosis.

      __Response: __In response to this point, we have added text in the introduction (line 100-102) to clarify the dynamic association of WDR62 in cytoplasmic compartment during interphase includes the golgi apparatus. We have also added reference to the study by Dell’Amico and co-workers (doi: 10.7554/eLife.81716, Ref #24 in revision) alluded to by reviewer #3.

      We utilized ectopic expression of tagged WDR62 constructs to determine redistribution to stress-responsive cytoplasmic granules and co-localization with purine enzymes. Immunofluorescence staining of endogenous WDR62 also appears to reveal granule assembly but these findings are not as clear as the primary antibodies also detect additional proteins independent of WDR62 (validated using our KO cells). We agree that protein overexpression may result in artificial localization patterns but this can be mitigated with careful controls. We find that stress-induced WDR62 granule localization is highly dynamic and reversible. We observe the same response with full-length protein using different fluorescent protein or small affinity tags at either N- or C-terminus. High expression of mutant WDR62 (e.g. 3936dupC) or a closely related family member (MAPKBP1) do not form the same purinosome-associated granules. Moreover, in response to related comments by reviewer #1 and #2, we have now included proximity ligation assays confirm interactions between WDR62, BAG2 and purine enzymes (Fig. 3 and Fig. 6).

      Fig. 1C lacks quantification of BAG2/CEP170/AURKA signal. Further, how can authors exclude that is not nocodazole effect on microtubules disruption which impairs WDR62 spindle pole localization and therefore protein-protein interactions? A panel showing that "low dose" nocodazole do not impinge endogenous and exogenous WDR62 localization in mitotic cells is needed.

      __Response: __WDR62-BirA specific biotinyation and affinity isolation of BAG2, CEP170 and AURKA, compared to BirA or WDR62-HA only controls, was very clear in Fig. 1C. We did not quantify the extent that mitotic synchronization increased or decreased binding to WDR62 as the mitosis specific context was not a focus in our subsequent figures. Rather we focused on and quantified in detail WDR62-BAG2-HPRT mechanisms in response to cell stress.

      We are also very confident that low dose nocodazole treatment does not prevent spindle pole localization. This treatment impinges on microtubule dynamics to trigger spindle checkpoints, arresting cells in mitosis. The bipolar organization of spindles is lost but spindle microtubules and minus-end microtubule directed localization of WDR62 at spindle asters are retained under these conditions and is specific to mitotic cells. The robust WDR62-BirA biotinylation of AURKA, which is spindle pole-associated, specifically in mitotic arrested cells further confirms WDR62 is retained at the spindle. We demonstrated this in our previous papers (Ref. 5+6). Others have also shown that both endogenous (doi: 10.7554/elife.81716) and exogenous WDR62 (doi: 10.1083/jcb.202007167, doi: 10.1242/jcs.157537) retain spindle pole localisation under similar conditions.

      Fig. 3 H-J: The fluorescence signals are saturated (also evident in the intensity profile plot) and thus not applicable for any analysis. Further, how these linear ROIs are chosen? The signal pattern is not homogenously distributed in those images. Please provide a more consistent fluorescence analysis.

      __Response: __We acknowledge reviewer #3 concerns but while some granules, particularly those expressing G3BP-EGFP, exhibit saturated fluorescence signals, this does not impact or prevent our analysis. Our aim was not to quantify subtle fluorescence intensity changes within individual granules, but rather to compare fluorescence signal between granules across different channels to identify overlap. The linear ROIs were selected at random to illustrate that WDR62 and G3BP signals do not overlap between WDR62 and G3BP-positive granules.

      Minor comments:

      Abstract, line 49: How can these WDR62 mutations can result in a complete loss of the protein ("In cells lacking WDR62") if authors report co-IP experiments (Fig. 2) with clear mutant WDR62 bands? Rephrase accordingly.

      __Response: __The statement in our original abstract referenced by reviewer #3 referred to results presented in Fig 7 (now Fig. 6 in our revision) comparing WDR62 KO with WT cells and not co-IP experiments with mutant WDR62 in Fig 2. We have revised our abstract substantially to incorporate additional experimental work and to ensure clarity in our statements related to KO cells lacking WDR62 and cells expressing WDR62 mutants.

      Result referred to Fig. 2D reports that "BAG2 co-immunoprecipitated with WDR62(N)-EGFP but not WDR62(C)-EGFP". The blot and the relative quantification in figure 2D instead show BAG2 signal in the WDR62(C)-EGFP - even if significantly lower. Please rephrase accordingly.

      __Response: __We have revised line 192 of the main text to more accurately state the reduced interaction between WDR62(C)-EGFP and BAG2.

      Lines 186-187: authors declare that the C-terminal tail comprising the helix-loop-helix domain is required for BAG2 to bind full-length WDR62. There are no such data in support of this. The C-terminal fragment includes both the disordered region and the dimerization domain. How can authors conclude that the dimerization domain alone is sufficient to bind BAG2?

      __Response: __In Fig. 2, we show that the co-IP of BAG2 was significantly impaired in cells expressing WDR62(3936dupC), which lacks the C-terminal helix-loop-helix (HLH) domain. Additionally, we demonstrate that the C-terminal half of WDR62, which includes the HLH domain, does not bind BAG2. Based on these findings, we conclude that while the HLH domain is necessary for BAG2 binding to full-length WDR62, it is alone not sufficient. To ensure clarity, we have revised the main text (lines 207-209) to state “…the C-terminal helix-loop-helix domain—required for WDR62 dimerisation—is necessary but not sufficient for BAG2 to bind full-length WDR62.”

      Lines 189-190: results in AD293 cell line are not directly applicable in demonstrating that poor WDR62-BAG2 interaction can lead to alterations in brain development. Please rephrase.

      __Response: __We established that WDR62 interacts with BAG2 co-chaperone and MCPH mutations in WDR62 disrupt this interaction. Although our results were performed in AD293 cells, it seemed reasonable to speculate that WDR62 interactions with chaperones might contribute to brain development given well established WDR62 functions in this context. However, we acknowledge that this speculation may not be appropriate at this point of the manuscript, so we have removed this text (line 210) in our revised manuscript.

      Line 196: Indicate here, as the first mention, stress granules as "SGs" and use the abbreviation consistently throughout the manuscript.

      __Response: __We have abbreviated stress granules as suggested (first mentioned at line 102) and utilized this abbreviation consistently throughout the manuscript.

      Line 255: are human neural progenitor cells enough sensitive to sorbitol? If not, the proposed experimental design is a bit artifactual and the results/conclusions cannot be related to neural development alterations. I suggest applying more "physiological" stressors and frame the results in meaningful neurodevelopmental/tumorigenic environment. Please add this point to the discussion.

      __Response: __Neural progenitors are likely sensitive to sorbitol, as hyperosmotic stress has been used to induce phase separation of a wide variety of proteins in neural contexts (doi: doi.org/10.1038/s41598-023-39090-w, doi.org/10.1016/j.celrep.2018.06.094). In this study, we leveraged sorbitol-induced hyperosmotic stress as a controlled and reproducible means of triggering WDR62 phase separation, enabling us to examine its downstream interactions with BAG2, HPRT, and other purine enzymes. We further extend these observations to metabolic cell stress with purine-depletion.

      We found that WDR62 phase separation occurs rapidly at low sorbitol concentrations (~50 mM) (Fig. 3B), suggesting that even milder osmotic stress, particularly under prolonged exposure, could similarly drive WDR62 condensation in physiological settings. As requested by the reviewer, we have added a small section to the discussion (lines 472-480) to discuss the physiological implications of sorbitol stress on WDR62 granule assembly.

      Line 240: WDR62 granules association with microtubules and especially mitochondria is not convincing (Fig. S5). This data seems to be a bit qualitative, please provide more detailed quantification of this parameter.

      __Response: __The association of WDR62 granules with microtubules and mitochondria is quantitatively assessed using two methods, as shown in the graphs to the right of the images. One graph presents the proportion of WDR62 granules overlapping with CytC/Tubulin, providing a binary measure of colocalization. We also examined the degree of signal correlation across the entire ROI by calculating Pearson’s correlation coefficient. In response to sorbitol, we showed a higher association of WDR62 with Tubulin and CytC compared to randomised controls. We have updated the Materials and Methods to include a detailed description of this analysis (lines 708-720).

      Fig. 4 is convoluted. I suggest moving some data to supplementary to improve the clarity of the figure.

      __Response: __In addressing this comment and related comments from other reviewers to focus our manuscript, we have removed our data on fluorescence recovery and post-stress disassembly of WDR62 granules from what was Fig. 4 in our original submission and combined remaining components with Fig. 3 to centre on stress-induced assembly of WDR62 granules for our revised manuscript.

      Line 273: "Liquid-like protein condensates also exchange their contents with the bulk cytosol [52]". Reference 52 reviews the existing literature referred to biomolecular condensates that exert nuclear function (e.g., genome organization, gene expression, and DNA repair). No mention on events involving cytoplasm. Please add a more relevant reference.

      __Response: __We thank the reviewer for highlighting this inconsistency. However, this reference is no longer required and has been removed from our revised manuscript as the section of the main text has been deleted in alignment with the above response where figure panels relating to WDR62 phase separation were removed for focus and clarity.

      Lines 290-291: have authors considered the effect of sorbitol on microtubules dynamic that might reflect in granules dynamic changes?

      __Response: __We thank the authors for this insightful comment. Hyperosmotic stressors such as sorbitol are known to reduce microtubule dynamicity (doi.org/10.1016/j.devcel.2022.02.001), likely due to increased cytoplasmic viscosity and crowding effects. While we have not directly assessed microtubule dynamics in our study, it is certainly possible that these changes could influence WDR62 granule dynamics, given their association with microtubules (Fig. S6). While we have reduced emphasis on the dynamic nature of WDR62 granules in our revision, a useful direction for future studies to explore how alterations in microtubule dynamics induced by physiological stressors facilitate changes in WDR62 granule assembly or dynamics (e.g., fission, fusion).

      Line 295: I suggest moving the prediction of the disordered region of WDR62 when first mentioned (e.g., Supplement referred to Fig. 2)

      __Response: __This text is no longer required as we have removed this dataset from our revised manuscript to address reviewer consensus feedback to enhance cohesiveness and clarity.

      Fig. S6C-E, I: Unclear which is the criterion by which a cell is marked as "with" or "without" granules.

      __Response: __This text is no longer required as we have removed this dataset from our revised manuscript to address reviewer consensus feedback to enhance cohesiveness and clarity.

      Fig. S8: Unclear, also from the micrograph showed in the figure, how authors have counted/considered the microtubules/mitochondria associated purinosomes. Seems very qualitative and observer dependent. Please provide a more reliable analysis.

      __Response: __We apologise for omitting a description of the methodology used in the analysis of the images in Fig. S8 (now Fig. S6 in revision). We have now provided a detailed description in the Materials and Methods section (lines 709-721) of how microtubule- and mitochondria-associated purinosomes were identified and quantified.

      Fig. 6A: The same blot of WDR62 KO is shown in Fig. S7. Please remove one.

      __Response: __As requested, we have removed a set of blots demonstrating WDR62 protein deletion in KO cells from Fig. S7 (Fig. S6 in revision).

      Fig. 6C, D: Method for cell proliferation measure is indirect and "rounded cells" as indicator of cell death is sub-optimal. Analysis with specific markers would be preferable in both cases.

      Response: We used an XTT assay to measure cell viability as a function of cell number. In revised text, and also detailed in our response to reviewer #1 (point 4 under Text and Figures), we clarified that this was a measure of cell viability in response to purine-depletion as oppose to a direct measure of cell proliferation. Our amended text attributes the results in Fig 6C (now Fig. 5B in revision) to changes in cell viability rather than proliferation.

      With regards to additional measure of cell death, we had also performed LDH release assays to quantify cell death in addition to our measurement of cell rounding. The LDH assay is widely used and accepted measure of cell death or cytotoxicity and is indicated in Figure 5D in the revision.

      Fig.7B: Why the transfection control vector "EGFP only" significantly increases/decreases the BAG2/HPRT expression with respect to the negative control?

      __Response: __The reviewer comment here on Fig. 7B (now Fig. 6B in revision) refers to the control vector (EGFP only) transfected into WDR62 KO cells, as opposed to WT cells. Therefore, the difference in protein expression in this condition does not match the WT cells in the first lane as BAG2 and HPRT are increased and decreased respectively in KO cells compared to WT. This aligns with results presented in Fig. 6A.

      Paragraph from line 410 to 434: very confusing, the reported results are not well conveyed and therefore not convincing. To be reformulated.

      __Response: __We thank the reviewer for the direct and constructive feedback. The revised section (lines 378–416) addresses whether WDR62-BAG2 regulates HPRT levels. It has been substantially updated to include new experimental data and to reflect our latest findings and conclusions. We believe these revisions have significantly improved the logical flow and clarity of the discussion.

      Lines 524-526: the author's conclusion that: "...the loss of purine metabolic enzymes, including HPRT, disrupts neurogenesis, resulting in microcephaly, cell cycle defects, ciliopathies, and abnormalities in proliferation and neural progenitor fate decisions, mirroring the loss of WDR62." is not supported by the cited literature [29] and by the results presented in this work. Please provide additional references or remove the statement.

      __Response: __ As requested by the reviewer, we have removed the statement and substantially revised this section of the discussion (lines 563-677) to incorporate findings from our additional studies such as in utero electroporation.

      Lines 527-529: if authors state that "...other WD repeat-containing and microcephaly-associated proteins interact with purine enzymes..." have to provide additional references in addition to the NWD1 one. Otherwise, these lines should be rephrased as "another WD repeat containing and microcephaly-associated protein...".

      __Response: __We have amended this statement (line 589-592 in revision) as requested.

      Reference 62 is not well indexed in the Reference section. Please adjust.

      __Response: __We thank the reviewer for pointing out this error. The reference to Rauch et al. (2014) [Ref. 60 in the revised manuscript] has been corrected and now includes the complete bibliographic details.

    2. Note: This preprint has been reviewed by subject experts for Review Commons. Content has not been altered except for formatting.

      Learn more at Review Commons


      Referee #3

      Evidence, reproducibility and clarity

      Summary:

      In the present work, authors describe a novel role of the microcephaly associated protein WDR62 in purine metabolism under cell stress conditions. In the proposed cellular model (AD293 WDR62 overexpression system), the WDR62 proximity binding partners are firstly identified and categorized according to their functional role in the cell (protein folding, purine metabolism, and stress granules). Among them, authors focus on BAG2 - a HSP70/90 co-chaperone involved in cellular stress responses. After the characterization of the WDR62-BAG2 physical interaction sites, suggested to be disrupted by WDR62 pathogenic mutations, their functional interaction in cellular stress responses is investigated. WDR62-associated granules are extensively characterized for their physical and dynamic properties under different conditions (i.e., hyper-osmotic stress). Further, through the evaluation of N-and C-terminally truncated form of WDR62 authors characterize the protein regions responsible for WDR62-containing granule condensation - suggesting a potential mechanism disruption in the event of pathological WDR62 mutations. Lastly, authors provide evidence that WDR62 condensation does not occur in canonical stress granules but in the so called-purinosomes, where it participates in the regulation of purine metabolic pathway stabilizing HPRT (purine salvage enzyme) via WDR62-BAG2-HSP70/90 axis.

      Major comments:

      Overexpression system and the employed cell line are a major limitation of the study. There is no experimental data on human neural cells and on endogenous WDR62, underestimating the potential difference in cell type-specific metabolism. In light of this consideration, the provided introduction and conclusions on neural development and microcephaly have to be re-formulated. I suggest providing a more general introduction/conclusions on WDR62 role (and alterations) in cell division and cell metabolism (neurodevelopment and cancer share common patterns) since purine homeostasis is not exclusive of neural progenitor cells.

      This reviewer thinks that the structure of the work is a bit convoluted (too many results in main figures that are not substantial). I suggest to re-organize and to prioritize the most relevant results. Further, it would be clinically relevant to add WDR62 mutant constructs in the functional evaluation of purine metabolism to better dissect the physiological role of WDR62 and the impact of the mutations on cellular physiology.

      Fig. 1: Overexpressed WDR62 fluorescence signal might be artifactual and may hide more detailed localization pattern during interphase. Authors should also provide endogenous WDR62 immunofluorescence panel in AD293 cells. Additionally, the "cytosolic" localization of WDR62 during interphase (indicated in the introduction, lines 88-89) has been re-defined in recent works pointing out that the protein is dynamically associated with the interphasic centrosome, the Golgi apparatus, and spindle poles during mitosis.

      Fig. 1C lacks quantification of BAG2/CEP170/AURKA signal. Further, how can authors exclude that is not nocodazole effect on microtubules disruption which impairs WDR62 spindle pole localization and therefore protein-protein interactions? A panel showing that "low dose" nocodazole do not impinge endogenous and exogenous WDR62 localization in mitotic cells is needed.

      Fig. 3 H-J: The fluorescence signals are saturated (also evident in the intensity profile plot) and thus not applicable for any analysis. Further, how these linear ROIs are chosen? The signal pattern is not homogenously distributed in those images. Please provide a more consistent fluorescence analysis.

      Minor comments:

      Abstract, line 49: How can these WDR62 mutations can result in a complete loss of the protein ("In cells lacking WDR62") if authors report co-IP experiments (Fig. 2) with clear mutant WDR62 bands? Rephrase accordingly.

      Result referred to Fig. 2D reports that "BAG2 co-immunoprecipitated with WDR62(N)-EGFP but not WDR62(C)-EGFP". The blot and the relative quantification in figure 2D instead show BAG2 signal in the WDR62(C)-EGFP - even if significantly lower. Please rephrase accordingly.

      Lines 186-187: authors declare that the C-terminal tail comprising the helix-loop-helix domain is required for BAG2 to bind full-length WDR62. There are no such data in support of this. The C-terminal fragment includes both the disordered region and the dimerization domain. How can authors conclude that the dimerization domain alone is sufficient to bind BAG2?

      Lines 189-190: results in AD293 cell line are not directly applicable in demonstrating that poor WDR62-BAG2 interaction can lead to alterations in brain development. Please rephrase.

      Line 196: Indicate here, as the first mention, stress granules as "SGs" and use the abbreviation consistently throughout the manuscript.

      Line 255: are human neural progenitor cells enough sensitive to sorbitol? If not, the proposed experimental design is a bit artifactual and the results/conclusions cannot be related to neural development alterations. I suggest applying more "physiological" stressors and frame the results in meaningful neurodevelopmental/tumorigenic environment. Please add this point to the discussion.

      Line 240: WDR62 granules association with microtubules and especially mitochondria is not convincing (Fig. S5). This data seems to be a bit qualitative, please provide more detailed quantification of this parameter.

      Fig. 4 is convoluted. I suggest moving some data to supplementary to improve the clarity of the figure.

      Line 273: "Liquid-like protein condensates also exchange their contents with the bulk cytosol [52]". Reference 52 reviews the existing literature referred to biomolecular condensates that exert nuclear function (e.g., genome organization, gene expression, and DNA repair). No mention on events involving cytoplasm. Please add a more relevant reference.

      Lines 290-291: have authors considered the effect of sorbitol on microtubules dynamic that might reflect in granules dynamic changes?

      Line 295: I suggest moving the prediction of the disordered region of WDR62 when first mentioned (e.g., Supplement referred to Fig. 2)

      Fig. S6C-E, I: Unclear which is the criterion by which a cell is marked as "with" or "without" granules.

      Fig. S8: Unclear, also from the micrograph showed in the figure, how authors have counted/considered the microtubules/mitochondria associated purinosomes. Seems very qualitative and observer dependent. Please provide a more reliable analysis.

      Fig. 6A: The same blot of WDR62 KO is shown in Fig. S7. Please remove one.

      Fig. 6C, D: Method for cell proliferation measure is indirect and "rounded cells" as indicator of cell death is sub-optimal. Analysis with specific markers would be preferable in both cases.

      Fig.7B: Why the transfection control vector "EGFP only" significantly increases/decreases the BAG2/HPRT expression with respect to the negative control?

      Paragraph from line 410 to 434: very confusing, the reported results are not well conveyed and therefore not convincing. To be reformulated.

      Lines 524-526: the author's conclusion that: "...the loss of purine metabolic enzymes, including HPRT, disrupts neurogenesis, resulting in microcephaly, cell cycle defects, ciliopathies, and abnormalities in proliferation and neural progenitor fate decisions, mirroring the loss of WDR62." is not supported by the cited literature [29] and by the results presented in this work. Please provide additional references or remove the statement.

      Lines 527-529: if authors state that "...other WD repeat-containing and microcephaly-associated proteins interact with purine enzymes..." have to provide additional references in addition to the NWD1 one. Otherwise, these lines should be rephrased as "another WD repeat containing and microcephaly-associated protein...".

      Reference 62 is not well indexed in the Reference section. Please adjust.

      Referees cross-commenting

      This reviewer thinks that the points raised by reviewer #1 and #2 are very accurate and significant. Some of them are also shared between our three review reports and in general are referred to: clarity of the manuscript improvement, little consistency between the results displayed in the figures and the text/conclusions in some points, concerns about the reliability of some measurements/result and the employed cellular model, and the lack of endogenous protein data.

      Significance

      General assessment:

      The here described new role of WDR62 in purine metabolism and the proposed pathway are novel and relevant to shed light on pathophysiological cellular and molecular mechanisms that potentially underlie neurodevelopmental defects and carcinogenesis - processes in which WDR62 is implicated. The experimental design is extended and generally well-conceived even though quite dispersive in some points.

      The strength of the work resides in its versatility - making these findings potentially applicable to different cell types and different contexts (e.g., from neural development to malignancies) - and in the protein-protein interactions characterization under several conditions.

      Similarly, the major weakness is the generalist trait of the findings that describes WDR62 cellular behavior mostly in an over-expression system in an immortalized cell line, underestimating the intrinsic metabolic and protein expression-level differences among cell types.

      Advance:

      WDR62 is a scaffold protein with pleiotropic functions and a plethora of molecular interactors. Literature reports many molecular pathways involving WDR62 mainly in cell cycle progression, primary cilia biogenesis and centrosomal functions in a neurodevelopmental context. In the present work, authors describe mechanistic insights of a never reported WDR62-BAG2-HSP70/90 molecular pathway shedding new light on the role of this protein in cellular metabolism thus providing a new perspective on WDR62 pathophysiological functions.

      Audience:

      Basic research audience will be interested in this research work. The described molecular pathway involving WDR62 in purine metabolism might be relevant to other research on how WDR62 cellular and molecular dynamics are impactful on neural development and malignancies.

      Expertise:

      Human neural development and alterations, iPSCs, neural stem cells, CRISPR-Cas9

    3. Note: This preprint has been reviewed by subject experts for Review Commons. Content has not been altered except for formatting.

      Learn more at Review Commons


      Referee #1

      Evidence, reproducibility and clarity

      In Morris, M.J. et al., the authors strive to better understand the roles for the microcephaly protein WDR62 in brain growth and function. To accomplish this, an in situ biotinylation assay was performed and identified 42 proteins proximal to WDR62 including the Hsp70 co-chaperone BAG2. Through a series of co-immunoprecipitation assays, the BAG2-WDR62 interaction was shown to be mediated through the structured N-terminal region of WDR62, and it was proposed that common WDR62 mutations disrupt this interaction. In AD293 cells, loss of WRD62 expression resulted in an increase in the expression of BAG2 expression while reducing HPRT expression. Subsequent loss of BAG2 expression by siRNA treatment restored the expression of HPRT suggesting that there is an association between the stability of HPRT and BAG2, likely mediated through its proposed association with Hsp70/90 molecular chaperones. Finally, the authors investigate the subcellular localization and ability of WRD62 to phase separate. WRD62 was shown to form discrete condensates induced by sorbitol-mediated hyperosmotic stress. The formation of WRD62 granules are hypothesized to be driven by cell volume exclusion and macromolecular crowding. These granules appear similar, both in physical appearance and characteristics, to other reported biomolecular condensates such as those reported in metabolism (e.g. purinosomes). WRD62-containing condensates were shown to colocalize with enzymes in de novo purine biosynthesis; however, this association is not required for purinosome formation and/or its stability under both purine-depleted and sorbitol-driven growth conditions. Overall, the manuscript provided a previously unrealized and exciting association between WDR62 and purine metabolism.

      EVIDENCE, REPRODUCIBILITY AND CLARITY

      Summary: The current manuscript reads as multiple manuscripts with findings that are at times weakly connected (in my opinion). For example, I had a hard time understanding how the BioID results relate to the discovery of WRD62 phase-separation and its colocalization with purinosomes. I would strongly encourage the authors to consider dividing the results into separate manuscripts to strengthen their claims and create a more focused and cohesive manuscript (or series of manuscripts). I believe then several of my reservations associated with the current manuscript will be addressed, and in my opinion, the hard work from the authors will be better received across the scientific community.

      I would like to commend the authors for all the work that went into the current version of the manuscript. Being part of a biochemistry and cell biology research group, I completely understand how much time and effort must have went into generating these data. That being said, I felt that there were several instances where clarification and additional information is warranted to arrive at the conclusions made by the authors. These points are outlined below.

      Major Comments:

      1. There appears to be a discrepancy between the data presented in Figure 1 and what is stated in the main text. Clarification is necessary to better understand the results:
        • The following statement (and derivatives of it) are repeated throughout the manuscript: "...we found that the WDR62 interactome comprised molecular chaperones such as HSP70, HSP90, and their co-regulators, BAG2, STIP1, and DNAJC7" (lines 91-93, 316-318, 422-425). STIP1 and DNAJC7 were not identified in the list of 42 proximal proteins to WDR62 (Figure 1D). DNAJC7 was included because of a previous report curated in the BioGRID database, and there is no mention of HSP90 in the data produced in Figure 1. Please revise the main text to reflect the data that was generated.
        • Based on the data presented in the Venn Diagrams in Figure 1D, the author's numbers do not seem to be consistent with the sentence on lines 126-128. I count 37 proteins unique to their BioID study, 90 unique to the BioGRID database, and 5 proteins that overlap between the two data sets. This sentence needs to be revised.
        • What data were used to generate the interaction map in Figure 1I? Enzymes tied to purine metabolism were not identified from the data presented in Figure 1D but have now appeared. A discussion of this in the main text is warranted.
      2. This reviewer has several reservations on how the various key players in the manuscript are related to substantiate the conclusions made in the manuscript. For instance, how is HPRT, purinosomes, and WDR62 related? How about HSP90, WRD62, and HPRT? Pairwise connections were made throughout the manuscript; however, trying to tie all three together is difficult with the data presented.
        • The authors tried to connect HPRT, purinosomes, and WDR62 with BAG2; however, this study could greatly improve if we understood how a knockdown of BAG2 impacts purinosome formation and/or WDR62 colocalization with purinosome enzymes.
        • Is HPRT a client of HSP90? And how are WRD62 and HSP90 related since they do not associated (based on your BioID data)? These connections would again strengthen the arguments made in the manuscript and help to explain the HSP90 inhibition data presented in Figures 7F and 7G.
      3. Caution is warranted when making conclusions about WDR62 (and its granules) and purinosomes.
        • The authors describe the association between WDR62 and purinosomes differently throughout the text. I would recommend that the authors come to some conclusion about this and be consistent.

      A. (Lines 339-340) "WDR62 granules represent or overlap substantially with the phase-separated metabolons known as purinosomes". Based on the data presented, it appears that these might still be different entities but either overlap or have similar components. Purinosome localization with mitochondria (approx 60-80%) and microtubules (approx 90-95%) were significantly higher than those reported for WDR62 granules (approx 40%). This comparison would suggest that not all WDR62 granules behave similarly to purinosomes. And from the dot plot in Figure 3G, about half of the characterized WDR62 granules do not align with the previously reported characteristics of purinosomes.

      B. In the abstract and introduction, the authors state that WDR62 is being recruited to the purinosome and leave out the other possibility. I would recommend that the authors soften this claim in these sections because of the above possibility but also the lack of characterization of the sorbitol-induced "purinosomes". There is little discussion or evidence for how sorbitol induces purinosome formation. Is de novo purine biosynthesis activated upon sorbitol treatment? Are multiple de novo purine biosynthetic enzymes present in the sorbitol-induced "purinosomes"? Further, I agree that there is a tendency for WDR62 to associate with condensates that bear an enzyme within de novo purine biosynthesis; however many of these proteins are known to self-aggregate upon cell stress. Therefore, the entities that are being observing and called purinosomes might not be bone fide purinosomes. Additional care is necessary to make these statements. In my opinion, the current data only suggests that this might be a possibility.

      • (Lines 325-329) The authors reference a previous manuscript demonstrating that co-chaperones co-cluster with purinosomes. Based on this fact, they infer that WDR62 granules might represent purinosomes since WDR62 interacts with these same set of co-chaperones. These co-chaperones interact with a large number of different proteins (in fact, most kinases), so it is uncertain how the authors decided to go down this path to link purine metabolism with WDR62. Discussion of how this connection was made would help elevate the story. What additional insights did they have that lead them down these investigations?
      • If WDR62 is not required for purinosome formation, why would it localize with the purinosome? Is there any hypothesis that could be readily tested to better help understand this observation? Providing a better understanding of this would greatly elevate the work.

      A. (OPTIONAL) Please validate that the associations between WDR62 and the purine biosynthetic enzymes occur on the endogenous level (void of transient transfection). Many methods such as immunofluorescence and proximity ligation assays have been used by others to demonstrate protein-purinosome interactions. This result would reduce any concern that the association is a result of overexpression (artifact).

      B. Figures 6F and 6G conclude that nucleosides from purine-depleted growth conditions accumulate while the corresponding monophosphates do not change between WRD62 knock-out and wildtype cells. Given that purine-depleted growth conditions activate de novo purine biosynthesis (uncertain if this has been demonstrated in AD293 cells), could this result simply demonstrate that purine salvage is no longer used and the nucleosides have accumulated and are awaiting degradation (or exportation) rather than a loss of HPRT expression as inferred from the stated conclusions? The conclusions could be better substantiated with the use of a stable isotope incorporation assay.

      Is there a difference in the contribution of de novo purine biosynthesis and purine salvage to the generation of the monophosphates (AMP, GMP) between WDR62 knockout and wildtype AD293 cells? Use of a stable isotope (such as 15N-glutamine) could help to come to the appropriate conclusion.

      (Lines 483-485) If there is a change in de novo purine biosynthesis, are there any detectable changes in AICAR levels that might influence purine metabolism at the transcriptional level?

      Are the data and the methods presented in such a way that they can be reproduced? Are the experiments adequately replicated and statistical analysis adequate?

      1. For purine-depleted studies (metabolite analyses, microscopy), how long were the cells grown in purine-depleted medium before the analysis? And how was the purine-depleted medium generated? Please reference any source that might have been used.
      2. Details describing the BioID experiment are minimal. How many replicates were performed, was label-free or TMT quantitation used for the protein identification. Further the data analysis and mining of the proteins from the BioID study are missing - What database was used to identify the proteins from the peptides? Please include this information in the Materials and Methods section as well as a link to a repository where the LC-MS/MS data generated can be found. Additionally, it would be very helpful to have a spreadsheet or table that lists the biotinylated proteins and expectant or p values for each.
      3. Please include information about the streptavidin pulldown presented in Figure 1C.
      4. Many of the figure legends could benefit from a statistical description.
      5. There seems to be only two data points for Figure S3A. While there is no significant difference observed, it would be ideal to have additional replicates.
      6. (Figure 5I) Please provide statistical analysis to demonstrate the colocalization between FGAMS and WDR62 is robust in purine-depleted AD293 cells.

      Minor Comments:

      Do you have suggestions that would help the authors improve the presentation of their ideas and conclusions?

      1. The use of HSP90 inhibitors is a little confusing given the connections being made with BAG2 and other HSP70 co-chaperones in Figure 1.
        • Does the same conclusions hold true with an HSP70 inhibitor or siRNA?
        • (OPTIONAL) There are a lot of discrepancies between Hsp90 inhibitors and effective treatment concentrations. For example, NVP-AUY922 caused purinosomes to disassemble whereas STA9090 cause purinosomes to change morphology and adopt a more aggregated state. Do other Hsp90 inhibitors share the same phenotypic response as NVP-AUY922 in this study?
        • The treatment time (24 h) with NVP-AUY922 is very long. Given that Hsp90 interacts with hundreds of proteins, it is hard to understand whether the effect of Hsp90 inhibition is direct or indirect. Shorter times (1 h or less) would be more insightful.
      2. (OPTIONAL) Does the 2.6-fold increase in BAG2 increase its association with WDR62?
      3. Is the degradation of HPRT occurring through BAG2-mediated proteasomal degradation? Showing HPRT recovery by treating the cells with MG132 along with CHX would provide meaningful clues as to how BAG2 and HPRT might be related - Is BAG2 concentration increasing to facilitate the enhanced degradation of HPRT?
      4. Does HPRT colocalize with WDR62 in cells?
      5. (OPTIONAL) It would be nice to see validation experiments of some of the hits in Figure 1D or 1E in a co-immunoprecipitation experiment conducted similar to Figure 1C.
      6. The authors presented the findings that suggest that BAG2 interacts differently with commonly observed WDR62 mutations in MCPH2? How do these mutations affect WDR62 condensation, colocalization with purinosomes, or alter HPRT activity? Tying back the observations to something clinical would help elevate the overall significance of the findings.

      Are the text and figures clear and accurate?

      1. There are many times throughout the manuscript that the wrong figure is being referenced. These mistakes caused significant confusion at many times while reviewing the manuscript. Please double check all in-text references to figures. For example, I believe that you meant to use Figure S1C instead of Figure 2E with the statement on lines 183-185. Again, I believe that correct figure reference on line 501 is Figure 7G not Figure 7E.
      2. The figure legend on Figure S4 does not match the figure and the main text references. Please verify that the text in the figure legends correspond correctly to the figure.
      3. Please provide this data for the sentence on lines 399-400 in the supplemental file.
      4. I believe that the authors use the phrase "cell proliferation" to describe cell viability in the main text. In the Materials and Methods section, the authors state "The XTT cell proliferation assay enables quantification of cellular redox potential, providing a colorimetric readout of cell viability." Cell proliferation, viability, and cytotoxicity are different measurements, so please revise to reflect the correct experiment that was performed.

      Other Minor Comments:

      1. Move the sentence "In contrast, despite reduced mRNA..." (lines 387-388) to the last section when a reduction in PFAS expression was first mentioned.
      2. Please reference the following in the manuscript:
        • BioGRID database in the main text and Materials and Methods section
        • The reported study showing the DNAJC7-WDR62 interaction (as curated from BioGRID)
        • Fiji in the Materials and Methods section
      3. (Line 461-463) The authors state the following: "the loss of WDR62 leads to an increase in BAG2 and vice-versa (Fig. 7A) (Fig. S9B). I am not sure that the vice-versa (i.e. loss of BAG2 increases WDR62) is true. From the data presented in Figure 7H, I do not see a significant change in WDR62 expression upon BAG2 siRNA treatment.
      4. For your BioID study, do you know how many or the proportion of cells that were mitotically arrested with the low dose of nocodazole (200 ng/mL)? Given the small number of unique proteins that were in the mitotic only population, it is curious to know how enriched the cells were and whether WDR62 localization is important in the context of this study.
      5. Just to clarify, the WDR62-HA lane (third in each set) in Figure 1C is not WDR62-BirA*-HA and that it is only being used as a control.
      6. In the Discussion (lines 439-441) "We also show that WDR62 forms dynamic, phase-separated granules that co-localise with chaperones and purine metabolic enzymes, resembling purinosomes." I believe that the authors meant to say co-chaperones instead of chaperones given no microscopy data was presented showing the colocalization of HSP70/90 with WDR62 granules. Please revise.

      Referees cross-commenting

      I agree with the comments and recommendations by the other reviewers. Many of our shared comments are those that need to be addressed to substantiate the claims made by the authors throughout the manuscript. The proposed experiments across the reviewer comments appear feasible given that similar experiments have already been presented in this version of the manuscript. I strongly encourage the authors to consider these comments when revising their manuscript to help strengthen their claims and boost its overall significance and impact.

      Significance

      Describe the nature and significance of the advance (e.g. conceptual, technical, clinical) for the field. Place the work in the context of the existing literature (provide references, where appropriate).

      The work presented explains a previously unknown role for WDR62 in the regulation of purine metabolism. Despite all the hard work that was performed to reach their conclusions, the use of the AD293 cell line and the lack of correlating the common WDR62 disease-promoting mutations to the observed findings throughout the entire manuscript slightly reduced my enthusiasm for this work. The presented study leverages a lot of existing literature to establish connections between WR62, co-chaperones, and purine metabolic enzymes, with an emphasis on purinosome metabolon, a condensate comprised of the enzymes in de novo purine biosynthesis.

      State what audience might be interested in and influenced by the reported findings.

      The audience that might be interested in the reported findings would likely be those tied to biomolecular condensates in cellular metabolism and their connection to disease. I also feel that researchers that study microcephaly might be interested in this work. In my opinion, I believe that a broader readership could happen if additional studies were performed to make stronger connections between studies presented.

      Define your field of expertise with a few keywords to help the authors contextualize your point of view. Indicate if there are any parts of the paper that you do not have sufficient expertise to evaluate.

      My field of expertise is tied to understanding the regulation of cellular metabolism through the use of biochemical and biophysical techniques. I am not as familiar with the in depth details of proteomic analysis such as those required for accurate reporting of data tied to protein proximity labeling (BioID) methods.

    1. August runoffs will decrease further, and also July runoffs will start to decrease for the 2.7°C and 4°C scenarios As a result of this shift, June (and for 4°C warming also May) runoff show an increase towards the end of the century

      You should bring this closer together in the text. You just mention above in bullet points what the study says and here you mention what you found. A sentence connecting the two would be nice (e.g. Rets et al. (2020) found ..., which is the same as we found ...)

    2. higher temperature scenarios (e.g. 4°C) lead to faster glacier volume and area loss compared to lower temperature scenarios (e.g. 1.5°C)

      but 2.7 and 4 are almost indistinguishable, this is not discussed

    3. most models, which might offer better statistical reliability while the 4°C scenario is supported by the fewest.

      also provide the exact numbers in your discussion. "most" and "fewest" is not quantitative

    1. Reviewer #1 (Public review):

      Summary:

      This is an interesting study characterizing and engineering so-called bathy phytochromes, i.e., those that respond to near infrared (NIR) light in the ground state, for optogenetic control of bacterial gene expression. Previously, the authors have developed a structure-guided approach to functionally link several light-responsive protein domains to the signaling domain of the histidine kinase FixL, which ultimately controls gene expression. Here, the authors use the same strategy to link bathy phytochrome light-responsive domains to FixL, resulting in sensors of NIR light. Interestingly, they also link these bathy phytochrome light-sensing domains to signaling domains from the tetrathionate-sensing SHK TtrS and the toluene-sensing SHK TodS, demonstrating the generality of their protein engineering approach more broadly across bacterial two-component systems.

      This is an exciting result that should inspire future bacterial sensor design. They go on to leverage this result to develop what is, to my knowledge, the first system for orthogonally controlling the expression of two separate genes in the same cell with NIR and Red light, a valuable contribution to the field.

      Finally, the authors reveal new details of the pH-dependent photocycle of bathy phytochromes and demonstrate that their sensors work in the gut - and plant-relevant strains E. coli Nissle 1917 and A. tumefaciens.

      Strengths:

      (1) The experiments are well-founded, well-executed, and rigorous.

      (2) The manuscript is clearly written.

      (3) The sensors developed exhibit large responses to light, making them valuable tools for ontogenetic applications.

      (4) This study is a valuable contribution to photobiology and optogenetics.

      Weaknesses:

      (1) As the authors note, the sensors are relatively insensitive to NIR light due to the rapid dark reversion process in bathy phytochromes. Though NIR light is generally non-phototoxic, one would expect this characteristic to be a limitation in some downstream applications where light intensities are not high (e.g., in vivo).

      (2) Though they can be multiplexed with Red light sensors, these bathy phytochrome NIR sensors are more difficult to multiplex with other commonly used light sensors (e.g., blue) due to the broad light responsivity of the Pfr state. This challenge may be overcome by careful dosing of blue light, as the authors discuss, but other bacterial NIR sensing systems with less cross-talk may be preferred in some applications.

    2. Reviewer #2 (Public review):

      Summary:

      In this manuscript, Meier et al. engineer a new class of light-regulated two-component systems. These systems are built using bathy-bacteriophytochromes that respond to near-infrared (NIR) light. Through a combination of genetic engineering and systematic linker optimization, the authors generate bacterial strains capable of selective and tunable gene expression in response to NIR stimulation. Overall, these results are an interesting expansion of the optogenetic toolkit into the NIR range. The cross-species functionality of the system, modularity, and orthogonality have the potential to make these tools useful for a range of applications.

      Strengths:

      (1) The authors introduce a novel class of near-infrared light-responsive two-component systems in bacteria, expanding the optogenetic toolbox into this spectral range.

      (2) Through engineering and linker optimization, the authors achieve specific and tunable gene expression, with minimal cross-activation from red light in some cases.

      (3) The authors show that the engineered systems function robustly in multiple bacterial strains, including laboratory E. coli, the probiotic E. coli Nissle 1917, and Agrobacterium tumefaciens.

      (4) The combination of orthogonal two-component systems can allow for simultaneous and independent control of multiple gene expression pathways using different wavelengths of light.

      (5) The authors explore the photophysical properties of the photosensors, investigating how environmental factors such as pH influence light sensitivity.

      Weaknesses:

      (1) The expression of multi-gene operons and fluorescent reporters could impose a metabolic burden. The authors should present data comparing optical density for growth curves of engineered strains versus the corresponding empty-vector control to provide insight into the burden and overall impact of the system on host viability and growth.

      (2) The manuscript consistently presents normalized fluorescence values, but the method of normalization is not clear (Figure 2 caption describes normalizing to the maximal fluorescence, but the maximum fluorescence of what?). The authors should provide a more detailed explanation of how the raw fluorescence data were processed. In addition, or potentially in exchange for the current presentation, the authors should include the raw fluorescence values in supplementary materials to help readers assess the actual magnitude of the reported responses.

      (3) Related to the prior point, it would be useful to have a positive control for fluorescence that could be used to compare results across different figure panels.

      (4) Real-time gene expression data are not presented in the current manuscript, but it would be helpful to include a time-course for some of the key designs to help readers assess the speed of response to NIR light.

    1. Reviewer #3 (Public review):

      Summary:

      The paper studies learning rules in a simple sigmoidal recurrent neural network setting. The recurrent network has a single layer of 10 to 40 units. It is first confirmed that feedback alignment (FA) can learn a value function in this setting. Then so-called bio-plausible constraints are added: (1) when value weights (readout) is non-negative, (2) when the activity is non-negative (normal sigmoid rather than downscaled between -0.5 and 0.5), (3) when the feedback weights are non-negative, (4) when the learning rule is revised to be monotic: the weights are not downregulated. In the simple task considered all four biological features do not appear to impair totally the learning.

      Strengths:

      (1) The learning rules are implemented in a low-level fashion of the form: (pre-synaptic-activity) x (post-synaptic-activity) x feedback x RPE. Which is therefore interpretable in terms of measurable quantities in the wet-lab.

      (2) I find that non-negative FA (FA with non negative c and w) is the most valuable theoretical insight of this paper: I understand why the alignment between w and c is automatically better at initialization.

      (3) The task choice is relevant, since it connects with experimental settings of reward conditioning with possible plasticity measurements.

      Weaknesses:

      (4) The task is rather easy, so it's not clear that it really captures the computational gap that exists with FA (gradient-like learning) and simpler learning rule like a delta rule: RPE x (pre-synpatic) x (post-synaptic). To control if the task is not too trivial, I suggest adding a control where the vector c is constant c_i=1.

      (5) Related to point 3), the main strength of this paper is to draw potential connection with experimental data. It would be good to highlight more concretely the prediction of the theory for experimental findings. (Ideally, what should be observed with non-negative FA that is not expected with FA or a delta rule (constant global feedback) ?).

      (6a) Random feedback with RNN in RL have been studied in the past, so it is maybe worth giving some insights how the results and the analyzes compare to this previous line of work (for instance in this paper [1]). For instance, I am not very surprised that FA also works for value prediction with TD error. It is also expected from the literature that the RL + RNN + FA setting would scale to tasks that are more complex than the conditioning problem proposed here, so is there a more specific take-home message about non-negative FA? or benefits from this simpler toy task?

      (6b) Related to task complexity, it is not clear to me if non-negative value and feedback weights would generally scale to harder tasks. If the task in so simple that a global RPE signal is sufficient to learn (see 4 and 5), then it could be good to extend the task to find a substantial gap between: global RPE, non-negative FA, FA, BP. For a well chosen task, I expect to see a performance gap between any pair of these four learning rules. In the context of the present paper, this would be particularly interesting to study the failure mode of non-negative FA and the cases where it does perform as well as FA.

      (7) I find that the writing could be improved, it mostly feels more technical and difficult than it should. Here are some recommendations:<br /> 7a) For instance, the technical description of the task (CSC) is not fully described and requires background knowledge from other paper which is not desirable.<br /> 7b) Also the rationale for the added difficulty with the stochastic reward and new state is not well explained.<br /> 7c) In the technical description of the results I find that the text dives into descriptive comments of the figures but high-level take home messages would be helpful to guide the reader. I got a bit lost, although I feel that there is probably a lot of depth in these paragraphs.

      (8) Related to the writing issue and 5), I wished that "bio-plausibility" was not the only reason to study positive feedback and value weights. Is it possible to develop a bit more specifically what and why this positivity is interesting? Is there an expected finding with non-negative FA both in the model capability? or maybe there is a simpler and crisp take-home message to communicate the experimental predictions to the community would be useful?

      [1] https://www.nature.com/articles/s41467-020-17236-y

      Comments on revisions:

      Thank you for addressing all my comments in your reply.

    2. Author response:

      The following is the authors’ response to the original reviews

      Summary of our revisions

      (1) We have explained the reason why the untrained RNN with readout (value-weight) learning only could not well learn the simple task: it is because we trained the models continuously across trials with random inter-trial intervals rather than separately for each episodic trial and so it was not trivial for the models to recognize that cue presentation in different trials constitutes a same single state since the activities of untrained RNN upon cue presentation should differ from trial to trial (Line 177-185).

      (2) We have shown that dimensionality was higher in the value-RNNs than in the untrained RNN (Fig. 2K,6H).

      (3) We have shown that even when distractor cue was introduced, the value-RNNs could learn the task (Fig. 10).

      (4) We have shown that extended value-RNNs incorporating excitatory and inhibitory units and conforming to the Dale's law could still learn the tasks (Fig. 9,10-right column).

      (5) In the original manuscript, the non-negatively constrained value-RNN showed loose alignment of value-weight and random feedback from the beginning but did not show further alignment over trials. We have clarified its reason and found a way, introducing a slight decay (forgetting), to make further alignment occur (Fig. 8E,F).

      (6) We have shown that the value-RNNs could learn the tasks with longer cue-reward delay (Fig. 2M,6J) or action selection (Fig. 11), and found cases where random feedback performed worse than symmetric feedback.

      (7) We compared our value-RNNs with e-prop (Bellec et al., 2020, Nat Commun). While e-prop incorporates the effects of changes in RNN weights across distant times through "eligibility trace", our value-RNNs do not. The reason why our models can still learn the tasks with cue-reward delay is considered to be because our models use TD error and TD learning itself, even TD(0) without eligibility trace, is a solution for temporal credit assignment. In fact, TD error-based e-prop was also examined, but for that, result with symmetric feedback, but not with random feedback, was shown (their Fig. 4,5) while for another setup of reward-based e-prop without TD error, result with random feedback was shown (their SuppFig. 5). We have noted these in Line 695-711 (and also partly in Line 96-99).

      (8) In the original manuscript, we emphasized only the spatial locality (random rather than symmetric feedback) of our learning rule. But we have now also emphasized the temporal locality (online learning) as it is also crucial for bio-plausibility and critically different from the original value-RNN with BPTT. We also changed the title.

      (9) We have realized that our estimation of true state values was invalid (as detailed in page 34 of this document). Effects of this error on performance comparisons were small, but we apologize for this error.

      Reviewer #1 (Public review):

      Summary:

      Can a plastic RNN serve as a basis function for learning to estimate value. In previous work this was shown to be the case, with a similar architecture to that proposed here. The learning rule in previous work was back-prop with an objective function that was the TD error function (delta) squared. Such a learning rule is non-local as the changes in weights within the RNN, and from inputs to the RNN depends on the weights from the RNN to the output, which estimates value. This is non-local, and in addition, these weights themselves change over learning. The main idea in this paper is to examine if replacing the values of these non-local changing weights, used for credit assignment, with random fixed weights can still produce similar results to those obtained with complete bp. This random feedback approach is motivated by a similar approach used for deep feed-forward neural networks.

      This work shows that this random feedback in credit assignment performs well but is not as well as the precise gradient-based approach. When more constraints due to biological plausibility are imposed performance degrades. These results are not surprising given previous results on random feedback. This work is incomplete because the delay times used were only a few time steps, and it is not clear how well random feedback would operate with longer delays. Additionally, the examples simulated with a single cue and a single reward are overly simplistic and the field should move beyond these exceptionally simple examples.

      Strengths:

      • The authors show that random feedback can approximate well a model trained with detailed credit assignment.

      • The authors simulate several experiments including some with probabilistic reward schedules and show results similar to those obtained with detailed credit assignments as well as in experiments.

      • The paper examines the impact of more biologically realistic learning rules and the results are still quite similar to the detailed back-prop model.

      Weaknesses:

      *please note that we numbered your public review comments and recommendations for the authors as Pub1 and Rec1 etc so that we can refer to them in our replies to other comments.

      Pub1. The authors also show that an untrained RNN does not perform as well as the trained RNN. However, they never explain what they mean by an untrained RNN. It should be clearly explained.

      These results are actually surprising. An untrained RNN with enough units and sufficiently large variance of recurrent weights can have a high-dimensionality and generate a complete or nearly complete basis, though not orthonormal (e.g: Rajan&Abbott 2006). It should be possible to use such a basis to learn this simple classical conditioning paradigm. It would be useful to measure the dimensionality of network dynamics, in both trained and untrained RNN's.

      We have added an explanation of untrained RNN in Line 144-147:

      “As a negative control, we also conducted simulations in which these connections were not updated from initial values, referring to as the case with "untrained (fixed) RNN". Notably, the value weights w (i.e., connection weights from the RNN to the striatal value unit) were still trained in the models with untrained RNN.”

      We have also analyzed the dimensionality of network dynamic by calculating the contribution ratios of each principal component of the trajectory of RNN activities. It was revealed that the contribution ratios of later principal components were smaller in the cases with untrained RNN than in the cases with trained value RNN. We have added these results in Fig. 2K and Line 210-220 (for our original models without non-negative constraint):

      “In order to examine the dimensionality of RNN dynamics, we conducted principal component analysis (PCA) of the time series (for 1000 trials) of RNN activities and calculated the contribution ratios of PCs in the cases of oVRNNbp, oVRNNrf, and untrained RNN with 20 RNN units. Figure 2K shows a log of contribution ratios of 20 PCs in each case. Compared with the case of untrained RNN, in oVRNNbp and oVRNNrf, initial component(s) had smaller contributions (PC1 (t-test p = 0.00018 in oVRNNbp; p = 0.0058 in oVRNNrf) and PC2 (p = 0.080 in oVRNNbp; p = 0.0026 in oVRNNrf)) while later components had larger contributions (PC3~10,15~20 p < 0.041 in oVRNNbp; PC5~20 p < 0.0017 in oVRNNrf) on average, and this is considered to underlie their superior learning performance. We noticed that late components had larger contributions in oVRNNrf than in oVRNNbp, although these two models with 20 RNN units were comparable in terms of cue~reward state values (Fig. 2J-left).”

      and Fig. 6H and Line 412-416 (for our extended models with non-negative constraint):

      “Figure 6H shows contribution ratios of PCs of the time series of RNN activities in each model with 20 RNN units. Compared with the cases with naive/shuffled untrained RNN, in oVRNNbp-rev and oVRNNrf-bio, later components had relatively high contributions (PC5~20 p < 1.4×10,sup>−6</sup> (t-test vs naive) or < 0.014 (vs shuffled) in oVRNNbp-rev; PC6~20 p < 2.0×10<sup>−7</sup> (vs naive) or PC7~20 p < 5.9×10<sup>−14</sup> (vs shuffled) in oVRNNrf-bio), explaining their superior value-learning performance.”

      Regarding the poor performance of the model with untrained RNN, we would like to add a note. It is sure that untrained RNN with sufficient dimensions should be able to well represent just <10 different states, and state values should be able to be well learned through TD learning regardless of whatever representation is used. However, a difficulty (nontriviality) lies in that because we modeled the tasks in a continuous way, rather than in an episodic way, the activity of untrained RNN upon cue presentation should generally differ from trial to trial. Therefore, it was not trivial for RNN to know that cue presentation in different trials, even after random lengths of inter-trial interval, should constitute a same single state. We have added this note in Line 177-185:

      “This inferiority of untrained RNN may sound odd because there were only four states from cue to reward while random RNN with enough units is expected to be able to represent many different states (c.f., [49]) and the effectiveness of training of only the readout weights has been shown in reservoir computing studies [50-53]. However, there was a difficulty stemming from the continuous training across trials (rather than episodic training of separate trials): the activity of untrained RNN upon cue presentation generally differed from trial to trial, and so it is non-trivial that cue presentation in different trials should be regarded as the same single state, even if it could eventually be dealt with at the readout level if the number of units increases.”

      The original value RNN study (Hennig et al., 2023, PLoS Comput Biol) also modeled tasks in a continuous way (though using backprop-through-time (BPTT) for training) and their model with untrained RNN also showed considerably larger RPE error than the value RNN even when the number of RNN units was 100 (the maximum number plotted in their Fig. 6A).

      Pub2. The impact of the article is limited by using a network with discrete time-steps, and only a small number of time steps from stimulus to reward. What is the length of each time step? If it's on the order of the membrane time constant, then a few time steps are only tens of ms. In the classical conditioning experiments typical delays are of the order to hundreds of milliseconds to seconds. Authors should test if random feedback weights work as well for larger time spans. This can be done by simply using a much larger number of time steps.

      In the revised manuscript, we examined the cases in which the cue-reward delay (originally 3 time steps) was elongated to 4, 5, or 6 time-steps. Our online value RNN models with random feedback could still achieve better performance (smaller squared value error) than the models with untrained RNN, although the performance degraded as the cue-reward delay increased. We have added these results in Fig. 2M and Line 223-228 (for our original models without non-negative constraint)

      “We further examined the cases with longer cue-reward delays. As shown in Fig. 2M, as the delay increased, the mean squared error of state values (at 3000-th trial) increased, but the relative superiority of oVRNNbp and oVRNNrf over the model with untrained RNN remained to hold, except for cases with small number of RNN units (5) and long delay (5 or 6) (p < 0.0025 in Wilcoxon rank sum test for oVRNNbp or oVRNNrf vs untrained for each number of RNN units for each delay).”

      and Fig. 6J and Line 422-429 (for our extended models with non-negative constraint):

      “Figure 6J shows the cases with longer cue-reward delays, with default or halved learning rates. As the delay increased, the mean squared error of state values (at 3000-th trial) increased, but the relative superiority of oVRNNbp-rev and oVRNNrf-bio over the models with untrained RNN remained to hold, except for a few cases with 5 RNN units (5 delay oVRNNrf-bio vs shuffled with default learning rate, 6 delay oVRNNrf-bio vs naive or shuffled with halved learning rate) (p < 0.047 in Wilcoxon rank sum test for oVRNNbp-rev or oVRNNrf-bio vs naive or shuffled untrained for each number of RNN units for each delay).”

      Also, we have added the note about our assumption and consideration on the time-step that we described in our provisional reply in Line 136-142:

      “We assumed that a single RNN unit corresponds to a small population of neurons that intrinsically share inputs and outputs, for genetic or developmental reasons, and the activity of each unit represents the (relative) firing rate of the population. Cortical population activity is suggested to be sustained not only by fast synaptic transmission and spiking but also, even predominantly, by slower synaptic neurochemical dynamics [46] such as short-term facilitation, whose time constant can be around 500 milliseconds [47]. Therefore, we assumed that single time-step of our rate-based (rather than spike-based) model corresponds to 500 milliseconds.”

      Pub3. In the section with more biologically constrained learning rules, while the output weights are restricted to only be positive (as well as the random feedback weights), the recurrent weights and weights from input to RNN are still bi-polar and can change signs during learning. Why is the constraint imposed only on the output weights? It seems reasonable that the whole setup will fail if the recurrent weights were only positive as in such a case most neurons will have very similar dynamics, and the network dimensionality would be very low. However, it is possible that only negative weights might work. It is unclear to me how to justify that bipolar weights that change sign are appropriate for the recurrent connections and inappropriate for the output connections. On the other hand, an RNN with excitatory and inhibitory neurons in which weight signs do not change could possibly work.

      We examined extended models that incorporated inhibitory and excitatory units and followed Dale's law with certain assumptions, and found that these models could still learn the tasks. We have added these results in Fig. 9 and subsection “4.1 Models with excitatory and inhibitory units” and described the details of the extended models in Line 844-862:

      Pub4. Like most papers in the field this work assumes a world composed of a single cue. In the real world there many more cues than rewards, some cues are not associated with any rewards, and some are associated with other rewards or even punishments. In the simplest case, it would be useful to show that this network could actually work if there are additional distractor cues that appear at random either before the CS, or between the CS and US. There are good reasons to believe such distractor cues will be fatal for an untrained RNN, but might work with a trained RNN, either using BPPT or random feedback. Although this assumption is a common flaw in most work in the field, we should no longer ignore these slightly more realistic scenarios.

      We examined the performance of the models in a task in which distractor cue randomly appeared. As a result, our model with random feedback, as well as the model with backprop, could still learn the state values much better than the models with untrained RNN. We have added these results in Fig. 10 and subsection “4.2 Task with distractor cue”

      Reviewer #1 (Recommendations for the authors):

      Detailed comments to authors

      Rec1. Are the untrained RNNs discussed in methods? It seems quite good in estimating value but has a strong dopamine response at time of reward. Is nothing trained in the untrained RNN or are the W values trained. Untrained RNN are not bad at estimating value, but not as good as the two other options. It would seem reasonable that an untrained RNN (if I understand what it is) will be sufficient for such simple Pavlovian conditioning paradigms. This is provided that the RNN generates a complete, or nearly complete basis. Random RNN's provided that the random weights are chosen properly can indeed generate a nearly complete basis. Once there is a nearly complete temporal basis, it seems that a powerful enough learning rule will be able to learn the very simple Pavlovian conditioning. Since there are only 3 time-steps from cue to reward, an RNN dimensionality of 3 would be sufficient. A failure to get a good approximation can also arise from the failure of the learning algorithm for the output weights (W).

      As we mentioned in our reply to your public comment Pub1 (page 3-5), we have added an explanation of "untrained RNN" (in which the value weights were still learnt) (Line 144-147). We also analyzed the dimensionality of network dynamics by calculating the contribution ratios of principal components of the trajectory of RNN activities, showing that the contribution ratios of later principal components were smaller in the cases with untrained RNN than in the cases with trained value RNN (Fig. 2K/Line 210-220, Fig.6H/Line 412-416). Moreover, also as we mentioned in our reply to your public comment Pub1, we have added a note that even learning of a small number of states was not trivially easy because we considered continuous learning across trials rather than episodic learning of separate trials and thus it was not trivial for the model to know that cue presentation in different trials after random lengths of inter-trial interval should still be regarded as a same single state (Line 177-185).

      Rec2. For all cases, it will be useful to estimate the dimensionality of the RNN. Is the dimensionality of the untrained RNN smaller than in the trained cases? If this is the case, this might depend on the choice of the initial random (I assume) recurrent connectivity matrix.

      As mentioned above, we have analyzed the dimensionality of the network dynamics, and as you said, the dimensionality of the model with untrained RNN (which was indeed the initial random matrix as you said, as we mentioned above) was on average smaller than the trained value RNN models (Fig. 2K/Line 210-220, Fig.6H/Line 412-416).

      Rec3. It is surprising that the error starts increasing for more RNN units above ~15. See discussion. This might indicate a failure to adjust the learning parameters of the network rather than a true and interesting finding.

      Thank you very much for this insightful comment. In the original manuscript, we set the learning rate to a fixed value (0.1), without normalization by the squared norm of feature vector (as we mentioned in Line 656-7 of the original manuscript) because we thought such a normalization could not be locally (biologically) implemented. However, we have realized that the lack of normalization resulted in excessively large learning rate when the number of RNN units was large and it could cause instability and error increase as you suggested. Therefore, in the revised manuscript, we have implemented a normalization of learning rate (of value weights) that does not require non-local computations, specifically, division by the number of RNN units. As a result, the error now monotonically decreased, as the number of RNN units increased, in the non-negatively constrained models (Fig. 6E-left) and also largely in the unconstrained model with random feedback, although still not in the unconstrained model with backprop or untrained RNN (Fig. 2J-left)

      Rec4. Not numbering equations is a problem. For example, the explanations of feedback alignment (lines 194-206) rely on equations in the methods section which are not numbered. This makes it hard to read these explanations. Indeed, it will also be better to include a detailed derivation of the explanation in these lines in a mathematical appendix. Key equations should be numbered.

      We have added numbers to key equations in the Methods, and references to the numbers of corresponding equations in the main text. Detailed derivations are included in the Methods.

      Rec5. What is shown in Figure 3C? - an equation will help.

      We have added an explanation using equations in the main text (Line 256-259).

      Rec6. The explanation of why alignment occurs is not satisfactory, but neither is it in previous work on feedforward networks. The least that should be done though

      Regarding why alignment occurs, what remained mysterious (to us) was that in the case of nonnegatively constrained model, while the angle between value weight vector (w) and the random feedback vector (c) was relatively close (loosely aligned) from the beginning, it appeared (as mentioned in the manuscript) that there was no further alignment over trials, despite that the same mechanism for feedback alignment that we derived for the model without non-negative constraint was expected to operate also under the non-negative constraint. We have now clarified the reason for this, and found a way, introduction of slight decay (forgetting) of value weights, by which feedback alignment came to occur in the non-negatively constraint model. We have added these in the revised manuscript (Line 463-477):

      “As mentioned above, while the angle between w and c was on average smaller than 90° from the beginning, there was no further alignment over trials. This seemed mysterious because the mechanism for feedback alignment that we derived for the models without non-negative constraint was expected to work also for the models with non-negative constraint. As a possible reason for the non-occurrence of feedback alignment, we guessed that one or a few element(s) of w grew prominently during learning, and so w became close to an edge or boundary of the non-negative quadrant and thereby angle between w and other vector became generally large (as illustrated in Fig. 8D). Figure 8Ea shows the mean±SEM of the elements of w ordered from the largest to smallest ones after 1500 trials. As conjectured above, a few elements indeed grew prominently.

      We considered that if a slight decay (forgetting) of value weights (c.f., [59-61]) was assumed, such a prominent growth of a few elements of w may be mitigated and alignment of w to c, beyond the initial loose alignment because of the non-negative constraint, may occur. These conjectures were indeed confirmed by simulations (Fig. 8Eb,c and Fig. 8F). The mean squared value error slightly increased when the value-weightdecay was assumed (Fig. 8G), however, presumably reflecting a decrease in developed values and a deterioration of learning because of the decay.”

      Rec7. I don't understand the qualitative difference between 4G and 4H. The difference seems to be smaller but there is still an apparent difference. Can this be quantified?

      We have added pointers indicating which were compared and statistical significance on Fig. 4D-H, and also Fig. 7 and Fig. 9C.

      Rec8. More biologically realistic constraints.

      Are the weights allowed to become negative? - No.

      Figure 6C - untrained RNN with non-negative x_i. Again - it was not explained what untrained RNN is. However, given my previous assumption, this is probably because the units developed in an untrained RNN is much further from representing a complete basis function. This cannot be done with only positive values. It would be useful to see network dynamics of units for untrained RNN. It might also be useful in all cases to estimate the dimensionality of the RNN. For 3 time-steps, it needs to be at least 3, and for more time steps as in Figure 4, larger.

      As we mentioned in our reply to your public comment Pub3 (page 6-8), in the revised manuscript we examined models that incorporated inhibitory and excitatory units and followed Dale's law, which could still learn the tasks (Fig. 9, Line 479-520). We have also analyzed the dimensionality of network dynamics as we mentioned in our replies to your public comment Pub1 and recommendations Rec1 and Rec2.

      Rec9. A new type of untrained RNN is introduced (Fig 6D) this is the first time an explanation of of the untrained RNN is given. Indeed, the dimensionality of the second type of untrained RNN should be similar to the bioVRNNrf. The results are still not good.

      In the model with the new type of untrained RNN whose elements were shuffled from trained bioVRNNrf, contribution ratios of later principal components of the trajectory of RNN activities (Fig. 6H gray dotted line) were indeed larger than those in the model with native untrained RNN (gray solid line) but still much smaller than those in the trained value RNN models with backprop (red line) or random feedback (blue line). It is considered that in value RNN, RNN connections were trained to realize high-dimensional trajectory, and shuffling did not generally preserve such an ability.

      Rec10. The discussion is too long and verbose. This is not a review paper.

      We have made the original discussion much more compact (from 1686 words to 940 words). We have added new discussion, in response to the review comments, but the total length remains to be shorter than before (1589 words).

      Reviewer #2 (Public review):

      Summary:

      Tsurumi et al. show that recurrent neural networks can learn state and value representations in simple reinforcement learning tasks when trained with random feedback weights. The traditional method of learning for recurrent network in such tasks (backpropagation through time) requires feedback weights which are a transposed copy of the feed-forward weights, a biologically implausible assumption. This manuscript builds on previous work regarding "random feedback alignment" and "value-RNNs", and extends them to a reinforcement learning context. The authors also demonstrate that certain nonnegative constraints can enforce a "loose alignment" of feedback weights. The author's results suggest that random feedback may be a powerful tool of learning in biological networks, even in reinforcement learning tasks.

      Strengths:

      The authors describe well the issues regarding biologically plausible learning in recurrent networks and in reinforcement learning tasks. They take care to propose networks which might be implemented in biological systems and compare their proposed learning rules to those already existing in literature. Further, they use small networks on relatively simple tasks, which allows for easier intuition into the learning dynamics.

      Weaknesses:

      The principles discovered by the authors in these smaller networks are not applied to deeper networks or more complicated tasks, so it remains unclear to what degree these methods can scale up, or can be used more generally.

      We have examined extended models that incorporated inhibitory and excitatory units and followed Dale's law with certain assumptions, and found that these models could still learn the tasks. We have added these results in Fig. 9 and subsection “4.1 Models with excitatory and inhibitory units”.

      We have also examined the performance of the models in a task in which distractor cue randomly appeared, finding that our models could still learn the state values much better than the models with untrained RNN. We have added these result in Fig. 10 and subsection “4.2 Task with distractor cue”.

      Regarding the depth, we continue to think about it but have not yet come up with concrete ideas.

      Reviewer #2 (Recommendations for the authors):

      (1) I think the work would greatly benefit from more proofreading. There are language errors/oddities throughout the paper, I will list just a few examples from the introduction:

      Thank you for pointing this out. We have made revisions throughout the paper.

      line 63: "simultaneously learnt in the downstream of RNN". Simultaneously learnt in networks downstream of the RNN? Simulatenously learn in a downstream RNN? The meaning is not clear in the original sentence.

      We have revised it to "simultaneously learnt in connections downstream of the RNN" (Line 67-68).

      starting in line 65: " A major problem, among others.... value-encoding unit" is a run-on sentence and would more readable if split into multiple sentences.

      We have extensively revised this part, which now consists of short sentences (Line 70-75).

      line 77: "in supervised learning of feed-forward network" should be either "in supervised learning of a feed-forward network" or "in supervised learning of feed-forward networks".

      We have changed "feed-forward network" to "feed-forward networks" (Line 83).

      (2) Under what conditions can you use an online learning rule which only considers the influence of the previous timestep? It's not clear to me how your networks solve the temporal credit assignment problem when the cue-reward delay in your tasks is 3-5ish time steps. How far can you stretch this delay before your networks stop learning correctly because of this one-step assumption? Further, how much does feedback alignment constrain your ability to learn long timescales, such as in Murray, J.M. (2019)?

      The reason why our models can solve the temporal credit assignment problem at least to a certain extent is considered to be because temporal-difference (TD) learning, which we adopted, itself has a power to resolve temporal credit assignment, as exemplified in that TD(0) algorithms without eligibility trance can still learn the value of distant rewards. We have added a discussion on this in Line 702-705:

      “…our models do not have "eligibility trace" (nor memorable/gated unit, different from the original value-RNN [26]), but could still solve temporal credit assignment to a certain extent because TD learning is by itself a solution for it (notably, recent work showed that combination of TD(0) and model-based RL well explained rat's choice and DA patterns [132]).”

      We have also examined the cases in which the cue-reward delay (originally 3 time steps) was elongated to 4, 5, or 6 time-steps, and our models with random feedback could still achieve better performance than the models with untrained RNN although the performance degraded as the cue-reward delay increased. We have added these results in Fig. 2M and Line 223-228 (for our original models without non-negative constraint)

      “We further examined the cases with longer cue-reward delays. As shown in Fig. 2M, as the delay increased, the mean squared error of state values (at 3000-th trial) increased, but the relative superiority of oVRNNbp and oVRNNrf over the model with untrained RNN remained to hold, except for cases with small number of RNN units (5) and long delay (5 or 6) (p < 0.0025 in Wilcoxon rank sum test for oVRNNbp or oVRNNrf vs untrained for each number of RNN units for each delay).”

      and Fig. 6J and Line 422-429 (for our extended models with non-negative constraint):

      “Figure 6J shows the cases with longer cue-reward delays, with default or halved learning rates. As the delay increased, the mean squared error of state values (at 3000-th trial) increased, but the relative superiority of oVRNNbp-rev and oVRNNrf-bio over the models with untrained RNN remained to hold, except for a few cases with 5 RNN units (5 delay oVRNNrf-bio vs shuffled with default learning rate, 6 delay oVRNNrf-bio vs naive or shuffled with halved learning rate) (p < 0.047 in Wilcoxon rank sum test for oVRNNbp-rev or oVRNNrf-bio vs naive or shuffled untrained for each number of RNN units for each delay).”

      As for the difficulty due to random feedback compared to backprop, there appeared to be little difference in the models without non-negative constraint (Fig. 2M), whereas in the models with nonnegative constraint, when the cue-reward delay was elongated to 6 time-steps, the model with random feedback performed worse than the model with backprop (Fig. 6J bottom-left panel).

      (3) Line 150: Were the RNN methods trained with continuation between trials?

      Yes, we have added

      “The oVRNN models, and the model with untrained RNN, were continuously trained across trials in each task, because we considered that it was ecologically more plausible than episodic training of separate trials.” in Line 147-150. This is considered to make learning of even the simple cue-reward association task nontrivial, as we describe in our reply to your comment 9 below.

      (4) Figure 2I, J: indicate the statistical significance of the difference between the three methods for each of these measures.

      We have added statistical information for Fig. 2J (Line 198-203):

      “As shown in the left panel of Fig. 2J, on average across simulations, oVRNNbp and oVRNNrf exhibited largely comparable performance and always outperformed the untrained RNN (p < 0.00022 in Wilcoxon rank sum test for oVRNNbp or oVRNNrf vs untrained for each number of RNN units), although oVRNNbp somewhat outperformed or underperformed oVRNNrf when the number of RNN units was small (≤10 (p < 0.049)) or large (≥25 (p < 0.045)), respectively.”

      and also Fig. 6E (for non-negative models) (Line 385-390):

      “As shown in the left panel of Fig. 6E, oVRNNbp-rev and oVRNNrf-bio exhibited largely comparable performance and always outperformed the models with untrained RNN (p < 2.5×10<sup>−12</sup> in Wilcoxon rank sum test for oVRNNbp-rev or oVRNNrf-bio vs naive or shuffled untrained for each number of RNN units), although oVRNNbp-rev somewhat outperformed or underperformed oVRNNrf-bio when the number of RNN units was small (≤10 (p < 0.00029)) or large (≥25 (p < 3.7×10<sup>−6</sup>)), respectively…”

      Fig. 2I shows distributions, whose means are plotted in Fig. 2J, and we did not add statistics to Fig. 2I itself.

      (5) Line 178: Has learning reached a steady state after 1000 trials for each of these networks? Can you show a plot of error vs. trial number?

      We have added a plot of error vs trial number for original models (Fig. 2L, Line 221-223):

      “We examined how learning proceeded across trials in the models with 20 RNN units. As shown in Fig. 2L, learning became largely converged by 1000-th trial, although slight improvement continued afterward.”

      and non-negatively constrained models (Fig. 6I, Line 417-422):

      “Figure 6I shows how learning proceeded across trials in the models with 20 RNN units. While oVRNNbp-rev and oVRNNrf-bio eventually reached a comparable level of errors, oVRNNrf-bio outperformed oVRNNbp-rev in early trials (at 200, 300, 400, or 500 trials; p < 0.049 in Wilcoxon rank sum test for each). This is presumably because the value weights did not develop well in early trials and so the backprop-type feedback, which was the same as the value weights, did not work well, while the non-negative fixed random feedback worked finely from the beginning.”

      As shown in these figures, learning became largely steady at 1000 trials, but still slightly continued, and we have added simulations with 3000 trials (Fig. 2M and Fig. 6J).

      (6) Line 191: Put these regression values in the figure caption, as well as on the plot in Figure 3B.

      We have added the regression values in Fig. 3B and its caption.

      (7) Line 199: This idea of being in the same quadrant is interesting, but I think the term "relatively close angle" is too vague. Is there another more quantatative way to describe this what you mean by this?

      We have revised this (Line 252-254) to “a vector that is in a relatively close angle with c , or more specifically, is in the same quadrant as (and thus within at maximum 90° from) c (for example, [c<sub>1</sub>  c<sub>2</sub>  c<sub>3</sub>]<sup>T</sup> and [0.5c<sub>1</sub> 1.2c<sub>2</sub> 0.8c<sub>3</sub>]T) “

      (8) Line 275: I'd like to see this measure directly in a plot, along with the statistical significance.

      We have added pointers indicating which were compared and statistical significance on Fig. 4D-H, and also Fig. 7 and Fig. 9C.

      (9) Line 280: Surely the untrained RNN should be able to solve the task if the reservoir is big enough, no? Maybe much bigger than 50 units, but still.

      We think this is not sure. A difficulty lies in that because we modeled the tasks in a continuous way rather than in an episodic way (as we mentioned in our reply to your comment 3), the activity of untrained RNN upon cue presentation should generally differ from trial to trial. Therefore, it was not trivial for RNN to know that cue presentation in different trials, even after random lengths of inter-trial interval, should constitute a same single state. We have added this note in Line 177-185:

      “This inferiority of untrained RNN may sound odd because there were only four states from cue to reward while random RNN with enough units is expected to be able to represent many different states (c.f., [49]) and the effectiveness of training of only the readout weights has been shown in reservoir computing studies [50-53]. However, there was a difficulty stemming from the continuous training across trials (rather than episodic training of separate trials): the activity of untrained RNN upon cue presentation generally differed from trial to trial, and so it is non-trivial that cue presentation in different trials should be regarded as the same single state, even if it could eventually be dealt with at the readout level if the number of units increases.”

      The original value RNN study (Hennig et al., 2023, PLoS Comput Biol) also modeled tasks in a continuous way (though using BPTT for training) and their model with untrained RNN also showed considerably larger RPE error than the value RNN even when the number of RNN units was 100 (the maximum number plotted in their Fig. 6A).

      (10) It's a bit confusing to compare Figure 4C to Figure 4D-H because there are also many features of D-H which do not match those of C (response to cue, response to late reward in task 1). It would make sense to address this in some way. Is there another way to calculate the true values of the states (e.g., maybe you only start from the time of the cue) which better approximates what the networks are doing?

      As we mentioned in our replies to your comments 3 and 9, our models with RNN were trained continuously across trials rather than separately for each episodic trial, and whether the models could still learn the state representation is a key issue. Therefore, starting learning from the time of cue would not be an appropriate way to compare the models, and instead we have made statistical comparison regarding key features, specifically, TD-RPEs at early and late rewards, as indicated in Fig. 4D-H.

      (11) Line 309: Can you explain why this non-monotic feature exists? Why do you believe it would be more biologically plausible to assume monotonic dependence? It doesn't seem so straightforward to me, I can imagine that competing LTP/LTD mechanisms may produce plasticity which would have a non-monotic dependence on post-synaptic activity.

      Thank you for this insightful comment. As you suggested, non-monotonic dependence on the postsynaptic activity (BCM rule) has been proposed for unsupervised learning (cortical self-organization) (Bienenstock et al., 1982 J Neurosci), and there were suggestions that triplet-based STDP could be reduced to a BCM-like rule and additional components (Gjorgjieva et al., 2011 PNAS; Shouval, 2011 PNAS). However, the non-monotonicity appeared in our model, derived from the backprop rule, is maximized at the middle and thus opposite from the BCM rule, which is minimized at the middle (i.e., initially decrease and thereafter increase). Therefore we consider that such an increase-then-decreasetype non-monotonicity would be less plausible than a monotonic increase, which could approximate an extreme case (with a minimum dip) of the BCM rule. We have added a note on this point in Line 355-358:

      “…the dependence on the post-synaptic activity was non-monotonic, maximized at the middle of the range of activity. It would be more biologically plausible to assume a monotonic increase (while an opposite shape of nonmonotonicity, once decrease and thereafter increase, called the BCM (Bienenstock-Cooper-Munro) rule has actually been suggested [56-58]).”

      (12) Line 363: This is the most exciting part of the paper (for me). I want to learn way more about this! Don't hide this in a few sentences. I want to know all about loose vs. feedback alignment. Show visualizations in 3D space of the idea of loose alignment (starting in the same quadrant), and compare it to how feedback alignment develops (ending in the same quadrant). Does this "loose" alignment idea give us an idea why the random feedback seems to settle at 45 degree angle? it just needs to get the signs right (same quadrant) for each element?

      In reply to this encouraging comment, we have made further analyses of the loose alignment. By the term "loose alignment", we meant that the value weight vector w and the feedback vector c are in the same (non-negative) quadrant, as you said. But what remained mysterious (to us) was while the angle between w and c was relatively close (loosely aligned) from the beginning, it appeared (as mentioned in the manuscript) that there was no further alignment over trials (and the angle actually settled at somewhat larger than 45°), despite that the same mechanism for feedback alignment that we derived for the model without non-negative constraint was expected to operate also under the nonnegative constraint. We have now clarified the reason for this, and found a way, introduction of slight decay (forgetting) of value weights, by which feedback alignment came to occur in the non-negatively constraint model. We have added this in Line 463-477:

      “As mentioned above, while the angle between w and c was on average smaller than 90° from the beginning, there was no further alignment over trials. This seemed mysterious because the mechanism for feedback alignment that we derived for the models without non-negative constraint was expected to work also for the models with non-negative constraint. As a possible reason for the non-occurrence of feedback alignment, we guessed that one or a few element(s) of w grew prominently during learning, and so w became close to an edge or boundary of the non-negative quadrant and thereby angle between w and other vector became generally large (as illustrated in Fig. 8D). Figure 8Ea shows the mean±SEM of the elements of w ordered from the largest to smallest ones after 1500 trials. As conjectured above, a few elements indeed grew prominently.

      We considered that if a slight decay (forgetting) of value weights (c.f., [59-61]) was assumed, such a prominent growth of a few elements of w may be mitigated and alignment of w to c, beyond the initial loose alignment because of the non-negative constraint, may occur. These conjectures were indeed confirmed by simulations (Fig. 8Eb,c and Fig. 8F). The mean squared value error slightly increased when the value-weightdecay was assumed (Fig. 8G), however, presumably reflecting a decrease in developed values and a deterioration of learning because of the decay.”

      As for visualization, because the model's dimension was high such as 12, we could not come up with better ways of visualization than the trial versus angle plot (Fig. 3A, 8A,F). Nevertheless, we would expect that the abovementioned additional analyses of loose alignment (with graphs) are useful to understand what are going on.

      (13) Line 426: how does this compare to some of the reward modulated hebbian rules proposed in other RNNs? See Hoerzer, G. M., Legenstein, R., & Maass, W. (2014). Put another way, you arrived at this from a top-down approach (gradient descent->BP->approximated by RF->non-negativity constraint>leads to DA dependent modulation of Hebbian plasticity). How might this compare to a bottom up approach (i.e. starting from the principle of Hebbian learning, and adding in reward modulation)

      The study of Hoerzer et al. 2014 used a stochastic perturbation, which we did not assume but can potentially be integrated. On the other hand, Hoerzer et al. trained the readout of untrained RNN, whereas we trained both RNN and its readout. We have added discussion to compare our model with Hoerzer et al. and other works that also used perturbation methods, as well as other top-down approximation method, in Line 685-711 (reference 128 is Hoerzer et al. 2014 Cereb Cortex):

      “As an alternative to backprop in hierarchical network, aside from feedback alignment [36], Associative Reward-Penalty (A<sub>R-P</sub>) algorithm has been proposed [124-126]. In A<sub>R-P</sub>, the hidden units behave stochastically, allowing the gradient to be estimated via stochastic sampling. Recent work [127] has proposed Phaseless Alignment Learning (PAL), in which high-frequency noise-induced learning of feedback projections proceeds simultaneously with learning of forward projections using the feedback in a lower frequency. Noise-induced learning of the weights on readout neurons from untrained RNN by reward-modulated Hebbian plasticity has also been demonstrated [128]. Such noise- or perturbation-based [40] mechanisms are biologically plausible because neurons and neural networks can exhibit noisy or chaotic behavior [129-131], and might improve the performance of value-RNN if implemented.

      Regarding learning of RNN, "e-prop" [35] was proposed as a locally learnable online approximation of BPTT [27], which was used in the original value RNN 26. In e-prop, neuron-specific learning signal is combined with weight-specific locally-updatable "eligibility trace". Reward-based e-prop was also shown to work [35], both in a setup not introducing TD-RPE with symmetric or random feedback (their Supplementary Figure 5) and in another setup introducing TD-RPE with symmetric feedback (their Figure 4 and 5). Compared to these, our models differ in multiple ways.

      First, we have shown that alignment to random feedback occurs in the models driven by TD-RPE. Second, our models do not have "eligibility trace" (nor memorable/gated unit, different from the original valueRNN [26]), but could still solve temporal credit assignment to a certain extent because TD learning is by itself a solution for it (notably, recent work showed that combination of TD(0) and model-based RL well explained rat's choice and DA patterns [132]). However, as mentioned before, single time-step in our models was assumed to correspond to hundreds of milliseconds, incorporating slow synaptic dynamics, whereas e-prop is an algorithm for spiking neuron models with a much finer time scale. From this aspect, our models could be seen as a coarsetime-scale approximation of e-prop. On top of these, our results point to a potential computational benefit of biological non-negative constraint, which could effectively limit the parameter space and promote learning.”

      Related to your latter point (and also replying to other reviewer's comment), we also examined the cases where the random feedback in our model was replaced with uniform feedback, which corresponds to a simple bottom-up reward-modulated triplet plasticity rule. As a result, the model with uniform feedback showed largely comparable, but somewhat worse, performance than the model with random feedback. We have added the results in Fig. 2J-right and Line 206-209 (for our original models without non-negative constraint):

      “The green line in Fig. 2J-right shows the performance of a special case where the random feedback in oVRNNrf was fixed to the direction of (1, 1, ..., 1)<sup>T</sup> (i.e., uniform feedback) with a random coefficient, which was largely comparable to, but somewhat worse than, that for the general oVRNNrf (blue line).”

      and Fig. 6E-right and Line 402-407 (for our extended models with non-negative constraint):

      “The green and light blue lines in the right panels of Figure 6E and Figure 6F show the results for special cases where the random feedback in oVRNNrf-bio was fixed to the direction of (1, 1, ..., 1) <sup>T</sup> (i.e., uniform feedback) with a random non-negative magnitude (green line) or a fixed magnitude of 0.5 (light blue line). The performance of these special cases, especially the former (with random magnitude) was somewhat worse than that of oVRNNrf-bio, but still better than that of the models with untrained RNN. and also added a biological implication of the results in Line 644-652:

      We have shown that oVRNNrf and oVRNNrf-bio could work even when the random feedback was uniform, i.e., fixed to the direction of (1, 1, ..., 1) <sup>T</sup>, although the performance was somewhat worse. This is reasonable because uniform feedback can still encode scalar TD-RPE that drives our models, in contrast to a previous study [45], which considered DA's encoding of vector error and thus regarded uniform feedback as a negative control. If oVRNNrf/oVRNNrf-bio-like mechanism indeed operates in the brain and the feedback is near uniform, alignment of the value weights w to near (1, 1, ..., 1) is expected to occur. This means that states are (learned to be) represented in such a way that simple summation of cortical neuronal activity approximates value, thereby potentially explaining why value is often correlated with regional activation (fMRI BOLD signal) of cortical regions [113].”

      Reviewer #3 (Public review):

      Summary:

      The paper studies learning rules in a simple sigmoidal recurrent neural network setting. The recurrent network has a single layer of 10 to 40 units. It is first confirmed that feedback alignment (FA) can learn a value function in this setting. Then so-called bio-plausible constraints are added: (1) when value weights (readout) is non-negative, (2) when the activity is non-negative (normal sigmoid rather than downscaled between -0.5 and 0.5), (3) when the feedback weights are non-negative, (4) when the learning rule is revised to be monotic: the weights are not downregulated. In the simple task considered all four biological features do not appear to impair totally the learning.

      Strengths:

      (1) The learning rules are implemented in a low-level fashion of the form: (pre-synaptic-activity) x (post-synaptic-activity) x feedback x RPE. Which is therefore interpretable in terms of measurable quantities in the wet-lab.

      (2) I find that non-negative FA (FA with non negative c and w) is the most valuable theoretical insight of this paper: I understand why the alignment between w and c is automatically better at initialization.

      (3) The task choice is relevant since it connects with experimental settings of reward conditioning with possible plasticity measurements.

      Weaknesses:

      (4) The task is rather easy, so it's not clear that it really captures the computational gap that exists with FA (gradient-like learning) and simpler learning rule like a delta rule: RPE x (pre-synpatic) x (postsynaptic). To control if the task is not too trivial, I suggest adding a control where the vector c is constant c_i=1.

      We have examined the cases where the feedback was uniform, i.e., in the direction of (1, 1, ..., 1) in both models without and with non-negative constraint. In both models, the models with uniform feedback performed somewhat worse than the original models with random feedback, but still better than the models with untrained RNN. We have added the results in Fig. 2J-right and Line 206-209 (for our original models without non-negative constraint):

      “The green line in Fig. 2J-right shows the performance of a special case where the random feedback in oVRNNrf was fixed to the direction of (1, 1, ..., 1) <sup>T</sup> (i.e., uniform feedback) with a random coefficient, which was largely comparable to, but somewhat worse than, that for the general oVRNNrf (blue line).”

      and Fig. 6E-right and Line 402-407 (for our extended models with non-negative constraint):

      “The green and light blue lines in the right panels of Figure 6E and Figure 6F show the results for special cases where the random feedback in oVRNNrf-bio was fixed to the direction of (1, 1, ..., 1) <sup>T</sup> (i.e., uniform feedback) with a random non-negative magnitude (green line) or a fixed magnitude of 0.5 (light blue line). The performance of these special cases, especially the former (with random magnitude) was somewhat worse than that of oVRNNrf-bio, but still better than that of the models with untrained RNN.”

      We have also added a discussion on the biological implication of the model with uniform feedback mentioned in our provisional reply in Line 644-652:

      “We have shown that oVRNNrf and oVRNNrf-bio could work even when the random feedback was uniform, i.e., fixed to the direction of (1, 1, ..., 1) <sup>T</sup>, although the performance was somewhat worse. This is reasonable because uniform feedback can still encode scalar TD-RPE that drives our models, in contrast to a previous study [45], which considered DA's encoding of vector error and thus regarded uniform feedback as a negative control. If oVRNNrf/oVRNNrf-bio-like mechanism indeed operates in the brain and the feedback is near uniform, alignment of the value weights w to near (1, 1, ..., 1) is expected to occur. This means that states are (learned to be) represented in such a way that simple summation of cortical neuronal activity approximates value, thereby potentially explaining why value is often correlated with regional activation (fMRI BOLD signal) of cortical regions [113].”

      In addition, while preparing the revised manuscript, we found a recent simulation study, which showed that uniform feedback coupled with positive forward weights was effective in supervised learning of one-dimensional output in feed-forward network (Konishi et al., 2023, Front Neurosci).

      We have briefly discussed this work in Line 653-655:

      “Notably, uniform feedback coupled with positive forward weights was shown to be effective also in supervised learning of one-dimensional output in feed-forward network [114], and we guess that loose alignment may underlie it.”

      (5) Related to point 3), the main strength of this paper is to draw potential connection with experimental data. It would be good to highlight more concretely the prediction of the theory for experimental findings. (Ideally, what should be observed with non-negative FA that is not expected with FA or a delta rule (constant global feedback) ?).

      We have added a discussion on the prediction of our models, mentioned in our provisional reply, in Line 627-638:

      “oVRNNrf predicts that the feedback vector c and the value-weight vector w become gradually aligned, while oVRNNrf-bio predicts that c and w are loosely aligned from the beginning. Element of c could be measured as the magnitude of pyramidal cell's response to DA stimulation. Element of w corresponding to a given pyramidal cell could be measured, if striatal neuron that receives input from that pyramidal cell can be identified (although technically demanding), as the magnitude of response of the striatal neuron to activation of the pyramidal cell. Then, the abovementioned predictions could be tested by (i) identify cortical, striatal, and VTA regions that are connected, (ii) identify pairs of cortical pyramidal cells and striatal neurons that are connected, (iii) measure the responses of identified pyramidal cells to DA stimulation, as well as the responses of identified striatal neurons to activation of the connected pyramidal cells, and (iv) test whether DA→pyramidal responses and pyramidal→striatal responses are associated across pyramidal cells, and whether such associations develop through learning.”

      Moreover, we have considered another (technically more doable) prediction of our model, and described it in Line 639-643:

      “Testing this prediction, however, would be technically quite demanding, as mentioned above. An alternative way of testing our model is to manipulate the cortical DA feedback and see if it will cause (re-)alignment of value weights (i.e., cortical striatal strengths). Specifically, our model predicts that if DA projection to a particular cortical locus is silenced, effect of the activity of that locus on the value-encoding striatal activity will become diminished.”

      (6a) Random feedback with RNN in RL have been studied in the past, so it is maybe worth giving some insights how the results and the analyzes compare to this previous line of work (for instance in this paper [1]). For instance, I am not very surprised that FA also works for value prediction with TD error. It is also expected from the literature that the RL + RNN + FA setting would scale to tasks that are more complex than the conditioning problem proposed here, so is there a more specific take-home message about non-negative FA? or benefits from this simpler toy task? [1] https://www.nature.com/articles/s41467-020-17236-y

      As for a specific feature of non-negative models, we did not describe (actually did not well recognize) an intriguing result that the non-negative random feedback model performed generally better than the models without non-negative constraint with either backprop or random feedback (Fig. 2J-left versus Fig. 6E-left (please mind the difference in the vertical scales)). This suggests that the non-negative constraint effectively limited the parameter space and thereby learning became efficient. We have added this result in Line 392-395:

      “Remarkably, oVRNNrf-bio generally achieved better performance than both oVRNNbp and oVRNNrf, which did not have the non-negative constraint (Wilcoxon rank sum test, vs oVRNNbp : p < 7.8×10,sup>−6</sup> for 5 or ≥25 RNN units; vs oVRNNrf: p < 0.021 for ≤10 or ≥20 RNN units).”

      Also, in the models with non-negative constraint, the model with random feedback learned more rapidly than the model with backprop although they eventually reached a comparable level of errors, at least in the case with 20 RNN units. This is presumably because the value weights did not develop well in early trials and so the backprop-based feedback, which was the same as the value weights, did not work well, while the non-negative fixed random feedback worked finely from the beginning. We have added this result in Fig. 6I and Line 417-422:

      “Figure 6I shows how learning proceeded across trials in the models with 20 RNN units. While oVRNNbp-rev and oVRNNrf-bio eventually reached a comparable level of errors, oVRNNrf-bio outperformed oVRNNbp-rev in early trials (at 200, 300, 400, or 500 trials; p < 0.049 in Wilcoxon rank sum test for each). This is presumably because the value weights did not develop well in early trials and so the backprop-type feedback, which was the same as the value weights, did not work well, while the non-negative fixed random feedback worked finely from the beginning.”

      We have also added a discussion on how our model can be positioned in relation to other models including the study you mentioned (e-prop by Bellec, ..., Maass, 2020) in subsection “Comparison to other algorithms” of the Discussion):

      Regarding the slightly better performance of the non-negative model with random feedback than that of the non-negative model with backprop when the number of RNN units was large (mentioned in our provisional reply), state values in the backprop model appeared underdeveloped than those in the random feedback model. Slightly better performance of random feedback than backprop held also in our extended model incorporating excitatory and inhibitory units (Fig. 9B).

      (6b) Related to task complexity, it is not clear to me if non-negative value and feedback weights would generally scale to harder tasks. If the task in so simple that a global RPE signal is sufficient to learn (see 4 and 5), then it could be good to extend the task to find a substantial gap between: global RPE, non-negative FA, FA, BP. For a well chosen task, I expect to see a performance gap between any pair of these four learning rules. In the context of the present paper, this would be particularly interesting to study the failure mode of non-negative FA and the cases where it does perform as well as FA.

      In the cue-reward association task with 3 time-steps delay, the non-negative model with random feedback performed largely comparably to the non-negative model with backprop, and this remained to hold in a task where distractor cue, which was not associated with reward, appeared in random timings. We have added the results in Fig. 10 and subsection “4.2 Task with distractor cue”.

      We have also examined the cases where the cue-reward delay was elongated. In the case of longer cue-reward delay (6 time-steps), in the models without non-negative constraint, the model with random feedback performed comparably to (and slightly better than when the number of RNN units was large) the model with backprop (Fig. 2M). In contrast, in the models with non-negative constraint, the model with random feedback underperformed the model with backprop (Fig. 6J, left-bottom). This indicates a difference between the effect of non-negative random feedback and the effect of positive+negative random feedback.

      We have further examined the performance of the models in terms of action selection, by extending the models to incorporate an actor-critic algorithm. In a task with inter-temporal choice (i.e., immediate small reward vs delayed large reward), the non-negative model with random feedback performed worse than the non-negative model with backprop when the number of RNN units was small. When the number of RNN increased, these models performed more comparably. These results are described in Fig. 11 and subsection “4.3 Incorporation of action selection”.

      (7) I find that the writing could be improved, it mostly feels more technical and difficult than it should. Here are some recommendations:

      7a) for instance the technical description of the task (CSC) is not fully described and requires background knowledge from other paper which is not desirable.

      7b) Also the rationale for the added difficulty with the stochastic reward and new state is not well explained.

      7c) In the technical description of the results I find that the text dives into descriptive comments of the figures but high-level take home messages would be helpful to guide the reader. I got a bit lost, although I feel that there is probably a lot of depth in these paragraphs.

      As for 7a), 'CSC (complete serial compound)' was actually not the name of the task but the name of the 'punctate' state representation, in which each state (timing from cue) is represented in a punctate manner, i.e., by a one-hot vector such as (1, 0, ..., 0), (0, 1, ..., 0), ..., and (0, 0, ..., 1). As you pointed out, using the name of 'CSC' would make the text appearing more technical than it actually is, and so we have moved the reference to the name of 'CSC' to the Methods (Line 903-907):

      “For the agents with punctate state representation, which is also referred to as the complete serial compound (CSC) representation [1, 48, 133], each timing from a cue in the tasks was represented by a 10-dimensional one-hot vector, starting from (1 0 0 ... 0)<sup>T</sup> for the cue state, with the next state (0 1 0 ... 0) <sup>T</sup> and so on.”

      and in the Results we have instead added a clearer explanation (Line 163-165):

      “First, for comparison, we examined traditional TD-RL agent with punctate state representation (without using the RNN), in which each state (time-step from a cue) was represented in a punctate manner, i.e., by a one-hot vector such as (1, 0, ..., 0), (0, 1, ..., 0), and so on.”

      As for 7b), we have added the rationale for our examination of the tasks with probabilistic structures (Line 282-294):

      “Previous work [54] examined the response of DA neurons in cue-reward association tasks in which reward timing was probabilistically determined (early in some trials but late in other trials). There were two tasks, which were largely similar but there was a key difference that reward was given in all the trials in one task whereas reward was omitted in some randomly determined trials in another task. Starkweather et al. [54] found that the DA response to later reward was smaller than the response to earlier reward in the former task, presumably reflecting the animal's belief that delayed reward will surely come, but the opposite was the case in the latter task, presumably because the animal suspected that reward was omitted in that trial. Starkweather et al.[54] then showed that such response patterns could be explained if DA encoded TD-RPE under particular state representations that incorporated the probabilistic structures of the task (called the 'belief state'). In that study, such state representations were 'handcrafted' by the authors, but the subsequent work [26] showed that the original value-RNN with backprop (BPTT) could develop similar representations and reproduce the experimentally observed DA patterns.”

      As for 7c), we have extensively revised the text of the results, adding high-level explanations while trying to reduce the lengthy low-level descriptions (e.g., Line 172-177 for Fig2E-G).

      (8) Related to the writing issue and 5), I wished that "bio-plausibility" was not the only reason to study positive feedback and value weights. Is it possible to develop a bit more specifically what and why this positivity is interesting? Is there an expected finding with non-negative FA both in the model capability? or maybe there is a simpler and crisp take-home message to communicate the experimental predictions to the community would be useful?

      There is actually an unexpected finding with non-negative model: the non-negative random feedback model performed generally better than the models without non-negative constraint with either backprop or random feedback (Fig. 2J-left versus Fig. 6E-left), presumably because the nonnegative constraint effectively limited the parameter space and thereby learning became efficient, as we mentioned in our reply to your point 6a above (we did not well recognize this at the time of original submission).

      Another potential merit of our present work is the simplicity of the model and the task. This simplicity enabled us to derive an intuitive explanation on why feedback alignment could occur. Such an intuitive explanation was lacking in previous studies while more precise mathematical explanations did exist. Related to the mechanism of feedback alignment, one thing remained mysterious to us at the time of original submission. Specifically, in the non-negatively constraint random feedback model, while the angle between the value weight (w) and the random feedback (c) was relatively close (loosely aligned) from the beginning, it appeared (as mentioned in the manuscript) that there was no further alignment over trials (and the angle actually settled at somewhat larger than 45°), despite that the same mechanism for feedback alignment that we derived for the model without non-negative constraint was expected to operate also under the non-negative constraint. We have now clarified the reason for this, and found a way, introduction of slight decay (forgetting) of value weights, by which feedback alignment came to occur in the non-negatively constraint model. We have added this in Line 463-477:

      “As mentioned above, while the angle between w and c was on average smaller than 90° from the beginning, there was no further alignment over trials. This seemed mysterious because the mechanism for feedback alignment that we derived for the models without non-negative constraint was expected to work also for the models with non-negative constraint. As a possible reason for the non-occurrence of feedback alignment, we guessed that one or a few element(s) of w grew prominently during learning, and so w became close to an edge or boundary of the non-negative quadrant and thereby angle between w and other vector became generally large (as illustrated in Fig. 8D). Figure 8Ea shows the mean±SEM of the elements of w ordered from the largest to smallest ones after 1500 trials. As conjectured above, a few elements indeed grew prominently.

      We considered that if a slight decay (forgetting) of value weights (c.f., [59-61]) was assumed, such a prominent growth of a few elements of w may be mitigated and alignment of w to c, beyond the initial loose alignment because of the non-negative constraint, may occur. These conjectures were indeed confirmed by simulations (Fig. 8Eb,c and Fig. 8F). The mean squared value error slightly increased when the value-weightdecay was assumed (Fig. 8G), however, presumably reflecting a decrease in developed values and a deterioration of learning because of the decay.”

      Correction of an error in the original manuscript

      In addition to revising the manuscript according to your comments, we have made a correction on the way of estimating the true state values. Specifically, in the original manuscript, we defined states by relative time-steps from a reward and estimated their values by calculating the sums of discounted future rewards starting from them through simulations. However, we assumed variable inter-trial intervals (ITIs) (4, 5, 6, or 7 time-steps with equal probabilities), and so until receiving cue information, agent should not know when the next reward will come. Therefore, states for the timings up to the cue timing cannot be defined by the upcoming reward, but previously we did so (e.g., state of "one timestep before cue") without taking into account the ITI variability.

      We have now corrected this issue, having defined the states of timings with respect to the previous (rather than upcoming) reward. For example, when ITI was 4 time-steps and agent existed in its last time-step, agent will in fact receive a cue at the next time-step, but agent should not know it until actually receiving the cue information and instead should assume that s/he was at the last time-step of ITI (if ITI was 4), last − 1 (if ITI was 5), last − 2 (if ITI was 6), or last − 3 (if ITI was 7) with equal probabilities (in a similar fashion to what we considered when thinking about state definition for the probabilistic tasks). We estimated the true values of states defined in this way through simulations. As a result, the corrected true value of the cue-timing has become slightly smaller than the value described in the original manuscript (reflecting the uncertainty about ITI length), and consequently small positive TD-RPE has now appeared at the cue timing.

      Because we measured the performance of the models by squared errors in state values, this correction affected the results reporting the performance. Fortunately, the effects were relatively minor and did not largely alter the results of performance comparisons. However, we sincerely apologize for this error. In the revised manuscript, we have used the corrected true values throughout the manuscript, and we have described the ways of estimating these values in Line 919-976.

    1. Note: This response was posted by the corresponding author to Review Commons. The content has not been altered except for formatting.

      Learn more at Review Commons


      Reply to the reviewers

      1. General Statements [optional]

      The authors wish to thank the reviewers for fair and constructive comments and Review Commons for facilitating the process.

      2. Point-by-point description of the revisions

      Point-by-point replies to reviewers' comments on the original submitted manuscript are below. Authors' responses are in plain font.

      Reviewers' comments:

      Reviewer #1

      (Evidence, reproducibility and clarity (Required)):

      Summary: The authors identify cancer-associated ERBB4 mutations that are selected for functional characterization. Utilizing the BaF3 and MCF10A models, the authors investigate the potential oncogenic role for 11 recurrent ERBB4 mutations. Three mutants (S303F, E452K and L798R) were strongly transforming with the ability to transform both cell models, S303F being unique in its ability to transform both models in the absence of NRG-1. The authors perform modeling to decipher potential mechanisms of action of the ERBB4 S303F, E452K and L798R mutations. The authors assess the ability of HER3 mutations to dimerize with other HER family members and demonstrate that ERBB4 S303F can mediate its activating functions by stabilizing homo- and heterodimers with other ERBB receptors and that the heterodimerization is likely cell/tissue context dependent. The authors demonstrate that transforming ERBB4 mutants are sensitive to pan-ERBB inhibitors and drive resistance to EGFR-targeted therapy in EGFR-mutant NSCLC cells.

      Major comments:

      Patient data analysis is performed in more than 15 months ago in January 2024. This analysis should be updated.

      We thank the reviewer for pointing out the aspect of constantly expanding mutation data in clinical cancer sample databases. We reanalyzed the patient data in cBioPortal (data download 02 May 2025). In this new analysis, the distribution of mutations in ERBB4 did not change (Reviewer only Fig. 1A), and the 18 selected mutations were still the most recurrently mutated ERBB4 mutations (Reviewer only Fig. 1B). Reanalysis of updated patient data did not change the initial rationale of the study, or the conclusions in the submitted manuscript.

      Reviewer only Figure 1. Comparison of patient data derived from cBioPortal on January 2024 (01/2024) or May 2025 (05/2025). A) Figure 1B of the original submitted manuscript. B) Supplementary Figure S1C of the original submitted manuscript.

      The rationale for selecting the mutations to be studied is not entirely clear. There are no references to support studying mutations in Fig 1B red boxes.

      We apologize for not being sufficiently clear on our rationale for selecting the mutations for analysis. The spectrum of mutations across the ERBB4 gene do not demonstrate clear hotspots as seen in for example EGFR, KRAS, or BRAF. However, we observed that there are regions (not necessarily individual amino acid changes) in ERBB4 that seem to accumulate more mutations than other regions. Looking more closely, we observed that these "hot regions" tend to be located in areas where activating mutations have been described for other oncogenic ERBB family members and/or target structurally important regions for receptor activation such as dimerization interfaces. We hypothesized that these characteristics would suggest functional relevance for the mutations in these "hot regions". In the revised manuscript (on page 11), we have revised the text describing the selection of mutations for further analysis, and added references to justify our selection:

      "While the missense mutations were distributed across the 1,308 amino acid sequence of ERBB4, lacking obvious hotspot mutations such as observed for example in EGFR or KRAS, clusters of recurrent mutations could be identified (Fig. 1B). These clusters tended to be located in specific regions that are targeted by activating mutations in other oncogenic ERBB family members (Greulich et al., 2005, 2012; Lee et al., 2006; Bose et al., 2013; Jaiswal et al., 2013)and/or are important for receptor activation (Ferguson et al., 2003; Bouyain et al., 2005; Liu et al., 2012), suggesting functional relevance (red boxes in Fig. 1B). Some recurrent mutations were located in the unstructured C-terminal tail of ERBB4 (Fig. 1B). We selected in total 18 ERBB4 missense mutations (indicated in Fig. 1B) that were recurrent and/or located in the abovementioned regions of interest for functional characterization (indicated in Fig. 1B and Supplementary Fig. S1C) - hypothesizing that these mutations would be actionable. Of the different mutants at the same position of ERBB4 amino acid sequence, the most recurrent amino acid change was selected for characterization."

      Cell proliferation should be shown for BaF3 cells for continuity in Figure 2 instead of doubling time.

      We agree that it may cause confusion that the results for the Ba/F3 and MCF10a experiments in Fig. 2C and D (Fig. 2D and E in the revised manuscript) are reported using a different metric. The reason for this is that these assays measure different outputs: in the Ba/F3 assay, the emergence of proliferating cells under IL3 deprivation is measured, with repeated cell viability measurements over time. In the MCF10a experiment, the ability of ERBB4 mutations to sustain the proliferation of MCF10a cells in the absence of EGF is measured, using a fixed time point (8 days). Thus, doubling time, as an indicator for the time required for the emergence of proliferating cells, is more suitable metric to quantify the relative transforming capability of the different ERBB4 mutations in the Ba/F3 cells. In the case of MCF10a cells, the relevant metric is the cell viability (as a surrogate marker for the number of cells) at the endpoint measurement.

      The relative expression of HER3 constructs must be shown for BaF3 and MCF10A cells in Figure 2.

      We assume the reviewer is asking to demonstrate the expression levels of different ERBB4 mutants in the Ba/F3 and MCF10a cells used in experiments in Fig. 2C and D (Fig. 2D and E in the revised manuscript). We would like to thank the reviewer for this very relevant point. Western blots demonstrating the expression levels of different ERBB4 mutants in the Ba/F3 and MCF10a cells have now been added as a data new panel in the Figure 2 (Fig. 2B in the revised manuscript). No ERBB3 expression constructs were introduced into the cells.

      Blots in Figure 4 must be quantified.

      The blots in Figure 4 have now been quantified, and the relative signal intensities are shown below each blot. We thank the reviewer for suggesting this relevant analysis. The analysis revealed two issues that we have now revised:

      1) in Fig. 4D, the dimerization of EGFR with ERBB4 S303F is not convincingly increased when compared to EGFR dimerization with wild-type ERBB4. Therefore, we have omitted that conclusion from the results section:

      "Taking into account these expression level differences, ERBB4 S303F did indeed co-immunoprecipitate more efficiently than wild-type ERBB4 with ERBB2 and EGFR both in the presence or absence of NRG-1 (Fig. 4D), demonstrating that the S303F mutation promotes the formation of ERBB heterodimers."

      Omitting this data does not change our final conclusion, that the ERBB4 S303F mutation leads to enhanced ERBB4 heterodimerization.

      2) In Fig. 4C, the previously published ERBB4 D595V mutant, used as a control in the experiment, does not clearly demonstrate enhanced ERBB4 homodimerization after quantifying the blots. Therefore, we have cropped the lanes representing the ERBB4 D595V mutant from the blot, and omitted the part of the results text that discusses this ERBB4 mutant:

      "ERBB4 homodimers were assessed by crosslinking cell surface proteins with a cell membrane impermeable BS3, enabling detection of ERBB4 dimers as high molecular weight species of ERBB4 in western blot. Another activating extracellular ERBB4 mutation, D595V, was used as a positive control, as we have previously demonstrated D595V to stabilize ERBB4 dimers using the same assay (Kurppa et al., 2016). As predicted by the structural analyses, S303F resulted in more abundant active, phosphorylated ERBB4 dimers than wild-type ERBB4 in the presence of NRG-1, while the activating intracellular domain mutation L798R, that served as a negative control for dimer stabilization, did not (Fig. 4C)."

      Omitting these data does not change our final conclusion, that the ERBB4 S303F mutation leads to enhanced ERBB4 homodimerization.

      There are major concerns with Supplemental files. It is imperative that the effectiveness of HER3 shRNA be shown in S Fig3. These data are not interpretable without this.

      We apologize for confusion related to the supplemental files. The effectiveness of the ERBB3 (HER3) shRNA is shown in the Supplementary Figure S3B of the original submitted manuscript.

      Lanes in S Fig 4 are not marked again making data not interpretable.

      Some of the lanes in the Supplementary Figure 4B were not marked because the experiment contained other ERBB4 constructs in addition to the ones that are marked and discussed in the manuscript text. The reason for leaving the unmarked lanes in the final figure was to emphasize that the bands indicated come from the same membrane, blot and exposure. We understand how this may cause confusion, and thus have now cropped the blots to include only the lanes discussed in the manuscript text.

      It's unclear why Table 1 is included as this is already published data. This previously published data should be summarized in the text.

      We are happy to elaborate the novelty of the data in Table 1 of the original submitted manuscript. The data is from the SUMMIT trial (NCT01953926) (Hyman et al., 2018), the results of which have been published. However, the three patients in the top part of the table were enrolled to the SUMMIT trial based on the ERBB4mutation in their tumor, and the data for these patients have not previously been published. We received these data directly from Puma Biotechnology. In addition, while the ERBB4 mutation status for the patients in the lower part of the table has been published in the supplementary files of the Hyman and others publication, we feel that the patients' ERBB4 mutations merit discussion, and including these patient data in the table would complement the data on the three patients in the top part of the table. Due to these reasons, we feel that the table contains unpublished and relevant data for the study, and would like to keep the table in the manuscript by moving it into the Supplementary Data (Supplementary Table S2).

      To clarify the sources of the patient data, we have modified the methods section related to the table as follows:

      "Neratinib efficacy data, cancer types and co-alterations of patients harboring an ERBB4 alteration, enrolled in PUMA-NER-5201, the SUMMIT trial (NCT01953926), and treated with neratinib as a single agent (240 mg/day) were obtained from Puma Biotechnology (for patients enrolled based on an ERBB4 mutation - previously unpublished data) and cBioPortal (for patients with ERBB4 as a co-altered gene, enrolled based on an ERBB2 or ERBB3 mutation)."

      This text is now moved to "Supplementary Methods" under a new section "Neratinib efficacy in patients" on page 9 of the revised Supplementary Data -file

      There is a disconnect why the last two figures focus on a single model of NSCLC whereas the three most transforming mutations are found most commonly in breast, melanoma and GI tract cancers.

      The reviewer is correct in that the most transforming ERBB4 mutations are indeed found most commonly in beast and esophagogastric cancers and in melanoma. However, in the context of targeted therapy resistance,mutations that confer resistance are often acquired during therapy, and may not represent the typical cancer type-specific mutational patterns. The strongest evidence for a potential role of mutant ERBB4 in therapy resistance comes from the context of EGFR-targeted therapies and lung cancer. As mentioned in the results and discussion sections of the submitted manuscript, ERBB4 mutations identified in patients who developed resistance to EGFR-targeted therapy (Cremolini et al., 2019; Jänne et al., 2022), include the same mutation or mutation in the same residue as analyzed in the current study: the strongly transforming S303F or L798I. In addition, a recent study showed that EGFR-mutant lung cancer patients with co-occurring ERBB4 mutations have shorter relapse-free survival on osimertinib treatment (Vokes et al., 2022). Therefore, we focused on EGFR-mutant lung cancer as the model system to assess, as proof-of-concept, whether activating, transforming ERBB4 mutations are able to confer resistance to EGFR-targeted therapy. To make the transition to cancer therapy resistance and the rationale for choosing the model context more clear, we have added text to the start of the "Activating ERBB4 mutations drive resistance to EGFR-targeted therapy in EGFR-mutant NSCLC cells" -chapter of the revised manuscript:

      "There is emerging evidence associating ERBB4 with cancer therapy resistance across various cancer types and treatment regimens (Merimsky et al., 2001, 2002; Mendoza-Naranjo et al., 2013; Nafi et al., 2014; Saglam et al., 2017; Wege et al., 2018; Wang et al., 2019; Zhang et al., 2023; Debets et al., 2023; Albert et al., 2024; Arribas et al., 2024), including ERBB4 mutations that have been found in patient tumors after acquisition of therapy resistance (Cremolini et al., 2019; Jänne et al., 2022; Vokes et al., 2022; Yaeger et al., 2023; Yuan et al., 2023). Intriguingly, the ERBB4 mutations identified in patients who developed resistance to EGFR-targeted therapy (Cremolini et al., 2019; Jänne et al., 2022), include the same mutation or mutation in the same residue as analyzed in the current study: the strongly transforming S303F or L798I. In addition, co-occurring ERBB4 mutations in EGFR-mutant lung cancer patients have been shown to associate with shorter progression-free survival on EGFR inhibitor therapy (Vokes et al., 2022). These observations point to the possibility that mutant ERBB4 could promote resistance to targeted therapies."

      What are the differences in the recurrent ERBB4 mutant tumors versus ERBB4 wild-type tumors described in Figure 7?

      The reviewer points out a very relevant question. We suspect that in the tumors expressing mutant ERBB4, the activating ERBB4 mutants are able to compensate for the loss of EGFR signaling, particularly since the on-treatment cancer cells demonstrate elevated levels of ERBB4 ligands (Fig. 7C, D). This is analogous to accumulating evidence suggesting that ERBB4 independently and together with ERBB3 (and/or with increased availability of their ligands) compensate for survival and growth signaling upon ERBB2- or EGFR-targeted therapy (Carrión-Salip et al., 2012; Wilson et al., 2012; Nafi et al., 2014; Canfield et al., 2015; Yonesaka et al., 2015; Donoghue et al., 2018; Shi et al., 2018; Debets et al., 2023; Udagawa et al., 2023). Unfortunately, we are unable to approach this hypothesis using samples from the in vivo experiment in Fig.7. The treatment of the mice was stopped after 189 days of treatment in order to assess how many tumors grew back (i.e. how many mice were cured by the treatment). For this reason, we do not have the appropriate controls to analyze ERBB4 mutant-associated changes in on-treatment tumors.

      Figure 7C, D should be moved to supplemental as this is from previously published data and not strictly relevant to data shown in Fig 7.

      The data shown in Fig. 7C and D are a re-analysis of published single-cell RNA-seq data. While the single cell RNA-sequencing data set is previously published, the analysis of ERBB4 ligand expression performed, and shown in Fig. 7C and D has not been published before. We feel that these data provide evidence of a previously unrecognized upregulation of ERBB4 ligand expression in on-treatment EGFR-mutant NSCLC cells in vivo. Furthermore, as discussed in the results section of the original submitted manuscript (page 26; page 28 of the revised manuscript), the upregulation of ERBB4 ligands in the on-treatment tumors provides a plausible mechanism supporting mutant ERBB4 activation upon EGFR inhibitor treatment, as the transforming ERBB4 mutants seem to retain at least partly the dependency of ligand stimulation. Thus, we feel that these data are unpublished and relevant for the manuscript, and we would like to keep these data panels in the main Figure 7.

      Limitations should include consideration of endogenous levels of ERBB4 in the model systems used and disparate expression levels of wt ERBB4 versus ERBB4 mutation.

      We thank the reviewer for pointing out that we have not thoroughly disclosed the endogenous levels of ERBB4 expression in the used model systems. None of the used model systems (MCF10a, Ba/F3, COS-7, PC-9) express detectable levels of ERBB4 protein. This was mentioned in the original submitted manuscript for COS-7 (page 19; page 20 of the revised manuscript), Ba/F3 cells (page 18; page 19 of the revised manuscript), and PC-9 cells (page 24; page 24 of the revised manuscript), but not for MCF10a cells. We have now made this point more clear, and added a sentence "Neither of these models express detectable levels of ERBB4" in the results section under the chapter "Majority of the recurrent ERBB4 mutations are transforming in Ba/F3 or MCF10a cells" (page 12-13 of the revised manuscript), as well as to the discussion section (page 30 of the revised manuscript).

      Regarding the expression levels of different ERBB4 mutants versus ERBB4 wild-type, we have now added the new Figure 2B, showing the expression of all ERBB4 mutants and ERBB4 wild-type in Ba/F3 and MCF10a cells. We have also included the following text describing the expression levels of ERBB4 mutants in the results section under "Majority of the recurrent ERBB4 mutations are transforming in Ba/F3 or MCF10a cells" (page 13 of the revised manuscript):

      "The different ERBB4 mutants demonstrated similar expression levels compared to wild-type ERBB4 in both model systems with the exception of R106C and G907E mutants that were expressed predominantly as immature receptor forms in both models, suggesting defective receptor maturation. Also, the R1304W mutant demonstrated lower expression levels in the Ba/F3 cells, and could not be expressed at all in the MCF10a cells (Fig. 2B)."

      Minor comments:

      Fig1B lists ERBB3 V104V mutation?

      Thank you for noticing this mistake. This has now been corrected in the revised Figure 1B.

      List frequency of ERBB4 mutations in the introduction

      We thank the reviewer for the suggestion and have revised the introduction to include an example of the high frequency of ERBB4 missense mutations in cancer as follows:

      "Yet, despite the high frequency of ERBB4 missense mutations in various cancer types (up to 30% in non-melanoma skin cancer, Supplementary Fig. S1A, B) and characterization of several potentially oncogenic ERBB4 mutations (Prickett et al. 2009; Nakamura et al. 2016; Chakroborty et al. 2022; Kurppa et al. 2016; Tvorogov et al. 2009), the rationale for clinically targeting ERBB4 in cancer has not been fully developed."

      Clarification throughout if cells are serum-starved (how long) if stimulated with NRG-1

      We thank the reviewer for the thoughtful suggestion and have revised the main text and figure legends accordingly; in the revised manuscript on pages 6, 8, 9, 13, 17, 20, 25 and 26 "(10% serum)", on page 25 "following short-term stimulation with NRG-1 after overnight serum starvation (Fig. 6A).", as well as figure legends of Fig. 2, 4, 5, 6, S2, and S3.

      Reviewer #1 (Significance (Required)):

      General assessment: This work fills a gap in cancer research understanding if ERBB4 mutations could be targeted. Concerns and comments need to be addressed before definitive conclusions can be made.

      The authors wish to thank the reviewer for the positive assessment.


      Reviewer #2

      (Evidence, reproducibility and clarity (Required)):

      Ojala et al. report a very extensive exploration of the functional relevance of somatic mutations occurring in the ERBB4 gene. The Authors demonstrate that 11 out of 18 mutations they studied have oncogenic potential, with some of them actionable using clinically available ERBB inhibitors, while giving resistance to EGFR inhibitors.

      A very minor comment. At the beginning of page 21, I'd not define PD as the best respone. The Authors can write that all four patients progressed under treatment.

      We would like to thank the reviewer for the comment. We agree with the reviewer, and have now revised the sentence in question as follows:

      "Two of the three patients that were qualified for the SUMMIT trial due to a mutation in ERBB4, with no other qualifying mutations in ERBB family genes, had an ERBB4 mutation characterized in this study to be transforming (R544W and V840I) (Supplementary Table S2). Yet, neither of these patients, nor the patient with an ERBB4 VUS N465K, responded to neratinib and progressed under treatment (Supplementary Table S2)."

      Reviewer #2 (Significance (Required)):

      The work by Ojala et al. is the most detailed study of mutations occurring in ERBB4. Since these are relatively rare, they have not been properly studied up to now. The study is very well done.

      The authors wish to thank the reviewer for the very positive statement.


      Reviewer #3

      (Evidence, reproducibility and clarity (Required)):

      Summary - This work has mined cBioPortal to identify candidate cancer driver mutations in the gene encoding the ERBB4 receptor tyrosine kinase (Figure 1). These ERBB4 mutations occurred in clusters that are paralogous to activating mutations in other ERBB receptor genes or in clusters predicted to serve as dimerization interfaces of ERBB4. Eighteen such ERBB4 mutations were selected for characterization.

      • These mutants were tested in BaF3 and MCF-10A cells in the context of the ERBB4 JM-a CYT-2 isoform (Figure 2). Several of these ERBB4 mutants exhibited greater agonist-dependent coupling to cell proliferation than wild-type ERBB4. Moreover, some of the mutants exhibited greater agonist-independent coupling to cell proliferation than wild-type ERBB4. Five ERBB4 mutants (S303F, E452K, L798R, R992C, S1289A) exhibited greater activity in the BaF3 cells, whereas nine ERBB4 mutants (S303F, R393W, E452K, R544W, R711C, S774G, L798R, V840I, G870R) exhibited greater activity in the MCF10A cells. Thus, eleven of the ERBB4 mutants (S303F, R393W, E452K, R544W, R711C, S774G, L798R, V840I, G870R, R992C, S1289A) exhibited a gain-of-function phenotype. It should be noted that several of the ERBB4 gain-of-function mutants (R393W, R544W, R711C, V840I, G870R, R992C, S1289A) exhibited cell type specificity.

      • PyMol was used to "model" the effect of the most potent (S303F, E452K, and L798R) gain-of-function mutations on the structure of ERBB4 (Figure 3). These three mutations are predicted to cause increased ERBB4 dimerization.

      • When expressed in MCF-10A cells, the most potent (S303F, E452K, and L798R) gain-of-function ERBB4 mutants exhibited elevated ligand-dependent and ligand-independent tyrosine phosphorylation. This was accompanied by elevated EGFR, ERBB2, and ERBB4 tyrosine phosphorylation and elevated signaling by canonical effector proteins (Figure 4).

      • The homo- and heterodimerization of the most potent ERBB4 mutant (S303F) was studied following transient transfection of COS-7 cells (Figure 4). As predicted, the S303F mutant exhibited greater ERBB4 homodimerization and greater heterodimerization with EGFR and ERBB2, but not with ERBB3.

      • The data from the clinical trial NCT01953926 was mined to evaluate whether the presence of an ERBB4 activating mutation found in this work is associated with sensitivity to the pan-ERBB inhibitor neratinib (Table 1). Surprisingly, a compelling association was NOT found. In contrast, the proliferation of BaF3 cells that express gain-of-function ERBB4 mutants is sensitive to the irreversible pan-ERBB inhibitors neratinib, afatinib, and dacomitinib (Figure 5).

      • Mining the cBioPortal, AACR GENIE, and COSMIC datasets indicates that the three most potent ERBB4 gain-of-function mutants (S303F, E452K, and L798R) exhibit tissue specificity (Supplementary Figure S5). Moreover, the S303F mutation is coincident with a mutation in another ERBB receptor to a much lesser degree than other gain-of-function ERBB4 mutants, particularly E452K. This too is suggestive of differences in the mechanism of action among the gain-of-function ERBB4 mutants (Supplementary Figure S5).

      • To test the effect of ERBB4 gain-of-function mutants on resistance to EGFR inhibitors, PC-9 NSCLC cells (which contain an endogenous gain-of-function EGFR mutant but do not endogenously express ERBB4) were transduced with ERBB4 gain-of-function mutants. In these cells the S303F and L715K mutants exhibited elevated ERBB4 signaling, but the L798R and K935I mutants did not. Nonetheless, the S303F, E715K, and K935I mutants promoted osimertinib resistance upon long-term treatment in vitro, whereas the L798R mutant did not (Figure 6). Moreover, the E715K and S303F mutants caused osimertinib resistance in vivo.

      • Overall, this is an impressive body of work. The experiments have been carefully performed and the data are clearly presented. However, the breadth of this work makes it a bit unfocused and difficult to digest.

      The authors wish to thank the reviewer for the positive statement.

      Major Issues Affecting the Conclusions

      The COS-7 data in Figure 4 are probably generated using supraphysiological levels of ERBB4 expression, raising concerns about the ability to draw general conclusions from these data. This issue should be addressed.

      We appreciate the reviewer's insight on the details concerning experimentation in COS-7 cells. We acknowledge the drawbacks in experiments performed using transient overexpression of proteins in COS-7 cells using vectors with strong viral promoters. To mitigate these drawbacks, we routinely perform transient overexpression in COS-7 cells using the retroviral pBABE-vectors, which have a weak promoter and produce relatively moderate protein expression level. We have included here a reviewer-only figure (Reviewer-only Figure 2) that demonstrates the ERBB4 expression level derived from the pBABE-vector, compared to endogenous expression level of ERBB4 in T47D and MCF7 cells, as well as to ERBB4 expression derived from pcDNA3.1 vector that harbors a strong viral CMV promoter. With this, we hope to convince the reviewer that the ERBB4 expression levels in our COS-7 cell experiments are not supraphysiological.

      Reviewer-only Figure 2. The expression level of ERBB4 in T47D and MCF7 cells, as well as in COS-7 cells transiently transfected with equal amounts of pBABE-puro-gateway-ERBB4JM-aCYT-2 plasmid, or pcDNA3.1.-ERBB4JM-aCYT-2 plasmid.

      The inhibitor data shown in Figure 5 may be over-interpreted. The affinity of neratinib, afatinib, and dacomitinib for EGFR is reportedly higher than the affinity of these drugs for ERBB4. Thus, the failure of ERBB4 gain-of-function mutants to cause resistance to these inhibitors may be because the inhibitors bind to endogenous EGFR and therefore fail to bind to ERBB4.

      We thank the reviewer for the insightful comments. The experiments in Figure 5 were performed in Ba/F3 cells, which do not express endogenous EGFR, or other kinase competent ERBB receptors (Riese et al., 1995). Therefore, it is unlikely that the observed cellular responses to neratinib, afatinib, or dacomitinib are affected by the drugs' preferable binding to EGFR.

      Moreover, the conclusion that the gain-of-function ERBB4 mutants are targetable with these inhibitors appears to be an overreach.

      We have revised our conclusion into that ERBB4 mutants are "sensitive to" these inhibitors, as supported by our data in Figure 5. This revision has been made in the abstract (page 2), introduction section (page 4), results section (page 23), and in the discussion (page 31) of the revised manuscript.

      The inhibitor data shown in Figure 6 demonstrates that activating ERBB4 mutations are sufficient to drive inhibitor resistance. However, these data do not demonstrate that the mutations are necessary to drive inhibitor resistance. Thus, these data are of less value than represented in this work. Knockout or silencing (CRISPR or siRNA) experiments would be more definitive.

      We agree with the reviewer that performing knock-out or silencing experiments to demonstrate the necessity of mutant ERBB4 for inhibitor resistance would strengthen the conclusions. However, the PC-9 cells (or any other EGFR-mutant NSCLC cell lines) do not express endogenous ERBB4, and do not have endogenous ERBB4 mutations. Therefore, knock-out or silencing experiments are unfortunately not possible in this setting.

      Minor Issues That Can Confidently Be Addressed

      In Figure 2, the MCF10A data are more compelling than the BaF3 data. Thus, an argument can be made that the BaF3 data belong in a supplemental figure. However, the combination of data from both cell lines illustrate the fact that ERBB4 mutants appear to exhibit cell type specificity. If this point is emphasized in the text, then Figure 2 should remain as currently presented.

      We agree with the reviewer that our data suggest that the ERBB4 mutants demonstrate a level of context-specificity. This was mentioned in the results section of the original submitted manuscript (page 20; page 21 of the revised manuscript) as well as discussed in the discussion section (page 29; page 29 of the revised manuscript). To emphasize this further, we have revised our conclusions at the end of the "Majority of the recurrent ERBB4 mutations are transforming in Ba/F3 or MCF10a cells" -section as follows:

      "Taken together, these analyses indicate a potential oncogenic role for 11 recurrent ERBB4 mutations. Eight of the mutations were transforming in only one of the models used, suggesting context-specificity. Three mutants (S303F, E452K and L798R) were strongly transforming with the ability to transform both cell models, S303F being unique in its ability to transform both models in the absence of NRG-1."

      The modeling data shown in Figure 3 are a bit under-interpreted. It would appear that the S303F, E452K, and L798R mutants would cause increased ERBB4 signaling by (1) shifting the equilibrium of ERBB4 monomers between the tethered (inactive) state and the extended (active) state or by (2) directly fostering receptor dimerization. The modeling data should be interpreted in the context of these two paradigms.

      We thank the reviewer again for an insightful observation. We have now revised the text describing the modeling data based on the reviewer's suggestions (please see the revised manuscript, under "Structural analysis of the transforming ERBB4 mutations").

      The mechanistic data shown in Figure 4 are also a bit under-interpreted. The data from Figure 2 suggest that ERBB4 gain-of-function mutants are more likely to promote ERBB4 heterodimerization than ERBB4 homodimerization. Do the data from Figure 4 support this hypothesis?

      The authors agree with the reviewer in that the activating ERBB4 mutations lead to increased activation of other ERBB family members (Fig. 4A), supporting a hypothesis that activating ERBB4 mutations lead to increased heterodimerization. We have discussed this throughout the original submitted manuscript, for example making these conclusions:

      Results section, page 16 (page 18 of the revised manuscript): "In summary, these data indicate that S303F, E452K and L798R are activating, gain-of-function ERBB4 mutations that may co-operate with other ERBB receptors in malignant transformation.", page 19 (page 20 of the revised manuscript): "Together, these data suggest that while ERBB4 can be transforming in the absence of other ERBB receptors, mutant ERBB4 co-operates with ERBB3 to promote ligand-independent cell transformation.".

      Discussion section, page 30 (page 31 of the revised manuscript: "Together, these findings imply that ERBB4 heterodimers with other ERBB receptors can contribute to cell transformation and growth, supporting the rationale for pan-ERBB inhibition approach in targeting mutant ERBB4 in cancer."

      Reviewer #3 (Significance (Required)):

      General Assessment: Strengths and Limitations

      • This work makes a significant contribution to the hypothesis that ERBB4 gain-of-function mutants drive multiple human malignancies. However, this work dances around two issues. (1) Is heterodimerization of EGFR or ERBB2 with ERBB4 required for the transforming activity of these ERBB4 mutants? (2) Are these ERBB4 mutants found in the context of the JM-a/CYT-2 isoform or some other isoform? Are these ERBB4 mutants active in the context of isoforms other than JM-a/CYT-2?

      We thank the reviewer for the very positive assessment and insight on specific ERBB4 biology that could affect the functional effect of mutations in ERBB4. We would like to comment on these insights:

      1) Since the strongly transforming ERBB mutations all promoted the activation of EGFR, ERBB2, and ERBB3 (Fig. 4A), it is possible that heterodimerization plays a role in the transforming activity of these ERBB4 mutants. However, our data suggests that EGFR and ERBB2 are not necessary for transformation, since the Ba/F3 cells, where transformation by ERBB4 mutants was observed (Fig. 2D), do not express EGFR or ERBB2. We did see a consistent upregulation of endogenous ERBB3 upon IL3 deprivation in the ERBB4 S303F -expressing Ba/F3 cells (Fig. 4B), which contributed to the ERBB4 S303F -driven, IL3-independent transformation (Supplementary Fig. S3C-D).

      2) None of the analyzed ERBB4 mutations are located in the JM- or CYT-regions of ERBB4, and thus could hypothetically be expressed in the context of any of the four ERBB4 isoforms. However, cancer tissues almost exclusively express the JM-a isoforms of ERBB4, with roughly similar ratios of CYT-1 and CYT-2 isoforms. We chose to use the JM-a CYT-2 isoform in this study, based on our previous work that has implicated the JM-a CYT-2 isoform as being more oncogenic than JM-a CYT-1 isoform, as elaborated in the original submitted manuscript: "The ERBB4 JM-a CYT-2 isoform was used in the studies based on previous findings suggesting that JM-a CYT-2 is the more oncogenic ERBB4 isoform of the cancer-associated isoforms (Veikkolainen et al., 2011) in hematopoietic cell contexts (relevant for the Ba/F3 cell model) (Määttä et al., 2006; Chakroborty et al., 2022)". We do agree with the reviewer that future studies should determine the relative contribution of JM-a CYT-1 and JM-a CYT-2 isoforms in the ability of mutant ERBB4 to drive cancer growth.

      Advance: How Does This Work Advance the Field

      • This work will undoubtedly reinvigorate the ERBB4 field.

      Audience:

      • Those with an interest in the role that ERBB receptors play in human tumors.

      My Expertise:

      • 30+ years of experience studying ERBB receptors.

      REFERENCES

      Albert, V. et al. (2024) 'HER4 Affects Sensitivity to Tamoxifen and Abemaciclib in Luminal Breast Cancer Cells and Restricts Tumor Growth in MCF-7-Based Humanized Tumor Mice', International Journal of Molecular Sciences. Multidisciplinary Digital Publishing Institute, 25(13), p. 7475. doi: 10.3390/ijms25137475.

      Arribas, A. J. et al. (2024) 'ERBB4-mediated signaling is a mediator of resistance to BTK and PI3K inhibitors in B cell lymphoid neoplasms', Molecular Cancer Therapeutics, 23(3), pp. 368-380. doi: https://doi.org/10.1158/1535-7163.MCT-23-0068.

      Bose, R. et al. (2013) 'Activating HER2 mutations in HER2 gene amplification negative breast cancer', Cancer Discovery, 3(2), pp. 224-237. doi: 10.1158/2159-8290.CD-12-0349.

      Bouyain, S. et al. (2005) 'The extracellular region of ErbB4 adopts a tethered conformation in the absence of ligand', Proceedings of the National Academy of Sciences. National Academy of Sciences, 102(42), pp. 15024-15029. doi: 10.1073/pnas.0507591102.

      Canfield, K. et al. (2015) 'Receptor tyrosine kinase ERBB4 mediates acquired resistance to ERBB2 inhibitors in breast cancer cells', Cell Cycle. Taylor & Francis, 14(4), pp. 648-655. doi: 10.4161/15384101.2014.994966.

      Carrión-Salip, D. et al. (2012) 'Androgen-independent prostate cancer cells circumvent EGFR inhibition by overexpression of alternative HER receptors and ligands', International Journal of Oncology. Int J Oncol, 41(3), pp. 1128-1138. doi: 10.3892/ijo.2012.1509.

      Chakroborty, D. et al. (2022) 'An Unbiased Functional Genetics Screen Identifies Rare Activating ERBB4 Mutations', Cancer Research Communications, 2(1), pp. 10-27. doi: 10.1158/2767-9764.crc-21-0021.

      Cremolini, C. et al. (2019) 'Benefit from anti-EGFRs in RAS and BRAF wild-type metastatic transverse colon cancer: A clinical and molecular proof of concept study', ESMO Open, 4(2), p. e000489. doi: 10.1136/esmoopen-2019-000489.

      Debets, D. O. et al. (2023) 'Deep (phospho)proteomics profiling of pre- treatment needle biopsies identifies signatures of treatment resistance in HER2+ breast cancer', Cell Reports Medicine. Elsevier, 4(10), p. 101203. doi: 10.1016/j.xcrm.2023.101203.

      Donoghue, J. F. et al. (2018) 'Activation of ERBB4 in glioblastoma can contribute to increased tumorigenicity and influence therapeutic response', Cancers. Multidisciplinary Digital Publishing Institute (MDPI), 10(8), p. 243. doi: 10.3390/cancers10080243.

      Ferguson, K. M. et al. (2003) 'EGF Activates Its Receptor by Removing Interactions that Autoinhibit Ectodomain Dimerization', Molecular Cell, 11(2), pp. 507-517. doi: 10.1016/S1097-2765(03)00047-9.

      Greulich, H. et al. (2005) 'Oncogenic Transformation by Inhibitor-Sensitive and -Resistant EGFR Mutants', PLOS Medicine. Public Library of Science, 2(11), p. e313. doi: 10.1371/JOURNAL.PMED.0020313.

      Greulich, H. et al. (2012) 'Functional analysis of receptor tyrosine kinase mutations in lung cancer identifies oncogenic extracellular domain mutations of ERBB2', Proceedings of the National Academy of Sciences. National Academy of Sciences, 109(36), pp. 14476-14481. doi: 10.1073/pnas.1203201109.

      Hyman, D. M. et al. (2018) 'HER kinase inhibition in patients with HER2-and HER3-mutant cancers', Nature. Nature Publishing Group, 554(7691), pp. 189-194. doi: 10.1038/nature25475.

      Jaiswal, B. S. S. et al. (2013) 'Oncogenic ERBB3 Mutations in Human Cancers', Cancer Cell, 23(5), pp. 603-617. doi: 10.1016/j.ccr.2013.04.012.

      Jänne, P. A. et al. (2022) 'Efficacy and Safety of Patritumab Deruxtecan (HER3-DXd) in EGFR Inhibitor- Resistant, EGFR-Mutated Non-Small Cell Lung Cancer', Cancer Discovery. American Association for Cancer Research, 12(1), pp. 74-89. doi: 10.1158/2159-8290.CD-21-0715.

      Kurppa, K. J. et al. (2016) 'Activating ERBB4 mutations in non-small cell lung cancer', Oncogene. Nature Publishing Group, 35(10), pp. 1283-1291. doi: 10.1038/onc.2015.185.

      Lee, J. C. et al. (2006) 'Epidermal Growth Factor Receptor Activation in Glioblastoma through Novel Missense Mutations in the Extracellular Domain', PLoS Medicine | www, 3. doi: 10.1371/journal.

      Liu, P. et al. (2012) 'A single ligand is sufficient to activate EGFR dimers', Proceedings of the National Academy of Sciences, 109(27), pp. 10861-10866. doi: 10.1073/pnas.1201114109.

      Määttä, J. A. et al. (2006) 'Proteolytic cleavage and phosphorylation of a tumor-associated ErbB4 isoform promote ligand-independent survival and cancer cell growth', Molecular Biology of the Cell, 17(1), pp. 67-79. doi: 10.1091/mbc.E05-05-0402.

      Mendoza-Naranjo, A. et al. (2013) 'ERBB4 confers metastatic capacity in Ewing sarcoma', EMBO Molecular Medicine. Nature Publishing Group, 5(7), pp. 1019-1034. doi: 10.1002/emmm.201202343.

      Merimsky, O. et al. (2001) 'Correlation between c-erbB-4 receptor expression and response to gemcitabine-cisplatin chemotherapy in non-small-cell lung cancer', Annals of Oncology. Ann Oncol, 12(8), pp. 1127-1131. doi: 10.1023/A:1011665216616.

      Merimsky, O. et al. (2002) 'ErbB-4 expression in limb soft-tissue sarcoma: Correlation with the results of neoadjuvant chemotherapy', European Journal of Cancer. Eur J Cancer, 38(10), pp. 1335-1342. doi: 10.1016/S0959-8049(02)00075-8.

      Nafi, S. N. M. et al. (2014) 'Nuclear HER4 mediates acquired resistance to trastuzumab and is associated with poor outcome in HER2 positive breast cancer', Oncotarget. Impact Journals, LLC, 5(15), pp. 5934-5949. doi: 10.18632/oncotarget.1904.

      Nakamura, Y. et al. (2016) 'Afatinib against esophageal or head-and-neck squamous cell carcinoma: Significance of activating oncogenic HER4 mutations in HNSCC', Molecular Cancer Therapeutics. American Association for Cancer Research, 15(8), pp. 1988-1997. doi: 10.1158/1535-7163.MCT-15-0737.

      Prickett, T. D. et al. (2009) 'Analysis of the tyrosine kinome in melanoma reveals recurrent mutations in ERBB4.', Nature genetics, 41(10), pp. 1127-1132. doi: 10.1038/ng.438.

      Riese, D. J. et al. (1995) 'The cellular response to neuregulins is governed by complex interactions of the erbB receptor family', Molecular and Cellular Biology, 15(10), pp. 5770-5776. doi: 10.1128/mcb.15.10.5770.

      Saglam, O. et al. (2017) 'ERBB4 Expression in Ovarian Serous Carcinoma Resistant to Platinum-Based Therapy', Cancer control. NIH Public Access, 24(1), p. 89. doi: 10.1177/107327481702400115.

      Shi, J. et al. (2018) 'The HER4-YAP1 axis promotes trastuzumab resistance in HER2-positive gastric cancer by inducing epithelial and mesenchymal transition', Oncogene, 37(22), pp. 3022-3038. doi: 10.1038/s41388-018-0204-5.

      Tvorogov, D. et al. (2009) 'Somatic mutations of ErbB4: Selective loss-of-function phenotype affecting signal transduction pathways in cancer', Journal of Biological Chemistry, 284(9), pp. 5582-5591. doi: 10.1074/jbc.M805438200.

      Udagawa, H. et al. (2023) 'HER4 and EGFR Activate Cell Signaling in NRG1 Fusion-Driven Cancers: Implications for HER2-HER3-specific Versus Pan-HER Targeting Strategies', Journal of Thoracic Oncology. Elsevier Inc, 19(1), pp. 106-118. doi: 10.1016/j.jtho.2023.08.034.

      Veikkolainen, V. et al. (2011) 'Function of ERBB4 is determined by alternative splicing', Cell Cycle, 10(16), pp. 2647-2657. doi: 10.4161/cc.10.16.17194.

      Vokes, N. I. et al. (2022) 'Concurrent TP53 mutations facilitate resistance evolution in EGFR mutant lung adenocarcinoma', Journal of Thoracic Oncology. International Association for the Study of Lung Cancer, 17(6), pp. 779-792. doi: 10.1016/j.jtho.2022.02.011.

      Wang, D. S. et al. (2019) 'Liquid biopsies to track trastuzumab resistance in metastatic HER2-positive gastric cancer', Gut. BMJ Publishing Group, 68(7), pp. 1152-1161. doi: 10.1136/gutjnl-2018-316522.

      Wege, A. K. et al. (2018) 'HER4 expression in estrogen receptor-positive breast cancer is associated with decreased sensitivity to tamoxifen treatment and reduced overall survival of postmenopausal women', Breast Cancer Research. Breast Cancer Res, 20(1). doi: 10.1186/s13058-018-1072-1.

      Wilson, T. R. et al. (2012) 'Widespread potential for growth-factor-driven resistance to anticancer kinase inhibitors', Nature. Nature Publishing Group, 487(7408), pp. 505-509. doi: 10.1038/nature11249.

      Yaeger, R. et al. (2023) 'Molecular Characterization of Acquired Resistance to KRASG12C-EGFR Inhibition in Colorectal Cancer', Cancer Discovery, 13(1), pp. 41-55. doi: 10.1158/2159-8290.CD-22-0405.

      Yonesaka, K. et al. (2015) 'The pan-HER family tyrosine kinase inhibitor afatinib overcomes HER3 ligand heregulin-mediated resistance to EGFR inhibitors in non-small cell lung cancer.', Oncotarget. Oncotarget, 6(32), pp. 33602-11. doi: 10.18632/oncotarget.5286.

      Yuan, S. Q. et al. (2023) 'Residual circulating tumor DNA after adjuvant chemotherapy effectively predicts recurrence of stage II-III gastric cancer', Cancer Communications. John Wiley & Sons, Ltd, 43(12), pp. 1312-1325. doi: 10.1002/cac2.12494.

      Zhang, J. et al. (2023) 'Tracking of trastuzumab resistance in patients with HER2-positive metastatic gastric cancer by CTC liquid biopsy.', American journal of cancer research. e-Century Publishing Corporation, 13(11), pp. 5684-5697. Available at: http://www.ncbi.nlm.nih.gov/pubmed/38058840 (Accessed: 16 April 2024).

    2. Note: This preprint has been reviewed by subject experts for Review Commons. Content has not been altered except for formatting.

      Learn more at Review Commons


      Referee #3

      Evidence, reproducibility and clarity

      Summary

      • This work has mined cBioPortal to identify candidate cancer driver mutations in the gene encoding the ERBB4 receptor tyrosine kinase (Figure 1). These ERBB4 mutations occurred in clusters that are paralogous to activating mutations in other ERBB receptor genes or in clusters predicted to serve as dimerization interfaces of ERBB4. Eighteen such ERBB4 mutations were selected for characterization.
      • These mutants were tested in BaF3 and MCF-10A cells in the context of the ERBB4 JM-a CYT-2 isoform (Figure 2). Several of these ERBB4 mutants exhibited greater agonist-dependent coupling to cell proliferation than wild-type ERBB4. Moreover, some of the mutants exhibited greater agonist-independent coupling to cell proliferation than wild-type ERBB4. Five ERBB4 mutants (S303F, E452K, L798R, R992C, S1289A) exhibited greater activity in the BaF3 cells, whereas nine ERBB4 mutants (S303F, R393W, E452K, R544W, R711C, S774G, L798R, V840I, G870R) exhibited greater activity in the MCF10A cells. Thus, eleven of the ERBB4 mutants (S303F, R393W, E452K, R544W, R711C, S774G, L798R, V840I, G870R, R992C, S1289A) exhibited a gain-of-function phenotype. It should be noted that several of the ERBB4 gain-of-function mutants (R393W, R544W, R711C, V840I, G870R, R992C, S1289A) exhibited cell type specificity.
      • PyMol was used to "model" the effect of the most potent (S303F, E452K, and L798R) gain-of-function mutations on the structure of ERBB4 (Figure 3). These three mutations are predicted to cause increased ERBB4 dimerization.
      • When expressed in MCF-10A cells, the most potent (S303F, E452K, and L798R) gain-of-function ERBB4 mutants exhibited elevated ligand-dependent and ligand-independent tyrosine phosphorylation. This was accompanied by elevated EGFR, ERBB2, and ERBB4 tyrosine phosphorylation and elevated signaling by canonical effector proteins (Figure 4).
      • The homo- and heterodimerization of the most potent ERBB4 mutant (S303F) was studied following transient transfection of COS-7 cells (Figure 4). As predicted, the S303F mutant exhibited greater ERBB4 homodimerization and greater heterodimerization with EGFR and ERBB2, but not with ERBB3.
      • The data from the clinical trial NCT01953926 was mined to evaluate whether the presence of an ERBB4 activating mutation found in this work is associated with sensitivity to the pan-ERBB inhibitor neratinib (Table 1). Surprisingly, a compelling association was NOT found. In contrast, the proliferation of BaF3 cells that express gain-of-function ERBB4 mutants is sensitive to the irreversible pan-ERBB inhibitors neratinib, afatinib, and dacomitinib (Figure 5).
      • Mining the cBioPortal, AACR GENIE, and COSMIC datasets indicates that the three most potent ERBB4 gain-of-function mutants (S303F, E452K, and L798R) exhibit tissue specificity (Supplementary Figure S5). Moreover, the S303F mutation is coincident with a mutation in another ERBB receptor to a much lesser degree than other gain-of-function ERBB4 mutants, particularly E452K. This too is suggestive of differences in the mechanism of action among the gain-of-function ERBB4 mutants (Supplementary Figure S5).
      • To test the effect of ERBB4 gain-of-function mutants on resistance to EGFR inhibitors, PC-9 NSCLC cells (which contain an endogenous gain-of-function EGFR mutant but do not endogenously express ERBB4) were transduced with ERBB4 gain-of-function mutants. In these cells the S303F and L715K mutants exhibited elevated ERBB4 signaling, but the L798R and K935I mutants did not. Nonetheless, the S303F, E715K, and K935I mutants promoted osimertinib resistance upon long-term treatment in vitro, whereas the L798R mutant did not (Figure 6). Moreover, the E715K and S303F mutants caused osimertinib resistance in vivo.
      • Overall, this is an impressive body of work. The experiments have been carefully performed and the data are clearly presented. However, the breadth of this work makes it a bit unfocused and difficult to digest.

      Major Issues Affecting the Conclusions

      • The COS-7 data in Figure 4 are probably generated using supraphysiological levels of ERBB4 expression, raising concerns about the ability to draw general conclusions from these data. This issue should be addressed.
      • The inhibitor data shown in Figure 5 may be over-interpreted. The affinity of neratinib, afatinib, and dacomitinib for EGFR is reportedly higher than the affinity of these drugs for ERBB4. Thus, the failure of ERBB4 gain-of-function mutants to cause resistance to these inhibitors may be because the inhibitors bind to endogenous EGFR and therefore fail to bind to ERBB4. Moreover, the conclusion that the gain-of-function ERBB4 mutants are targetable with these inhibitors appears to be an overreach.
      • The inhibitor data shown in Figure 6 demonstrates that activating ERBB4 mutations are sufficient to drive inhibitor resistance. However, these data do not demonstrate that the mutations are necessary to drive inhibitor resistance. Thus, these data are of less value than represented in this work. Knockout or silencing (CRISPR or siRNA) experiments would be more definitive.

      Minor Issues That Can Confidently Be Addressed

      • In Figure 2, the MCF10A data are more compelling than the BaF3 data. Thus, an argument can be made that the BaF3 data belong in a supplemental figure. However, the combination of data from both cell lines illustrate the fact that ERBB4 mutants appear to exhibit cell type specificity. If this point is emphasized in the text, then Figure 2 should remain as currently presented.
      • The modeling data shown in Figure 3 are a bit under-interpreted. It would appear that the S303F, E452K, and L798R mutants would cause increased ERBB4 signaling by (1) shifting the equilibrium of ERBB4 monomers between the tethered (inactive) state and the extended (active) state or by (2) directly fostering receptor dimerization. The modeling data should be interpreted in the context of these two paradigms.
      • The mechanistic data shown in Figure 4 are also a bit under-interpreted. The data from Figure 2 suggest that ERBB4 gain-of-function mutants are more likely to promote ERBB4 heterodimerization than ERBB4 homodimerization. Do the data from Figure 4 support this hypothesis?

      Significance

      General Assessment: Strengths and Limitations

      This work makes a significant contribution to the hypothesis that ERBB4 gain-of-function mutants drive multiple human malignancies. However, this work dances around two issues. (1) Is heterodimerization of EGFR or ERBB2 with ERBB4 required for the transforming activity of these ERBB4 mutants? (2) Are these ERBB4 mutants found in the context of the JM-a/CYT-2 isoform or some other isoform? Are these ERBB4 mutants active in the context of isoforms other than JM-a/CYT-2?

      Advance: How Does This Work Advance the Field

      This work will undoubtedly reinvigorate the ERBB4 field.

      Audience:

      Those with an interest in the role that ERBB receptors play in human tumors.

      My Expertise:

      30+ years of experience studying ERBB receptors.

    3. Note: This preprint has been reviewed by subject experts for Review Commons. Content has not been altered except for formatting.

      Learn more at Review Commons


      Referee #1

      Evidence, reproducibility and clarity

      Summary: The authors identify cancer-associated ERBB4 mutations that are selected for functional characterization. Utilizing the BaF3 and MCF10A models, the authors investigate the potential oncogenic role for 11 recurrent ERBB4 mutations. Three mutants (S303F, E452K and L798R) were strongly transforming with the ability to transform both cell models, S303F being unique in its ability to transform both models in the absence of NRG-1. The authors perform modeling to decipher potential mechanisms of action of the ERBB4 S303F, E452K and L798R mutations. The authors assess the ability of HER3 mutations to dimerize with other HER family members and demonstrate that ERBB4 S303F can mediate its activating functions by stabilizing homo- and heterodimers with other ERBB receptors and that the heterodimerization is likely cell/tissue context dependent. The authors demonstrate that transforming ERBB4 mutants are sensitive to pan-ERBB inhibitors and drive resistance to EGFR-targeted therapy in EGFR-mutant NSCLC cells.

      Major comments:

      1. Patient data analysis is performed in more than 15 months ago in January 2024. This analysis should be updated.
      2. The rationale for selecting the mutations to be studied is not entirely clear. There are no references to support studying mutations in Fig 1B red boxes.
      3. Cell proliferation should be shown for BaF3 cells for continuity in Figure 2 instead of doubling time. The relative expression of HER3 constructs must be shown for BaF3 and MCF10A cells in Figure 2.
      4. Blots in Figure 4 must be quantified.
      5. There are major concerns with Supplemental files. It is imperative that the effectiveness of HER3 shRNA be shown in S Fig3. These data are not interpretable without this. Lanes in S Fig 4 are not marked again making data not interpretable.
      6. It's unclear why Table 1 is included as this is already published data. This previously published data should be summarized in the text.
      7. There is a disconnect why the last two figures focus on a single model of NSCLC whereas the three most transforming mutations are found most commonly in breast, melanoma and GI tract cancers.
      8. What are the differences in the recurrent ERBB4 mutant tumors versus ERBB4 wild-type tumors described in Figure 7? Figure 7C, D should be moved to supplemental as this is from previously published data and not strictly relevant to data shown in Fig 7.
      9. Limitations should include consideration of endogenous levels of ERBB4 in the model systems used and disparate expression levels of wt ERBB4 versus ERBB4 mutation.

      Minor comments:

      1. Fig1B lists ERBB3 V104V mutation?
      2. List frequency of ERBB4 mutations in the introduction
      3. Clarification throughout if cells are serum-starved (how long) if stimulated with NRG-1

      Significance

      General assessment: This work fills a gap in cancer research understanding if ERBB4 mutations could be targeted. Concerns and comments need to be addressed before definitive conclusions can be made.

    1. Synthèse détaillée des thèmes et faits marquants de la présentation de Valérie Masson-Delmotte

      • Cette synthèse reprend les points essentiels de l'intervention de Valérie Masson-Delmotte sur les attaques contre les sciences du climat et de la durabilité, en contextualisant ces attaques par rapport aux faits scientifiques établis et en explorant les liens avec la vie démocratique et l'action climatique.

      I. Les attaques contre les sciences du climat et de la durabilité : Une nouvelle phase d'obstruction systémique

      • Valérie Masson-Delmotte introduit son intervention en situant sa propre expérience de recherche, notamment sur la géoingénierie polaire, comme une "distraction ou une diversion coûteuse" qui s'inscrit dans un contexte plus large d'attaques.

      Elle décrit une "nouvelle phase" dans les politiques favorables aux énergies fossiles, caractérisée non plus par un simple "rideau de fumée" de désinformation, mais par une "obstruction tous azimuts".

      A. Le Projet 2025 et ses objectifs

      Cette nouvelle phase, pensée par le Projet 2025, est motivée par la clarté des connaissances scientifiques et la capacité croissante à répondre aux besoins humains sans énergies fossiles.

      L'objectif est de "détruire la capacité à produire ces faits scientifiques".

      Les actions concrètes de l'administration Trump (si elle était réélue, nommée "Trump 2" dans le texte) incluent :

      • Affirmation d'une "urgence énergétique" et obstruction à la transition énergétique.
      • Suppression des étiquettes énergie des politiques favorables aux énergies fossiles.
      • Arrêt du plan Biden Inflation Reduction Act, favorable aux technologies propres.
      • Destruction des "pierres angulaires du droit de l'environnement", notamment le suivi des espèces menacées.
      • Ciblage de la décision de l'EPA (Endangerment Finding) classant les émissions de six gaz à effet de serre comme "dangereux pour le bien-être et la santé humaine".

      B. Méthodes d'intimidation et de démantèlement

      Les attaques se traduisent par :

      • Intimidation des organisations scientifiques, menaces de coupes budgétaires et leur réalisation.
      • Censure par mots clés et "licenciements massifs".
      • Suppression de contenu lié au changement climatique sur les sites ministériels.
      • Interdictions de formation intégrant les aspects liés au changement climatique.
      • Démantèlement de la capacité à produire des connaissances, notamment sur la santé environnementale à l'EPA.
      • Arrêt de financements de programmes de recherche sur le changement climatique et la santé pour le ministère de la Défense.
      • Sabotage de la capacité de suivi de l'état de l'atmosphère, entraînant la dégradation des prévisions météorologiques et la fermeture d'agences d'alerte.
      • Affaiblissement des capacités de suivi des lois environnementales (Endangered Species Act, Marine Mammal Protection Act).
      • Destruction de la capacité d'évaluation nationale sur le changement climatique (US Global Change Research Program).
      • Démantèlement de l'Office of Global Change au Département d'État, affectant la participation américaine aux instances internationales (IPCC).
      • Coupes budgétaires massives par mots clés (NSF, NOAA, NASA) visant à éliminer les laboratoires de recherche sur l'atmosphère, l'océan, l'Antarctique, et les instituts coopératifs.
      • Harcèlement (ex: arrêt du paiement du bail pour le laboratoire commun Columbia NASA).
      • Décimation des centres d'adaptation au changement climatique, d'information sur l'énergie et des centres sur les sciences de l'eau.
      • Volonté de démanteler l'agence de réponse rapide en cas de catastrophe.
      • Ciblage du suivi des émissions de gaz à effet de serre, des centres de modélisation et des aspects liés aux injustices environnementales.
      • Masson-Delmotte souligne l'interdiction explicite de mots clés tels que "atténuation", "gaz à effet de serre", "changement climatique", "science du climat", "risque climatique", "résilience", "justice environnementale", "pollution", "vulnérabilités", "evidence-based" et "science-based". Cette méthode, déjà observée sous Trump 1 à l'EPA, est désormais "généralisée", avec des leçons tirées pour une action "à une échelle plus large".

      II. Le constat scientifique, "trop clair" et "très clair"

      • La présentation met en lumière l'état actuel et l'évolution des indicateurs clés du système climatique, soulignant l'urgence et l'ampleur de l'influence humaine.

      *** A. Émissions et concentrations de gaz à effet de serre**

      • Émissions mondiales : Continuent d'augmenter, mais "moins vite sur la dernière décennie que précédemment". 24 pays ont réduit leurs émissions grâce à des politiques publiques efficaces.
      • Chine : Les émissions n'ont pas augmenté depuis environ un an, grâce à l'électrification des mobilités et le déploiement des énergies renouvelables.
      • Gaz à effet de serre fluorés : Baisse due à l'effet du Protocole de Montréal.
      • Composés soufrés : Leur réduction (effet refroidissant) contribue à dévoiler l'effet réchauffant des gaz à effet de serre.
      • Concentrations atmosphériques : Continuent d'augmenter, particulièrement vite pour le CO2 en 2023-2024, en partie à cause de l'effet El Niño qui a "fragilisé le puits de carbone terrestre". Le Global Carbon Project estime que l'effet climat a sapé "environ 27 % de l'augmentation du puits de carbone terrestre".
      • Forçage radiatif : L'influence humaine atteint environ "3 W par mètre carré", avec un rythme d'augmentation sur la dernière décennie "encore plus fort que la décennie précédente".

      B. Réchauffement climatique et ses conséquences

      • Déséquilibre énergétique de la Terre : A augmenté pour atteindre "1 W par mètre carré".
      • Réchauffement observé :
      • Moyenne planétaire : "1,24°C" sur la dernière décennie.
      • Océan : "1°C".
      • Continents : "environ 1,8°C".
      • Part attribuable aux activités humaines : "1,22°C" sur les 1,24°C observés.
      • Rythme de hausse : "0,27°C de plus par décennie".
      • Réchauffement attribuable à l'influence humaine (extrapolé) : "1,36°C plus chaud".
      • Dépassement des seuils : Atteindre "plus d'un degré et demi comme en 2024 pour la première fois, c'est une chance sur 6" ; avec El Niño et variabilité chaude Atlantique Nord, "c'est une chance sur deux".
      • Montée du niveau de la mer : "Quasiment 23 cm depuis 1900".

      Rythme sur les 10 dernières années : "plus de 4 mm par an" avec une accélération due à l'accumulation de chaleur dans l'océan et la contribution croissante du Groenland et de l'Antarctique.

      C. Attribution des responsabilités

      Les méthodes d'attribution, développées par Klaus Hasselman, "n'ont fait que s'affiner pour un constat qui est vraiment très clair maintenant".

      • Responsabilité historique par pays (depuis 1851) :
      • États-Unis : "premier responsable du réchauffement à ce jour".
      • Chine : "2e rang", devant l'Union européenne à 27.
      • Certaines analyses suggèrent que l'effort de décarbonation en Chine pourrait faire qu'elle "ne rattrape jamais le niveau de responsabilité des États-Unis".
      • Tensions géopolitiques : Les pays en développement estiment que l'Accord de Paris "remet à zéro" la responsabilité historique, tandis que les pays industrialisés et exportateurs d'énergies fossiles sont plus à l'aise avec cette approche.
      • Pays les moins développés : "6 % des de contribution au réchauffement historique", alors qu'ils sont "le milliard de personnes qui vit dans l'ensemble des pays les moins développés" et sont les plus vulnérables.
      • Responsabilité par catégorie de revenus (étude de 2024, incluant consommation et investissements) :
      • "2/3 du réchauffement est attribuable au top 10 %" des émetteurs mondiaux depuis 1990.
      • "1/5 au top 1 %" des émetteurs.
      • Si tout le monde avait le même train d'émissions que les 10 % les plus riches, le réchauffement aurait déjà été de "3 degrés au lieu de 0,6°C depuis 1990".
      • Le top 10 % contribue "6 et demi fois plus" que la moyenne planétaire par personne.
      • Les émissions du top 10 % en Chine ou aux États-Unis ont une responsabilité "deux à trois fois plus grande que la moyenne de la population mondiale sur l'augmentation des vagues de chaleur dans des régions particulièrement vulnérables".
      • Responsabilité des acteurs économiques : Application de la méthode d'attribution "end-to-end" (émission -> réchauffement -> événement extrême -> coût des dommages) aux "plus grandes supermajors pétrolières".
      • Les cinq plus grandes entreprises pétrolières et gazières mondiales sont responsables depuis 1991 d'"environ 2 000 milliards de dollars de pertes économiques uniquement liées à la chaleur extrême".
      • Ces constats "dérangent bien sûr" et posent la question de la "responsabilité par rapport aux pertes et dommages".
      • Droits des générations futures : L'exposition "sans précédent" aux extrêmes climatiques des jeunes générations. Pour les personnes nées en 2020 :
      • Si le réchauffement est limité à 1°C, "52 % de cette génération sera exposée de manière inédite".
      • Si le réchauffement atteint 3°C, "la quasi-totalité de cette génération" (plus de 90 %) sera exposée de manière inédite.
      • Ces connaissances scientifiques "très claires" peuvent "nourrir... des contentieux juridiques, des délibérations politiques" et sont perçues comme "hostiles" par certains acteurs économiques ou catégories de la population qui "tirent partie de la situation actuelle".

      III. Démocratie et action climatique : Des liens cruciaux et des défis

      Valérie Masson-Delmotte explore les liens entre la gouvernance démocratique et la capacité à mettre en œuvre une action climatique efficace, soulignant les vulnérabilités et les leviers d'action.

      A. Trajectoires socio-économiques et risques

      Le scénario de

      • "rivalité régionale",
      • "résurgence du nationalisme",
      • "préoccupation en matière de compétitivité sécurité",
      • "perte d'une vision plus large",
      • "baisse des investissements dans l'éducation et le développement technologique",
      • "développement économique lent",
      • "consommation à forte intensité matérielle",
      • "aggravation d'inégalité",
      • "faible priorité aux problèmes environnementaux",
      • "forte dégradation de l'environnement" (SSP3)

      est le scénario "à plus haut risque" pour l'atténuation et l'adaptation. * Il existe un "jeu d'acteur organisé puissant ancré dans le national conservatisme qui vise en fait à créer une bifurcation par rapport aux tendances récentes au focus mis sur la soutenabilité créer une bifcation vers ce type de trajectoire".

      B. Démocratie comme levier d'action climatique

      • Réduction des émissions : "24 pays qui l'ont déjà réduit les ont déjà réduites fortement dans la durée tous des démocraties".
      • Politiques publiques efficaces : Une étude comparant 1500 politiques publiques montre que "60 des 63 exemples de combinaison de politique publique efficace sont des pays qui ont des indices de démocratie parmi les plus élevés". Les exceptions sont l'Arabie Saoudite et la Chine.
      • Caractéristiques des démocraties efficaces : "Pluralisme, la liberté de la presse, le dynamisme de la société civile, contrôle de la corruption".
      • Capacités de transformation (selon le GIEC) : Vont de pair avec la capacité de "délibérer, de construire des transitions justes qui tiennent compte des inégalités des vulnérabilités des droits humains des enjeux de cohésion sociale", l'engagement des parties prenantes (y compris la jeunesse), le renforcement des processus délibératifs (assemblées citoyennes), des rôles clairs pour les pouvoirs publics, et un suivi et évaluation.

      C. Obstacles démocratiques à l'action climatique

      • Clientélisme et corruption : Le développement démocratique n'est associé à la réduction des émissions que dans les pays "qui ont un faible niveau de clientélisme et de corruption".
      • Rente des énergies fossiles : Les "effets de rente liés aux énergies fossiles sapent les institutions et la capacité à mettre en œuvre de manière efficace les lois et régulation environnementale". Les pays dépendants de l'extraction de pétrole et de gaz ont souvent des "difficultés de contrôle de la corruption" et maintiennent des "subventions élevées aux énergies fossiles".
      • Inégalités de revenus : Sapent la capacité à agir efficacement. Dans les pays les plus inégalitaires, les personnes à hauts revenus (très émettrices) "s'opposent au renforcement de la régulation environnementale" et leur opposition est renforcée par la possession de médias privés et le contrôle des réseaux sociaux.

      En conclusion, Valérie Masson-Delmotte souligne l'importance de "renouveler et vivifier la vie démocratique" face aux attaques des discours populistes et du contrôle de la désinformation.

      Le "renforcement des délibérations qui s'appuient sur les connaissances et les faits est pour moi un levier d'action critique par rapport à la défense de la capacité de délibération des sociétés démocratiques vis-à-vis du renforcement de l'action pour le climat".

    1. Note: This response was posted by the corresponding author to Review Commons. The content has not been altered except for formatting.

      Learn more at Review Commons


      Reply to the reviewers

      1. General Statements [optional]

      We thank the three reviewers for the time and caution taken to assess our manuscript, and for their constructive feedback that will help improve the study. We herewith provide a revision plan, expecting that the additional experiments and corrections will address the key points raised by the reviewers.

      2. Description of the planned revisions

      Insert here a point-by-point reply that explains what revisions, additional experimentations and analyses are planned to address the points raised by the referees.

      • *

      __Reviewer #1 (Evidence, reproducibility and clarity (Required)): __

      Summary: The manuscript by Delgado et al. reports the role of the actin remodeling Arp2/3 complex in the biology of Langerhans cells, which are specialized innate immune cells of the epidermis. The study is based on a conditional KO mouse model (CD11cCre;Arpc4fl/fl), in which the deletion of the Arp2/3 subunit ArpC4 is under the control of the myeloid cell specific CD11c promoter.

      In this model, the assembly of LC networks in the epidermis of ear and tail skin is preserved when examining animals immediately after birth (up to 1 week). Subsequently however LCs from ArpC4-deleted mice start displaying morphological aberrations (reduced elongation and number of branches at 4 weeks of age). Additionally, a profound decline in LC numbers is reported in the skin of both the ear and tail of young adult mice (8-10 weeks).

      To explore the cause of such decline, the authors then opt for the complementary in vitro study of bone-marrow derived DCs, given the lack of a model to study LCs in vitro. They report that ArpC4 deletion is associated with aberrantly shaped nuclei, decreased expression of the nucleoskeleton proteins Lamin A/C and B1, nuclear envelop ruptures and increased DNA damage as shown by γH2Ax staining. Importantly, they provide evidence that the defects evoked by ArpC4 deletion also occur in the LCs in situ (immunofluorescence of the skin in 4-week old mice).

      Increased DNA damage is further documented by staining differentiating DCs from ArpC4-deleted mice with the 53BP1 marker. In parallel, nuclear levels of DNA repair kinase ATR and recruitment of RPA70 (which recruits ATR to replicative forks) are reduced in the ArpC4-deleted condition. In vitro treatment of DCs with the topoisomerase II inhibitor etoposide and the Arp2/3 inhibitor CK666 induce comparable DNA damage, as well as multilobulated nuclei and DNA bridges. The authors conclude that the ArpC4-KO phenotype might stem, at least in part, from a defective ability to repair DNA damages occurring during cell division.

      The study in enriched by an RNA-seq analysis that points to an increased expression of genes linked to IFN signaling, which the authors hypothetically relate to overt activation of innate nucleic acid sensing pathways.

      The study ends by an examination of myeloid cell populations in ArpC4-KO mice beyond LCs. Skin cDC2 and cDC2 subsets display skin emigration defects (like LCs), but not numerical defects in the skin (unlike LCs). Myeloid cell subsets of the colon are also present in normal numbers. In the lungs, interstitial and alveolar macrophages are reduced, but not lung DC subsets. Collectively, these observations suggest that ArpC4 is essential for the maintenance of myeloid cell subsets that rely on cell division to colonize or to self-maintain within their tissue of residency (including LCs).

      MAJOR COMMENTS

      1. ArpC4 and Arp2/3 expression The authors argue that LCs from Arpc4KO mice should delete the Arpc4 gene in precursors that colonize the skin around birth. It would be important to show it to rule out the possibility that the lack of phenotype (initial seeding, initial proliferative burst) in young animals (first week) could be related to an incomplete deletion of ArpC4 expression. Also important would be to show what is happening to the Arp2/3 complex in LCs from Arpc4KO mice.

      __Response: __We thank this reviewer for the careful assessment of our manuscript. Regarding this specific comment, we would like to clarify that we do not expect ArpC4 to be deleted in LC precursors, as CD11c is only expressed once the cells have entered the epidermis. Instead, we expect the deletion to take place after birth around day 2-4 (Chorro et al., 2009). For this reason, we performed a deletion PCR of epidermal cells at postnatal day 7 (P7), a time at which the proliferative burst occurs. This analysis revealed CD11c-Cre-driven recombination in the ArpC4 locus (Fig. S2C). This experiment indicates that ArpC4 deletion does not alter LC proliferation and postnatal network formation.


      Revision plan: We will revise the manuscript text to more clearly explain when ArpC4 will be deleted during development when using the CD11c-Cre transgene, and better emphasize the rationale for the deletion PCR.

      In the in vitro studies with DCs, the level of ArpC4 and Arp2/3 deletion at the protein level is also not documented.


      __Response: __We have previously analyzed the expression of ArpC4 in BMDCs in a recent study, confirming its loss in CD11c-Cre;ArpC4fl/fl cells at the protein level: Rivera et al. Immunity 2022; doi: 10.1016/j.immuni.2021.11.008. PMID: 34910930 (Fig. S2D). Therefore, in the current manuscript we only refer to that paper (Results, first paragraph).

      The authors explain that surface expression of the CD11c marker, which drives Arpc4 deletion, gradually increased during differentiation of DCs: from 50% to 90% of the cells. Does that mean that loss of ArpC4 expression is only effective in a fraction of the cells examined before day 10 of differentiation (e.g. in the RNA-seq analysis)?

      __Response: __The reviewer is correct, there is heterogeneity in CD11c expression, which is inherent of these DC culture model, implying that Arpc4 gene deletion will be partial. However, despite this, we were able to detect significant differences between the transcriptomes of control and CD11c-Cre;ArpC4fl/fl DCs in early phases during differentiation, emphasizing that the phenotype of ArpC4 loss is robust.


      Revision Plan: We will include a notion on this heterogeneity in the revised manuscript text.

      Intra-nuclear versus extra-nuclear activities of Arp2/3

      The authors favor a model whereby intra-nuclear ArpC4 helps maintaining nuclear integrity during proliferation of DCs (and possibly LCs). However, multiple pools of Arp2/3 have been described and accordingly, multiple mechanisms may account for the observed phenotype: i) cytoplasmic pool to drive the protrusions sustaining the assembly of the LC network and its connectivity with keratinocytes ; ii) peri-nuclear pool to protect the nucleus ; iii) Intra-nuclear pool to facilite DNA repair mechanisms e.g. by stabilizing replicative forks (the scenario favored by the authors).


      __Response: __The referee is correct, and this is actually discussed in our manuscript (page 11, upper paragraph): we cannot exclude that several pools of branched actin are influencing the phenotype we here describe.

      Unfortunately, we have previously tested several antibodies against ArpC4, but in our hands, and despite comprehensive optimization, they did not yield specific signals that would enable us to assess changes in subcellular localization in murine cells. Upon this reviewer's comment, we will now reassess the available tools and found an antibody against ArpC2 (Millipore, Anti-p34-Arc/ARPC2, 07-227-I-100UG) that may work based on published data. We have ordered this product to test it for IF staining of ArpC2, hoping to be able to delineate the subcellular localization of ArpC2 in DCs and potentially LCs.

      Revision plan: Upon receipt, we will test the ArpC2 antibody (Millipore, #07-227-I-100UG) both in cultured DCs and in epidermal whole mounts, running various optimization protocols regarding fixation, permeabilization and blocking reagents, next to antibody dilution. That way we hope to be able to detect the subcellular localization of Arp2/3 complex components as requested by this reviewer.

      It is recommended that the authors try to gather more supportive data to sustain the intra-nuclear role. Documenting ArpC4 presence in the nucleus would help support the claim. It could be combined with treatments aiming at blocking proliferation in order to reinforce the possibility that a main function of ArpC4 is to protect proliferating cells by favoring DNA repair inside the nucleus.

      __Response: __We thank this reviewer for this very helpful comment. As outlined in the previous response, we will aim at obtaining subcellular localization data for Arp2/3 complex components, and along with that study a potential intranuclear localization. Beyond that, in comparison to commonly cultured cell types, however, we face two hurdles addressing the nuclear Arp2/3 role in full: 1) Due to poor transduction rates and epigenetic silencing, we cannot sufficiently express exogenous constructs such as ArpC4-NLS in DCs to assess the subcellular localization of Arp2/3 complex components. 2) We have performed preliminary tests to block proliferation in DCs, using the cyclin D kinase 1 inhibitor RO3306 at different concentrations and incubation times during DC differentiation. Unfortunately, most cells were found dead after treatment. Further lowering the inhibitor concentrations (below 3.5uM) will likely not block the cell cycle, rendering this approach unsuited.

      Revision plan: We will test the suitability of additional antibodies directed against Arp2/3 complex components to assess their subcellular localization, with the aim to discriminate peripheral cytoplasmic vs. perinuclear vs. intranuclear localization. In addition, we will add a comment in the discussion, further addressing this point. In the case we remain unable to pinpoint that Arp2/3 resides in the nucleus, we will further tone down our current phrasing in the discussion, also emphasizing the possibility that cytoplasmic or perinuclear pools of the complex may indirectly help maintain the integrity of the genome in LCs.

      Nuclear envelop ruptures

      The nuclear envelop ruptures are not sufficiently documented (how many cells were imaged? quantification?). The authors employ STED microscopy to examine Lamin B1 distribution. The image shown in Figure 4A does not really highlight the nuclear envelop, but rather the entire content. Whether it is representative is questionable. We would expect Lamin B1 staining intensity to be drastically reduced given the quantification shown in Figure 3D. In addition, although the authors have stressed in the previous figure that Arpc4-KO is associated with nucleus shape aberrations, the example shown in Figure 4A is that of a nucleus with a normal ovoid shape.

      It is recommended to quantify the ruptures with Lap2b antibodies (or another staining that would better delineate the envelop) in order to avoid the possible bias due to the reduced staining intensity of Lamin B1.

      __Response: __NE ruptures were quantified by imaging NLS-GFP-expressing DCs in microchannels to visualize leakage of their nuclear content (Fig. 4B,C). The STED image mentioned by the referee (Fig. 4A,D) was only shown to further illustrate examples of NE ruptures, here using Lamin B as an immunofluorescence marker for the NE. We do agree with the reviewer that it was not chosen optimally to represent the ArpC4-KO phenotype regarding nuclear shape and Lamin B1.

      Revision plan: We will provide representative examples of nuclear illustrations of the ArpC4-KO phenotype vs. control cells. In addition, we will perform STED microscopy of Lap2B immunostained DCs as suggested by the referee.

      A missing analysis is that of nuclear envelop ruptures as a function of nucleus deformations.

      __Response: __As stated in the manuscript (page 5, third paragraph), the morphology of DCs is quite heterogeneous. As mentioned above, nuclear rupture events were quantified by live-imaging of NLS-GFP expressing DCs, enabling the tracing of rupture events. Live imaging is the only robust manner to measure nuclear membrane rupture events as they are transient due to rapid membrane repair (Raab et al. Science 2016). The NLS-GFP label itself, however, is not accurate enough to also quantify nuclear deformations. The latter therefore was quantified after cell fixation, using DAPI and/or immunostaining for NE envelope markers (Figures 3 and S3).

      Revision plan: We will quantify nuclear deformations using Lap2B staining of the nuclear envelope as suggested by the referee.

      Fig 4B-C: same frequency of Arpc4-KO and WT cells displaying nuclear envelop ruptures in the 4-µm channels; however image show a rupture for the Arpc4-KO and no rupture for the WT cells (this is somehow misleading). Are ruptures similar in Arpc4-KO and WT cells in this condition?

      __Response: __We apologize for choosing an image that better reflects our quantification, our mistake.

      Revision plan: We will choose an image that better reflects our quantification.

      Fig 4D-E: is their a direct link between nuclear envelop ruptures and ƴH2A.X?

      __Response: __At present, we can only correlate the findings of increased gH2Ax and elevated events of nuclear envelope ruptures in ArpC4-KO DCs. Rescue experiments are very difficult to impossible in DCs (e.g. restoring Lamin A/C and B levels in the KOs and subsequently assessing the amount of DNA damage). While we are afraid that we cannot address a potential link between NE ruptures and DNA damage by experiments in a manner feasible within this manuscript's revision, we have discussed this interesting aspect based on observations in immortalized cell culture systems (page 10). However, we would like to note that this was indeed shown for different cell types in Nader et al. Cell 2021. This effect results from access of cytosolic nuclease Trex1 to nuclear DNA.

      Revision plan: This point will be clarified in our revised manuscript.


      Interesting (but optional) would be to understand what is happening to DNA, histones? Is their evidence for leakage in the cytoplasm?

      __Response: __We have not investigated so far. We will attempt to do so.

      Revision plan: To address this aspect, we plan to perform immunostainings for double-stranded DNA in the cytoplasm (along with an NE marker). This approach has been used in the field to mark cytoplasmic DNA.

      RNA seq analysis

      The RNA-seq analysis suffers from a lack of direct connection with the rest of the study. The extracted molecular information is not validated nor further explored. It remains very descriptive. The PCA analysis suggests a « more pronounced transcriptomic heterogeneity in differentiating Arpc4KO DCs ». However it seems difficult to make such a claim from the comparison of 3 mice per group. In addition, such heterogeneity is not seen in the more detailed analysis (Fig 5F). The authors claim that « day 10 control and Arpc4KO DCs showed no to very little differences in gene expression, in contrast to cells at days 7-9 of differentiation ». This is not obvious from the data displayed in the corresponding figure. In addition, it is not expected that cells that may take a divergent differentiation path at days 7-9 may would return to a similar transcriptional activity at day 10.

      A point that is not discussed is that before day 10 of DC differentiation, Arpc4 KO is expected to only occur in about 50% of the cell population. This is expected to impact the RNA-seq analysis.

      Not all clusters have been exploited (e.g. cluster 3 elevated, cluster 6 partly reduced). I suggest the authors reconsider their analysis and analysis of the RNA-seq analysis (or eventually invest in complementary analysis).

      __Response: __Despite a comprehensive analysis of the different transcriptomes of control and ArpC4 mutant cells during DC differentiation, we decided to focus the presentation and discussion of our RNAseq results on the most notable findings. Of these, the elevated innate immune responses in ArpC4-KO DCs (Fig. 5E,H) caught our particular attention, as this seemed highly meaningful in light of DC and LC functions.

      Revision plan: As suggested by the referee, in the revised manuscript, we will better connect the RNAseq data to the other cellular and molecular analyses shown, complementing these results by investigating the potential involvement of innate immune responses in the ArpC4-KO phenotype.

      What causes the profound numerical drop of LC in the epidermis?

      A major open question is what causes the massive drop of LCs. Although differentiating Arpc4KO DCs start accumulating DNA damage upon proliferation, they succeed in progressing through the cell cycle. There is even a slightly elevated expression of cell cycle genes at day 7 of differentiation in the DC model.

      Only a trend for increased apoptosis is observed in ear and tail skin. It would be important to provide complementary data documenting increased death (or aberrant emigration?) of LCs in the 4-8 week time window.

      __Response: __We agree with the reviewer that this is an important question. We exclude that elevated emigration causes the decline of LCs in ArpC4-KO epidermis, as ArpC4-mutant LCs are significantly reduced (and not increased) in skin-draining lymph nodes (Fig. 7E). To assess whether increased cell death contributed to LC loss, we have tried to identify LCs that are just about to die. As the reviewer noted, we could only observe a trend of apoptosis-positive LCs in mutant epidermis. We assume that this is because of a quick elimination of compromised LCs following DNA damage, with only a short time passing until LCs with impaired genome integrity will be cleared from the system, making it very difficult to detect gH2Ax-positive cells that are positive for markers of cell death.

      Revision plan: Despite the abovementioned expected limitations to detect DNA-damage-positive but viable LCs in vivo, for the manuscript revision we will collect 6-week-old mice to analyze LC numbers and apoptosis (cleaved Caspase-3), complementing our data derived from 7-day and 4-week-old mice (Figures S2A,B, S2E,F). Suited mice have been born end of May; we are ready to analyze them at 6-weeks of age, accordingly.

      Functional consequences

      Although the study reports novel aspects of LC biology, the consequence of ArpC4 deletion for skin barrier function and immunosurveillance are not investigated. It would seem very relevant to test how this model copes with radiation, chemical and/or microorganism challenges.

      __Response: __We fully agree with this reviewer that this is a very interesting point. Therefore, next to assessing the steady-state circulation of LCs and DCs, we also addressed the consequence of ArpC4 loss for LC function in chemically challenged skin: we performed skin painting experiments using the contact sensitizer fluorescein isothiocyanate (FITC), diluted in the sensitizing agent dibutyl phthalate (DBP), to detect cutaneous-derived phagocytes within draining lymph nodes. These experiments revealed that migration of Arpc4KO LCs (as well as of Arpc4KO DCs) to skin-draining lymph nodes was impaired (Fig. 7C-E), confirming an in vivo role of ArpC4 for immune cell migration to lymphatic organs following a chemical challenge. Considering the lengthy legal approval procedures for new animal experimentation procedures, additional in vivo challenges -beyond the provided FITC challenge study- would take at least 6 additional months, which would delay excessively the revision of our manuscript.

      Revision Plan: We will better explain the FITC painting experiment to highlight its importance.

      MINOR COMMENTS:

      1- Figure 1D

      Gating strategy: twice the same empty plots. The content seems to be missing... Does this need to be shown in the main figure?

      __Response: __We apologize for this problem; there might be a problem due to file conversion of PDF reader software. In our PDF versions (including the published bioRxiv preprint) we do see the data points (see below); however, we have earlier experienced incomplete FACS plots during manuscript preparation.


      Revision plan: We will take extra care and double-check the results after converting the figures into PDFs. In addition, we will provide JPG files when submitting the revised manuscript, to prevent such problems.

      2- Figure 2

      Best would be to keep same scale to compare P1 and P7 (tail skin, figure 2A)

      Response and revision plan: We will replace the examples with micrographs of comparable scale (already solved, will be provided with manuscript revision).

      Overlay of Ki67 and MHC-II does not allow to easily visualize the double-positive cells (Fig 2C)

      Response and revision plan: We will provide single-channel image next to the merged view, and improve the visualization of double-positive cells (already solved, will be provided with manuscript revision)

      Quality of Ki67 staining different for Arpc4-KO (less intense, less focused to the nuclei): a technical issue or could that reflect something?

      Response and revision plan: We thank the reviewer for spotting this. We have re-assessed all Ki67 micrographs and noted that the originally chosen examples indeed are not fully representative. We have meantime selected more representative examples of Ki67-positive cells in control and mutant tissues, reflecting no difference in the principal nature of Ki67 staining (already taken care of, will be provided with manuscript revision).

      Fig 2C: Panels mounted differently for ear and tail skin (different order to present the individual stainings, Dapi for tail skin only).

      Response and revision plan: We will harmonize the sequence of panels in figure 2 with submission of the revised manuscript.

      3- LC branch analysis (Fig 1 and 2)

      While Fig 1 indicates that ear skin LCs form in average twice as few branches as tail skin LCs (3-4 versus 8-9 branches per cell), Fig 2 shows the opposite (10-12 versus 6-7 branches per cell).

      Is this due to a very distinct pattern between the 2 considered ages (4 weeks versus 8-10 weeks)? Could the author double-check that there is no methodological bias in their analysis?


      Response: We thank the reviewer for hinting us on this apparent inconsistency. Indeed, our initial analysis suffered from a bias in detecting LC dendrites, as the tissue cellularity and overall morphology significantly differs between 4-week-old and adult animals: In adult animals, the immunostainings show a higher baseline background signal for the skin epithelium compared to P28. We had noted this beforehand and had adjusted the imaging pipeline accordingly, with a more stringent thresholding to eliminate background signals in the case of adult tissues. While we were able to detect the described ArpC4 phenotype, this strategy resulted in a reduced ability to detect dendrites (both in control and mutant tissues), explaining the seemingly reduced number of dendrites in adult vs. 4-week-old tissues.

      Revision plan: We have double-checked both the micrographs and the corresponding quantifications and did not identify errors. Instead, our assumption -that a too high stringency for background reduction in adults caused the discrepancy- turned out correct. At present, we are re-doing the detailled analyses of LC morphology at 4-week and adult stages by confocal microscopy using a 63x objective rather than a 40x objective as done previously. First results confirm that with this approach the number of LC dendrites across these ages are largely comparable, while the phenotypes of ArpC4 loss are retained. We will provide a completely new analysis with revision of the manuscript.

      4- Fig 3 E-G

      How many animals were examined (n=5)? Reproducible accros animals? Why was it done with 4-week animals (phenotype not complete? Event occurring before loss in numbers...)

      Response and revision plan: As mentioned in the figure legend for Fig. 3F we have analysed N = 4 control and N= 5 KO mice (for clarity, we will add this information to Figure 3E and G in the revised document). We chose the 4-week time-point as this was the stage when the loss of LCs first became apparent (even though non-significant at this age). We aimed to learn whether changes in nuclear morphology and nuclear envelope markers represented early molecular and cellular events following ArpC4 loss. Compared to later stages, this strategy poses a reduced risk to detect indirect effects of ArpC4 loss. We will clarify this in the revised manuscript text.

      Staining Lamin A/C globally more intense in the Arpc4-KO epidermis (also seems to apply to the masks corresponding to the LCs). Surprising to see that the quantification indicates a major drop of Lamin A/C intensity in the LCs.

      Response and revision plan: We again thank the reviewer for this careful assessment. The originally chosen micrographs are indeed not fully representative. As with many tissue stainings, there is inter-sample variability. We have now revisited the micrographs and did not find a significant global reduction of Lamin A/C in the entire epidermis (including keratinocytes/KCs). The drop of Lamin A/C intensity is restricted to ArpC4 LCs -and not KCs- and in line with the reduced Lamin A/C expression data in DCs (Fig. 3C,D). We have selected more representative examples, which will be provided with the revised manuscript.

      Legend Fig 4D replace confocal microscopy by STED microscopy

      Revision plan: We will replace "confocal microscopy" by "STED microscopy" accordingly.

      6- Figure 4F

      Intensity/background of γH2Ax staining very distinct between the 2 micrographs shown for WT and Arpc4-KO epidermis.

      Response and revision plan: We have revisited the micrographs and now selected more representative examples, which will be provided in the revised manuscript.

      7- Figure 7C, F, H

      Gating strategies: would be better to harmonize the style of the plots (dot plots and 2 types of contour plots have been used...)

      Response and revision plan: We agree and will provide a harmonized plot illustration in the revised manuscript.

      8- Figure 7H

      Legend of lower gating strategy seems to be wrong (KO and not WT).

      Response and revision plan: We thank the reviewer for pointing out this mistake. A corrected figure display will be provided with revision.

      Reviewer #1 (Significance (Required)):

      Strengths: the general quality of the manuscript is high. It is very clearly written and it contains a very detailed method section that would allow reproducing the reported experiments. This work entails a clear novelty in that it represents the first investigation of the role of ArpC4 in LCs. It opens an interesting perspective about specific mechanisms sustaining the maintenance of myeloid cell subsets in peripheral tissues. This work is therefore expected to be of interest for a large audience of cellular immunologists and beyond. Challenging skin function with an external trigger would lift the relevance for a even wider audience (see main point 6).

      __Response: __see point 6.

      Limitations: in its current version the manuscript suffers from a lack of solidity around a few analysis (see main points on ArpC4 and Arp2/3 protein expression, nuclear envelop rupture analysis,...). It also tends to formulate a narrative centered on the ArpC4 intra-nuclear function that is not definitely proven.

      The field of expertise of this reviewer is: cellular immunology and actin remodeling.

      Reviewer #2 (Evidence, reproducibility and clarity (Required)):

      SUMMARY This is a study in experimental mice employing both in vitro and, importantly, in vivo approaches. EPIDERMAL LANGERHANS CELLS serve as a paradigm for the maintenance of homeostasis of myeloid cells in a tissue, epidermis in this case. In addition to well known functions of the ACTIN NETWORK in cell migration, chemotaxis, cell adherence and phagocytosis the authors reveal a critical function of actin networks in the survival of cells in their home tissue.

      Actin-related proteins (Arp), specifically here the Arp2/3 complex, are necessary to form the filamentous actin networks. The authors use conditional knock-out mice where Arpc4 (an essential component of the Arp2/3 complex) is deleted under the control of CD11c, the most prominent dendritic cell marker which is also expressed on Langerhans cells. In normal mice, epidermal Langerhans cells reside in the epidermis virtually life-long. They initially settle the epidermis around and few days after birth an establish a dense network by a burst of proliferation and then they "linger on" by low level maintenance proliferation. In the epidermis of Arpc4 knock-out mice Langerhans cells also start off with this proliferative burst but, strikingly, they do not stay but are massively reduced by the age of 8-12 weeks.

      The analyses of this decline revealed that

      -- the shape (number of nuclear lobes) and integrity of cell nuclei was compromised; they were fragile and ruptured to some degree when Arpc4 was knocked out, i.e., the Arp2/3 complex was missing;

      -- DNA damage, as detected by staining for gamma-H2Ax or 53BP1 accumulated when Arpc4 was knocked out, i.e., the Arp2/3 complex was missing;

      -- recruitment of DNA repair molecules was inhibited when Arpc4 was knocked out, i.e., the Arp2/3 complex was missing;

      -- gene signatures of interferon signaling and response were increased when Arpc4 was knocked out, i.e., the Arp2/3 complex was missing;

      -- in vivo migration of dendritic cells and Langerhans cells from the skin to the draining lymph nodes in an inflammatory setting (FITC painting of the skin) was impaired when Arpc4 was knocked out, i.e., the Arp2/3 complex was missing;

      -- the persistence of the typical dense network of Langerhans cells in the epidermis, created by proliferation shortly after birth, is abrogated when Arpc4 was knocked out, i.e., the Arp2/3 complex was missing. Importantly, this was not the case for myeloid cell populations that settle a tissue without needing that initial burst of proliferation. For instance, numbers of colonic macrophages were not affected when Arpc4 was knocked out, i.e., the Arp2/3 complex was missing.

      Thus, the authors conclude that the Arp2/3 complex is essential by its formation of actin networks to maintain the integrity of nuclei and ensure DNA repair thereby ascertaining the maintenance proliferation of Langerhans cells and, as the consequence, the persistence of the dense epidermal netowrk of Langerhans cells.

      Up-to-date methodology from the fields of cell biology and cellular immunology (cell isolation from tissues, immunofluorescence, multiparameter flow cytometry, FISH, "good old" - but important - transmission electronmicroscopy, etc.) was used at high quality (e.g., immunofluorescence pictures!). Quantitative and qualitative analytical methods were timely and appropriate (e.g., Voronoi diagrams, cell shape profiling tools, Cre-lox gene-deletion technology, etc.). Importantly, the authors used a clever method, that they had developed several years ago, namely the analysis of dendritic cell migration in microchannels of defined widths. Molecular biology methods such as RNAseq were also employed and analysed by appropriate bioinformatic tools.

      MAJOR COMMENTS:

      • ARE THE KEY CONCLUSIONS CONVINCING? Yes, they are.

      • SHOULD THE AUTHORS QUALIFY SOME OF THEIR CLAIMS AS PRELIMINARY OR SPECULATIVE, OR REMOVE THEM ALTOGETHER? No, I think it is ok as it stands. The authors are wording their claims and conclusions not apodictically but cautiously, as it should be. They point out explicitely which lines of investigations they did not follow up here.

      • WOULD ADDITIONAL EXPERIMENTS BE ESSENTIAL TO SUPPORT THE CLAIMS OF THE PAPER? REQUEST ADDITIONAL EXPERIMENTS ONLY WHERE NECESSARY FOR THE PAPER AS IT IS, AND DO NOT ASK AUTHORS TO OPEN NEW LINES OF EXPERIMENTATION. I think that the here presented experimental evidence suffices to support the conclusions drawn. No additional experiments are necessary.

      • ARE THE SUGGESTED EXPERIMENTS REALISTIC IN TERMS OF TIME AND RESOURCES? IT WOULD HELP IF YOU COULD ADD AN ESTIMATED COST AND TIME INVESTMENT FOR SUBSTANTIAL EXPERIMENTS. Not applicable.

      • ARE THE DATA AND THE METHODS PRESENTED IN SUCH A WAY THAT THEY CAN BE REPRODUCED? Yes, they are.

      • ARE THE EXPERIMENTS ADEQUATELY REPLICATED AND STATISTICAL ANALYSIS ADEQUATE? Yes.

      __Response: __We thank the reviewer very much for assessing our work, for providing constructive suggestions, and for acknowledging the strength of the study.

      MINOR COMMENTS:

      • SPECIFIC EXPERIMENTAL ISSUES THAT ARE EASILY ADDRESSABLE. None

      • ARE PRIOR STUDIES REFERENCED APPROPRIATELY? Essentially yes. Regarding the reduction / loss of the adult epidermal Langerhans cell network, it may be of some interest to also refer to / discuss to another one of the few examples of this phenomenon. There, the initial burst of proliferation is followed by reduced proliferation and increased apoptosis when a critical member of the mTOR signaling cascade is conditionally knocked out (Blood 123:217, 2014).

      __Response and revision plan: __As suggested, we will include into the revised manuscript further examples with related phenotypes regarding the progressive decline of LCs.

      • ARE THE TEXT AND FIGURES CLEAR AND ACCURATE? Yes they are. Figures are well arranged for easy comprehension.

      • DO YOU HAVE SUGGESTIONS THAT WOULD HELP THE AUTHORS IMPROVE THE PRESENTATION OF THEIR DATA AND CONCLUSIONS?

      1. Materials & Methods. The authors write, regarding flow cytometry of epidermal cells: "Briefly, 1cm2 of back skin from 8-14 weeks old female wild-type and knockout littermates was dissociated in 0.25 mg/mL Liberase (Sigma, cat. #5401020001) and 0.5 mg/mL DNase (Sigma, cat.#10104159001) in 1 mL of RPMI (Sigma) and mechanically disaggregated in Eppendorf tubes, FOLLOWED BY INCUBATED for 2 h at 37 {degree sign}C." Followed by what?

      __Response and revision plan: __We apologize for this mistake. The text should read: "... followed by blocking and antibody labeling of cells in single cell suspension.". We will provide the correct text in the revised manuscript.

      Materials & Methods. BMDC electronmicroscopy. What is "IF". Please specify.

      __Response and revision plan: __We also regret this mistake in the method text. It should read: "... For electron microscopy analysis, after PDMS removal, cells were fixed using 2.5% glutaraldehyde ...". We will correct this in the revised manuscript.

      RESULTS in gene expression analyses. The authors observe some increase in apoptosis (as detected by cleaved-Caspase-3 staining). Is this observation in immunofluorescence also evident in the RNAseq data (where the IFN changes were seen), i.e., in Figure 5.

      __Response and revision plan: __We will check our RNAseq data regarding any changes in apoptosis-related genes and, if so, include these in the revised manuscript.

      Figure 7 F and G. Perhaps the authors may want to swap upper and lower panels in F or G, so that macrophage FACS plots and bar graphs are in the same row - ob, obiously, DC plots and bars likewise.

      __Response and revision plan: __We agree and will harmonize the panel sequence in the revised manuscript.

      Figure 7H. "Gating strategy in ArpC4WT Lung (previously gated in Live CD45+ cells)" - The lower row is knock-out, not WT. This is indicated correctly in the legand, but in the figure both rows are labeled as WT.

      __Response and revision plan: __Indeed, the legend information is correct, but the corresponding figure panel is incorrect. We will provide a corrected version with revision.

      The reference by Park et al. 2021 is missing in the list.

      __Response and revision plan: __We will add the reference to the revised bibliography.

      Figure 1D. Sure, the bar graphs are meant to say "CD11c"? The FACS plots show "CD11b".

      __Response and revision plan: __We will check the panels and correct where necessary.

      As to cDC1. In Figure 1D the FACS plot shows an absence of CD103+ cDC1 cells. In contrast, In Figure 7A-left side panel, there is not difference in cDC1 cells between WT and KO mice. Is therefore the flow cytometry plot in Figure 1D not representative regarding cDC1 cells? Correct?

      __Response and revision plan: __The reviewer is correct about this apparent discrepancy. We have not observed differences in the control vs. Aprc4-KO cDC1 population, hence Figure 7 represents our findings. For figure 1, we have by mistake chosen a non-representative plot, with the aim of illustrating the gating strategy. We apologize for this mistake and will provide a corrected an representative FACS plot figure in the revised manuscript.

      Reviewer #2 (Significance (Required)):

      • DESCRIBE THE NATURE AND SIGNIFICANCE OF THE ADVANCE (E.G. CONCEPTUAL, TECHNICAL, CLINICAL) FOR THE FIELD. This is a conceptual advance. It adds a big step to our understanding of how immune cells in tissues (which all come from the bone marrow or are seeded before birth from embryonal hematopoietic organs such as yolk sac and fetal liver) can remain resident in these tissues. For cell types such as Langerhans cells, which establish their final population density within their tissues of residence, the presented finding convincingly buttress the role of proliferation and thereby the role for the actin-related protein complex 2/3 (Arp2/3).

      • PLACE THE WORK IN THE CONTEXT OF THE EXISTING LITERATURE (PROVIDE REFERENCES, WHERE APPROPRIATE). While we know much about actin-related proteins (Arp), as correctly cited by the authors, this knowledge is derived mostly from in vitro studies. The submitted study translates the findings to an in vivo setting for the first time.

      • STATE WHAT AUDIENCE MIGHT BE INTERESTED IN AND INFLUENCED BY THE REPORTED FINDINGS. Skin immunologists foremost, but these findings are of interest to the entire community of immunologists, but also cell biologists.

      • DEFINE YOUR FIELD OF EXPERTISE. My expertise is in skin immunology, in particular skin dendritic cells including Langerhans cells.

      We acknowledge the referee for their positive assessment of our manuscript.

      Reviewer #3 (Evidence, reproducibility and clarity (Required)):

      Summary:

      The manuscript identifies a role of the Arp2/3 complex, the major regulator of actin branching in cells, for controlling the homeostasis of murine Langerhans cells (LCs), a specialized subset of dendritic cells in the skin epidermis. The findings of the study are based on the analysis of CD11c-Cre Arpc4-flox mice, a conditional knockout mouse model, which interferes with Arp2/3 function in Langerhans cells and other CD11c-expressing myeloid cells, e.g. dendritic cell or macrophage subsets. By using immunofluorescence and flow cytometry analysis of epidermis and skin tissues, the authors provide a detailed analysis of LC numbers at different developmental stages (postnatal day 1, 7, 28, and adult mice) and demonstrate that Arpc4-deficiency does not interfere with the establishment of LC networks until postnatal day 28. However, LCs in ear and tail skin are substantially reduced in Arpc4-deficient mice at 8-12 weeks of age. In parallel to their in vivo model, the authors analyze cultures of bone marrow-derived dendritic cells (BMDCs) from control and CD11c-Cre Arpc4-flox mice. Arpc4-deficiency in BMDCs, which develop over 8-10 days in culture, results in nuclear shape and lamina abnormalities, as well as signs of increased DNA damage. Aspects of this phenotype are also detected in Langerhans cells in epidermal preparations. Transcriptomic analysis of BMDCs highlights a gene signature of increased expression of the interferon response pathway and alterations in cell cycle regulation. Arpc4-deficient BMDCs show increased expression of DNA damage markers and reduced expression of certain DNA repair factors. Based on these correlative findings from the BMDC model, the authors conclude that the decline in LC numbers might develop from the accumulation of DNA damage over time, which the authors phrease "pre-mature aging of Langerhans cells". Lastly, the authors show a heterogenous picture how Arp2/3 depletion affects distinct DC populations in CD11c-Cre Arpc4-flox mice. While some tissue-resident DC subsets appear normal in numbers, others are declined in numbers in the tissue. This may be related to their proliferation potential in tissues.

      Major comments:

      • Are the claims and the conclusions supported by the data or do they require additional experiments or analyses to support them?

      1) The authors claim that Arpc4 deficiency selectively compromises myeloid cell populations that rely on proliferation for tissue colonization (Figure 7). The presented data might give hints for such a general hypothesis, but solid experimental proof to prove this is lacking. When comparing myeloid cell subsets from foru different irgans, the authors refer to published data that some dendritic cell subsets are more proliferative in tissues than others and that CD11cCre Arpc4-flox mice appear to have reduced cell numbers in these populations. However, the presented data are purely correlative and no functional connection to cell proliferation has been made to the phenotypes. While some dendritic cell subsets (Langerhans cells, alveolar DCs) show reduced cell numbers in CD11cCre Arpc4-flox mice, other myeloid cell cells subsets are unaffected (e.g. dermal cDC1 and 2, colon macrophages).There could be plenty of other reasons that might underly the observed discrepancies between these cell subsets, e.g. Arp2/3 knockout efficiency and myeloid cell turnover in the tissue are just two examples, which have not been taken into consideration. Direct measurement of cell proliferation, e.g. BrdU labeling, and the observed phenotype would be missing to make such claims. The data could either be removed. Experimentally addressing these points could take 3-6 months.

      Response and planned revisions: We thank the referee for bringing this point. We agree that these results give hints that support our conclusion but that do not address this question directly. However, we would like to insist on the fact that our conclusion is based on studies from others showing that alveolar macrophages self-maintain themselves through proliferation (Bain et al. Mucosal Immunology 2022). In contrast, it has been reported that most colonic macrophages are derived from monocytes that are being recruited to the gut through life (Bain et al. Mucosal Immunity 2023)

      We propose to better explain and discuss these points in our revised manuscripts. In addition, we will stress that we do not exclude that different intracellular Arpc4-dependent processes might contribute to the phenotypes observed (beyond maintenance of DNA integrity). These revisions will help mitigate our conclusions and leave open the potential implication of alternative mechanisms that will be discussed as suggested by the referee.

      2) The authors claim that DC subsets (e.g. dermal cDCs), which develop from pre-DCs, are not affected by Arp2/3 depletion (Figure 7, although the FACS plot in Fig. 1D would suggest a different picture for cDC1). This is surprising in light of the data with bone marrow-derived DCs (BMDCs), the major in vitro model of this study, which develop from CDPs that again develop from pre-DCs. BMDCs did show aberrant nuclei and signs of DNA damage. How would the authors then explain the discrepancies of the BMDC model with DC subsets, where the authors feel that the pre-DC origin explains the phenotypic difference? This is a general concern of the data interpretation and conclusions.

      __Response: __We thank the referee to bring this point that indeed requires clarification. Two non-exclusive hypotheses could explain this apparent discrepancy:

      • The ontogeny of bone-marrow-derived DCs: Depending on the protocol used, there might be variations in the precursors DCs develop from. We use one of the first protocols, which was pioneered by Paola Ricciardi-Castagnoli lab (Winzler et al. J.Exp.Med. 1997). It relies on a supernatant from J558 cells transfected with GMCSF, which contains additional cytokines and mainly generate DC2-like DCs. Langerhans cells are closer to DC2s, which resemble more macrophages than DC1s. We thus chose this protocol rather than the protocols that use Flt3-L, which produce both DC1s and DC2s developed from common dendritic-cell precursors (CDPs). It is thus possible that our BM-derived DCs develop from other precursor cells that are possibly closer to monocyte precursors.
      • As shown in Figure 5C, kinetics of acquisition of CD11c expression, and thus deletion of the Arpc4 gene, might be distinct in vivo and in vitro. In vivo, as stated in our manuscript, DCs acquire CD11c as preDCs and undergo few rounds of divisions after. In vitro, as shown by our cycling experiments, BM-derived DCs continuously cycle, so they will keep dividing after having acquire CD11c (around day 7) and deleting the Arpc4 gene. __Revision plan: __We propose to mention these hypotheses in the discussion of our manuscript to explain the apparent contradiction raised by the referee.

      3) In line with point 2, the authors never show that BMDCs show reduced proliferation, reduced cell numbers or increased cell death in Arpc4-deficient cell cultures, as a consequence of the detected DNA damage and impaired DNA repair. In fact, Figure 5C even shows that cell growth rates between control and KO are equal. This is a major mismatch in the current study. Since the authors use the BMDC model to explain the declining cell numbers in Langerhans cells (which derive from fetal liver cells), this phenotype is not mirrored by the BMDC culture and it remains open whether the observed changes in nuclear DNA damage and repair are indeed directly linked to the observed phenotype of declining cell numbers in the tissue. These aspects require argumentation why cell growth is unchanged in KO cells. Additional experiments addressing these points with sufficient biological replicates (cultures from different mice) could take 2-3 months, including preparation time.

      __Response____: __We thank the referee for bringing this point, which was probably not properly discussed in the first version of our manuscript. Indeed, Arpc4KO BM-derived DCs do not show the premature cell death phenotype observed in LCs in vivo, as stated by the referee. There are at least two putative non-exclusive explanations for this. First, unlike LCs, which are long-lived cells, BM-derived DCs can be kept in culture for only 10-12 days. As DNA damage-induced cell death takes time (LCs only start to die about 3-4 weeks after network establishment), the lifespan of BM-DCs could simply not be long enough to observe this phenotype. Second, in the epidermis, LCs are physically constrained and continuously exposed to diverse signals that might increase their sensitivity to DNA damage and thereby induction of subsequent cell death.

      __Revision Plan: __We will clarify this point in our revised manuscript by providing putative explanations for the death phenotype of Arpc4-deficient LCs not being observed in BM-derived DCs. We will further explain that this does not invalidate this cellular model as it was used to raise hypotheses on the putative role played by Arpc4 in myeloid cells, i.e. maintenance of DNA integrity, which was then confirmed in vivo (Arpc4KO LCs do indeed display DNA damage in the epidermis). Without this "imperfect cellular model", we would have probably not been able to uncover this novel function of Arp2/3 in immune cells.

      4) The authors refer to a "pre-mature aging" phenotype of Arpc4-deficient BMDCs and LCs, based on reductions in Lamin B, Lamin A and increases in gH2AX and 53BP1. I find this term and overstatement of the current data and suggest that other markers for cell senescence, such as p53, Rb, p21 and b-Galactosidase are then also used to make such strong claim on "aging" and cell senescence. Experimentally addressing this point with sufficient biological replicates could take 2-3 months, including preparation time.

      __Revision Plan: __We will assess the expression of these genes and senescence signatures in our RNAseq analysis as well as in Arpc4WT and Arpc4KO-derived DCs, as suggested by the referee.

      5) The study does not provide a mechanism how the Arp2/3 complex would mediate the observed effects on DNA damage and repairs has not been addressed in the cell model, and only potential scenarios from other non-myeloid cell lines are discussed. It remains unclear whether the observed phenotypes in Arpc4-depleted myleoid cells relate to the direct nuclear function of Arp2/3 or the cytosolic function of Arp2/3, including its roles in cytoskeletal regulation that may have secondary effects on the nuclear alterations. This is a general concern of the presented data, data on mechanism might require more than 6 months.

      __Revision Plan: __The referee is correct: Our manuscript shows that Arp2/3 deficiency in specific myeloid cells impacts on their survival in vivo and proposes that this could result at least in part from impaired maintenance of DNA integrity in these cells. We do not know whether this also applies to non-myeloid cells, which, although very interesting, is beyond the scope of the present study. In addition, we do not have any experimental tool to distinguish whether the DNA damage phenotype of Arpc4KO cells involves the nuclear or cortical pool of F-actin, this is why we have left this question open in the discussion of our manuscript.

      6) OPTIONAL: The authors make a strong case arguing that the increased interferon expression signature (based on the transcriptomics data) reflects the nuclear ruptures in Arpc4-deficient cells and adds to the observed phenotype. If this is so, what happens then in STING knockout cells in the presence of CK666 inhibitor?


      __Revision Plan____: __The referee is correct in that we do not show this point experimentally and should therefore temper this conclusion.

      • Are the data and the methods presented in such a way that they can be reproduced?

      1) The analyses include quite a number of intensity calculations of immunofluorescence signals (Fig. 3D, E; Fig. 4E, Fig. 5B and 6B)? The background stainings are often variable or very high. In some cases it is even unclear whether stainings are really detecting protein and go beyond background staining (Fig. 6A, Fig. 5F). How were immunofluorescence data acquired and dealt with different background staining intensities?

      __Revision Plan: __We will carefully describe the microscopes used for image acquisition as well as the downstream analyses for each experiment, which indeed vary depending on the signals observed with distinct antibodies or construct.

      2) It remained unclear to me on which basis the nuclear deformations in Fig. 3G, H were calculated?

      __Revision Plan: __We will carefully describe the methods used to quantify nuclear deformations.

      3) The detailed phenotype of control mice is a bit unclear. It appears as if these were Cre-negative animals. Did the authors have some proof-of-principle experiments showing that CD11cCre Arpc4 +/+ animals have comparable phenotypes to Cre-negative animals?

      • Are the experiments adequately replicated and statistical analysis adequate?

      __Revision Plan: __We have never observed any decline in LC numbers in other mouse lines/genotypes (for example in cPLA2flox/flox;CD11c-Cre mice shown in the manuscript, Fig. S6B), excluding a putative role for the Cre in LC death.

      For most experiments, the number of biological replicates (mice, or BMDC cultures from different mice) and individual values (n, cells) are indicated. Statistical analysis appears adequate.

      Minor comments:

      • Prior published studies on Arp2/3 function in immune cells are referenced accordingly. A number of additional pre-print manuscripts on this topic have not been cited and could be considered referencing.


      __Revision Plan: __We will fix this point and cite additional, relevant preprints.

      • The text is very clearly and very well written. Figures are clear and accurate for most cases. There are some open questions:

      • Fig. 1B: The number of dots betwenn graph and legend do not match. The dots are not n=12 for both genotypes. Additionally: What do the symbols in the circles in the graph stand for? This is also in another later figure unclear.

      • Fig. 2C: The current IF presentation (overlay MHCII with Ki67) is not very helpful. An additional image that shows only the Ki67 signal in the MHCII mask would be very helpful.

      • Fig. 4B: BMDCs of which culture day were used for these experiments?

      • Fig. 4A and D shows the same representative cells for two biological messages, which is only moderately convincing regarding a "general" phenotype.

      • Fig. 5, B: Scale bars are missing.

      __Revision Plan: __We will fix all these points.

      Reviewer #3 (Significance (Required)):

      Strengths and Advance:

      The study provides strong data and a very detailed analysis of how the Arp2/3 complex regulates stages of Langerhans cell development and homeostasis. The role of the Arp2/3 complex as regulator of actin branching, which is involved in many cellular functions, has previously not been reported for this cell type. Previous research in immune cells have already studied the Arp2/3 complex, but studies were focussed on its role in migration and the majority of published phenotypes related to cell migration. While there are already a number of in vitro studies showing that the Arp2/3 complex can regulate aspects of cell cycle control or cell death in non-immune cells, most of these studies were performed with immortalized, non-immune cell lines, which can be more easily manipulated to dissect mechanistic aspects of the cellular phenotype, but are limited in their physiological interpretation. Hence, it is a major strength of this study to investigate the effects of Arp2/3 in a primary immune cell type, directly in the native and physiological environment. This is important because in vitro data from other cell types cannot be easily extrapolated to any other cell type and it is critical for our understanding to collect physiological data from tissues, where the biology really happens. The finding that the Arp2/3 complex regulates the tissue-residency of Langerhans cell through processes that are unrelated to migration are partially unexpected, shifting the view of this protein complex's physiological role to other cell biological processes, e.g. regulation of cell proliferation.

      Limitations: The limitations of the study are detailed in the five major points listed above. The study accumulates many experiments that characterize the phenotype of Arpc4-depleted cells, showing signs of DNA damage in Langerhans cells and cultures of BMDCs. How the Arp2/3 complex would mechanistically mediate the observed effects on DNA damage and repairs have not been addressed. It also remains open whether this is due to the effects of the Arp2/3 complex in the nucleus or the cytosol, which would be biologically extremely important to understand. Above that, there are some discrepancies regarding the phenotype of the BMDC model, which does neither entirely match the Langerhans cell phenotype in the tissue (reduced proliferation, LC derive from different progenitors), nor other endogenous DC populations, which should also derive from similar progenitors.

      Audience and reviewer background:

      In its current form, the manuscript will already be of interest for several research fields: Langerhans cell and dendritic cell homeostasis, immune cell trafficking, actin and cytoskeleton regulation in immune cells, physiological role of actin-regulating proteins. My own field of expertise is immune cell trafficking in mouse models, leukocyte migration and cytoskeletal regulation. I cannot judge the analysis and clustering of the bulk RNA sequencing data.

      3. Description of the revisions that have already been incorporated in the transferred manuscript

      Please insert a point-by-point reply describing the revisions that were already carried out and included in the transferred manuscript. If no revisions have been carried out yet, please leave this section empty.

      • *

      4. Description of analyses that authors prefer not to carry out

      Please include a point-by-point response explaining why some of the requested data or additional analyses might not be necessary or cannot be provided within the scope of a revision. This can be due to time or resource limitations or in case of disagreement about the necessity of such additional data given the scope of the study. Please leave empty if not applicable.

    2. Note: This preprint has been reviewed by subject experts for Review Commons. Content has not been altered except for formatting.

      Learn more at Review Commons


      Referee #3

      Evidence, reproducibility and clarity

      Summary:

      The manuscript identifies a role of the Arp2/3 complex, the major regulator of actin branching in cells, for controlling the homeostasis of murine Langerhans cells (LCs), a specialized subset of dendritic cells in the skin epidermis. The findings of the study are based on the analysis of CD11c-Cre Arpc4-flox mice, a conditional knockout mouse model, which interferes with Arp2/3 function in Langerhans cells and other CD11c-expressing myeloid cells, e.g. dendritic cell or macrophage subsets. By using immunofluorescence and flow cytometry analysis of epidermis and skin tissues, the authors provide a detailed analysis of LC numbers at different developmental stages (postnatal day 1, 7, 28, and adult mice) and demonstrate that Arpc4-deficiency does not interfere with the establishment of LC networks until postnatal day 28. However, LCs in ear and tail skin are substantially reduced in Arpc4-deficient mice at 8-12 weeks of age. In parallel to their in vivo model, the authors analyze cultures of bone marrow-derived dendritic cells (BMDCs) from control and CD11c-Cre Arpc4-flox mice. Arpc4-deficiency in BMDCs, which develop over 8-10 days in culture, results in nuclear shape and lamina abnormalities, as well as signs of increased DNA damage. Aspects of this phenotype are also detected in Langerhans cells in epidermal preparations. Transcriptomic analysis of BMDCs highlights a gene signature of increased expression of the interferon response pathway and alterations in cell cycle regulation. Arpc4-deficient BMDCs show increased expression of DNA damage markers and reduced expression of certain DNA repair factors. Based on these correlative findings from the BMDC model, the authors conclude that the decline in LC numbers might develop from the accumulation of DNA damage over time, which the authors phrease "pre-mature aging of Langerhans cells". Lastly, the authors show a heterogenous picture how Arp2/3 depletion affects distinct DC populations in CD11c-Cre Arpc4-flox mice. While some tissue-resident DC subsets appear normal in numbers, others are declined in numbers in the tissue. This may be related to their proliferation potential in tissues.

      Major comments:

      • Are the claims and the conclusions supported by the data or do they require additional experiments or analyses to support them?

      1) The authors claim that Arpc4 deficiency selectively compromises myeloid cell populations that rely on proliferation for tissue colonization (Figure 7). The presented data might give hints for such a general hypothesis, but solid experimental proof to prove this is lacking. When comparing myeloid cell subsets from foru different irgans, the authors refer to published data that some dendritic cell subsets are more proliferative in tissues than others and that CD11cCre Arpc4-flox mice appear to have reduced cell numbers in these populations. However, the presented data are purely correlative and no functional connection to cell proliferation has been made to the phenotypes. While some dendritic cell subsets (Langerhans cells, alveolar DCs) show reduced cell numbers in CD11cCre Arpc4-flox mice, other myeloid cell cells subsets are unaffected (e.g. dermal cDC1 and 2, colon macrophages).There could be plenty of other reasons that might underly the observed discrepancies between these cell subsets, e.g. Arp2/3 knockout efficiency and myeloid cell turnover in the tissue are just two examples, which have not been taken into consideration. Direct measurement of cell proliferation, e.g. BrdU labeling, and the observed phenotype would be missing to make such claims. The data could either be removed. Experimentally addressing these points could take 3-6 months.

      2) The authors claim that DC subsets (e.g. dermal cDCs), which develop from pre-DCs, are not affected by Arp2/3 depletion (Figure 7, although the FACS plot in Fig. 1D would suggest a different picture for cDC1). This is surprising in light of the data with bone marrow-derived DCs (BMDCs), the major in vitro model of this study, which develop from CDPs that again develop from pre-DCs. BMDCs did show aberrant nuclei and signs of DNA damage. How would the authors then explain the discrepancies of the BMDC model with DC subsets, where the authors feel that the pre-DC origin explains the phenotypic difference? This is a general concern of the data interpretation and conclusions.

      3) In line with point 2, the authors never show that BMDCs show reduced proliferation, reduced cell numbers or increased cell death in Arpc4-deficient cell cultures, as a consequence of the detected DNA damage and impaired DNA repair. In fact, Figure 5C even shows that cell growth rates between control and KO are equal. This is a major mismatch in the current study. Since the authors use the BMDC model to explain the declining cell numbers in Langerhans cells (which derive from fetal liver cells), this phenotype is not mirrored by the BMDC culture and it remains open whether the observed changes in nuclear DNA damage and repair are indeed directly linked to the observed phenotype of declining cell numbers in the tissue. These aspects require argumentation why cell growth is unchanged in KO cells. Additional experiments addressing these points with sufficient biological replicates (cultures from different mice) could take 2-3 months, including preparation time.

      4) The authors refer to a "pre-mature aging" phenotype of Arpc4-deficient BMDCs and LCs, based on reductions in Lamin B, Lamin A and increases in gH2AX and 53BP1. I find this term and overstatement of the current data and suggest that other markers for cell senescence, such as p53, Rb, p21 and b-Galactosidase are then also used to make such strong claim on "aging" and cell senescence. Experimentally addressing this point with sufficient biological replicates could take 2-3 months, including preparation time.

      5) The study does not provide a mechanism how the Arp2/3 complex would mediate the observed effects on DNA damage and repairs has not been addressed in the cell model, and only potential scenarios from other non-myeloid cell lines are discussed. It remains unclear whether the observed phenotypes in Arpc4-depleted myleoid cells relate to the direct nuclear function of Arp2/3 or the cytosolic function of Arp2/3, including its roles in cytoskeletal regulation that may have secondary effects on the nuclear alterations. This is a general concern of the presented data, data on mechanism might require more than 6 months.

      6) OPTIONAL: The authors make a strong case arguing that the increased interferon expression signature (based on the transcriptomics data) reflects the nuclear ruptures in Arpc4-deficient cells and adds to the observed phenotype. If this is so, what happens then in STING knockout cells in the presence of CK666 inhibitor?

      • Are the data and the methods presented in such a way that they can be reproduced?

      1) The analyses include quite a number of intensity calculations of immunofluorescence signals (Fig. 3D, E; Fig. 4E, Fig. 5B and 6B)? The background stainings are often variable or very high. In some cases it is even unclear whether stainings are really detecting protein and go beyond background staining (Fig. 6A, Fig. 5F). How were immunofluorescence data acquired and dealt with different background staining intensities?

      2) It remained unclear to me on which basis the nuclear deformations in Fig. 3G, H were calculated?

      3) The detailed phenotype of control mice is a bit unclear. It appears as if these were Cre-negative animals. Did the authors have some proof-of-principle experiments showing that CD11cCre Arpc4 +/+ animals have comparable phenotypes to Cre-negative animals?

      • Are the experiments adequately replicated and statistical analysis adequate?

      For most experiments, the number of biological replicates (mice, or BMDC cultures from different mice) and individual values (n, cells) are indicated. Statistical analysis appears adequate.

      Minor comments:

      • Prior published studies on Arp2/3 function in immune cells are referenced accordingly. A number of additional pre-print manuscripts on this topic have not been cited and could be considered referencing.

      • The text is very clearly and very well written. Figures are clear and accurate for most cases. There are some open questions:

      1) Fig. 1B: The number of dots betwenn graph and legend do not match. The dots are not n=12 for both genotypes. Additionally: What do the symbols in the circles in the graph stand for? This is also in another later figure unclear.

      2) Fig. 2C: The current IF presentation (overlay MHCII with Ki67) is not very helpful. An additional image that shows only the Ki67 signal in the MHCII mask would be very helpful.

      3) Fig. 4B: BMDCs of which culture day were used for these experiments?

      4) Fig. 4A and D shows the same representative cells for two biological messages, which is only moderately convincing regarding a "general" phenotype.

      5) Fig. 5, B: Scale bars are missing.

      Significance

      Strengths and Advance:

      The study provides strong data and a very detailed analysis of how the Arp2/3 complex regulates stages of Langerhans cell development and homeostasis. The role of the Arp2/3 complex as regulator of actin branching, which is involved in many cellular functions, has previously not been reported for this cell type. Previous research in immune cells have already studied the Arp2/3 complex, but studies were focussed on its role in migration and the majority of published phenotypes related to cell migration. While there are already a number of in vitro studies showing that the Arp2/3 complex can regulate aspects of cell cycle control or cell death in non-immune cells, most of these studies were performed with immortalized, non-immune cell lines, which can be more easily manipulated to dissect mechanistic aspects of the cellular phenotype, but are limited in their physiological interpretation. Hence, it is a major strength of this study to investigate the effects of Arp2/3 in a primary immune cell type, directly in the native and physiological environment. This is important because in vitro data from other cell types cannot be easily extrapolated to any other cell type and it is critical for our understanding to collect physiological data from tissues, where the biology really happens. The finding that the Arp2/3 complex regulates the tissue-residency of Langerhans cell through processes that are unrelated to migration are partially unexpected, shifting the view of this protein complex's physiological role to other cell biological processes, e.g. regulation of cell proliferation.

      Limitations:

      The limitations of the study are detailed in the five major points listed above. The study accumulates many experiments that characterize the phenotype of Arpc4-depleted cells, showing signs of DNA damage in Langerhans cells and cultures of BMDCs. How the Arp2/3 complex would mechanistically mediate the observed effects on DNA damage and repairs have not been addressed. It also remains open whether this is due to the effects of the Arp2/3 complex in the nucleus or the cytosol, which would be biologically extremely important to understand. Above that, there are some discrepancies regarding the phenotype of the BMDC model, which does neither entirely match the Langerhans cell phenotype in the tissue (reduced proliferation, LC derive from different progenitors), nor other endogenous DC populations, which should also derive from similar progenitors.

      Audience and reviewer background:

      In its current form, the manuscript will already be of interest for several research fields: Langerhans cell and dendritic cell homeostasis, immune cell trafficking, actin and cytoskeleton regulation in immune cells, physiological role of actin-regulating proteins. My own field of expertise is immune cell trafficking in mouse models, leukocyte migration and cytoskeletal regulation. I cannot judge the analysis and clustering of the bulk RNA sequencing data.

    3. Note: This preprint has been reviewed by subject experts for Review Commons. Content has not been altered except for formatting.

      Learn more at Review Commons


      Referee #2

      Evidence, reproducibility and clarity

      Summary:

      • This is a study in experimental mice employing both in vitro and, importantly, in vivo approaches. EPIDERMAL LANGERHANS CELLS serve as a paradigm for the maintenance of homeostasis of myeloid cells in a tissue, epidermis in this case. In addition to well known functions of the ACTIN NETWORK in cell migration, chemotaxis, cell adherence and phagocytosis the authors reveal a critical function of actin networks in the survival of cells in their home tissue.

      • Actin-related proteins (Arp), specifically here the Arp2/3 complex, are necessary to form the filamentous actin networks. The authors use conditional knock-out mice where Arpc4 (an essential component of the Arp2/3 complex) is deleted under the control of CD11c, the most prominent dendritic cell marker which is also expressed on Langerhans cells. In normal mice, epidermal Langerhans cells reside in the epidermis virtually life-long. They initially settle the epidermis around and few days after birth an establish a dense network by a burst of proliferation and then they "linger on" by low level maintenance proliferation. In the epidermis of Arpc4 knock-out mice Langerhans cells also start off with this proliferative burst but, strikingly, they do not stay but are massively reduced by the age of 8-12 weeks.

      • The analyses of this decline revealed that

      a) the shape (number of nuclear lobes) and integrity of cell nuclei was compromised; they were fragile and ruptured to some degree when Arpc4 was knocked out, i.e., the Arp2/3 complex was missing;

      b) DNA damage, as detected by staining for gamma-H2Ax or 53BP1 accumulated when Arpc4 was knocked out, i.e., the Arp2/3 complex was missing;

      c) recruitment of DNA repair molecules was inhibited when Arpc4 was knocked out, i.e., the Arp2/3 complex was missing;

      d) gene signatures of interferon signaling and response were increased when Arpc4 was knocked out, i.e., the Arp2/3 complex was missing;

      e) in vivo migration of dendritic cells and Langerhans cells from the skin to the draining lymph nodes in an inflammatory setting (FITC painting of the skin) was impaired when Arpc4 was knocked out, i.e., the Arp2/3 complex was missing;

      f) the persistence of the typical dense network of Langerhans cells in the epidermis, created by proliferation shortly after birth, is abrogated when Arpc4 was knocked out, i.e., the Arp2/3 complex was missing. Importantly, this was not the case for myeloid cell populations that settle a tissue without needing that initial burst of proliferation. For instance, numbers of colonic macrophages were not affected when Arpc4 was knocked out, i.e., the Arp2/3 complex was missing.

      • Thus, the authors conclude that the Arp2/3 complex is essential by its formation of actin networks to maintain the integrity of nuclei and ensure DNA repair thereby ascertaining the maintenance proliferation of Langerhans cells and, as the consequence, the persistence of the dense epidermal netowrk of Langerhans cells.

      • Up-to-date methodology from the fields of cell biology and cellular immunology (cell isolation from tissues, immunofluorescence, multiparameter flow cytometry, FISH, "good old" - but important - transmission electronmicroscopy, etc.) was used at high quality (e.g., immunofluorescence pictures!). Quantitative and qualitative analytical methods were timely and appropriate (e.g., Voronoi diagrams, cell shape profiling tools, Cre-lox gene-deletion technology, etc.). Importantly, the authors used a clever method, that they had developed several years ago, namely the analysis of dendritic cell migration in microchannels of defined widths. Molecular biology methods such as RNAseq were also employed and analysed by appropriate bioinformatic tools.

      Major comments:

      • ARE THE KEY CONCLUSIONS CONVINCING? Yes, they are.

      • SHOULD THE AUTHORS QUALIFY SOME OF THEIR CLAIMS AS PRELIMINARY OR SPECULATIVE, OR REMOVE THEM ALTOGETHER? No, I think it is ok as it stands. The authors are wording their claims and conclusions not apodictically but cautiously, as it should be. They point out explicitely which lines of investigations they did not follow up here.

      • WOULD ADDITIONAL EXPERIMENTS BE ESSENTIAL TO SUPPORT THE CLAIMS OF THE PAPER? REQUEST ADDITIONAL EXPERIMENTS ONLY WHERE NECESSARY FOR THE PAPER AS IT IS, AND DO NOT ASK AUTHORS TO OPEN NEW LINES OF EXPERIMENTATION. I think that the here presented experimental evidence suffices to support the conclusions drawn. No additional experiments are necessary.

      • ARE THE SUGGESTED EXPERIMENTS REALISTIC IN TERMS OF TIME AND RESOURCES? IT WOULD HELP IF YOU COULD ADD AN ESTIMATED COST AND TIME INVESTMENT FOR SUBSTANTIAL EXPERIMENTS. Not applicable.

      • ARE THE DATA AND THE METHODS PRESENTED IN SUCH A WAY THAT THEY CAN BE REPRODUCED? Yes, they are.

      • ARE THE EXPERIMENTS ADEQUATELY REPLICATED AND STATISTICAL ANALYSIS ADEQUATE? Yes.

      Minor comments:

      • SPECIFIC EXPERIMENTAL ISSUES THAT ARE EASILY ADDRESSABLE. None

      • ARE PRIOR STUDIES REFERENCED APPROPRIATELY? Essentially yes. Regarding the reduction / loss of the adult epidermal Langerhans cell network, it may be of some interest to also refer to / discuss to another one of the few examples of this phenomenon. There, the initial burst of proliferation is followed by reduced proliferation and increased apoptosis when a critical member of the mTOR signaling cascade is conditionally knocked out (Blood 123:217, 2014).

      • ARE THE TEXT AND FIGURES CLEAR AND ACCURATE? Yes they are. Figures are well arranged for easy comprehension.

      • DO YOU HAVE SUGGESTIONS THAT WOULD HELP THE AUTHORS IMPROVE THE PRESENTATION OF THEIR DATA AND CONCLUSIONS?

      • Materials & Methods. The authors write, regarding flow cytometry of epidermal cells: "Briefly, 1cm2 of back skin from 8-14 weeks old female wild-type and knockout littermates was dissociated in 0.25 mg/mL Liberase (Sigma, cat. #5401020001) and 0.5 mg/mL DNase (Sigma, cat.#10104159001) in 1 mL of RPMI (Sigma) and mechanically disaggregated in Eppendorf tubes, FOLLOWED BY INCUBATED for 2 h at 37 {degree sign}C." Followed by what?

      • Materials & Methods. BMDC electronmicroscopy. What is "IF". Please specify.

      • RESULTS in gene expression analyses. The authors observe some increase in apoptosis (as detected by cleaved-Caspase-3 staining). Is this observation in immunofluorescence also evident in the RNAseq data (where the IFN changes were seen), i.e., in Figure 5.

      • Figure 7 F and G. Perhaps the authors may want to swap upper and lower panels in F or G, so that macrophage FACS plots and bar graphs are in the same row - ob, obiously, DC plots and bars likewise.

      • Figure 7H. "Gating strategy in ArpC4WT Lung (previously gated in Live CD45+ cells)" - The lower row is knock-out, not WT. This is indicated correctly in the legand, but in the figure both rows are labeled as WT.

      • The reference by Park et al. 2021 is missing in the list.

      • Figure 1D. Sure, the bar graphs are meant to say "CD11c"? The FACS plots show "CD11b".

      • As to cDC1. In Figure 1D the FACS plot shows an absence of CD103+ cDC1 cells. In contrast, In Figure 7A-left side panel, there is not difference in cDC1 cells between WT and KO mice. Is therefore the flow cytometry plot in Figure 1D not representative regarding cDC1 cells? Correct?

      Significance

      • DESCRIBE THE NATURE AND SIGNIFICANCE OF THE ADVANCE (E.G. CONCEPTUAL, TECHNICAL, CLINICAL) FOR THE FIELD. This is a conceptual advance. It adds a big step to our understanding of how immune cells in tissues (which all come from the bone marrow or are seeded before birth from embryonal hematopoietic organs such as yolk sac and fetal liver) can remain resident in these tissues. For cell types such as Langerhans cells, which establish their final population density within their tissues of residence, the presented finding convincingly buttress the role of proliferation and thereby the role for the actin-related protein complex 2/3 (Arp2/3).

      • PLACE THE WORK IN THE CONTEXT OF THE EXISTING LITERATURE (PROVIDE REFERENCES, WHERE APPROPRIATE). While we know much about actin-related proteins (Arp), as correctly cited by the authors, this knowledge is derived mostly from in vitro studies. The submitted study translates the findings to an in vivo setting for the first time.

      • STATE WHAT AUDIENCE MIGHT BE INTERESTED IN AND INFLUENCED BY THE REPORTED FINDINGS. Skin immunologists foremost, but these findings are of interest to the entire community of immunologists, but also cell biologists.

      • DEFINE YOUR FIELD OF EXPERTISE. My expertise is in skin immunology, in particular skin dendritic cells including Langerhans cells.

    4. Note: This preprint has been reviewed by subject experts for Review Commons. Content has not been altered except for formatting.

      Learn more at Review Commons


      Referee #1

      Evidence, reproducibility and clarity

      Summary:

      • The manuscript by Delgado et al. reports the role of the actin remodeling Arp2/3 complex in the biology of Langerhans cells, which are specialized innate immune cells of the epidermis. The study is based on a conditional KO mouse model (CD11cCre;Arpc4fl/fl), in which the deletion of the Arp2/3 subunit ArpC4 is under the control of the myeloid cell specific CD11c promoter.

      • In this model, the assembly of LC networks in the epidermis of ear and tail skin is preserved when examining animals immediately after birth (up to 1 week). Subsequently however LCs from ArpC4-deleted mice start displaying morphological aberrations (reduced elongation and number of branches at 4 weeks of age). Additionally, a profound decline in LC numbers is reported in the skin of both the ear and tail of young adult mice (8-10 weeks).

      • To explore the cause of such decline, the authors then opt for the complementary in vitro study of bone-marrow derived DCs, given the lack of a model to study LCs in vitro. They report that ArpC4 deletion is associated with aberrantly shaped nuclei, decreased expression of the nucleoskeleton proteins Lamin A/C and B1, nuclear envelop ruptures and increased DNA damage as shown by γH2Ax staining. Importantly, they provide evidence that the defects evoked by ArpC4 deletion also occur in the LCs in situ (immunofluorescence of the skin in 4-week old mice).

      • Increased DNA damage is further documented by staining differentiating DCs from ArpC4-deleted mice with the 53BP1 marker. In parallel, nuclear levels of DNA repair kinase ATR and recruitment of RPA70 (which recruits ATR to replicative forks) are reduced in the ArpC4-deleted condition. In vitro treatment of DCs with the topoisomerase II inhibitor etoposide and the Arp2/3 inhibitor CK666 induce comparable DNA damage, as well as multilobulated nuclei and DNA bridges. The authors conclude that the ArpC4-KO phenotype might stem, at least in part, from a defective ability to repair DNA damages occurring during cell division.

      • The study in enriched by an RNA-seq analysis that points to an increased expression of genes linked to IFN signaling, which the authors hypothetically relate to overt activation of innate nucleic acid sensing pathways.

      • The study ends by an examination of myeloid cell populations in ArpC4-KO mice beyond LCs. Skin cDC2 and cDC2 subsets display skin emigration defects (like LCs), but not numerical defects in the skin (unlike LCs). Myeloid cell subsets of the colon are also present in normal numbers. In the lungs, interstitial and alveolar macrophages are reduced, but not lung DC subsets. Collectively, these observations suggest that ArpC4 is essential for the maintenance of myeloid cell subsets that rely on cell division to colonize or to self-maintain within their tissue of residency (including LCs).

      Major comments:

      1. ArpC4 and Arp2/3 expression

      The authors argue that LCs from Arpc4KO mice should delete the Arpc4 gene in precursors that colonize the skin around birth. It would be important to show it to rule out the possibility that the lack of phenotype (initial seeding, initial proliferative burst) in young animals (first week) could be related to an incomplete deletion of ArpC4 expression. Also important would be to show what is happening to the Arp2/3 complex in LCs from Arpc4KO mice. In the in vitro studies with DCs, the level of ArpC4 and Arp2/3 deletion at the protein level is also not documented. The authors explain that surface expression of the CD11c marker, which drives Arpc4 deletion, gradually increased during differentiation of DCs: from 50% to 90% of the cells. Does that mean that loss of ArpC4 expression is only effective in a fraction of the cells examined before day 10 of differentiation (e.g. in the RNA-seq analysis)?

      1. Intra-nuclear versus extra-nuclear activities of Arp2/3

      The authors favor a model whereby intra-nuclear ArpC4 helps maintaining nuclear integrity during proliferation of DCs (and possibly LCs). However, multiple pools of Arp2/3 have been described and accordingly, multiple mechanisms may account for the observed phenotype: i) cytoplasmic pool to drive the protrusions sustaining the assembly of the LC network and its connectivity with keratinocytes ; ii) peri-nuclear pool to protect the nucleus ; iii) Intra-nuclear pool to facilite DNA repair mechanisms e.g. by stabilizing replicative forks (the scenario favored by the authors).

      It is recommended that the authors try to gather more supportive data to sustain the intra-nuclear role. Documenting ArpC4 presence in the nucleus would help support the claim. It could be combined with treatments aiming at blocking proliferation in order to reinforce the possibility that a main function of ArpC4 is to protect proliferating cells by favoring DNA repair inside the nucleus.

      1. Nuclear envelop ruptures

      The nuclear envelop ruptures are not sufficiently documented (how many cells were imaged? quantification?). The authors employ STED microscopy to examine Lamin B1 distribution. The image shown in Figure 4A does not really highlight the nuclear envelop, but rather the entire content. Whether it is representative is questionable. We would expect Lamin B1 staining intensity to be drastically reduced given the quantification shown in Figure 3D. In addition, although the authors have stressed in the previous figure that Arpc4-KO is associated with nucleus shape aberrations, the example shown in Figure 4A is that of a nucleus with a normal ovoid shape.

      It is recommended to quantify the ruptures with Lap2b antibodies (or another staining that would better delineate the envelop) in order to avoid the possible bias due to the reduced staining intensity of Lamin B1.

      A missing analysis is that of nuclear envelop ruptures as a function of nucleus deformations.

      Fig 4B-C: same frequency of Arpc4-KO and WT cells displaying nuclear envelop ruptures in the 4-µm channels; however image show a rupture for the Arpc4-KO and no rupture for the WT cells (this is somehow misleading). Are ruptures similar in Arpc4-KO and WT cells in this condition?

      Fig 4D-E: is their a direct link between nuclear envelop ruptures and ƴH2A.X?

      Interesting (but optional) would be to understand what is happening to DNA, histones? Is their evidence for leakage in the cytoplasm?

      1. RNA seq analysis

      The RNA-seq analysis suffers from a lack of direct connection with the rest of the study. The extracted molecular information is not validated nor further explored. It remains very descriptive. The PCA analysis suggests a « more pronounced transcriptomic heterogeneity in differentiating Arpc4KO DCs ». However it seems difficult to make such a claim from the comparison of 3 mice per group. In addition, such heterogeneity is not seen in the more detailed analysis (Fig 5F). The authors claim that « day 10 control and Arpc4KO DCs showed no to very little differences in gene expression, in contrast to cells at days 7-9 of differentiation ». This is not obvious from the data displayed in the corresponding figure. In addition, it is not expected that cells that may take a divergent differentiation path at days 7-9 may would return to a similar transcriptional activity at day 10. A point that is not discussed is that before day 10 of DC differentiation, Arpc4 KO is expected to only occur in about 50% of the cell population. This is expected to impact the RNA-seq analysis. Not all clusters have been exploited (e.g. cluster 3 elevated, cluster 6 partly reduced). I suggest the authors reconsider their analysis and analysis of the RNA-seq analysis (or eventually invest in complementary analysis).

      1. What causes the profound numerical drop of LC in the epidermis?

      A major open question is what causes the massive drop of LCs. Although differentiating Arpc4KO DCs start accumulating DNA damage upon proliferation, they succeed in progressing through the cell cycle. There is even a slightly elevated expression of cell cycle genes at day 7 of differentiation in the DC model. Only a trend for increased apoptosis is observed in ear and tail skin. It would be important to provide complementary data documenting increased death (or aberrant emigration?) of LCs in the 4-8 week time window.

      1. Functional consequences

      Although the study reports novel aspects of LC biology, the consequence of ArpC4 deletion for skin barrier function and immunosurveillance are not investigated. It would seem very relevant to test how this model copes with radiation, chemical and/or microorganism challenges.

      Minor comments:

      1. Figure 1D

      Gating strategy: twice the same empty plots. The content seems to be missing... Does this need to be shown in the main figure?

      1. Figure 2

      Best would be to keep same scale to compare P1 and P7 (tail skin, figure 2A)

      Overlay of Ki67 and MHC-II does not allow to easily visualize the double-positive cells (Fig 2C)

      Quality of Ki67 staining different for Arpc4-KO (less intense, less focused to the nuclei): a technical issue or could that reflect something?

      Fig 2C: Panels mounted differently for ear and tail skin (different order to present the individual stainings, Dapi for tail skin only).

      1. LC branch analysis (Fig 1 and 2)

      While Fig 1 indicates that ear skin LCs form in average twice as few branches as tail skin LCs (3-4 versus 8-9 branches per cell), Fig 2 shows the opposite (10-12 versus 6-7 branches per cell). Is this due to a very distinct pattern between the 2 considered ages (4 weeks versus 8-10 weeks)? Could the author double-check that there is no methodological bias in their analysis?

      1. Fig 3 E-G

      How many animals were examined (n=5)? Reproducible accros animals? Why was it done with 4-week animals (phenotype not complete? Event occurring before loss in numbers...)

      Staining Lamin A/C globally more intense in the Arpc4-KO epidermis (also seems to apply to the masks corresponding to the LCs). Surprising to see that the quantification indicates a major drop of Lamin A/C intensity in the LCs.

      1. Legend Fig 4D replace confocal microscopy by STED microscopy

      2. Figure 4F

      Intensity/background of γH2Ax staining very distinct between the 2 micrographs shown for WT and Arpc4-KO epidermis.

      1. Figure 7C, F, H

      Gating strategies: would be better to harmonize the style of the plots (dot plots and 2 types of contour plots have been used...)

      1. Figure 7H

      Legend of lower gating strategy seems to be wrong (KO and not WT).

      Significance

      Strengths: the general quality of the manuscript is high. It is very clearly written and it contains a very detailed method section that would allow reproducing the reported experiments. This work entails a clear novelty in that it represents the first investigation of the role of ArpC4 in LCs. It opens an interesting perspective about specific mechanisms sustaining the maintenance of myeloid cell subsets in peripheral tissues. This work is therefore expected to be of interest for a large audience of cellular immunologists and beyond. Challenging skin function with an external trigger would lift the relevance for a even wider audience (see main point 6).

      Limitations: in its current version the manuscript suffers from a lack of solidity around a few analysis (see main points on ArpC4 and Arp2/3 protein expression, nuclear envelop rupture analysis,...). It also tends to formulate a narrative centered on the ArpC4 intra-nuclear function that is not definitely proven.

      The field of expertise of this reviewer is: cellular immunology and actin remodeling.

    1. Note: This response was posted by the corresponding author to Review Commons. The content has not been altered except for formatting.

      Learn more at Review Commons


      Reply to the reviewers

      Revision Plan

      June 28, 2025

      Manuscript number: RC-2025-02982

      Corresponding author(s): Babita Madan, Nathan Harmston, David Virshup

      General Statements In Wnt signaling, the relative contributions of ‘canonical (β-catenin dependent) and non- canonical (β-catenin independent) signaling remains unclear. Here, we exploited a unique and highly robust in vivo system to study this. Our study is therefore the first comprehensive analysis of the β-catenin independent arm of the Wnt signaling pathway in a cancer model and illustrates how a combination of cis-regulatory elements can determine Wnt-dependent gene regulation.

      We are very pleased with the reviews; it appears we communicated our goal and our findings clearly, and in general the reviewers felt the study provided important information, was well planned and the results were “crystal clear”.

      While more experiments could strengthen and extend the results, we feel our results are already very robust due to the use of multiple replicates in the in vivo system.

      The Virshup lab in Singapore closed July 1, 2025 and so additional wet lab studies are not feasible.

      1. Description of the planned revisions

      Insert here a point-by-point reply that explains what revisions, additional experimentations and analyses are planned to address the points raised by the referees.

      Below we address the points raised by the reviewers:

      Reviewer #1 (Evidence, reproducibility and clarity (Required)):

      The article has the merit of addressing a yet-unsolved question in the field (if beta-catenin can also repress genes) that only a limited number of studies has tried to tackle, and provides useful datasets for the community. The system employed is elegant, and the PORCN-inhibition bypassed by a ____constitutively active beta-catenin is clean and ingenious. The manuscript is clearly written.

      We thank the reviewers for their kind comments on the importance of the data. Our orthotopic model provides the opportunity to exploit robust Wnt regulated gene expression in a more responsive microenvironment than can be achieved in cell culture and simple flank xenograft models.

      Here we propose a series of thoughts and comments that, if addressed, would in our opinion improve the study and its description.

      1) We wonder why a xenograft model is necessary to induce a robust WNT response in these cells.

      The authors describe this set-up as a strength, as it is supposed to provide physiological relevance, yet it is not clear to us why this is the case.

      We welcome the opportunity to expand on our choice of an orthotopic xenograft model. It has been long established that cancer cells behave differently in different in vivo locations (Killion et al., 1998). Building on this, we confirmed this in our system that identical pancreatic cancer cells treated with the same PORCN inhibitor had very different responses in vitro, in the flank and in their orthotopic environment (Madan et al., 2018). To quote from our prior paper, “Looking only at genes decreasing more than 1.5-fold at 56 hours, we would have missed 817/1867 (44%) genes using a subcutaneous or 939/1867 (50%) using an in vitro model. Thus, the overall response to Wnt inhibition was reduced in the subcutaneous model and further blunted in vitro. An orthotopic model more accurately represents real biology.

      The reason for this is presumably the very different orthotopic microenvironment, including tissue appropriate stroma-tumor, vascular-tumor, lymphatic-tumor, and humoral interactions.

      Moreover, as the authors homogenize the tumour to perform bulk RNA-seq, we wonder whether they are not only sequencing mRNA from the cancer cells but also from infiltrating immune cells and/or from the surrounding connective tissue.

      In experiments generating RNA-seq data from xenograft models, the resulting sequences can originate from either human (graft) or mouse (host). In order to account for this, following standard practice, we filtered reads prior to alignment using Xenome (Conway et al., 2012). We have added additional text to the methods to highlight this step in our pipeline.

      2) If, as the established view implies, Wnt/beta-catenin only leads to gene activation, pathway

      inhibition would free up the transcriptional machinery - there is evidence that some of its constituents are rate-limiting. The free machinery could now activate some other genes: the net effect observed would be their increased transcription upon Wnt inhibition, irrespective of beta-catenin's presence. Could this be considered as an alternative explanation for the genes that go up in both control and bcat4A lines upon ETC-159 administration? This, we think, is in part corroborated by the absence of enrichment of biological pathways in this group of genes. The genes that are beta-catenin-dependent and downregulated (D&R) are obviously not affected by this alternative explanation.

      This is an interesting suggestion, and we will incorporate this thought into our discussion of potential mechanisms.

      3) The authors mention that HPAF-II are Wnt addicted. Do they die upon ETC-159 administration, and is this effect rescued by exogenous WNT addition?

      We and several others have previously reported that Wnt-addicted cells differentiate and/or senesce upon Wnt withdrawal in vivo but not in vitro. This is related to the broader changes in gene expression in the orthotopic tumors. The effect of PORCN inhibition has been demonstrated by us and others and is rescued by Wnt addition, downstream activation of Wnt signaling by e.g. APC mutation, and, as we show here, stabilized β-catenin.

      4) Line 120: the authors write about Figure 1C: "This demonstrates that the growth of β-cat4A cells in vitro largely requires Wnts to activate β-catenin signaling." The opposite is true: control cells require WNT and form less colony with ETC159, while β-cat4A are independent from Wnt secretion.

      We appreciate the reviewer pointing out our mis-statement. This error has now been corrected in the revised manuscript.

      5) Lines 226-229: "The β-catenin independent repressed genes were notably enriched for motifs bound by homeobox factors including GSC2, POU6F2, and MSGN1. This finding aligns with the known role of non-canonical Wnt signaling in embryonic development" This statement assumes that target genes, or at least the beta-catenin independent ones, are conserved across tissues, including developing organs. This contrasts with the view that target genes in addition to the usual suspects (e.g., AXIN2, SP5 etc.) are modulated tissue-specifically - a view that the authors (and in fact, these reviewers) appear to support in their introduction.

      We agree with the reviewer that a majority of Wnt-regulated genes are tissue specific. Indeed, the β-catenin independent Wnt-repressed genes may also be tissue specific. In other tissues, we speculate that other β-catenin independent Wnt-repressed genes may also have homeobox factor binding sites as well and so the general concept remains valid. We do not have sufficient data in other tissues to resolve this issue.

      7) The luciferase and mutagenesis work presented in Figure 5 are crystal-clear. One important aspect that remains to be clarified is whether beta-catenin and/or TCF7L2 directly bind to the NRE sites. Or do the authors hypothesize that another factor binds here? We suggest the authors to show TCF7L2 binding tracks at the NRE/WRE motifs in the main figures.

      A major question of the reviewers was, can we provide additional evidence that the NRE is bound by LEF/TCF family members. Our initial analysis of more datasets indicates TCF7L2 peaks are enriched on NREs in Wnt-β-catenin responsive cell lines like HCT116 and PANC1. These analyses appear to further support the model that the NRE binds TCF7L2, but we fully agree these analyses can neither prove nor disprove the model.

      In our revision, we will analyze additional cut and run datasets as suggested and look at the HEPG2 datasets suggested by reviewer 1. We are concerned about tissue specificity as some of the genes are not expressed in e.g. HEPG2 or HEK293 cells where datasets are available. However, our data continues to support a functional role for the NRE in the modulation of β-catenin regulated genes. The best analysis would be more ChIP-Seq or Cut and Run assays on tissues, not cells, but these studies are beyond what we can do.

      What about other TCF/LEFs and beta-catenin? Are there relevant datasets that could be explored to test whether all these bind here during Wnt activation?

      As above, We will analyze additional ChIP and Cut & Run datasets to address this question looking at β-catenin and other LEF/TCF family members. We also reflect on the fact that ChIP-Seq does not necessarily imply that the targeted factor (e.g.,TCF7L2) is bound in the target site in all the cells.

      The repression might be mediated by beta-catenin partnering with other factors that bind the NRE even by competing with TCF7L2.

      We appreciate the insightful comments and now incorporate this into our discussion.

      8) In general, while we greatly appreciate the github page to replicate the analysis, we feel that the methods' description is lacking, both concerning analytical details (e.g., the cutoff used for MACS2 peak calling) or basic experimental planning (e.g, how the luciferase assays were performed).

      We thank reviewers for the suggestions and will add further details regarding the analysis

      and experimental planning in the method sections.

      9) The paper might benefit from the addition of quality metrics on the RNA-seq. Interesting for example would be to see a PCA analysis - as a more unbiased approach - rather than the kmeans clustering.

      We have this data and will add it to the revised manuscript.

      10) It seems that in Figure 3A the clusters are mislabelled as compared to Figure 3B and Figure 1. Here the repressor clusters are labelled DR5, DR6 and DN7 whereas in the rest of the paper they are labelled DR1, DR2 and DN1.

      Thank you for pointing out this issue. This has now been corrected in Figure 3.

      11) The siCTNNB1 in Figure 5E is described to be a significant effect in the text whereas in Figure 5E this has a p value of 0.075.

      Thank you for pointing out the p value did not cross the 0.05 threshold. We have modified the text to remove the word ‘significant’.

      12) Line 396: 'Here we confirm and extend the identification of a TCF-dependent negative regulatory element (NRE), where beta-catenin interacts with TCF to repress gene expression'. We suggest caution in stating that beta-catenin and TCF directly repress gene expression by binding to NRE. In the current state the authors do not show that TCF & beta-catenin bind to these elements. See our previous point 7.

      We appreciate the suggestion of the reviewers. We will be more cautious in our interpretation.

      Further suggestions - or food for thoughts:

      13) A frequently asked question in the field concerns the off-target effects of CHIR treatment as opposed to exposure to WNT ligands. CHIR treatment - in parallel to bcat4A overexpression - would allow the authors to delineate WNT independent effects of CHIR treatment and settle this debate.

      We thank the reviewers for suggesting this interesting experiment to sort out the non- Wnt effects of GSK3 inhibition. Such a study would require a new set of animal experiments and a different analysis; we think this is beyond the scope of this manuscript.

      14) We think that Figure 4C could be strengthened by adding more public TCF-related datasets (e.g., from ENCODE) to confirm the observation across datasets from different laboratories. In particular, the HEPG2 could possibly be improved as there is an excellent TCF7L2 dataset available by ENCODE.

      Many more datasets are easily searchable through: https://www.factorbook.org/.

      As above, we will analyze the HEPG2 dataset. We plan on updating Fig 4 with data from analysis from different datasets such as (Blauwkamp et al., 2008; Zambanini et al., 2022).

      15) The authors show that there is no specific spacing between NREs and WREs. This implies that it is not likely that TCF7L2 recognizes both at the same time through the C-clamp. Do the authors think that there might be a pattern discernible when comparing the location of WRE and NRE in relation to the TCF7L2 ChIP-seq peak summit? This would allow inferring whether TCF7L2 more likely directly binds the WRE (presumably) and if the NRE is bound by a cofactor.

      This is an interesting suggestion and we will conduct this analysis as suggested on available datasets (as the result may be different in different tissue types with varying degrees of Wnt/β-catenin signaling).

      Reviewer #2 (Evidence, reproducibility and clarity (Required)):

      Overall, the study provides a solid framework for understanding noncanonical transcriptional ____outputs of Wnt signaling in a cancer context. The majority of the conclusions are well supported by the data. However, there are a few substantive points that require clarification before the manuscript is ready for publication.

      Major Comments

      The authors' central claim-that their findings represent a comprehensive analysis of the β-catenin- independent arm of Wnt signaling and uncover a "cis-regulatory grammar" governing Wnt-dependent gene activation versus repression-is overstated based on the presented data.

      We appreciate the reviewers concern and will temper our language.

      Specifically:

      • Figure 3B identifies TF-binding motifs enriched among different Wnt-responsive gene clusters, but the authors only functionally investigate the role of NRE in β-catenin-dependent repression, particularly in the context of TCF motif interaction.

      • To support a broader claim regarding cis-regulatory grammar, additional analyses are required:

      o What is the distribution of NREs across all clusters? Are they exclusive to β-catenin-dependent repressed clusters, or more broadly present?

      The distribution of the NREs is a statistically significant enrichment; they are observed in the repressed clusters more frequently than expected by chance alone, but they are present elsewhere as well. We have tempered our language around the cis-regulatory grammar.

      o Do NREs interact with other enriched motifs beyond TCF? Is this interaction specific to repression or also involved in activation?

      This is an interesting question beyond the scope of this analysis. Our dataset uses multiple interventions; The NREs may interact with other motifs but we would need more transcriptional analysis data with biological intervention to assess this.

      o A more comprehensive analysis of cis-element combinations is needed to draw conclusions about their collective influence on gene regulation across clusters.

      We agree; This would be a great question if we had TCF binding data in our orthotopic xenograft model. It’s a dataset we do not have, nor do we have the resources to pursue this.

      Other important clarifications:

      • The use of the term "wild-type" to describe HPAF-II cells is potentially misleading. These cells are not genetically wild-type and harbor multiple oncogenic alterations.

      Thank you for pointing this out. We will use the word “parental” in the text

      • The manuscript does not clearly present the kinetics of Wnt target downregulation upon ETC-159 treatment of HPAF-II cells. Understanding whether repression mirrors activation dynamics (e.g., delay or persistence of Wnt effects) is essential to interpreting the system's temporal behavior.

      We previously addressed the temporal dynamics of activation and repression in our more comprehensive time course papers (Harmston et al., 2020; Madan et al., 2018); there are differences in the dynamics that are difficult to tease out in this new dataset as the density of time points is less. Having said that, we will compare the time course and annotate the sets of genes identified in this current study with the data from our original study to provide more information on the temporal dynamics of this system.

      Minor Comment

      • The statement in Figure 1C (lines 119-120) that "growth of β-cat4A cells in vitro largely requires Wnts to activate β-catenin signaling" is inconsistent with the data. As the β-cat4A allele encodes a constitutively active form of β-catenin, Wnts should not be required. Please revise this conclusion for clarity.

      We thank the reviewers for pointing out this mis-statement. We have corrected this.

      Reviewer #2 (Significance (Required)):

      This study offers a systematic classification of Wnt-responsive gene expression dynamics, differentiating between β-catenin-dependent and -independent mechanisms. The insights into temporal expression patterns and the potential role of the NRE element in transcriptional repression add depth to our understanding of Wnt signaling. These findings have relevance for developmental biology, stem cell biology, and cancer research-particularly in understanding how Wnt-mediated repression may influence tumor progression and therapeutic response.

      Nice review; thank you.

      Reviewer #3 (Evidence, reproducibility and clarity (Required)):

      … The work advances understanding of Wnt mediated repression via cis regulatory grammar.

      Major Concerns

      1) Statistical thresholds and clustering - The criteria for classifying β catenin-dependent versus - independent genes rely on FDR cutoffs above or below 0.1. If the more stringent cutoff of 0.05 was used, how many genes would still be considered Wnt regulated?

      We can readily address this in a revised manuscript.

      2) Validation of selected β catenin-dependent and -independent Wnt target genes - While the authors identify β catenin-dependent and -independent Wnt target genes (4 selected genes from different clusters in Fig.2), RT-qPCR based validation of Axin2 has been performed in Fig. S3. Authors should also validate other 3 genes as well.

      We had considered performing qPCR to re-validate some of our gene-expression changes but qPCR analyses is intrinsically more error prone than RNAseq, and we believe the literature shows that qPCR from the same samples will not add any extra utility. Previous studies that have examined this question have reported excellent correlation between the RNAseq and pPCR (Asmann et al., 2009; Griffith et al., 2010; Wu et al., 2014).

      3) NRE mechanistic insight - The most important contribution of this manuscript is the extension of the importance of the NRE motif in Wnt regulated enhancers. But the mutagenesis data provided is insufficient to conclusively nail down that the NREs are responsible for the repression. The effects in the synthetic reporters in Fig. 4D are small - it's not clear that there is much activity in the MimRep to be repressed by the NREs. The data in Fig. 5 is a better context to test the importance of the NREs, but the authors use deletion analysis which is too imprecise and settle for single nucleotide mutants in individual NREs in the ABHD11-AS1 reporter. In the Axin2 report, they mutate sequences outside of the NRE. It's too inconsistent. They should mutate 3 or 4 positions within the NRE in BOTH motifs in the context of the ABHD11-AS1 reporter. Same for the Axin2 reporter.

      We feel our analysis, coupled with the Kim paper (Kim et al., 2017), support the role of the NRE. We agree that more data is always desirable, but in our current circumstances are we cannot add additional wetlab experiments.

      Regarding Figure 4D, this is a synthetic system lacking the endogenous elements in the promoter. We agree with the reviewer that the effect is small but we would also like to point out that adding the well-established 2WRE in front of the MinRep increased the transcription activity to 1.5 fold, which is of similar magnitude change of the 2NRE deceasing the transcriptional activity 1/1.5 = 0.6.

      In Kim et al, it was shown that mutating the 11st nucleotide of the NRE motif showed the strongest effect, so we followed their lead in only mutated the 11st nucleotide in ABHD11- AS1 NRE.

      As for the putative NRE sequence present in AXIN2 promoter, its downstream sequence is polyT (__GTGTTTTTTTT__TTTTTTTTTT), if we only mutate 11st nucleotide to G/C, we could create similar sequence to NRE, so we mutated sequences outside of the NRE to fully disrupt it.

      4) Even if the mutagenesis is done more completely, the results simply replicate that of the Goentoro group. In Kim et al 2017, they provide suggestive (not convincing) evidence that TCFs directly bind to the NRE. The authors of this manuscript should explore that in more detail, e.g., can purified TCF bind to the NRE sequence? Can the authors design experiments to directly test whether beta-catenin is acting through the NRE - their data currently only demonstrates that the NRE provide a negative input to the reporters - that's an important mechanistic difference.

      We point out that our minimal reporter studies with the NRE showed a repressive effect in HCT116 (colorectal cancer cells with stabilized β-catenin) but not HT1080 (sarcoma cells with low Wnt) supporting the importance of β-catenin acting through the NRE (Figs. 4D, 4E).

      We fully agree with the reviewers that additional study of TCF interaction with the NRE would be of value. While EMSA and culture-based ChIP assays would be of some value, the best study should be done in vivo where the system is most robust. We are not in a position to do these studies, but we will add in a discussion of this as a limitation of the current study.

      5) In vertebrates, some TCFs are more repressive than others and TLEs have been implicated in repressive. Exploring these factors in the context of the NRE would increase the value of this story.

      This is an interesting idea but beyond the scope of the current manuscript. It is likely this would be dependent on tissue specific expression, local expression levels, and local binding of co-factors. As we look at other TCF members in other datasets we may be able to address this. Further wetlab experiments are beyond the scope of this work.

      **Referees cross-commenting**

      I respectfully disagree that the luciferase assays are sufficient. Using deletion analysis to understand the function of specific binding sites is insufficient and the more specific mutations of NREs are incomplete. Regarding this paper extending our knowledge of direct transcriptional repression by Wnt/bcat signaling, I don't agree that it adds much - there are numerous datasets where Wnt signaling activates and represses genes - the trick is determining whether any of the repressed genes are the result and direct regulation by TCF/bcat. They don't explore that. The main finding is an extension of the work by Lea Goentoro on the importance of the NRE motif, but they don't address whether TCF directly associates with this sequence. Goentoro argued in the 2017 paper that it does, but that data is unconvincing to me. Can purified TCF bind the NRE? Without that information (done carefully) this manuscript is very limited.

      We respectfully disagree with the reviewer regarding the contribution of this manuscript. There are certainly many datasets looking at Wnt-regulated genes in tissue culture, but these cell-based studies are underpowered to really understand Wnt biology. There are only two papers, ours and Cantú’s, that address Wnt repressed genes in any depth. No prior papers have differentiated β-catenin dependent from β-catenin independent genes before, and certainly not in an orthotopic animal model.

      A major impact of our study is the finding that only 10% of Wnt regulated genes are independent of β-catenin, at least in pancreatic cancer. We feel this is a major contribution. We further add to this analysis by re-enforcing/extend the prior evidence on the NRE in humans (and correct the motif sequence!) for Wnt-repressed genes. Our data supports the fine-tuning of the Wnt/β-catenin regulated genes by a cis-regulatory grammar.

      Reviewer #3 (Significance (Required)):

      Overall, this study advances our understanding of the dual roles of Wnt signaling in gene activation and repression, highlighting the role of the NRE motif. But this is an extension of the original NRE paper (Kim et al 2017) with no mechanistic advance beyond that original work. The transcriptomics in the first part of the manuscript have some value, but similar data sets already exist.

      We respectfully but strongly disagree with the reviewer. First, our work examines the NRE in a large-scale in vivo transcriptome dataset, significantly extending the candidate gene approach of Kim et al. Secondly, we disagree with the comment that “similar data sets already exist.” Indeed, reviewer 1 (C. Cantú) specifically pointed out we had addressed an “yet-unsolved question in the field” on whether and how β-catenin repressed genes.

      __3. __Description of the revisions that have already been incorporated in the transferred manuscript

      To date we have only corrected several typographical errors.

      1. Description of analyses that authors prefer not to carry out

      We fully agree with the reviewers that additional study of TCF interaction with the NRE would be of value. While EMSA and cell culture-based ChIP assays would be of some modest value, they have already been done in vitro by Kim et al. (Kim et al., 2017) and the best next study should be done in vivo in Wnt-responsive cancers or tissues where the biology is most robust (Madan et al., 2018) . We are not in a position to do these studies, but we will add this into the discussion as a limitation of the current study. We also acknowledge that the NRE may interact with other currently unidentified factors.

      Reviewer 1 asked about considering experiments to determine non-Wnt effects of GSK3 inhibitors like CHIR. Such a study, while interesting, would require a new set of animal experiments and a different analysis; we think this is beyond the scope of this manuscript.

      Finally, we note that the Virshup lab at Duke-NUS Medical School in Singapore, where these in vivo studies were performed, has closed as of July 1, 2025 and the various lab members have moved on to new adventures. Because of this, we are unable to undertake new wet-lab studies.

      Thank you for your consideration,

      For the authors,

      David Virshup

      References:

      Asmann YW, Klee EW, Thompson EA, Perez EA, Middha S, Oberg AL, Therneau TM, Smith DI,

      Poland GA, Wieben ED, Kocher J-PA. 2009. 3’ tag digital gene expression profiling of human

      brain and universal reference RNA using Illumina Genome Analyzer. BMC Genom 10:531–

      1. doi:10.1186/1471-2164-10-531

      Blauwkamp TA, Chang MV, Cadigan KM. 2008. Novel TCF-binding sites specify transcriptional

      repression by Wnt signalling. The EMBO Journal 27:1436–1446. doi:10.1038/emboj.2008.80

      Conway T, Wazny J, Bromage A, Tymms M, Sooraj D, Williams ED, Beresford-Smith B. 2012.

      Xenome—a tool for classifying reads from xenograft samples. Bioinformatics 28:i172–i178.

      doi:10.1093/bioinformatics/bts236

      Griffith M, Griffith OL, Mwenifumbo J, Goya R, Morrissy AS, Morin RD, Corbett R, Tang MJ, Hou

      Y-C, Pugh TJ, Robertson G, Chittaranjan S, Ally A, Asano JK, Chan SY, Li HI, McDonald H,

      Teague K, Zhao Y, Zeng T, Delaney A, Hirst M, Morin GB, Jones SJM, Tai IT, Marra MA.

      1. Alternative expression analysis by RNA sequencing. Nat Methods 7:843–847.

      doi:10.1038/nmeth.1503

      Harmston N, Lim JYS, Arqués O, Palmer HG, Petretto E, Virshup DM, Madan B. 2020.

      Widespread Repression of Gene Expression in Cancer by a Wnt/β-Catenin/MAPK Pathway.

      Cancer Res 81:464–475. doi:10.1158/0008-5472.can-20-2129

      Killion JJ, Radinsky R, Fidler IJ. 1998. Orthotopic models are necessary to predict therapy of

      transplantable tumors in mice. Cancer metastasis reviews 17:279–284.

      Kim K, Cho J, Hilzinger TS, Nunns H, Liu A, Ryba BE, Goentoro L. 2017. Two-Element

      Transcriptional Regulation in the Canonical Wnt Pathway. Current Biology 27:2357-2364.e5.

      doi:10.1016/j.cub.2017.06.037

      Madan B, Harmston N, Nallan G, Montoya A, Faull P, Petretto E, Virshup DM. 2018. Temporal

      dynamics of Wnt-dependent transcriptome reveals an oncogenic Wnt/MYC/ribosome axis. J

      Clin Invest 128:5620–5633. doi:10.1172/jci122383

      Wu AR, Neff NF, Kalisky T, Dalerba P, Treutlein B, Rothenberg ME, Mburu FM, Mantalas GL,

      Sim S, Clarke MF, Quake SR. 2014. Quantitative assessment of single-cell RNA-sequencing

      methods. Nat Methods 11:41–46. doi:10.1038/nmeth.2694

      Zambanini G, Nordin A, Jonasson M, Pagella P, Cantù C. 2022. A new cut&run low volume-

      urea (LoV-U) protocol optimized for transcriptional co-factors uncovers Wnt/b-catenin tissue-

      specific genomic targets. Development 149. doi:10.1242/dev.201124

    2. Note: This preprint has been reviewed by subject experts for Review Commons. Content has not been altered except for formatting.

      Learn more at Review Commons


      Referee #3

      Evidence, reproducibility and clarity

      The authors use a PORCN inhibitor (ETC 159) in an orthotopic RNF43 mutant pancreatic cancer model to distinguish β catenin-dependent from -independent Wnt target genes. They find that ~90% of Wnt regulated genes in this system are β catenin dependent. Approximately half of these genes are activated by Wnt signaling, half repressed. Clustering and functional enrichment link dependent versus independent targets to distinct pathways. They observe enrichment of sequence motifs similar to the 11 bp Negative Regulatory Element (NRE) previously identified by Lea Goentoro's group in the region around the TSS of β catenin-repressed genes. Using reporter constructs, both synthetic and regulatory DNA from Wnt targets (e.g., ABHD11 AS1, AXIN2), they provide evidence that the NREs are a negative input on expression. The work advances understanding of Wnt mediated repression via cis regulatory grammar.

      Major Concerns

      1. Statistical thresholds and clustering - The criteria for classifying β catenin-dependent versus -independent genes rely on FDR cutoffs above or below 0.1. If the more stringent cutoff of 0.05 was used, how many genes would still be considered Wnt regulated?
      2. Validation of selected β catenin-dependent and -independent Wnt target genes - While the authors identify β catenin-dependent and -independent Wnt target genes (4 selected genes from different clusters in Fig.2), RT-qPCR based validation of Axin2 has been performed in Fig. S3. Authors should also validate other 3 genes as well.
      3. NRE mechanistic insight - The most important contribution of this manuscript is the extension of the importance of the NRE motif in Wnt regulated enhancers. But the mutagenesis data provided is insufficient to conclusively nail down that the NREs are responsible for the repression. The effects in the synthetic reporters in Fig. 4D are small - it's not clear that there is much activity in the MimRep to be repressed by the NREs. The data in Fig. 5 is a better context to test the importance of the NREs, but the authors use deletion analysis which is too imprecise and settle for single nucleotide mutants in individual NREs in the ABHD11-AS1 reporter. In the Axin2 report, they mutate sequences outside of the NRE. It's too inconsistent. They should mutate 3 or 4 positions within the NRE in BOTH motifs in the context of the ABHD11-AS1 reporter. Same for the Axin2 reporter.
      4. Even if the mutagenesis is done more completely, the results simply replicate that of the Goentoro group. In Kim et al 2017, they provide suggestive (not convincing) evidence that TCFs directly bind to the NRE. The authors of this manuscript should explore that in more detail, e.g., can purified TCF bind to the NRE sequence? Can the authors design experiments to directly test whether beta-catenin is acting through the NRE - their data currently only demonstrates that the NRE provide a negative input to the reporters - that's an important mechanistic difference.
      5. In vertebrates, some TCFs are more repressive than others and TLEs have been implicated in repressive. Exploring these factors in the context of the NRE would increase the value of this story.

      Referees cross-commenting

      I respectfully disagree that the luciferase assays are sufficient. Using deletion analysis to understand the function of specific binding sites is insufficient and the more specfic mutations of NREs are incomplete. Regarding this paper extending our knowledge of direct transcriptional repression by Wnt/bcat signaling, I don't agree that it adds much - there are numerous datasets where Wnt signaling activates and represses genes - the trick is determining whether any of the repressed genes are the result and direct regulation by TCF/bcat. They don't explore that. The main finding is an extension of the work by Lea Goentoro on the importance of the NRE motif, but they don't address whether TCF directly associates with this sequence. Goentoro argued in the 2017 paper that it does, but that data is unconvincing to me. Can purified TCF bind the NRE? Without that information (done carefully) this manuscript is very limited.

      Significance

      Overall, this study advances our understanding of the dual roles of Wnt signaling in gene activation and repression, highlighting the role of the NRE motif. But this is an extension of the original NRE paper (Kim et al 2017) with no mechanistic advance beyond that original work. The transcriptomics in the first part of the manuscript have some value, but similar data sets already exist.

      Addressing the major points-especially gaining a deeper mechanistic insight into NRE function-would elevate the manuscript's impact. Major revisions are recommended.

    3. Note: This preprint has been reviewed by subject experts for Review Commons. Content has not been altered except for formatting.

      Learn more at Review Commons


      Referee #1

      Evidence, reproducibility and clarity

      Shiyang Liu and colleagues investigate the transcription induced by Wnt/beta-catenin by employing PORCN inhibition (ECT-159, blocking the secretion of WNTs) in the Wnt-addicted HPAF-II cell line. Classical targets, such as AXIN2, are downregulated by PORCN inhibition (as expected), while many other genes are upregulated, suggesting that Wnt/beta-catenin represses them. Overexpression of a GSK3/CK1-insensitive beta-catenin variant leads to the re-established upregulation of AXIN2 and the concomitant repression of the other group of repressed genes, demonstrating that the repression is mediated by beta-catenin. Other genes are repressed (activated by ECT-159) irrespective of the presence of activated beta-catenin, and the authors conclude that they are beta-catenin-independent Wnt-repressed genes. The authors observe that beta-catenin-dependent repressed genes present enrichment, in their promoters, of the Negative Regulatory Element (NRE) previously identified by the Goentoro lab. In elegant Luciferase assays, the authors now confirm that individual NRE elements are causally involved in target gene repression by -catenin. The article has the merit of addressing a yet-unsolved question in the field (if beta-catenin can also repress genes) that only a limited number of studies has tried to tackle, and provides useful datasets for the community. The system employed is elegant, and the PORCN-inhibition bypassed by a constitutively active beta-catenin is clean and ingenious. The manuscript is clearly written.

      Here we propose a series of thoughts and comments that, if addressed, would in our opinion improve the study and its description.

      1. We wonder why a xenograft model is necessary to induce a robust WNT response in these cells. The authors describe this set-up as a strength, as it is supposed to provide physiological relevance, yet it is not clear to us why this is the case. Moreover, as the authors homogenize the tumour to perform bulk RNA-seq, we wonder whether they are not only sequencing mRNA from the cancer cells but also from infiltrating immune cells and/or from the surrounding connective tissue.
      2. If, as the established view implies, Wnt/beta-catenin only leads to gene activation, pathway inhibition would free up the transcriptional machinery - there is evidence that some of its constituents are rate-limiting. The free machinery could now activate some other genes: the net effect observed would be their increased transcription upon Wnt inhibition, irrespective of beta-catenin's presence. Could this be considered as an alternative explanation for the genes that go up in both control and cat4A lines upon ETC-159 administration? This, we think, is in part corroborated by the absence of enrichment of biological pathways in this group of genes. The genes that are beta-catenin-dependent and downregulated (D&R) are obviously not affected by this alternative explanation.
      3. The authors mention that HPAF-II are Wnt addicted. Do they die upon ETC-159 administration, and is this effect rescued by exogenous WNT addition?
      4. Line 120: the authors write about Figure 1C: "This demonstrates that the growth of β-cat4A cells in vitro largely requires Wnts to activate β-catenin signaling." The opposite is true: control cells require WNT and form less colony with ETC159, while β-cat4A are independent from Wnt secretion.
      5. Lines 226-229: "The β-catenin independent repressed genes were notably enriched for motifs bound by homeobox factors including GSC2, POU6F2, and MSGN1. This finding aligns with the known role of non-canonical Wnt signaling in embryonic development." This statement assumes that target genes, or at least the beta-catenin independent ones, are conserved across tissues, including developing organs. This contrasts with the view that target genes in addition to the usual suspects (e.g., AXIN2, SP5 etc.) are modulated tissue-specifically - a view that the authors (and in fact, these reviewers) appear to support in their introduction.
      6. The luciferase and mutagenesis work presented in Figure 5 are crystal-clear. One important aspect that remains to be clarified is whether beta-catenin and/or TCF7L2 directly bind to the NRE sites. Or do the authors hypothesize that another factor binds here? We suggest the authors to show TCF7L2 binding tracks at the NRE/WRE motifs in the main figures. What about other TCF/LEFs and beta-catenin? Are there relevant datasets that could be explored to test whether all these bind here during Wnt activation? We also reflect on the fact that ChIP-Seq does not necessarily imply that the targeted factor (e.g., TCF7L2) is bound in the target site in all the cells. The repression might be mediated by beta-catenin partnering with other factors that bind the NRE even by competing with TCF7L2.
      7. In general, while we greatly appreciate the github page to replicate the analysis, we feel that the methods' description is lacking, both concerning analytical details (e.g., the cutoff used for MACS2 peak calling) or basic experimental planning (e.g, how the luciferase assays were performed).
      8. The paper might benefit from the addition of quality metrics on the RNA-seq. Interesting for example would be to see a PCA analysis - as a more unbiased approach - rather than the kmeans clustering.
      9. It seems that in Figure 3A the clusters are mislabelled as compared to Figure 3B and Figure 1. Here the repressor clusters are labelled DR5, DR6 and DN7 whereas in the rest of the paper they are labelled DR1, DR2 and DN1.
      10. The siCTNNB1 in Figure 5E is described to be a significant effect in the text whereas in Figure 5E this has a p value of 0.075.
      11. Line 396: 'Here we confirm and extend the identification of a TCF-dependent negative regulatory element (NRE), where beta-catenin interacts with TCF to repress gene expression'. We suggest caution in stating that beta-catenin and TCF directly repress gene expression by binding to NRE. In the current state the authors do not show that TCF & beta-catenin bind to these elements. See our previous point 7.

      Further suggestions - or food for thoughts: 13. A frequently asked question in the field concerns the off-target effects of CHIR treatment as opposed to exposure to WNT ligands. CHIR treatment - in parallel to bcat4A overexpression - would allow the authors to delineate WNT independent effects of CHIR treatment and settle this debate. 14. We think that Figure 4C could be strengthened by adding more public TCF-related datasets (e.g., from ENCODE) to confirm the observation across datasets from different laboratories. In particular, the HEPG2 could possibly be improved as there is an excellent TCF7L2 dataset available by ENCODE. Many more datasets are easily searchable through: https://www.factorbook.org/. 15. The authors show that there is no specific spacing between NREs and WREs. This implies that it is not likely that TCF7L2 recognizes both at the same time through the C-clamp. Do the authors think that there might be a pattern discernible when comparing the location of WRE and NRE in relation to the TCF7L2 ChIP-seq peak summit? This would allow inferring whether TCF7L2 more likely directly binds the WRE (presumably) and if the NRE is bound by a cofactor.

      Review by Claudio Cantù and Yorick van de Grift

      Why we sign: we believe that peer review should be a transparent dialogue. We strive to be critical but honest and professional, and care that our opinions and criticisms are formulated as if we were meeting the authors in person.

      Our expertise lies in the genomics impact of Wnt/beta-catenin activation, and in the search of mechanisms that drive the tissue-specific functions of this pathway across developmental and disease contexts.

      Significance

      Shiyang Liu and colleagues investigate the transcription induced by Wnt/beta-catenin by employing PORCN inhibition (ECT-159, blocking the secretion of WNTs) in the Wnt-addicted HPAF-II cell line. Classical targets, such as AXIN2, are downregulated by PORCN inhibition (as expected), while many other genes are upregulated, suggesting that Wnt/beta-catenin represses them. Overexpression of a GSK3/CK1-insensitive beta-catenin variant leads to the re-established upregulation of AXIN2 and the concomitant repression of the other group of repressed genes, demonstrating that the repression is mediated by beta-catenin. Other genes are repressed (activated by ECT-159) irrespective of the presence of activated beta-catenin, and the authors conclude that they are beta-catenin-independent Wnt-repressed genes. The authors observe that beta-catenin-dependent repressed genes present enrichment, in their promoters, of the Negative Regulatory Element (NRE) previously identified by the Goentoro lab. In elegant Luciferase assays, the authors now confirm that individual NRE elements are causally involved in target gene repression by -catenin. The article has the merit of addressing a yet-unsolved question in the field (if beta-catenin can also repress genes) that only a limited number of studies has tried to tackle, and provides useful datasets for the community. The system employed is elegant, and the PORCN-inhibition bypassed by a constitutively active beta-catenin is clean and ingenious. The manuscript is clearly written.

    1. Document de Synthèse : Lancement du Cours en Ligne "Qui S'en Soucie ?" : Un Guide ARAO pour le Soutien à la Santé Mentale des Jeunes

      Introduction

      • Ce document de synthèse présente les thèmes principaux, les idées et les faits les plus importants tirés du lancement du cours en ligne "Qui S'en Soucie ? Un guide antiraciste et anti-oppressif pour soutenir la santé mentale des jeunes". Ce webinaire, animé par Katherine Project de la Fondation Canadienne des Femmes (FCF), avec la participation d'Erin Willlet de New Room et de Roxane Deforge de Pure and Applied, marque le dévoilement d'une ressource essentielle développée pour soutenir les travailleurs jeunesse au Canada, en particulier ceux qui travaillent avec des jeunes marginalisés.

      1. Contexte et Objectifs du Projet

      La Fondation Canadienne des Femmes est un leader national dans le mouvement pour l'égalité des genres au Canada, œuvrant depuis 1991 au changement systémique.

      Le projet "Qui S'en Soucie ?" est le résultat d'un financement de la Fondation Tree of Life, visant à créer un outil utile pour les bénéficiaires du Fonds pour les Filles (Girls Fund) de la FCF.

      • Le Fonds pour les Filles : Depuis 20 ans, le Fonds pour les Filles soutient des programmes pour les filles et les jeunes non-binaires âgés de 9 à 13 ans. Ces programmes variés (sciences, sports, arts, leadership, enseignements autochtones) partagent tous l'objectif de "donner aux participants des outils pour développer leur estime de soi, apprendre à se connaître et acquérir de nouvelles compétences dans un espace sûr et aussi dans un espace réservé aux filles ou aux filles et jeunes non-binaires".
      • Identification d'un besoin crucial : Les praticiens jeunesse ont identifié la santé mentale comme une préoccupation majeure dans leur travail avec les jeunes, exacerbée par la pandémie de COVID-19 et le climat politique actuel, qui rend le monde "moins sûr pour certains jeunes, en particulier les jeunes trans et non-binaires". Les impacts sont "plus graves pour certaines populations, en particulier les jeunes autochtones, les jeunes noirs et racisés, ainsi que les jeunes trans et non-binaires."
      • Objectif du cours : Le projet vise à "mieux équiper" les travailleurs jeunesse, qui ne sont pas nécessairement des professionnels de la santé mentale, pour "intervenir" face aux besoins des jeunes, sans chercher à en faire des professionnels de la santé mentale. L'accent est mis sur "l'importance du travail communautaire, travailler en communauté" et "utiliser le pouvoir de leur communauté pour agir."

      2. Phase de Recherche : Constats et Recommandations Clés

      La phase de recherche a été menée par Taylor Newberry Consulting, combinant une revue de littérature et des consultations (entretiens et groupes de discussion) avec des jeunes et des organisations jeunesse.

      L'objectif était de comprendre les défis rencontrés par les jeunes racisé.e.s et de diverses identités de genre dans l'accès aux services de santé mentale, ainsi que le rôle des organisations jeunesse.

      • Impact du racisme et de la transphobie : La recherche a montré que "le racisme et la transphobie ont un impact négatif sur la santé mentale des jeunes". Il est crucial de disposer de recherches pour "étayer cela et montrer l'impact plus en détail", soulignant l'importance d'une "approche anti-oppressive et d'un travail en communauté" pour améliorer la santé mentale des jeunes, plutôt que des solutions purement individuelles.
      • Recommandations spécifiques aux groupes :
      • Jeunes trans et non-binaires : Nécessitent un "soutien solide de la part des aidants", des "relations sociales et entre pairs solides" et un "accès à des soins d'affirmation de genre" pour protéger leur bien-être.
      • Jeunes filles noires : Le personnel de soutien devrait "les encourager à célébrer leur identité ethnique et raciale" et travailler avec les aidants pour "promouvoir le patrimoine culturel".
      • Jeunes racisé.e.s : Une "programmation tenant compte des traumatismes est essentielle" pour améliorer leur bien-être mental.
      • Jeunes autochtones : Il est "essentiel de fournir une programmation de santé mentale culturellement sûre et appropriée", en travaillant avec des "aînés autochtones et des gardiens du savoir pour favoriser l'identité culturelle, la connexion et autonomiser les jeunes autochtones".
      • Besoins des jeunes : Les jeunes ont exprimé le désir d'avoir des "conversations plus profondes sur la santé mentale" et la nécessité d'"espaces sûrs et inclusifs au sein de la communauté où ils peuvent accéder si besoin." Ces espaces sont "très nécessaires pour bâtir une communauté parmi les jeunes racisé.e.s et non-conformes au genre."
      • Approche intersectionnelle : Le projet a veillé à ne pas "mettre tous ces jeunes et tous ces groupes dans le même sac", reconnaissant les "particularités de chaque groupe et aussi au sein de chaque groupe". Le cours insiste sur "l'importance de prendre chaque jeune individuellement pour ce qu'il est et de s'assurer que les services sont adaptés à ses besoins."
      • Importance de la communauté élargie : Les prestataires de services ont souligné l'importance de "ne pas se concentrer uniquement sur les jeunes eux-mêmes, mais de fournir une éducation à l'ensemble de la communauté" pour sensibiliser au racisme et à la transphobie.

      3. Phases de Conception et de Pilotage du Cours en Ligne

      Le développement du cours a été un processus intensif de 10 mois, impliquant New Room et Pure and Applied, ainsi que les bénéficiaires du Fonds pour les Filles.

      • Évaluation des besoins : Cette phase "fondamentale" a complété la recherche de Taylor Newberry en incluant des "conversations approfondies avec 14 équipes de bénéficiaires". Cela a permis de comprendre leurs "expériences vécues", les "implications de leur travail" et les "obstacles à la prestation de ce type de soins de santé mentale axés sur les jeunes."
      • Co-création et partenariat : Le projet a mis l'accent sur le "pouvoir du partenariat", de la "collaboration" et de la "co-création" pour bâtir des approches "durables et stratégiques". Roxane Deforge a souligné l'importance de "décentrer soi-même" en tant que concepteur pédagogique pour que le contenu "parle vraiment à l'apprenant visé et ne soit donc pas utile." Erin Willlet a insisté sur les "valeurs féministes intersectionnelles" de la FCF, "fondamentales pour bâtir un cours comme celui-ci".
      • Modèle basé sur les compétences : Le cours se concentre sur les compétences ("skills-based model") plutôt que sur la simple transmission de connaissances, afin de permettre aux apprenants "d'appliquer ce qu'ils ont appris dans le contexte de leur travail quotidien."
      • Structure du cours : Le cours est conçu pour être à la fois individuel et "auto-rythmé" ("self-paced"), tout en encourageant l'aspect communautaire. Il comprend quatre modules :
      • Aperçu du cours (très court)
      • Contexte, théorie et langage (informations fondamentales sur les systèmes d'oppression, les dynamiques de pouvoir, la suprématie des adultes, le contexte historique des jeunes marginalisés).
      • Pratiques, compétences et exercices (le "toolkit", abordant trois types d'outils) :
      • Sensibilité culturelle (cultural responsiveness) : "fondamentale pour faire ce travail avec humilité et curiosité et célébrer l'identité et les éléments culturels".
      • Créer des espaces plus sûrs (building safer spaces) : Axé sur les pratiques de facilitation tenant compte des traumatismes et l'établissement du ton.
      • Autonomisation des jeunes (empowering the youth) : Soutenir les jeunes dans leur processus de transformation.
      • L'auto-soin est un soin communautaire (self-care is community care) : Un module essentiel pour la résilience des travailleurs jeunesse, abordant le bien-être physique, mental, émotionnel, spirituel, artistique et créatif. L'objectif est de rendre l'auto-soin "plus intentionnel" et "propre à votre identité, à votre culture, à vos croyances spirituelles."
      • Métaphore du papillon et du jardin : Le cours utilise la métaphore du papillon (représentant les jeunes en pleine métamorphose entre 9 et 13 ans), du cocon (l'environnement de soutien) et du jardin (la communauté et le contexte culturel) pour inspirer la conception visuelle et conceptuelle du contenu.
      • Format et accessibilité : Le cours est disponible gratuitement en ligne sur learn.canadianwomen.org. Il est estimé à "20 à 25 heures" d'apprentissage, incluant les activités et la réflexion personnelle. Il n'est pas nécessaire de le suivre de manière linéaire, les apprenants peuvent "sauter entre les sections" en fonction de leurs besoins. Il est recommandé de prendre son temps, car le cours "vise à susciter beaucoup de réflexion personnelle" et non pas à être rapidement terminé. Un "cahier d'exercices éditable" est fourni pour la réflexion et l'application pratique. Le contenu est disponible en français et en anglais.

      4. Public Cible et Application Pratique

      Le cours est principalement destiné aux travailleurs jeunesse, mais sa portée est plus large :

      • Flexibilité pour les apprenants : Le cours est conçu pour être "quelque chose que les gens peuvent tirer" en fonction de "qui ils sont, du contexte dans lequel ils se trouvent, du travail qu'ils font, des jeunes qui sont devant eux."
      • Potentiel pour divers contextes : Le cours est "absolument" adapté aux bénévoles dans les refuges ou toute personne travaillant avec des jeunes en groupe, comme les professeurs de lycée.
      • Approche communautaire encouragée : Bien qu'il s'agisse d'un cours individuel, il est fortement encouragé de le suivre "avec des collègues ou avec des amis" pour créer une "communauté" d'apprentissage et de soutien, avec des enregistrements réguliers.

      5. Représentation et Perspectives Futures

      La question de la représentation au sein des présentateurs a été soulevée et adressée.

      Bien que les présentatrices du webinaire soient toutes blanches, l'équipe de développement du cours était diverse, incluant la partenaire d'affaires d'Erin Willlet, Danny Joe, qui est noire.

      Les intervenantes ont reconnu l'importance de cette préoccupation et ont remercié la participante de l'avoir soulevée, promettant de faire mieux à l'avenir en termes de représentation lors des présentations publiques.

      • Projets futurs : La FCF a l'intention d'approfondir les modules existants et d'en créer de nouveaux. Un projet en cours, financé par Condition féminine Canada, vise à "adapter ce programme à la population du Nord" en se concentrant sur les "perspectives inuites". L'objectif est de continuer à "aller plus en profondeur" plutôt que de reproduire des programmes 101 déjà existants.
        1. Thèmes Importants Abordés dans le Cours
      • Anti-racisme et anti-oppression : Un fil conducteur essentiel, reconnaissant les impacts systémiques sur la santé mentale des jeunes.
      • Humilité culturelle et curiosité : Considérées comme les compétences les plus importantes pour les praticiens.
      • Intervention axée sur les traumatismes : Intégrée dans les pratiques de facilitation.
      • Auto-soin et résilience : Crucial pour les travailleurs jeunesse afin de prévenir l'épuisement professionnel.
      • L'importance du contexte et des systèmes : Comprendre comment les structures de pouvoir influencent le bien-être des jeunes.

      En conclusion, le cours "Qui S'en Soucie ?" est une ressource complète et soigneusement élaborée, ancrée dans la recherche et la co-création, visant à renforcer la capacité des travailleurs jeunesse à soutenir la santé mentale des jeunes marginalisés à travers une lentille antiraciste, anti-oppressive et axée sur la communauté.

    1. Compte rendu : Le Recueil de la Parole des Enfants Victimes et le Défi des Enquêtes sur les Agressions Sexuelles

      Ce document examine les méthodes et les défis rencontrés par la police, en particulier la brigade des mineurs, lors du recueil de la parole des enfants victimes de violences, notamment sexuelles.

      Il met en lumière l'évolution des pratiques d'audition, l'importance des environnements adaptés et la complexité de l'enquête judiciaire face à des témoignages d'enfants.

      1. L'Évolution du Recueil de la Parole des Enfants : Les "Salles Mélanie"

      Historiquement, l'audition des enfants victimes se faisait dans des "bureaux ordinaires, des endroits où les conditions de confort et d'écoute n'étaient pas réunies pour avoir leur témoignage souvent si douloureux."

      Conscients de cette lacune, de nouvelles approches ont été mises en place, notamment la création de "salles Mélanie".

      • Concept et Aménagement : Les salles Mélanie, nommées d'après la première enfant auditionnée dans ces conditions, sont des "pièces spécialement aménagées avec du mobilier, des jeux pour enfants, des couleurs chaudes et qui permettent un petit peu comme un petit cocon de recueillir la parole de ces enfants de manière plus efficace et plus délicate."

      L'objectif est de créer un environnement qui "ressemble à une école, ça ressemble à ce qu'ils ont d'habitude, ça ressemble à une chambre d'enfance, ça ressemble pas à un bureau", afin de les "sécuriser" et qu'ils se "sentent en sécurité ici."

      • Outils Pédagogiques : Ces salles sont équipées de divers outils pour faciliter l'expression des enfants.

      Les poupées anatomiques, par exemple, sont essentielles : "Il y a un garçon et une fille et on peut complètement les déshabiller de des chaussures jusqu'au vêtements...

      Ce qui fait que ça permet à l'enfant de matérialiser s'il souhaite pas parler, ben finalement il peut nous expliquer à travers les les poupons en fait."

      Des dessins ou l'utilisation d'objets comme des stylos peuvent également aider l'enfant à "montrer ce qu'il a demandé de faire".

      • Impact sur le Témoignage : Les enquêteurs estiment que ces environnements permettent une parole plus "précise" et plus libre.

      Un policier souligne que l'enfant "va révéler le traumatisme qu'il a pu vivre."

      2. La Spécificité de l'Audition des Mineurs

      L'audition d'un enfant diffère grandement de celle d'un adulte ou même d'un adolescent, nécessitant des compétences et des approches spécifiques.

      • Difficulté d'Expression : Contrairement aux adolescents qui "vont tout nous expliquer", l'enfant "va falloir aller chercher un peu plus les éléments."

      Ils peuvent bloquer, avoir peur, ou manquer de vocabulaire pour exprimer ce qu'ils ont vécu.

      Certains "font que des signes de la tête qui veulent pas parler mais par contre qui vont nous répondre à travers ce gestuel surtout les petits parce qu'ils ont peut-être moins de vocabulaire moins la facilité de s'exprimer."

      • Techniques d'Audition Modernes : L'affaire Outreau a marqué un tournant, amenant de "grands changements par rapport au recueil de la parole de l'enfant."

      Auparavant, les questions étaient "dirigées" ("il a mis son zizi dans ton sexe"), ce qui pouvait influencer l'enfant.

      Désormais, la technique consiste à aborder le sujet "du général" et d'y aller "petit à petit", pour que l'enfant "puisse dire ce qui s'est passé exactement mais de façon moins brutale et moins l'influencer aussi."

      L'enquêteur doit s'adapter au "terme" propre à l'enfant pour désigner les parties intimes ou les actes.

      La Vérité et le Mensonge : Une règle fondamentale est de "dire que la vérité et puis jamais de mensonge."

      L'enfant est invité à donner un exemple de mensonge, comme "Il m'a rien fait" si un problème est survenu.

      Cependant, la déstabilisation de l'enquêteur face à un enfant qui ne parle pas révèle la complexité de cette approche.

      3. La Charge Émotionnelle et Psychologique des Enquêteurs

      Le travail à la brigade des mineurs est humainement très exigeant et impacte profondément les policiers.

      • Sensibilité du Travail : Les enquêteurs sont confrontés à des "affaires de mœurs, de viol" impliquant des enfants, ce qui est "pas forcément évident".

      Un enquêteur confie que cela "nous bouleverse", car ils ne sont "pas dénué du tout de sentiments.

      Bien au contraire." Ils doivent cependant "essayer de mettre de la distance parce que sinon c'est trop ça serait trop compliqué au quotidien."

      • Mécanismes d'Adaptation : Avec le temps, les enquêteurs se "forge une sorte de carapace".

      Le fait d'en "parler aussi, c'est aussi une façon de de se libérer quoi, de passer à autre chose, de pas garder tout pour nous."

      L'humour peut parfois être utilisé comme "une façon de détourner en fait."

      Certains dossiers restent cependant "ancrés dans un coin du cerveau et c'est vrai que parfois c'est difficile de faire le vide en rentrant à la maison."

      • Motivation : Malgré la difficulté, les enquêteurs trouvent ce domaine "passionnant, intéressant" car "un enfant, il a pas moyen de défense.

      Donc c'est vrai que c'est important de pouvoir l'aider à notre niveau si on si on peut essayer de comprendre et puis de lui trouver une solution."

      4. Le Processus Judiciaire et ses Limites

      Le recueil de la parole de l'enfant n'est que le début d'un processus judiciaire complexe où la preuve est primordiale.

      • Le Doute et la Preuve : La crédibilité de la parole de l'enfant est au centre de l'enquête.

      "C'est difficile de dire au départ si la parole de l'enfant est crédible ou pas."

      L'enquête vise à "vérifier les paroles que l'enfant a pu dénoncer à travers des auditions de témoin, à travers des examens médicaux, à travers des choses comme ça.

      Parce que justement, il faut bah il faut étayer les paroles de l'enfant."

      • L'Absence de Preuves Matérielles : L'un des cas présentés illustre la difficulté lorsque le mis en cause "nie la totalité des faits" et qu'il n'y a "aucun autre élément matériel" pour corroborer la version de l'enfant, y compris le certificat médical. Dans ce cas, "c'est une parole, contre une autre" et "on n'a rien de plus."

      • Le Classement Sans Suite : Face à l'insuffisance de preuves, le parquet peut décider un "classement 21" (classement sans suite).

      Cette décision est une source de "frustration" pour les enquêteurs car, même si cela ne signifie pas que la parole de l'enfant est mise en doute, "on n'a pas assez d'éléments pour vous confronter." C'est une application du principe "le doute profite à l'accusé."

      • Conséquences : Malgré la libération de l'accusé, le passage par les services de police et l'inscription dans les fichiers constituent un "précédent" pour le futur.

      L'exemple de Zoé, toujours placée en famille d'accueil et ne vivant plus avec son beau-père, montre que des mesures de protection sont prises indépendamment de l'issue judiciaire.

      En conclusion, si la création des salles Mélanie et l'évolution des techniques d'audition représentent une avancée majeure pour mieux recueillir la parole des enfants victimes, la phase d'enquête et la confrontation aux limites de la preuve matérielle restent un défi constant pour la justice et un lourd fardeau pour les enquêteurs.

    1. Note d'information détaillée : Le marché du contenu pour adultes en ligne (OnlyFans & MYM)

      Thèmes principaux et idées clés :

      Ce document résume les informations clés concernant l'évolution du marché de la pornographie et de l'érotisme, avec une focalisation sur les plateformes en ligne comme OnlyFans et MYM.

      Il explore les motivations des créateurs de contenu, le modèle économique de ces plateformes, leurs dérives (notamment la présence de mineurs et le rôle des agents), et le vide juridique actuel en France.

      1. La transformation du marché du contenu pour adultes : De la rue à internet.

      • Changement de paradigme : Le marché du porno et de l'érotisme a quitté les "vitrines aveugles de la pornographie" dans les rues de Pigalle pour se déporter massivement sur internet. Les "sites porno classiques" ont été rejoints par de nouvelles plateformes.
      • Plateformes problématiques : OnlyFans et MYM (Me Your Me) sont identifiées comme des plateformes où l'on "vend des photos ou des vidéos osées" mais qui "posent problème" en raison de la présence de mineurs et d'autres dérives.

      2. Le modèle économique des plateformes (OnlyFans et MYM).

      • Monétisation du contenu personnel : Les créateurs comme Coralie et Daniela transforment leurs espaces privés en studios pour réaliser des photos et vidéos.
      • Fonctionnement de OnlyFans :Abonnement mensuel : Les utilisateurs paient un abonnement pour accéder au contenu général du créateur (ex: Coralie demande 11 dollars/mois).
      • Messagerie privée et contenu sur mesure ("médias") : Les abonnés peuvent échanger directement avec les créateurs et commander du contenu personnalisé, ce qui est très lucratif (ex: une vidéo basique de 25 minutes pour Coralie coûte 250 €, le BDSM double le prix ; Bryce Adams vend des vidéos sur mesure à 500 dollars la minute).
      • Commissions : La plateforme prend une commission de 20% sur les revenus des créateurs.
      • Rapports financiers : OnlyFans est une multinationale britannique avec 4,12 millions de créateurs et plus de 300 millions d'utilisateurs. Son chiffre d'affaires net en 2024 est de "plus d'un milliard de dollars".
      • Fonctionnement de MYM :Modèle similaire : MYM, une plateforme française lancée en 2019, fonctionne sur le même principe d'abonnement et de demandes privées.
      • Croissance rapide : En 6 ans, le chiffre d'affaires de MYM est passé de 3 millions d'euros à plus de 100 millions, et l'entreprise compte plus de 60 collaborateurs.
      • Contenu pour adultes majoritaire : Le contenu pour adultes représenterait, selon la plateforme, "la moitié de ses revenus", mais des sources internes estiment ce chiffre à 60-80%.
      • Gains des créateurs : Les revenus peuvent être très élevés. Coralie gagne "2900 € net en moyenne chaque mois", soit plus que son ancien salaire d'employée de bureau. Bryce Adams et son compagnon sont devenus "multimillionnaires", gagnant "plus de 30 millions de dollars" en 4 ans.

      3. Les motivations des créateurs de contenu.

      • Gains financiers rapides : Le principal attrait est la possibilité de "gagner beaucoup d'argent et très rapidement".
      • Indépendance et autonomie : Des créatrices comme Coralie démissionnent de leur emploi traditionnel pour se consacrer pleinement à cette activité, appréciant d'être leur "propre patron" et de "tenir [leur] vie entre [leurs] mains".
      • Complément de revenu : Pour d'autres, comme Daniela, c'est un "bon complément de revenu".
      • Réalisation du "rêve américain" : Bryce Adams considère le fait d'être créatrice de contenu comme une "nouvelle façon de réaliser le rêve américain".

      4. Les dérives du marché : Mineurs et manque de régulation.

      • Présence de mineurs : Malgré l'interdiction stricte aux mineurs sur les deux plateformes, des enquêtes (Reuters pour OnlyFans, Envoyer Spécial pour MYM) ont détecté des comptes ouverts par des mineurs.
      • Facilité de contournement des contrôles : Roman, 17 ans, a réussi à s'inscrire sur MYM à 15 ans avec une "fausse carte" imprimée, le système de vérification "n'a pas vu que c'était du papier".
      • Témoignage de Roman : Elle propose du contenu axé sur les pieds, gagnant près de 1500 € pour des actions qu'elle n'avait pas "envie de faire" mais qui étaient "bien payé[es]". Elle estime que c'est une "sorte de prostitution".
      • Expérience du faux profil test : Un faux profil de mineur (16 ans) créé par les journalistes a été validé par MYM en seulement "15 minutes" et est resté actif pendant "44 jours" avant d'être suspendu.
      • Faiblesse des systèmes de contrôle : Les plateformes affirment utiliser des "processus de validation strict" et des "technologies et équipes de modération massives", mais l'enquête révèle que l'IA utilisée a une "marge d'erreur de plus d'un an sur la tranche 13-17 ans".
      • Reconnaissance interne des fraudes : D'anciens employés de MYM confirment que les "tentatives de fraude à la carte d'identité, ce sont des occurrences quotidiennes" et que "des jeunes filles notamment qui passaient entre les mains du filet" étaient connues en interne.
      • Manque de régulation et auto-régulation :ARCOM : L'autorité de régulation de la communication audiovisuelle et numérique (ARCOM) ne cible pas prioritairement MYM dans ses actions de contrôle.
      • Ministère de l'Intérieur : La police nationale n'est pas un modérateur, et la "grande majorité des profils sont privés", rendant les constatations difficiles pour les enquêteurs.
      • Absence de réponses de MYM : Les fondateurs de MYM ont refusé toute interview, répondant par écrit qu'ils n'avaient "pas repéré de profil de créateur mineurs".
      • Priorité au chiffre : Selon un ancien employé, la question éthique et morale est "rarement abordé[e]" en interne chez MYM, la priorité étant de "faire du chiffre d'abord".

      5. Le rôle croissant des "managers fan" et ses dérives.

      • Émergence des agents : Des hommes comme Quentin Stelma (23 ans) se positionnent comme "manager fan", agissant comme agents pour les modèles, monétisant leur contenu sur les plateformes.
      • Modèle économique des agents : Ils prennent 50% des gains de la modèle. L'utilisation d'un agent peut multiplier les revenus d'une modèle (ex: Sorena est passée de 1900 € seule à 15000 € avec un agent).
      • Stratégies marketing : Les agents utilisent les réseaux sociaux classiques (ex: Instagram) pour créer une communauté et rediriger les abonnés vers les plateformes privées.
      • Les "chatters" : Une "supercherie" où des jeunes hommes répondent aux utilisateurs "à la place de la modèle" pour "vendre le maximum de photos et vidéos possibles", créant l'illusion que le client parle directement à la créatrice. Les chatters touchent 10 à 15% des ventes. Les clients sont souvent des personnes "célibataires" ou qui "n'arrivent pas justement à aller voir des femmes".
      • Discours misogyne et masculiniste : Des "gourous" comme Anthony Sirius (23 ans) proposent des formations en ligne pour futurs agents. Ces formations véhiculent une "vision marchande de la femme", la présentant comme un "produit qu'il faut optimiser, qu'il faut rentabiliser". Les critères de sélection des modèles incluent d'être "belle", "bonne", "jeune voire très jeune", et "blanche".
      • Marché parallèle de contrats : Les agents organisent des "marchés aux femmes" sur des messageries cryptées (ex: Telegram) où ils "achètent et [re]ventent des contrats de modèle du monde entier" (ex: "18 ans, Ukraine 800 dollars", "22 ans, France 450 €"), sans interaction avec les modèles.
      • Abus et absence de protection juridique :Témoignage de Christine : Elle a subi de la "maltraitance psychologique" de la part de son agent, qui est devenu "très méchant" et "harcel[ait] même de dizaines de messages" pour la pousser à produire plus.
      • Tentative d'escroquerie : L'agent de Christine aurait tenté de remplacer son RIB par le sien pour détourner ses revenus, conduisant Christine à porter plainte.
      • Vide juridique : L'absence de cadre juridique spécifique rend les modèles "sans protection face à des agents qui peuvent être abusifs".

      L'avocat Raphaël Molina évoque le "proxénétisme 2.0" mais souligne l'absence de "relation physique" nécessaire pour la qualification de proxénétisme actuel.

      6. Perspectives de régulation.

      • Nécessité d'une législation spécifique : Le "vide juridique" actuel nécessite une nouvelle loi pour encadrer ce phénomène.

      Idées de régulation :

      • Créer une qualification juridique de "proxénétisme 2.0".
      • Interdire la promotion de ces plateformes sur les réseaux sociaux.
      • Interdire les liens de redirection des réseaux sociaux classiques vers les plateformes privées, ou à minima les encadrer.
      • Mettre en place une prévention et une sensibilisation "auprès des jeunes et auprès des parents sur les risques" liés à cette activité.

      • Conscience des parlementaires : Une commission d'enquête parlementaire a commencé à s'intéresser au sujet, montrant une prise de conscience, même si les députés n'étaient "pas du tout" au courant du fonctionnement de ces plateformes au départ.

    1. Synthèse du Briefing : PFAS - La Grande Intox de l'Industrie

      • Ce briefing explore la problématique des PFAS (substances per- et polyfluoroalkylées), surnommés "polluants éternels", en se basant sur une enquête journalistique approfondie, notamment en France avec les cas de l'entreprise Tefal (groupe Seb) et Arkema, ainsi qu'aux États-Unis.

      Il met en lumière la dangerosité de ces molécules, les efforts de l'industrie pour dissimuler leurs effets et retarder la réglementation, et les conséquences sanitaires et environnementales.

      1. Les PFAS : Molécules "Miracles" devenues "Polluants Éternels"

      Les PFAS sont des molécules chimiques synthétiques, plus de 10 000 recensées, créées dans les années 1930.

      Elles ont révolutionné de nombreux secteurs grâce à leurs propriétés uniques : "ultra résistantes à la chaleur, imperméables à l'eau." Initialement utilisées pour la fabrication de la bombe atomique, leurs applications industrielles se sont multipliées : "poêles anti-adhésives, batteries électriques, vêtements imperméables, cosmétiques."

      Le problème majeur des PFAS est leur persistance : "Indestructibles, ils s'accumulent dans l'environnement. On les appelle les polluants éternels."

      On les retrouve "dans le corps des gens, dans la faune et la flore, dans l'air, dans l'eau. Toute notre planète est contaminée."

      2. Dangers pour la Santé et l'Environnement

      L'enquête révèle que la dangerosité de certaines de ces substances est connue depuis des décennies par les industriels, qui auraient "dissimulé pendant très longtemps ce qu'ils savaient sur ces molécules."

      Le PFOA (acide perfluorooctanoïque), un PFAS particulièrement nocif utilisé par Tefal jusqu'en 2012, a été classé "cancérogène pour l'homme en 2023" par le Centre international de recherche sur le cancer (OMS).

      L'exposition aux PFAS est associée à de nombreux effets sur la santé :

      Cholestérol et diabète.

      • Cancers : "cancer des testicules et du rein," "augmenterait aussi le risque de cancer du sein."
      • Système immunitaire : Baisse de l'efficacité des vaccins et des antibiotiques, notamment chez les enfants exposés.
      • Impact sur le fœtus : Le PFOA "modifierait le génome du fétus, augmentant sa probabilité de développer du diabète ou un futur cancer." Un expert déclare : "Nous transmettons désormais la toxicité à la prochaine génération qui paiera pour cela."
      • Foie : Une exposition répétée peut provoquer des "effets néfastes sur le foie."

      Un ancien salarié de Tefal témoigne de la détérioration de son foie avec des enzymes hépatiques "jusqu'à deux fois supérieures à la normale."

      • Dans l'environnement, les PFAS contaminent "nos légumes, dans nos œufs, dans nos eaux potables." La contamination des nappes phréatiques peut être "pour l'éternité."

      3. Dissimulation et Stratégies Industrielles

      L'enquête dénonce les décennies d'efforts des industriels pour "tromper les pouvoirs publics, tromper la communauté scientifique à propos de leur impact réel sur la santé."

      Tefal/Groupe Seb à Rumilly (Haute-Savoie) :

      • Rejets historiques : Tefal a utilisé "plus d'une tonne par an" de PFOA jusqu'en 2012. L'usine a rejeté "des substances chimiques dans l'environnement" et des documents confidentiels révèlent que des "boues de traitement des effluants environ 30000 m³ ont été déposées dans une ancienne carrière" (le plan d'eau des Puys) et d'autres sites, souvent "à même le sol sans bâche de protection."
      • Connaissance des risques : Dès 2002, une fiche de sécurité d'un fournisseur de Tefal précisait que le PFOA "est absorbé à travers les poumons, l'appareil gastro-intestinal et la peau et n'est éliminé que très lentement du sang. Une exposition répétée au-dessus de la limite d'exposition professionnelle peut provoquer des effets néfastes sur le foie."
      • Déni et communication : Le directeur général de Seb affirme que "Le PFO n'est pas considéré comme nocif pour les ouvriers et nous n'avons eu aucune maladie professionnelle d à ça."

      Pourtant, un email confidentiel de 2024 évoque des "campagnes de surveillance biologique" montrant une "corrélation entre la suppression du PFOA dans les matières premières et la diminution des valeurs biologiques mesurées," suggérant une présence antérieure dans le sang des ouvriers.

      • Pollution de l'eau potable : En novembre 2022, l'eau potable de Rumilly a été "brusquement considérée impropre à la consommation" en raison d'une contamination aux PFAS.

      Les habitants ont bu de l'eau contaminée pendant des décennies, certains affichant des taux de PFOA "cinq fois plus que la moyenne française" dans le sang.

      Arkema (Sud de Lyon) :

      • Connaissance précoce : Dès 2006, Arkema était "informé de la contamination des populations aux alentours des usines américaines," avec un lien clair entre les concentrations de PFA dans l'eau potable et le sang.
      • Stratégie de défense : En 2009, des industriels, dont Arkema, réfléchissaient déjà à "une stratégie de défense" sur la question de la présence des PFAS dans l'eau potable "avant qu'il n'apparaisse dans les médias ou qu'il n'engendre des pressions réglementaires."
      • Solution connue mais retardée : Dès 2013, Arkema avait validé en laboratoire une solution (charbons actifs) pour "réduire de manière très importante les émissions" de PFAS, mais n'a installé la station qu'en 2022, "presque 10 ans plus tard."
      • Dissimulation de rapport : Une version tronquée d'un rapport d'analyse indépendant a été transmise à la justice par Arkema, supprimant une partie de la conclusion "détaillant pourquoi les molécules retrouvées dans la nappe pourrait en partie provenir des rejets de l'usine Archema."

      Un journaliste dénonce : "Ce sont des industriels qui fabriquent en permanence ce doute et qui n'ont pas peur de tronquer leur rapport."

      4. Lobbying et Influence Politique

      Les industriels déploient des efforts considérables pour "empêcher leur interdiction" et "retarder, retarder, retarder pour repousser le plus loin possible toute réglementation qui pourrait affecter ses produits, ses procédés et au final ses profits."

      • Tefal face à la loi française : Lors de l'examen d'une loi visant à interdire les polluants éternels, Tefal a mené une "vaste campagne de lobbying," allant jusqu'à "payer les salariés pour faire grève" et manifestants devant l'Assemblée nationale.

      L'entreprise a fourni aux parlementaires des "éléments de langage" défendant les fluoropolymères, un type de PFAS, comme étant "peu préoccupant aux impacts insignifiants sur la santé et sur l'environnement" et "incapable de traverser la barrière gastro-intestinale."

      L'OCDE réfute avoir "finalisé de telles conclusions," et le directeur de recherche au CNRS, Pierre Labadi, déclare que cette présentation est "tronquée" car "le caractère extrêmement persistant de l'ensemble d'épiface" est "avéré."

      • Résultat du lobbying : Les ustensiles de cuisine ont été "exclus du champ d'application de la loi" en première lecture, un député écologique dénonçant une "grosse pression au niveau de Ber."

      • Lobbying européen : Au niveau européen, l'industrie a inondé les autorités de "milliers de mails d'études socio-économiques, de rapports scientifiques" avec les mêmes arguments.

      5. Coût de la Dépollution et Responsabilité

      La dépollution des sites contaminés est un défi "titanesque."

      Le coût estimé de la dépollution de toute l'Europe est de "100 milliards d'euros par an, plus de la moitié du budget annuel de l'Union européenne."

      • Responsabilité industrielle : Les autorités locales et les associations estiment que les pollueurs devraient payer. La métropole de Lyon, confrontée à une dépollution de l'eau potable coûtant "entre 5 et 10 millions d'euros," a saisi la justice, refusant que "l'usager qui paie qui qui subit à la pollution et qui paye le coût de la dépollution."
      • Déni de responsabilité : Tefal a versé 3600 € à la collectivité de Rumilly pour les filtres à charbon, mais le directeur général refuse d'admettre la pleine responsabilité, arguant qu'il n'y avait "pas de norme" à l'époque et que "il y a au moins cinq entreprises mobilisées par l'adréal" sur le site.
      • Non-reconnaissance des maladies professionnelles : Tefal nie toute maladie professionnelle liée aux PFAS, malgré les témoignages d'anciens salariés.

      Conclusion

      Le scandale des PFAS est symptomatique d'une industrie chimique qui a sciemment dissimulé les dangers de ses produits pendant des décennies, privilégiant les profits.

      Les conséquences sanitaires et environnementales sont massives et durables, avec un coût de dépollution faramineux qui soulève la question de la responsabilité des industriels.

      La bataille pour une réglementation stricte et l'indemnisation des victimes est loin d'être terminée, face à un lobbying industriel puissant.

      Comme le souligne un militant, "Chaque mois, chaque année qui passe, ça se compte en vie humaine.

      Donc c'est absolument inacceptable."

    1. Dossier d'information détaillé : Mieux dans ma tête - Parlons santé mentale

      Introduction

      Ce dossier vise à synthétiser les thèmes principaux et les informations cruciales abordées lors de l'émission "Mieux dans ma tête - Parlons santé mentale".

      L'objectif central de cette émission est de libérer la parole autour de la santé mentale et de démystifier les troubles psychiques, souvent entourés de tabous et de stigmatisation en France.

      Comme le souligne Eddie Riner, parrain de cette initiative, "La santé mentale, c'est une chose dont tout le monde devrait [se] soucier en France."

      1. La Santé Mentale, un Sujet Universel et encore Tabou

      Une préoccupation pour tous : L'émission insiste sur le fait que la santé mentale concerne chacun d'entre nous.

      "Au cours de notre vie, nous allons tous connaître des moments où notre santé mentale sera altérée. Ça peut commencer avec un simple stress, mais aussi des tâches quotidiennes qui nous dépassent avec la fameuse charge mentale."

      Les troubles psychiques : Au-delà du stress quotidien, des troubles plus complexes comme la dépression, la bipolarité et la schizophrénie sont évoqués, pour lesquels "on ose moins parler".

      Le tabou persistant : Un sondage Ipsos révèle que "près d'un Français sur deux" trouve qu'il est difficile de parler de santé mentale, démontrant à quel point le sujet reste un tabou dans le pays.

      2. Démystification et Lutte contre la Stigmatisation

      L'émission met en lumière des témoignages poignants pour changer la perception des troubles psychiques.

      • Schizophrénie : Une maladie qui ne rime pas avec "débilité mentale".Florent, atteint de schizophrénie, partage son expérience :

      "Au début de la maladie, j'associais la schizophrénie avec une forme de débilité mentale. C'est-à-dire que je m'interdisais de vivre puisque je me dis... de toutes les façons c'était vrai l'échec puisque j'étais plus bête que la moyenne."

      • Le Professeur Antoine Pellissolo, psychiatre, déconstruit cette idée reçue :

      "Absolument. Ça n'a rien à voir avec l'intelligence en fait. Les troubles psychiques, ce sont des maladies qui perturbent les émotions, la perception du monde... mais pas l'intelligence."

      • L'exemple de "grands personnages" comme Einstein ou Léonard de Vinci, ayant connu des épisodes psychiques, a aidé Florent à déclencher une prise de conscience et à croire en une vie heureuse malgré la maladie.

      • Bruno Guillon témoigne de son changement de perception après avoir rencontré des personnes atteintes de schizophrénie :

      "Pour moi, quelqu'un qui était atteint de de schizophrénie, c'était un fou. C'est-à-dire c'était l'iconographie de la chambre capitonnée avec la camisole de force et quelqu'un qui a aucun discernement."

      Son reportage à la radio "Les Antoonoirs" a prouvé le contraire.

      • La radio comme outil thérapeutique : Le reportage sur "Les Antoonoirs" à Roubaix montre comment des personnes atteintes de troubles psychiques, dont la schizophrénie, animent une émission de radio sous prescription médicale.

      Ce projet leur permet de "ne pas être dans la solitude parce que la solitude elle tue plus qu'une maladie" et de "diminuer le traitement médicamenteux".

      • Le désir d'être vu comme des "êtres humains à part entière": Un participant de l'émission des "Antoonoirs" exprime :

      "Moi, j'espère qu'une chose, c'est qu'on nous voit vraiment comme ce qu'on est, des êtres humain à part entière. Euh sur un même plan d'égalité, ça c'est important."

      • Bipolarité : Un chemin de "rétablissement" continu.Noël, atteint de troubles bipolaires, insiste sur la distinction fondamentale : "on ne vous qualifie pas comme patient bipolaire mais quelqu'un qui souffre de trouble bipolaire car la distinction est très importante." Il préfère le terme "en rétablissement" car "c'est un chemin qui se poursuit et qui comporte ce long périple."

      • Les tatouages de Noël symbolisent son parcours et sa volonté de vivre, comme le montre l'inscription "No way you kill yourself".

      • Le rôle de la famille : La mère de Noël, Monique, exprime le soulagement d'avoir enfin un diagnostic : "D'avoir un mot, je pense que ça a aidé parce que jusqu'ici on est bon, on savait que Noël était pas bien...

      Mais le fait qu'il y a un nom euh sur la maladie, c'est quand même quelque chose, c'est quand même positif parce que ça ça nous dit bah finalement depuis son enfance, depuis tout le temps, il était pas bien mais on sait pourquoi et c'était peut-être pas de notre faute, c'était comme ça quoi."

      • L'hérédité : Astrid Chevance explique que les antécédents familiaux peuvent indiquer une vulnérabilité : "L'hérédité c'est pas seulement la génétique, c'est aussi le partage d'une vie commune, le milieu social et cetera."

      3. Comprendre et Gérer la Dépression

      La dépression est présentée comme la maladie psychiatrique la plus fréquente en France, touchant "12,5 % des Français âgés de 18 à 85 ans" chaque année.

      • Distinction déprime/dépression : La déprime est passagère, tandis que la dépression est "beaucoup plus intense" et "nous terrasse".

      • Symptômes de la dépression : Antoine Pellissolo décrit la dépression comme "une rupture avec sa vie habituelle", incluant désespoir, douleur et "dérèglements du corps" (perte d'appétit, troubles du sommeil, fatigue).

      • Ce qui se passe dans le cerveau : Une animation explique la baisse des neurotransmetteurs (sérotonine, dopamine, noradrénaline) entraînant moins de plaisir et de motivation.

      Le cortex préfrontal, responsable des décisions rationnelles, n'est plus en mesure de prendre du recul, et l'amygdale cérébrale "surinterprète des messages négatifs".

      Une "tempête de molécules inflammatoires" (cytokines) aggrave les symptômes.

      • Le rôle des aidants et la difficulté à parler : Marise, qui a vaincu la dépression, témoigne de "idées très sombres, noires".

      Son mari, Michel, a été un aidant malgré lui, soulignant la difficulté de la famille à savoir comment aider et l'absence de soutien pour eux.

      • Briser la culpabilité du patient : Marise a rencontré un psychologue avec lequel le courant ne passait pas et s'est dit "ils étaient tous pareils". Anne-Victoire Rousselet, psychologue, insiste sur le droit du patient de changer de thérapeute : "Bah, évidemment qu'on a le droit... c'est une histoire de rencontre."

      4. Le Burnout : Une Maladie des "Forts"

      Christophe partage son expérience du burnout, soulignant que "beaucoup de gens considèrent que c'est la [maladie] des faibles et au contraire, c'est plutôt la maladie des forts, des personnes qui se sont pas écoutées, qui se sont pas arrêtées à temps."

      • Les signaux faibles : Douleurs physiques inexpliquées ("le corps parlait"), arrêt des activités plaisantes ("j'ai pas le temps d'aller au sport en ce moment").

      • Le soutien de l'entourage : La femme de Christophe témoigne de son désarroi face à son mari "sur son canapé toute la journée à se morfondre", sans savoir comment agir. Il est souligné que les aidants souffrent aussi et ont besoin de soutien.

      • Prévention en entreprise : L'importance de poser des questions sur le bien-être au travail et à la maison est mise en avant.

      • La durée de l'arrêt de travail : Christophe n'a été arrêté que 3 mois, ce qui est considéré comme très court.

      En Belgique, où l'épuisement professionnel est reconnu, la moyenne est de 14 mois. L'idée est qu'il faut "sortir du milieu hostile" et revenir "outillé et différent".

      5. L'Anxiété Généralisée et les Crises d'Angoisse

      Clara souffre de troubles anxieux généralisés, ayant connu de "terribles crises d'angoisse" et des difficultés à sortir de chez elle.

      • Symptômes : Cœur qui bat à fond, pertes d'équilibre, sentiment de déréalisation ("on est plus ancré dans la réalité").

      • Le cercle vicieux : La peur de refaire des crises d'angoisse alimente les crises elles-mêmes : "on a peur d'avoir peur et plus on a peur d'angoisser, plus on fait des crises d'angoisse."

      • Thérapie et soutien : Clara a suivi une "thérapie comportementale et cognitive" pendant deux ans. Son compagnon l'a soutenue en étant à l'écoute et en contactant sa psychologue pour obtenir des outils.

      • La reconquête de soi : Clara a réalisé son rêve de voyager seule pendant un mois, défi qu'elle ne pouvait pas relever auparavant, montrant ainsi son rétablissement.

      6. Le Rôle des Professionnels de la Santé Mentale Une clarification est apportée sur les différents rôles :

      • Médecin généraliste : Premier recours pour un diagnostic initial et une orientation.

      • Psychiatre : Médecin spécialiste des troubles psychiques (8-9 ans d'études de médecine). Ils peuvent prescrire des médicaments et certains sont également formés aux psychothérapies. Leurs consultations sont remboursées.

      • Psychologue : Ont un master de psychologie clinique et des stages. Ils sont décrits comme des "rééducateurs de la psychée". Depuis peu, "12 séances chez un psychologue sont remboursé[e]s par l'assurance maladie" sans prescription médicale.

      • Psychothérapeute/Psychopraticien : Des distinctions sont nécessaires pour s'y retrouver.

      • L'importance du bon "feeling" : Il est crucial de trouver un professionnel avec qui le courant passe. "C'est une histoire de rencontre."

      7. L'Impact de l'Hygiène de Vie sur la Santé Mentale

      L'émission met en évidence trois piliers essentiels pour le bien-être mental :

      • Le Sommeil : "Chouchouter son sommeil" est crucial. "Quand on dort pas, on est fatigué, on a du mal à se concentrer sur les choses, à gérer ses émotions." La quantité (environ 7h) et la régularité sont importantes.

      L'Activité Physique : Le sport a un impact direct sur le cerveau.

      • Mécanismes : Libération d'endorphines (hormones du bonheur) apaisant la douleur et procurant un sentiment de bien-être.

      Production de dopamine (motivation, plaisir) et de sérotonine (humeur), "le même que celui visé par certains antidépresseurs."

      Stimulation de la "neurogénèse" (création de nouveaux neurones) dans l'hippocampe, essentielle contre la dépression.

      • Témoignages : Marise a vaincu sa dépression grâce au football en rejoignant une équipe de femmes. Clara, Noël, Florent et Christophe témoignent tous des bienfaits de la danse, du vélo, de la musculation ou de la marche.

      • La "surf thérapie" : Des psychiatres utilisent le surf comme outil thérapeutique pour des patients atteints de troubles psychiques, permettant une "resocialisation" et une reconquête de la confiance en soi.

      Virginie témoigne : "Ça m'a apporté ce côté-là. Ouais. de reprendre confiance en moi, de retrouver une certaine fierté de ce que je fais parce qu'au départ, je ne pensais pas y arriver."

      L'Alimentation : Le régime méditerranéen est fortement recommandé.

      • Impact : Une étude montre qu'un régime de type méditerranéen a conduit à "une rémission pour un tiers des participants de la dépression en moins de 3 mois."

      • Composition : Principalement végétal, local, de saison, coloré, riche en antioxydants, polyphénols, oléagineux, céréales complètes, bonnes matières grasses (huile d'olive) et poissons gras (oméga-3).

      • Méfiance envers les aliments ultra-transformés : Ils "sont faits pour être irrésistibles" mais leur consommation excessive augmente le risque "d'anxiété, de dépression, de trouble du sommeil" en créant une inflammation "persistante" dans le corps.

      • L'équilibre : Les plaisirs occasionnels ("junk food") sont acceptables, mais ne doivent pas devenir la norme.

      8. L'Importance de la Prévention et du Soutien

      • Le défi "Courir pour toi" : Louis, dont le frère Simon s'est suicidé après des années de lutte contre la dépression, a lancé un défi sportif (130 marathons en 150 jours) pour sensibiliser et lever des fonds pour la "Maison Perchée", une association qui aide les personnes confrontées à des troubles psychiques.

      • Détecter les signaux et agir : En cas d'idées noires ou suicidaires, il est crucial de "saisir la perche", d'être à l'écoute et d'engager le dialogue. Il ne faut jamais banaliser ces propos.

      • Appeler à l'aide : Si la situation est inquiétante, il faut contacter le médecin traitant ou, en urgence, le SAMU (15).

      • Différences hommes/femmes face à la dépression :

      Les femmes sont plus souvent diagnostiquées (2 pour 1 homme), peut-être parce que la société leur laisse plus d'espace pour exprimer la tristesse, tandis que les hommes peuvent avoir plus de mal à parler de leur souffrance.

      • La "Maison Perchée" : Un lieu "sans jugement" qui sert de "sas entre l'hospitalisation et la le retour à la vraie vie", offrant des ateliers et un soutien par les pairs ("pair-aidance"). Flavie, bipolaire, y a trouvé "une pluralité dans l'être humain" et a pu "renaître".

      Conclusion

      • L'émission "Mieux dans ma tête - Parlons santé mentale" est un appel vibrant à la prise de conscience et à l'action.

      Elle démontre que les troubles psychiques sont des maladies réelles et complexes, qui ne doivent plus être stigmatisées.

      Grâce aux témoignages et aux éclaircissements des professionnels, elle offre de l'espoir en montrant que des solutions existent, qu'il s'agisse de thérapies, de médicaments ou d'une meilleure hygiène de vie.

      Le message clé est clair : oser en parler, demander de l'aide et reconnaître l'importance d'une approche globale pour la santé mentale.

      Comme le dit un participant des "Antoonoirs", il s'agit de voir les personnes atteintes de troubles psychiques comme des "êtres humains à part entière" sur un pied d'égalité.

    1. Author response:

      The following is the authors’ response to the original reviews

      Public Reviews:

      Reviewer #1 (Public review):

      Summary:

      MHC (Major Histocompatibility Complex) genes have long been mentioned as cases of trans-species polymorphism (TSP), where alleles might have their most recent common ancestor with alleles in a different species, rather than other alleles in the same species (e.g., a human MHC allele might coalesce with a chimp MHC allele, more recently than the two coalesce with other alleles in either species). This paper provides a more complete estimate of the extent and ages of TSP in primate MHC loci. The data clearly support deep TSP linking alleles in humans to (in some cases) old world monkeys, but the amount of TSP varies between loci.

      Strengths:

      The authors use publicly available datasets to build phylogenetic trees of MHC alleles and loci. From these trees they are able to estimate whether there is compelling support for Trans-species polymorphisms (TSPs) using Bayes Factor tests comparing different alternative hypotheses for tree shape. The phylogenetic methods are state-of-the-art and appropriate to the task.

      The authors supplement their analyses of TSP with estimates of selection (e.g., dN/dS ratios) on motifs within the MHC protein. They confirm what one would suspect: classical MHC genes exhibit stronger selection at amino acid residues that are part of the peptide binding region, and non-classical MHC exhibit less evidence of selection. The selected sites are associated with various diseases in GWAS studies.

      Weaknesses:

      An implication drawn from this paper (and previous literature) is that MHC has atypically high rates of TSP. However, rates of TSP are not estimated for other genes or gene families, so readers have no basis of comparison. No framework to know whether the depth and frequency of TSP is unusual for MHC family genes, relative to other random genes in the genome, or immune genes in particular. I expect (from previous work on the topic), that MHC is indeed exceptional in this regard, but some direct comparison would provide greater confidence in this conclusion.

      We agree that context is important! Although we expected to get the most interesting results from studying the classical genes, we did include the non-classical genes specifically for comparison. They are located in the same genomic region, have multiple sequences catalogued in different species (although they are less diverse), and perform critical immune functions. We think this is a more appropriate set to compare with the classical MHC genes than, say, a random set of genes. Interestingly, we did not detect TSP in these non-classical genes. This likely means that the classical MHC genes are truly exceptional, but it could also mean that not enough sequences are available for the non-classical genes to detect TSP. 

      It would be very interesting to repeat this analysis for another gene family to see whether such deep TSP also occurs in other immune or non-immune gene families. We are lucky that decades of past work and a dedicated database exists for cataloging MHC sequences. When this level of sequence collection is achieved for other highly polymorphic gene families, it will be possible to do a comparable analysis.  

      Given the companion paper's evidence of genic gain/loss, it seems like there is a real risk that the present study under-estimates TSP, if cases of TSP have been obscured by the loss of the TSP-carrying gene paralog from some lineages needed to detect the TSP. Are the present analyses simply calculating rates of TSP of observed alleles, or are you able to infer TSP rates conditional on rates of gene gain/loss?

      We were not able to infer TSP rates conditional on rates of gene gain/loss. We agree that some cases of TSP were likely lost due to the loss of a gene paralog from certain species. Furthermore, the dearth of MHC whole-region and allele sequences available for most primates makes it difficult to detect TSP, even if the gene paralog is still present. Long-read sequencing of more primate genomes should help with this. We agree that it would also be very interesting to study TSPs that were maintained for millions of years but were lost recently.

      Figure 5 (and 6) provide regression model fits (red lines in panel C) relating evolutionary rates (y axis not labeled) to site distance from the peptide binding groove, on the protein product. This is a nice result. I wonder, however, whether a linear model (as opposed to non-linear) is the most biologically reasonable choice, and whether non-linear functions have been evaluated. The authors might consider generalized additive models (GAMs) as an alternative that relaxes linearity assumptions.

      We agree that a linear model is likely not the most biologically reasonable choice, as protein interactions are complex. However, we made the choice to implement the simplest model because the evolutionary rates we inferred were relative, making parameters relatively meaningless. We were mainly concerned with positive or negative slopes and we leave the rest to the protein interaction experts.

      The connection between rapidly evolving sites, and disease associations (lines 382-3) is very interesting. However, this is not being presented as a statistical test of association. The authors note that fast-evolving amino acids all have at least one association: but is this really more disease-association than a random amino acid in the MHC? Or, a randomly chosen polymorphic amino acid in MHC? A statistical test confirming an excess of disease associations would strengthen this claim.

      To strengthen this claim, we added Figure 6 - Figure Supplement 7 (NOTE: this needs to be renamed as Table 1 - Figure Supplement 1, which the eLife template does not allow). Here, we plot the number of associations for each amino acid against evolutionary rate, revealing a significant positive slope in Class I. We also added explanatory text for this figure in lines 400-404.

      Reviewer #2 (Public review):

      Summary

      In this study, the authors characterized population genetic variation in the MHC locus across primates and looked for signals of long-term balancing selection (specifically trans-species polymorphism, TSP) in this highly polymorphic region. To carry out these tasks, they used Bayesian methods for phylogenetic inference (i.e. BEAST2) and applied a new Bayesian test to quantify evidence supporting monophyly vs. transspecies polymorphism for each exon across different species pairs. Their results, although mostly confirmatory, represent the most comprehensive analyses of primate MHC evolution to date and novel findings or possible discrepancies are clearly pointed out. However, as the authors discuss, the available data are insufficient to fully capture primates' MHC evolution.

      Strengths of the paper include: using appropriate methods and statistically rigorous analyses; very clear figures and detailed description of the results methods that make it easy to follow despite the complexity of the region and approach; a clever test for TSP that is then complemented by positive selection tests and the protein structures for a quite comprehensive study.

      That said, weaknesses include: lack of information about how many sequences are included and whether uneven sampling across taxa might results in some comparisons without evidence for TSP; frequent reference to the companion paper instead of summarizing (at least some of) the critical relevant information (e.g., how was orthology inferred?); no mention of the quality of sequences in the database and whether there is still potential effects of mismapping or copy number variation affecting the sequence comparison.

      To address these comments, we added Tables 2-4 to allow readers to more readily understand the data we included in each group. We refer to these tables in the introduction (line 95), in the “Data” section of the results (lines 128-129), and the “Data” section of the methods (lines 532-534).  We also added text (lines 216-219 and 250-252) to more explicitly point out that our method is conservative when few sequences are available.

      We also added a paragraph to the discussion which addresses data quality and mismapping issues (lines 473-499).

      We clarified the role of our companion paper (line 49-50) by changing “In our companion paper, we explored the relationships between the different classical and non-classical genes” to “In our companion paper, we built large multi-gene trees to explore the relationships between the different classical and non-classical genes.” We also changed the text in lines 97-99 from “In our companion paper, we compared genes across dozens of species and learned more about the orthologous relationships among them” to “In our companion paper, we built trees to compare genes across dozens of species. When paired with previous literature, these trees helped us infer orthology and assign sequences to genes in some cases.”

      Reviewer #3 (Public review):

      Summary

      The study uses publicly available sequences of classical and non-classical genes from a number of primate species to assess the extent and depth of TSP across the primate phylogeny. The analyses were carried out in a coherent and, in my opinion, robust inferential framework and provided evidence for ancient (even > 30 million years) TSP at several classical class I and class II genes. The authors also characterise evolutionary rates at individual codons, map these rates onto MHC protein structures, and find that the fastest evolving codons are extremely enriched for autoimmune and infectious disease associations.

      Strengths

      The study is comprehensive, relying on a large data set, state-of-the-art phylogenetic analyses and elegant tests of TSP. The results are not entirely novel, but a synthesis and re-analysis of previous findings is extremely valuable and timely.

      Weaknesses

      I've identified weaknesses in several areas (details follow in the next section):

      -  Inadequate description and presentation of the data used

      -  Large parts of the results read like extended figure captions, which breaks the flow. - Older literature on the subject is duly cited, but the authors don't really discuss their findings in the context of this literature.

      -  The potential impact of mechanisms other than long-term maintenance of allelic lineages by balancing selection, such as interspecific introgression and incorrect orthology assessment, needs to be discussed.

      We address these comments in the more detailed section below.

      Recommendations for the authors:  

      Reviewer #1 (Recommendations for the authors):

      The abstract could benefit from being sharpened. A personal pet peeve is a common habit of saying we don't know everything about a topic (line 16 - "lack a full picture of primate MHC evolution"); We never know everything on a topic, so this is hardly a strong rationale to do more work on it. This is followed by "to start addressing this gap" - which is vague because you haven't explicitly stated any gap, you simply said we are not yet omniscent on the topic. Please clearly identify a gap in our knowledge, a question that you will be able to answer with this paper.

      That makes sense! We added another sentence to the abstract to make the specific gap clearer. Inserted “In particular, we do not know to what extent genes and alleles are retained across speciation events” in lines 16-17.

      Reviewer #2 (Recommendations for the authors):

      - Some discussion of alternative explanations when certain comparisons were not found to have TSP - is this consistent with genetic drift sometimes leading to lineage loss, or does it suggest that the proposed tradeoff between autoimmunity and pathogen recognition might differ depending on primates' life history and/or exposure to similar pathogens? Could the trade-off of pathogen to self-recognition not be as costly in some species?

      This is consistent with genetic drift, as no lineages are expected to be maintained across these distantly-diverged primates under neutral selection. These ideas are certainly possible, but our Bayes Factor test only reveals evidence (or lack thereof) for deviations from the species tree and cannot provide reasons why or why not.

      - It would be interesting to put these results on very long-term balancing selection in the context of what has been reported at the region for shorter term balancing selection. The discussion compares findings of previous genes in the literature but not regarding the time scale.

      Indeed, there is some evidence for the idea of “divergent allele advantage”, in which MHC-heterozygous individuals have a greater repertoire of peptides that they can present, leading to greater resistance against pathogens and greater fitness. This heterozygote advantage thus leads to balancing selection (Pierini and Lenz, 2018; Chowell et al., 2019). Our discussion mentions other time scales of balancing selection across the primates at the MHC and other loci, but we choose to focus more on long-term than short-term balancing selection.

      - Lines 223-226 - how is the difference in BF across exons in MHC-A to be interpreted? The paragraph is about MHC-A, but then the explanation in the last sentence is for when similar BF are observed which is not the case for MHC-A. Is this interpreted as lack of evidence for TSP? Or something about recombination or gene conversion? Or that one exon may be under balancing selection but not the other?

      Thank you for pointing out the confusing logic in this paragraph. 

      Previous: “For MHC-A, Bayes factors vary considerably depending on exon and species pair. Many sequences had to be excluded from MHC-A comparisons because they were identified as gene-converted in the \textit{GENECONV} analysis or were previously identified as recombinants \citep{Hans2017,Gleimer2011,Adams2001}. Importantly, for MHC-A we do not see concordance in Bayes factors across the different exons, whereas we do for the other gene groups. Similar Bayes factors across all exons for a given comparison is thus evidence in favor of TSP being the primary driver of the observed deep coalescence structure (rather than recombination or gene conversion).” Current (lines 228-238): 

      “For MHC-A, Bayes factors vary considerably depending on exon and species pair. Past work suggests that this gene has had a long history of gene conversion affecting different exons, resulting in different evolutionary histories for different parts of the gene \citep{Hans2017,Gleimer2011,Adams2001}. Indeed, we excluded many MHC-A sequences from our Bayes factor calculations because they were identified as gene-converted in our \textit{GENECONV} analysis or were previously suggested to be recombinants. As shown in \FIG{bayes_factors_classI}, the lack of concordance in Bayes factors across the different exons for MHC-A is evidence for gene conversion, rather than balancing selection, being the most important factor in this gene's evolution. In contrast, the other gene groups generally show concordance in Bayes factors across exons. We interpret this as evidence in favor of TSP being the primary driver of the observed deep coalescence structure for MHC-B and -C (rather than recombination or gene conversion).”

      - In Figures 5C and 6C, the points sometimes show a kind of smile pattern of possibly higher rates further from the peptide. Did authors explore other fits like a polynomial? Or, whether distance only matters in close proximity to the peptide? Out of curiosity, is it possible to map substitution time/branch into the distance to the peptide binding region for each substitution? Is there any pattern with distance to interacting proteins in non-peptide binding MHC proteins like MHC-DOA? Although they don't have a PBR they do interact with other proteins.

      Thank you for these ideas! We did not explore other fits, such as a polynomial, because we wanted to implement the simplest model. Our evolutionary rates are relative, making parameters relatively meaningless. We were mainly concerned with positive or negative slopes and we leave the rest to the protein interaction experts.

      There is most likely a relationship between evolutionary rate and the distance to interacting proteins in the non-peptide-binding molecules MHC-DM and -DO. However, there are few currently available models and it is difficult to determine which residues in these models are actually interacting. However, researchers with more experience in protein interactions would be able to undertake such an analysis. 

      - How biased is the database towards human alleles? Could this affect some of the analyses, including the coincidence of rapidly evolving sites with associations? Are there more associations than expected under some null model?

      While the database is indeed biased toward human alleles, we included only a small subset of these in order to create a more balanced data set spanning the primates. This is unlikely to affect the coincidence of rapidly-evolving sites with associations; however, we note that there are no such association studies meeting our criteria in other species, meaning the associations are only coming from studies on humans.

      - To this reader, it is unnecessary and distracting to describe the figures within the text; there are frequent sentences in the text that belongs in the figure legend instead (e.g., lines 139-143, 208-211, 214-215, 328-330, etc). It would be better to focus on the results from the figures and then cite the figure, where the colors and exactly what is plotted can be in the figure legend.

      We appreciate these comments on overall flow. We removed lines 139-143 and lengthened the Figure 2 caption (and associated supplementary figure captions) to contain all necessary detail. We removed lines 208-211 and 214-215 and lengthened the captions for Figure 3, Figure 4, and associated supplementary figures. We removed a sentence from lines 303-304.  

      - I'm still concerned that the poor mappability of short-read data is contributing in some ways. Were the sequences in the database mostly from long-reads? Was nucleotide diversity calculated directly from the sequences in the database or from another human dataset? Is missing data at some sites accounted for in the denominator?

      The sequences in the database are mostly from short reads and come from a wide array of labs. We have added a paragraph to the discussion to explain the limitations of this (lines 473-499). However, the nucleotide diversity calculations shown in Figure 1 do not rely on the MHC database; rather, they are calculated from the human genomes in the 1000 Genomes project. Nucleotide diversity would be calculable for other species, but we did not do so for exactly the reason you mention–too much missing data.

      - The Figure 2 and Figure 3 supplements took me a little bit to understand - is it really worth pointing out the top 5 Bayes-factor comparisons when there is no evidence for TSP? A lot of the colored squares are not actually supporting TSP but in the grids you can't see which are and which aren't without looking at the Bayes Factor. I wonder if it would help if only those with BF > 100 were shown? Or if these were marked some other way so that it was easy to see where TSPs are supported.

      Thank you for your perspective on these figures! We initially limited them to only show >100 Bayes factors for each gene group and region, but some gene groups have no high Bayes factors. Additionally, the “summary” tree pictured in these figures is necessarily a simplification of the full space of posterior trees. We felt that showing low Bayes factor comparisons could help readers understand this relationship. For example, allele sets that look non-monophyletic on the summary tree may still have a low Bayes factor, showing that they are generally monophyletic throughout the larger (un-visualizable) space of trees.

      Reviewer #3 (Recommendations for the authors):

      Specific comments

      Abstract

      I think the abstract would benefit from some editing. For example, one might get the impression that you equate allele sharing, which would normally be understood as sharing identical sequences, with sharing ancestral allelic lineages. This distinction is important because you can have many TSPs without sharing identical allele sequences. In l. 20 you write about "deep TSP", which requires either definition of reformulation. In l. 21-23 you seem to suggest that long-term retention of allelic lineages is surprising in the light of rapid sequence evolution - it may be, depending on the evolutionary scenarios one is willing to accept, but perhaps it's not necessary to float such a suggestion in the abstract where it cannot be properly explained due to space constraints? The last sequence needs a qualifier like "in some cases".

      Thank you for catching these! For clarity, we changed several words:

      ● “alleles” to “allelic lineages” in line 13

      ● “deep” to “ancient” in line 21

      ● “Despite” to “in addition to” in line 22

      ● Added “in some cases” to line 28

      Results - Overall, parts of the results read like extended figure captions. I understand that the authors want to make the complex figures accessible to the reader. However, including so much information in the text disrupts the flow and makes it difficult to follow what the main findings and conclusions are.

      We appreciate these comments on overall flow. We removed lines 139-143 and lengthened the Figure 2 caption (and associated supplementary figure captions) to contain all necessary detail. We removed lines 208-211 and 214-215 and lengthened the captions for Figure 3, Figure 4, and associated supplementary figures. We removed a sentence from lines 303-304.  

      l. 37-39 such a short sentence on non-classical MHC is necessarily an oversimplification, I suggest it be expanded or deleted.

      There is certainly a lot to say about each of these genes! While we do not have space in this paper’s introduction to get into these genes’ myriad functions, we added a reference to our companion paper in lines 40-41:

      “See the appendices of our companion paper \citep{Fortier2024a} for more detail.”

      These appendices are extensive, and readers can find details and references for literature on each specific gene there. In addition, several genes are mentioned in analyses further on in the results, and their specific functions are discussed in more detail when they arise.

      l. 47 -49 It would be helpful to briefly outline your criteria for selecting these 17 genes, even if this is repeated later.

      Thank you! For greater clarity, we changed the text (lines 50-52) from “Here, we look within 17 specific genes to characterize trans-species polymorphism, a phenomenon characteristic of long-term balancing selection.” to “Here, we look within 17 specific genes---representing classical, non-classical, Class I, and Class II ---to characterize trans-species polymorphism, a phenomenon characteristic of long-term balancing selection.“  

      l.85-87 I may be completely wrong, but couldn't problems with establishing orthology in some cases lead to false inferences of TSP, even in primates? Or do you think the data are of sufficient quality to ignore such a possibility? (you touch on this in pp. 261-264)

      Yes, problems with establishing orthology can lead to false inferences of TSP, and it has happened before. For example, older studies that used only exon 2 (binding-site-encoding) of the MHC-DRB genes inferred trees that grouped NWM sequences with ape and OWM sequences. Thus, they named these NWM genes MHC-DRB3 and -DRB5 to suggest orthology with ape/OWM MHC-DRB3 and -DRB5, and they also suggested possible TSP between the groups. However, later studies that used non-binding-site-encoding exons or introns noticed that these NWM sequences did not group with ape/OWM sequences (which now shared the same name), providing evidence against orthology. This illustrates that establishing orthology is critical before assessing TSP (as is comparing across regions). This is part of the reason we published a companion paper (https://doi.org/10.7554/eLife.103545.1), which clears up questions of orthology and supports the analyses we did in this paper. In cases where orthology was ambiguous, this also helped us to be conservative in our conclusions here. The problems with ambiguous gene assignment are also discussed in lines 488-499.

      l. 88-93 is the first place (others are pp. 109-118 and 460-484) where a fuller description of the data used would be welcome. It's clear that the amount of data from different species varies enormously, not only in the number of alleles per locus, but also in the loci for which polymorphism data are available. In such a synthesis study, one would expect at least a tabulation of the data used in the appendices and perhaps a summary table in the main article.

      l. 109-118 Again, a more quantitative summary of the data used, with reference to a table, would be useful.

      Thank you! To address these comments, we added Tables 2-4 to allow readers to more readily understand the data we included in each group. We refer to these tables in the introduction (line 95), in the “Data” section of the results (lines 128-129), and the “Data” section of the methods (lines 532-534). Supplementary Files listing the exact alleles and sequences used in each group are also included in the resubmission.

      l. 123-124 here you say that the definition of the "16 gene groups" is in the methods (probably pp. 471-484), but it would be useful to present an informative summary of your rationale in the introduction or here

      Thank you! We agree that it is helpful to outline these groups earlier. We have changed the paragraph in lines 123-135 from: 

      “We considered 16 gene groups and two or three different genic regions for each group: exon 2 alone, exon 3 alone, and/or exon 4 alone. Exons 2 and 3 encode the peptide-binding region (PBR) for the Class I proteins, and exon 2 alone encodes the PBR for the Class II proteins. For the Class I genes, we also considered exon 4 alone because it is comparable in size to exons 2 and 3 and provides a good contrast to the PBR-encoding exons. See the Methods for more detail on how gene groups were defined. Because few intron sequences were available for non-human species, we did not include them in our analyses.” To: 

      “We considered 16 gene groups spanning MHC classes and functions. These include the classical Class I genes (MHC-A-related, MHC-B-related, MHC-C-related), non-classical Class I genes (MHC-E-related, MHC-F-related, MHC-G-related), classical Class IIA genes (MHC-DRA-related, MHC-DQA-related, MHC-DPA-related), classical Class IIB genes (MHC-DRB-related, MHC-DQB-related, MHC-DPB-related), non-classical Class IIA genes (MHC-DMA-related, MHC-DOA-related, and non-classical Class IIB genes (MHC-DMB-related, MHC-DOB-related). We studied two or three different genic regions for each group: exon 2 alone, exon 3 alone, and (for Class I) exon 4 alone. Exons 2 and 3 encode the peptide-binding region (PBR) for the Class I proteins, and exon 2 alone encodes the PBR for the Class II proteins. For the Class I genes, we also considered exon 4 alone because it is comparable in size to exons 2 and 3 and provides a good contrast to the PBR-encoding exons. Because few intron sequences were available for non-human species, we did not include them in our analyses.”

      l. 100 "alleles" -> "allelic lineages"

      Thank you for catching this. We have changed this language in line 104.

      l. 227-238 it's important to discuss the possible effect of the number of sequences available on the detectability of TSP - this is particularly important as the properties of MHC genealogies may differ considerably from those expected for neutral genealogies.

      This is a good point that may not be obvious to readers. We have added several sentences to clarify this:

      Line 193-194: “In a neutral genealogy, monophyly of each species' sequences is expected.”

      Line 213-219: “Note that the number of sequences available for comparison also affects the detectability of TSP. For example, if the only sequences available are from the same allelic lineage, they will coalesce more recently in the past than they would with alleles from a different lineage and would not show evidence for TSP. This means our method is well-suited to detect TSP when a diverse set of allele sequences are available, but it is conservative when there are few alleles to test. There were few available alleles for some non-classical genes, such as MHC-F, and some species, such as gibbon.”

      Line 244-246: “However, since there are fewer alleles available for the non-classical genes, we note that our method is likely to be conservative here.”

      l. 301 and 624-41 it's been difficult for me to understand the rationale behind using rates at mostly gap positions as the baseline and I'd be grateful for a more extensive explanation

      Normalizing the rates posed a difficult problem. We couldn’t include every single sequence in the same alignment because BEAST’s computational needs scale with the number of sequences. Therefore, we had to run BEAST separately on smaller alignments focused on a single group of genes at a time. We still wanted to be able to compare evolutionary rates across genes, but because of the way SubstBMA is implemented, evolutionary rates are relative, not absolute. Recall that to help us compare the trees, we included a common set of “backbone” sequences in all of the 16 alignments. This set included some highly-diverged genes. Initially, we planned to use 4-fold degenerate sites as the baseline sites for normalization, but there simply weren’t enough of them once we included the “backbone” set on top of the already highly diverse set of sequences in each alignment. This diversity presented an opportunity.  In BEAST, gaps are treated as missing and do not contribute any probability to the relevant branch or site (https://groups.google.com/g/beast-users/c/ixrGUA1p4OM/m/P4R2fCDWMUoJ?pli=1). So, we figured that sites that were “mostly gap” (a gap in all the human backbone sequences but with an insertion in some sequence) were mostly not contributing to the inference of the phylogeny or evolutionary rates. Because the “backbone” sequences are common to all alignments, making the “mostly gap” sites somewhat comparable across sets while not affecting inferred rates, we figured they would be a reasonable choice for the normalization (for lack of a better option).

      We added text to lines 680 and 691-693 to clarify this rationale.

      l. 380-84 this overview seems rather superficial. Would it be possible to provide a more quantitative summary?

      To make this more quantitative, we plotted the number of associations for each amino acid against evolutionary rate, shown in Figure 6 - Figure Supplement 7 (NOTE: this needs to be renamed as Table 1 - Figure Supplement 1, which the template does not allow). This reveals a significant positive slope for the Class I genes, but not for Class II. We also added explanatory text for this figure in lines 400-404.

      Discussion - your approach to detecting TSP is elegant but deserves discussion of its limitations and, in particular, a clear explanation of why detecting TSP rather than quantifying its extent is more important in the context of this work. Another important point for discussion is alternative explanations for the patterns of TSP or, more broadly, gene tree - species tree discordance. Although long-term maintenance of allelic lineages due to long-term balancing selection is probably the most convincing explanation for the observed TSP, interspecific introgression and incorrect orthology assessment may also have contributed, and it would be good to see what the authors think about the potential contribution of these two factors.

      Overall, our goal was to use modern statistical methods and data to more confidently assess how ancient the TSP is at each gene. We have added several lines of text (as noted elsewhere in this document) to more clearly illustrate the limitations of our approach. We also agree that interspecific introgression and incorrect orthology assessment can cause similar patterns to arise. We attempted to minimize the effect of incorrect orthology assessment by creating multi-gene trees and exploring reference primate genomes, as described in our companion paper (https://doi.org/10.7554/eLife.103545.1), but cannot eliminate it completely. We have added a paragraph to the discussion to address this (lines 488-499). Interspecific introgression could also cause gene tree-species tree discordance, but we are not sure about how systematic this would have to be to cause the overall patterns we observe, nor about how likely it would have been for various clades of primates across the world.

      l. 421 -424 A more nuanced discussion distinguishing between positive selection, which facilitates the establishment of a mutation, and directional selection, which leads to its fixation, would be useful here.

      We added clarification to this sentence (line 443-445), from “Indeed, within the phylogeny we find that the most rapidly-evolving codons are substituted at around 2--4-fold the baseline rate.” to “Indeed, within the phylogeny we find that the most rapidly-evolving codons are substituted at around 2--4-fold the baseline rate, generating ample mutations upon which selection may act.”

      l. 432-434 You write here about the shaping of TCR repertoires, but I couldn't find any such information in the paper, including Table 1.

      We did not include a separate column for these, so they can be hard to spot. They take the form of “TCR 𝛽 Interaction Probability >50%”, “TCR Expression (TRAV38-1)”, or “TCR 𝛼 Interaction Probability >50%” and can be found in Table 1.

      l. 436-442 Here a more detailed discussion in the context of divergent allelic advantage and even the evolution of new S-type specificities in plants would be valuable.

      We added an additional citation to a review article to this sentence (lines 438-439).  

      l. 443 The use of the word "training" here is confusing, suggesting some kind of "education" during the lifetime of the animal.

      We agree that “train” is not an entirely appropriate term, and have changed it to “evolve” (line 465).

      489-491 What data were used for these calculations?

      Apologies for missing this citation! We used the 1000 genomes project data, and the citation has been updated (line 541-542).

    1. Note: This preprint has been reviewed by subject experts for Review Commons. Content has not been altered except for formatting.

      Learn more at Review Commons


      Referee #2

      Evidence, reproducibility and clarity

      Summary:

      There is growing appreciation for the important of luminal (apical) ECM in tube development, but such matrices are much less well understood than basal ECMs. Here the authors provide insights into the aECM that shapes the Drosophila salivary gland (SG) tube and the importance of PAPSS-dependent sulfation in its organization and function.

      The first part of the paper focuses on careful phenotypic characterization of papss mutants, using multiple markers and TEM. This revealed reduced markers of sulfation (Alcian Blue staining) and defects in both apical and basal ECM organization, Golgi (but not ER) morphology, number and localization of other endosomal compartments, plus increased cell death. The authors focus on the fact that papss mutants have an irregular SG lumen diameter, with both narrowed regions and bulged regions. They address the pleiotropy, showing that preventing the cell death and resultant gaps in the tube did not rescue the SG luminal shape defects and discussing similarities and differences between the papss mutant phenotype and those caused by more general trafficking defects. The analysis uses a papss nonsense mutant from an EMS screen - I appreciate the rigorous approach the authors took to analyze transheterozygotes (as well as homozygotes) plus rescued animals in order to rule out effects of linked mutations.

      The 2nd part of the paper focuses on the SG aECM, showing that Dpy and Pio ZP protein fusions localize abnormally in papss mutants and that these ZP mutants (and Np protease mutants) have similar SG lumen shaping defects to the papss mutants. A key conclusion is that SG lumen defects correlate with loss of a Pio+Dpy-dependent filamentous structure in the lumen. These data suggest that ZP protein misregulation could explain this part of the papss phenotype.

      Overall, the text is very well written and clear. Figures are clearly labeled. The methods involve rigorous genetic approaches, microscopy, and quantifications/statistics and are documented appropriately. The findings are convincing, with just a few things about the fusions needing clarification.

      Minor comments:

      1. Although the Dpy and Qsm fusions are published reagents, it would still be helpful to mention whether the tags are C-terminal as suggested by the nomenclature, and whether Westerns have been performed, since (as discussed for Pio) cleavage could also affect the appearance of these fusions.

      2. The Dpy-YFP reagent is a non-functional fusion and therefore may not be a wholly reliable reporter of Dpy localization. There is no antibody confirmation. As other reagents are not available to my knowledge, this issue can be addressed with text acknowledgement of possible caveats.

      3. TEM was done by standard chemical fixation, which is fine for viewing intracellular organelles, but high pressure freezing probably would do a better job of preserving aECM structure, which looks fairly bad in Fig. 2G WT, without evidence of the filamentous structures seen by light microscopy. Nevertheless, the images are sufficient for showing the extreme disorganization of aECM in papss mutants.

      4. The authors may consider citing some of the work that has been done on sulfation in nematodes, e.g. as reviewed here: https://pubmed.ncbi.nlm.nih.gov/35223994/ Sulfation has been tied to multiple aspects of nematode aECM organization, though not specifically to ZP proteins.

      Significance

      This study will be of interest to researchers studying developmental morphogenesis in general and specifically tube biology or the aECM. It should be particularly of interest to those studying sulfation or ZP proteins (which are broadly present in aECMs across organisms, including humans).

      This study adds to the literature demonstrating the importance of luminal matrix in shaping tubular organs and greatly advances understanding of the luminal matrix in the Drosophila salivary gland, an important model of tubular organ development and one that has key matrix differences (such as no chitin) compared to other highly studied Drosophila tubes like the trachea.

      The detailed description of the defects resulting from papss loss suggests that there are multiple different sulfated targets, with a subset specifically relevant to aECM biology. A limitation is that specific sulfated substrates are not identified here (e.g. are these the ZP proteins themselves or other matrix glycoproteins or lipids?); therefore it's not clear how direct or indirect the effects of papss are on ZP proteins. However, this is clearly a direction for future work and does not detract from the excellent beginning made here.

      My expertise: I am a developmental geneticist with interests in apical ECM

    2. Note: This preprint has been reviewed by subject experts for Review Commons. Content has not been altered except for formatting.

      Learn more at Review Commons


      Referee #1

      Evidence, reproducibility and clarity

      PAPS is required for all sulfotransferase reactions in which a sulfate group is covalently attached to amino acid residues of proteins or to side chains of proteoglycans. This sulfation is crucial for properly organizing the apical extracellular matrix (aECM) and expanding the lumen in the Drosophila salivary gland. Loss of Papss potentially leads to decreased sulfation, disorganizing the aECM, and defects in lumen formation. In addition, Papss loss destabilizes the Golgi structures.

      In Papss mutants, several changes occur in the salivary gland lumen of Drosophila. The tube lumen is very thin and shows irregular apical protrusions. There is a disorganization of the apical membrane and a compaction of the apical extracellular matrix (aECM). The Golgi structures and intracellular transport are disturbed. In addition, the ZP domain proteins Piopio (Pio) and Dumpy (Dpy) lose their normal distribution in the lumen, which leads to condensation and dissociation of the Dpy-positive aECM structure from the apical membrane. This results in a thin and irregularly dilated lumen.

      1. The authors describe various changes in the lumen in mutants, from thin lumen to irregular expansion. I would like to know the correct lumen diameter, and length, besides the total area, by which one can recognize thin and irregular.

      2. The rescue is about 30%, which is not as good as expected. Maybe the wrong isoform was taken. Is it possible to find out which isoform is expressed in the salivary glands, e.g., by RNA in situ Hyb? This could then be used to analyze a more focused rescue beyond the paper.

      3. Crb is a transmembrane protein on the apicolateral side of the membrane. Accordingly, the apicolateral distribution can be seen in the control and the mutant. I believe there are no apparent differences here, not even in the amount of expression. However, the view of the cells (frame) shows possible differences. To be sure, a more in-depth analysis of the images is required. Confocal Z-stack images, with 3D visualization and orthogonal projections to analyze the membranes showing Crb staining together with a suitable membrane marker (e.g. SAS or Uif). This is the only way to show whether Crb is incorrectly distributed. Statistics of several papas mutants would also be desirable and not just a single representative image. When do the observed changes in Crb distribution occur in the development of the tubes, only during stage 16? Is papass only involved in the maintenance of the apical membrane? This is particularly important when considering the SJ and AJ, because the latter show no change in the mutants.

      4. A change in the ECM is only inferred based on the WGA localization. This is too few to make a clear statement. WGA is only an indirect marker of the cell surface and glycosylated proteins, but it does not indicate whether the ECM is altered in its composition and expression. Other important factors are missing here. In addition, only a single observation is shown, and statistics are missing.

      5. Reduced WGA staining is seen in papas mutants, but this could be due to other circumstances. To be sure, a statistic with the number of dots must be shown, as well as an intensity blot on several independent samples. The images are from single confocal sections. It could be that the dots appear in a different Z-plane. Therefore, a 3D visualization of the voxels must be shown to identify and, at best, quantify the dots in the organ.

      6. A colocalization analysis (statistics) should be shown for the overlap of WGA with ManII-GFP.

      7. I do not understand how the authors describe "statistics of secretory vesicles" as an axis in Figure 3p. The TEM images do not show labeled secretory vesicles but empty structures that could be vesicles.

      8. The quality of the presented TEM images is too low to judge any difference between control and mutants. Therefore, the supplement must present them in better detail (higher pixel number?).

      9. Line 266: the conclusion that apical trafficking is "significantly impaired" does not hold. This implies that Papass is essential for apical trafficking, but the analyzed ECM proteins (Pio, Dumpy) are found apically enriched in the mutants, and Dumpy is even secreted. Moreover, they analyze only one marker, Sec15, and don't provide data about the quantification of the secretion of proteins.

      10. DCP-1 was used to detect apoptosis in the glands to analyze acellular regions. However, the authors compare ST16 control with ST15 mutant salivary glands, which is problematic. Further, it is not commented on how many embryos were analyzed and how often they detect the dying cells in control and mutant embryos. This part must be improved.

      11. WGA and Dumpy show similar condensed patterns within the tube lumen. The authors show that dumpy is enriched from stage 14 onwards. How is it with WGA? Does it show the same pattern from stage 14 to 16? Papass mutants can suffer from a developmental delay in organizing the ECM or lack of internalization of luminal proteins during/after tube expansion, which is the case in the trachea.

      12. Line 366. Luminal morphology is characterized by bulging and constrictions. In the trachea, bulges indicate the deformation of the apical membrane and the detachment from the aECM. I can see constrictions and the collapsed tube lumen in Fig. 6C, but I don't find the bulges of the apical membrane in pio and Np mutants. Maybe showing it more clearly and with better quality will be helpful.

      13. The authors state that Papass controls luminal secretion of Pio and Dumpy, as they observe reduced luminal staining of both in papass mutants. However, the mCh-Pio and Dumpy-YFP are secreted towards the lumen. Does papass overexpression change Pio and Dumpy secretion towards the lumen, and could this be another explanation for the multiple phenotypes? Regulation of luminal ZP protein level is essential to modulate the tube expansion; therefore, Np releases Pio and Dumpy in a controlled manner during st15/16. Thus, the analysis of Pio and Dumpy in NP overexpression embryos will be critical to this manuscript to understand more about the control of luminal ZP matrix proteins.

      14. Minor: Fig. 5 C': mChe-Pio and Dumpy-YFP are mixed up at the top of the images. Sup. Fig7. A shows Pio in purple but B in green. Please indicate it correctly.

      Significance

      In 2023, the functions of Pio, Dumpy, and Np in the tracheal tubes of Drosophila were published. The study here shows similar results, with the difference that the salivary glands do not possess chitin, but the two ZP proteins Pio and Dumpy take over its function. It is, therefore, a significant and exciting extension of the known function of the three proteins to another tube system. In addition, the authors identify papass as a new protein and show its essential function in forming the luminal matrix in the salivary glands. Considering the high degree of conservation of these proteins in other species, the results presented are crucial for future analyses and will have further implications for tubular development, including humans.

    1. Reviewer #1 (Public review):

      Summary and Strengths:

      This work shows that the gene encoding Layilin is expressed preferentially in human skin Tregs, and that the fraction of Tregs expressing Layilin may overexpress genes related to T cell activation and adhesion. Expression of Layilin on Tregs would have no impact on activation markers or in vitro suppressive function. However, activation of Layilin either with a cross-linking antibody or collagen IV, its natural ligand, would promote cell adhesion via LFA1 activation. The in vivo functional role of Layilin in Tregs is studied in a conditional KO mouse model in a model of skin inflammation. Deletion of Layilin in Tregs led to an attenuation of the disease score and a reduction in the cutaneous lymphocyte infiltrate. This work is clearly innovative, but a number of major points limit its interest.

      Weakness and major points:

      (1) The number of panels and figures suggests that this story is quite complete but several data presented in the main figures do not provide essential information for a proper understanding of Layilin's role in Tregs.

      Figures 1I, 1J, and the whole of Figure 2 could be placed as supplementary figures. Also, for Figure 3E, it would be preferable to show the percentage of cells expressing cytokines rather than their absolute numbers. In fact, the drop in the numbers of cytokine-producing cells is probably due solely to the drop in total cell numbers and not to a decrease in the proportion of cells expressing cytokines. If this is the case, these data should be shown in supplementary figures. Finally, Figures 4 and 5 could be merged.

      (2) Some important data are not shown or not mentioned.

      (a) It would be important to show the proportion of Treg, Tconv, and CD8 expressing Layilin in healthy skin and in patients developing psoriasis, as well as in the blood of healthy subjects.<br /> (b) We lack information to be convinced that there is enrichment for migration and adhesion genes in Layilin+ Tregs in the GSEA data. The authors should indicate what geneset libraries they used. Indeed, it is tempting to show only the genesets that give results in line with the message you want to get across. If these genesets come from public banks, the bank used should be indicated, and the results of all gene sets shown in an unbiased way. In addition, it should be indicated whether the analyses were performed on untransformed or pseudobulk scRNAseq data analyses. Finally, it would be preferable to confirm the GSEA data with z-score analyses, as Ingenuity does, for example. Indeed, in GSEA-type analyses, there are genes that have activating but also inhibiting effects on a pathway in a given gene set.<br /> (c) For all FACS data, the raw data should be shown as histograms or dot plots for representative samples.<br /> (d) For Figure 5B, the number of samples analyzed is insufficient to draw clear conclusions.

      (3) For Figs. 4 and 5, the design of the experiment poses a problem. Indeed, the comparison between Layn+ and Layn- cells may, in part, not be directly linked to the expression or absence of expression of this protein. Indeed, Layn+ and Layn- Tregs may constitute populations with different biological properties, beyond the expression of Layn. However, in the experiment design used here, a significant fraction of the sorted Layn- Tregs will be cells belonging to the population that has never expressed this protein. It would have been preferable to sort first the Layn+ Tregs, then knock down this protein and re-sort the Layn- Tregs and Layn+ Tregs. If this experiment is too cumbersome to perform, I agree that the authors should not do it. However, it would be important to mention the point I have just made in the text.

    2. Reviewer #3 (Public review):

      Summary:

      Gouirand et al explore the function of Layilin on Treg in the context of psoriasis using both patient samples and a conditional mutant mouse model. They perform functional analysis in the patient samples using Cas9-mediated deletion. The authors suggest that Layilin works in concert with integrins to bind collagen IV to attenuate cell movement.

      The work is well done and built on solid human data. The report is a modest advance from the authors' previous report in 2021 that focused on tumor responses, with this report focusing on psoriasis. There are some experimental concerns that should be considered.

      Strengths:

      (1) Good complementation of patient and animal model data.

      (2) Solid experimentation using state-of-the-art approaches.

      (3) There is clearly a biological effect of LAYN deficiency in the mouse model.

      (4) The report adds some new information to what was already known from the previous reports.

      Weaknesses:

      (1) It is not clear that the assays used for functional analysis of the patient samples were optimal.

      (2) Several conclusions are not fully substantiated.

      (3) The report is lacking some experimental details.

    3. Author response:

      Reviewer 1:

      Concern 1: Figures 1I, 1J, and the whole of Figure 2 could be placed as supplementary figures. Also, for Figure 3E, it would be preferable to show the percentage of cells expressing cytokines rather than their absolute numbers. In fact, the drop in the numbers of cytokine-producing cells is probably due solely to the drop in total cell numbers and not to a decrease in the proportion of cells expressing cytokines. If this is the case, these data should be shown in supplementary figures. Finally, Figures 4 and 5 could be merged.

      We thank you for your recommendations. As rearranging figures is not critical to convey the data, we have decided to keep the figures and supplemental figures as they are currently presented.

      Concern 2a: It would be important to show the proportion of Treg, Tconv, and CD8 expressing Layilin in healthy skin and in patients developing psoriasis, as well as in the blood of healthy subjects.

      This data is published in a previous manuscript from our group. Please see Figure 1 in “Layilin Anchors Regulatory T Cells in Skin” (PMID: 34470859)

      Concern 2b: We lack information to be convinced that there is enrichment for migration and adhesion genes in Layilin+ Tregs in the GSEA data. The authors should indicate what geneset libraries they used. Indeed, it is tempting to show only the genesets that give results in line with the message you want to get across. If these genesets come from public banks, the bank used should be indicated, and the results of all gene sets shown in an unbiased way. In addition, it should be indicated whether the analyses were performed on untransformed or pseudobulk scRNAseq data analyses. Finally, it would be preferable to confirm the GSEA data with z-score analyses, as Ingenuity does, for example. Indeed, in GSEA-type analyses, there are genes that have activating but also inhibiting effects on a pathway in a given gene set.

      Given that we have already shown that layilin plays a major role in Treg and CD8+ T cell adhesion in tissues, we used a candidate approach for our GSEA. We tested the hypothesis that adhesion and motility pathways are enriched in Layilin-expressing Tregs. There was a statistically significant enrichment for these genes in Layilin+ Tregs compared to Layilin- Tregs, which we feel adequately tests our hypothesis.

      Concern 2c: For all FACS data, the raw data should be shown as histograms or dot plots for representative samples.

      We respect this concern. We omit these secondary to space constraints.

      Concern 2d: For Figure 5B, the number of samples analyzed is insufficient to draw clear conclusions.

      We respectfully disagree. Three doners were used in a paired fashion (internally controlled) achieving statistical significance.

      Concern 3: For Figs. 4 and 5, the design of the experiment poses a problem. Indeed, the comparison between Layn+ and Layn- cells may, in part, not be directly linked to the expression or absence of expression of this protein. Indeed, Layn+ and Layn- Tregs may constitute populations with different biological properties, beyond the expression of Layn. However, in the experiment design used here, a significant fraction of the sorted Layn- Tregs will be cells belonging to the population that has never expressed this protein. It would have been preferable to sort first the Layn+ Tregs, then knock down this protein and re-sort the Layn- Tregs and Layn+ Tregs. If this experiment is too cumbersome to perform, I agree that the authors should not do it. However, it would be important to mention the point I have just made in the text.

      We agree. However, as the reviewer points out, these experiments are not logistically and practically feasible at this point. We do perform several experiments in this manuscript in which layilin is reduced via gene editing with results supporting our hypotheses.

      Reviewer 2:

      Some of the conclusions drawn by the authors must be treated with caution, as the experimental conditions were not always appropriate, leading to a risk of misinterpretation.

      We have been transparent with all our methods and data. We will leave this to the reader to determine level of rigor and the robustness of the data.

      Reviewer 3:

      Weaknesses:

      It is not clear that the assays used for functional analysis of the patient samples were optimal. (2) Several conclusions are not fully substantiated. (3) The report is lacking some experimental details.

      We have tried to be as comprehensive and thorough as possible. We feel that the data supports our conclusions. We will leave this to the reader to interpret and conclude.

    1. Author response:

      The following is the authors’ response to the original reviews

      Public Reviews:

      Reviewer #1 (Public review):

      Summary:

      Aicardi-Goutières Syndrome (AGS) is a genetic disorder that primarily affects the brain and immune system through excessive interferon production. The authors sought to investigate the role of microglia in AGS by first developing bone-marrow-derived progenitors in vitro that carry the estrogen-regulated (ER) Hoxb8 cassette, allowing them to expand indefinitely in the presence of estrogen and differentiate into macrophages when estrogen is removed. When injected into the brains of Csf1r-/- mice, which lack microglia, these cells engraft and resemble wild-type (WT) microglia in transcriptional and morphological characteristics, although they lack Sall1 expression. The authors then generated CRISPR-Cas9 Adar1 knockout (KO) ER-Hoxb8 macrophages, which exhibited increased production of inflammatory cytokines and upregulation of interferon-related genes. This phenotype could be rescued using a Jak-Stat inhibitor or by concurrently mutating Ifih1 (Mda5). However, these Adar1-KO macrophages fail to successfully engraft in the brain of both Csf1r-/- and Cx3cr1-creERT2:Csf1rfl/fl mice. To overcome this, the authors used a mouse model with a patient-specific Adar1 mutation (Adar1 D1113H) to derive ER-Hoxb8 bone marrow progenitors and macrophages. They discovered that Adar1 D1113H ER-Hoxb8 macrophages successfully engraft the brain, although at lower levels than WT-derived ER-Hoxb8 macrophages, leading to increased production of Isg15 by neighboring cells. These findings shed new light on the role of microglia in AGS pathology.

      Strengths:

      The authors convincingly demonstrate that ER-Hoxb8 differentiated macrophages are transcriptionally and morphologically similar to bone marrow-derived macrophages. They also show evidence that when engrafted in vivo, ER-Hoxb8 microglia are transcriptomically similar to WT microglia. Furthermore, ER-Hoxb8 macrophages engraft the Csf1r-/- brain with high efficiency and rapidly (2 weeks), showing a homogenous distribution. The authors also effectively use CRISPR-Cas9 to knock out TLR4 in these cells with little to no effect on their engraftment in vivo, confirming their potential as a model for genetic manipulation and in vivo microglia replacement.

      Weaknesses:

      The robust data showing the quality of this model at the transcriptomic level can be strengthened with confirmation at protein and functional levels. The authors were unable to investigate the effects of Adar1-KO using ER-Hoxb8 cells and instead had to rely on a mouse model with a patient-specific Adar1 mutation (Adar1 D1113H). Additionally, ER-Hoxb8-derived microglia do not express Sall1, a key marker of microglia, which limits their fidelity as a full microglial replacement, as has been rightfully pointed out in the discussion.

      Overall, this paper demonstrates an innovative approach to manipulating microglia using ER-Hoxb8 cells as surrogates. The authors present convincing evidence of the model's efficacy and potential for broader application in microglial research, given its ease of production and rapid brain engraftment potential in microglia-deficient mice. While Adar1-KO macrophages do not engraft well, the success of TLR4-KO line highlights the model's potential for investigating other genes. Using mouse-derived cells for transplantation reduces complications that can come with the use of human cell lines, highlighting the utility of this system for research in mouse models.

      Thank you for this thoughtful and balanced assessment. The major suggestion from Reviewer 1 was that confirmation of RNAseq data with protein or functional studies would add strength.  We provided protein staining by IHC for IBA1 in vivo, as well as protein staining by FACS for CD11B, CD45, and TMEM119 in vitro and in vivo.  For TLR4, we showed successful protein KO and blunted response to LPS (a TLR4 ligand) challenge, which we believe provides some protein and functional data to support the approach.  To bolster these data, we added staining for P2RY12 on brain-engrafted ER-Hoxb8s.

      Regarding the Adar1 KO phenotypes showing non-engraftment. Because ADAR1 KO mice are embryonically lethal due to hematopoietic failure, we see the health impacts of Adar1 KO on ER-Hoxb8s as a strength of the transplantation model, enabling the assessment of ADAR1 global function in macrophages and microglia-like cells without generation of a transgenic mouse line. In addition, it was a surprise that the health impact occurs at the macrophage and not the progenitor stage, perhaps providing insight for future studies of ADAR1’s role in hematopoiesis. Instead, we were able to show a significant impact of complete loss of Adar1 on survival and engraftment, suggesting an important biological function of ADAR1. Macrophage-specific D1113H mutation, which affects part of the deaminase domain, shows that when the RNA deamination (but not the RNA binding) function of ADAR1 is disrupted, we find brain-wide interferonopathy. This is very exciting to our group and hopefully the community as astrocytes are thought to be a major driver of brain interferonopathy in patients with ADAR1 mutations. Instead, this suggests that disruption of brain macrophages is also a major contributor. 

      Reviewer #2 (Public review):

      Summary:

      Microglia have been implicated in brain development, homeostasis, and diseases. "Microglia replacement" has gained traction in recent years, using primary microglia, bone marrow or blood-derived myeloid cells, or human iPSC-induced microglia. Here, the authors extended their previous work in the area and provided evidence to support: (1)

      Estrogen-regulated (ER) homeobox B8 (Hoxb8) conditionally immortalized macrophages from bone marrow can serve as stable, genetically manipulated cell lines. These cells are highly comparable to primary bone marrow-derived (BMD) macrophages in vitro, and, when transplanted into a microglia-free brain, engraft the parenchyma and differentiate into microglia-like cells (MLCs). Taking advantage of this model system, the authors created stable, Adar1-mutated ER-Hoxb8 lines using CRISPR-Cas9 to study the intrinsic contribution of macrophages to the Aicardi-Goutières Syndrome (AGS) disease mechanism.

      Strengths:

      The studies are carefully designed and well-conducted. The imaging data and gene expression analysis are carried out at a high level of technical competence and the studies provide strong evidence that ER-Hoxb8 immortalized macrophages from bone marrow are a reasonable source for "microglia replacement" exercise. The findings are clearly presented, and the main message will be of general interest to the neuroscience and microglia communities.

      Recommendations for the authors:

      Reviewer #1 (Recommendations for the authors):

      This is an elegant study, demonstrating both the utility and limitations of ER-Hoxb8 technology as a surrogate model for microglia in vivo. The manuscript is well-designed and clearly written, but authors should consider the following suggestions:

      (1) Validation of RNA hits at the protein level: To strengthen the comparison between ER-Hoxb8 macrophages and WT bone marrow-derived macrophages, validating several RNA hits at the protein level would be beneficial. As many of these hits are surface markers, flow cytometry could be employed for confirmation (e.g., Figure 1D, Figure 3E).

      In vitro, we show protein levels by flow cytometry for CD11B (ITGAM) and CD45 (PTPRC; Figure 1C), as well as TMEM119 (Supplemental Figure 2A) and TLR4 (Supplemental Figure 3C/D). In vivo, we show TMEM119 protein levels by flow cytometry (Figure 3A), as well as their CD11B/CD45 pregates (Supplemental Figure 2C), plus immunostaining for IBA1 (AIF1; Figure 2D). We now provide additional data showing P2RY12 immunostaining in brain-engrafted cells (Supplemental Figure 2B). 

      (2) The authors should consider testing the phagocytic capacity of ER-Hoxb8-derived macrophages to further validate their functionality.

      Thank you for the suggestion. We measured ER-Hoxb8 macrophage ability to engulf phosphatidylserine-coated beads that mimic apoptotic cells, compared with phosphatidylcholine-coated beads, now as new Supplemental Figure 1C/D. This agrees with existing literature showing efficient engulfment/phagocytosis by ER-Hoxb8-derived cells (Elhag et al., 2021).

      (3) For Figure 3E, incorporating a wild-type (WT) microglia reference would be beneficial to establish a baseline for comparison (e.g. including WT microglia data in the graph or performing a ratio analysis against WT expression levels).

      We agree - we now include bars representing our sequenced primary microglia data in Figure 3E as a comparison.  

      (4) Some statistical analyses may require refinement. Specifically, for Figure 4J, where the effects of Adar1 KO and Adar1 KO with Bari are compared, it would be more appropriate to use a two-way ANOVA.

      Thank you for noting it. We have now done more appropriate two-way ANOVA and included the updated results in Figure 4J and the corresponding Supplemental Figure 4G. Errors in figure legend texts have also been corrected to reflect the statistical tests used.

      (5) Cx3cr1-creERT2 pups injected with tamoxifen: The authors could clarify the depletion ratio in these experiments before the engraftment and assess whether the depletion is global or regional. In comparison to Csf1r-/-, where TLR4-KO ER-Hoxb8 engraft globally, in Cx3cr1-creERT2, the engraftment seems more regional (Figure 5A vs Supplementary Figure 5B); is this due to the differences in depletion efficiency?

      This is an excellent question and observation, and one that we are very interested in, though that finding does not change the conclusions of this particular study.  We find some region-specific differences in depletion early after tamoxifen injection, but that all brain regions are >95% depleted by P7. For instance, in a recently published manuscript (Bastos et al., 2025) we find some differences in the depletion kinetics in the genetic model. By P3, we find 90% depletion in cortex with 50-60% in thalamus and hippocampus. In other studies, we typically deliver primary monocytes, and this is the first study where we report engraftment of ER-Hoxb8 cells in the inducible model.  In this sense, it is possible that depletion kinetics may regionally affect engraftment, but future studies are required to more finely assess this point with ER-Hoxb8s, as it may change how these models are used in the future.

      Bastos et al., Monocytes can efficiently replace all brain macrophages and fetal liver monocytes can generate bonafide SALL1+ microglia, Immunity (2025), https://doi.org/10.1016/j.immuni.2025.04.006

      (6) It would be helpful for the authors to clarify whether Adar1 is predominantly expressed by microglia, especially since the study aims to show its role in dampening the interferon response.

      That’s a wonderful point. Adar1 is expressed by all brain cells, with highest transcript level in some neurons, astrocytes, and oligodendrocytes. It is an interferon-stimulated gene, and mutation itself leads to interferonopathy, we believe, due to poor RNA editing and detection of endogenous RNA as non-self by MDA5. We hope it can dampen the interferon response, but in the case of mutation, Adar1 is probably causal of interferonopathy.  It is induced in microglia upon systemic inflammatory challenge (LPS). We have edited the text to highlight its expression pattern.  See BrainRNAseq.org (Zhang*, Chen*, Sloan*, et al., 2014 and Bennett et al., 2016)

      Reviewer #2 (Recommendations for the authors):

      (1) There appears to be a morphological difference between wt and Adar1/Ifih1 double KO (dKO) cells in the engrafted brains (Figure 5). It would be good if the authors could systematically compare the morphology (e.g., soma size, number, and length of branches) of the engrafted MLCs between the wt and mutant cells.

      We agree. While cells did not differ in branch number or length, engrafted dKO cells had significantly larger somas compared with controls, which we now present in Figure S5A.

      (2) To fully appreciate the extent of how those engrafted ER-Hoxb8 immortalized macrophages resemble primary, engrafted yolk sac-myeloid cells, vs engrafted iPSC-induced microglia, it would be informative to provide a comparison of their RNAseq data derived from the engrafted ER-Hoxb8 immortalized macrophages with published data transcriptomic data sets (e.g. Bennett et al. Neuron 2018; Chadarevian et al. Neuron 2024; Schafer et al. Cell 2023).

      Thank you for this suggestion. To address this, we provide our full dataset for additional experiments. To compare with a similar non-immortalized model, we compared top up- and down-regulated genes from our data to those of ICT yolk sac progenitor cells from our previous work (Bennett et al., 2018). We find overlap between brain-engrafted ER-Hoxb8-, bone marrow-, and yolk sac-derived cells (Supplemental Figure 2F, Supplemental Table 3).  

      Minor comments:

      Figure 6C: red arrow showing zoom in regions are not matchable. It might be beneficial to provide bigger images with each channel for C and D as a Supplemental Figure.

      We fixed this in Figure 6C to show areas of interest in the cortex for both conditions. Figure S7A shows intermediate power images to aid in interpretation.

    1. Author response:

      The following is the authors’ response to the original reviews

      Reviewer 1 (Public review):

      Weaknesses:

      While the data generally supports the authors' conclusions, a weakness of this manuscript lies in their analytical approach where EEG feature-space comparisons used the number of spontaneous or evoked seizures as their replicates as opposed to the number of IHK mice; these large data sets tend to identify relatively small effects of uncertain biological significance as being highly statistically significant. Furthermore, the clinical relevance of similarly small differences in EEG feature space measurements between seizure-naïve and epileptic mice is also uncertain.

      In this work, we used linear mixed effect model to address two levels of variability –between animals and within animals. The interactive linear mixed effect model shows that most (~90%) of the variability in our data comes from within animals (Residual), the random effect that the model accounts for, rather than between animals. Since variability between animals are low, the model identifies common changes in seizure propagation across animals, while accounting for the variability in seizures within each animal. Therefore, the results we find are of changes that happen across animals, not of individual seizures. We made text edits to clarify the use of the linear mixed effect model. (page6, second paragraph and page 11, first paragraph)

      Finally, the multiple surgeries and long timetable to generate these mice may limit the value compared to existing models in drug-testing paradigms.

      Thank you for the suggestion. We added a discussion in the ‘Comparison to other seizure models…’ section on pages 15 and 16. In an existing model investigating spontaneous tonic-clonic seizures (such as the intra-amygdala kainate injection model), the time investment is back-loaded, requiring two to three weeks per condition while counting spontaneous seizures, which may occur only once a day. In contrast, our model requires a front-loaded time investment. Once the animals are set up, we can test multiple drugs within a few weeks, providing significant time savings. Additionally, we did not pre-screen animals in our study. Existing models often pre-select mice with high rates of spontaneous seizures, whereas in our model, seizures can be induced even in animals with few spontaneous seizures. We believe that bypassing the need for pre-screening also is a key advantage of our induced seizure model.  

      Reviewer 1 (Recommendations for the authors):

      (1) Address why the EEG data comparisons were performed between seizures and not between animals (as explicitly described in the public review). Further, a discussion of the biological significance (or lack thereof) of the effect size differences observed is warranted. This is especially concerning when the authors make the claim that spontaneous and induced seizures are essentially the same while their analysis shows all evaluated feature space parameters were significantly difference in the initial 1/3 of the EEG waveforms.

      We made text edits to clarify the use of the linear mixed effects model (page 6, second paragraph, and page 11, first paragraph)

      (2) The authors place great emphasis on the use of clinically/etiologically relevant epilepsy models in drug discovery research. There is discussion criticizing the time points required to enact kindling and the artificial nature of acute seizure induction methods. However, the combination IHK-opto seizure induction model also requires a lengthy timeline. A more tempered discussion of this novel model's strengths may benefit readers.

      Thank you for the suggestion. We added a discussion in the ‘Comparison to other seizure models…’ section on pages 15 and 16.

      (3) The authors should further emphasize the benefit of having an inducible seizure model of focal epilepsy since other mouse models (e.g., genetic or TBI models) may have superior etiological relevance (construct and face validity) but may not be amenable to their optogenetic stimulation approach.

      Thank you for the suggestion. We revised the manuscript to better emphasize the potential significance of our approach. We added a discussion in the 'Application of Models...' section on page 15, second paragraph. The on-demand seizure model can be applied to address biologically and clinically relevant questions beyond its utility in drug screening. For example, crossing the Thy1-ChR2 mouse line with genetic epilepsy models, such as Scn1a mutants, could reveal how optogenetic stimulation differentially induces seizures in mutant versus non-mutant mice, providing insights into seizure generation and propagation in Dravet syndrome. Due to the cellular specificity of optogenetics, we also envision this approach being used to study circuit-specific mechanisms of seizure generation and propagation.

      (4) Suggestion: Provide immunolabeled imagery demonstrating ChR2 presence in Thy1 cells.

      Thank you for the suggestion. We added a fluorescence image showing ChR2 expression in Fig. 2A

      (5) It might be prudent to mention any potential effects of laser heat on hippocampal cell damage, although the 10 Hz, ~10 mW, and 6 s stim is unlikely to cause any substantial burns. Without knowing the diameter and material of the optic fiber, this is left up to some interpretation.

      Thank you for the comments. In the Methods section, we listed the optical fiber diameter as 400 microns (page 17, EEG and Fiber Implantation section). Using 5–18 mW laser power with a relatively large fiber diameter of 400 microns, the power density falls within the range of commonly employed channelrhodopsin activation conditions in vivo. That said, we would like to investigate potential heat effects or cell damage in a follow-up study.

      (6) There are instances in the manuscript where the authors describe experimental and analytical parameters vaguely (e.g. "Seizures were induced several times a day", "stimulation was performed every 1 - 3 hours over many days"). These descriptions can and should be more precise.

      Thank you for the comments. To enhance clarity, we added the stimulation protocol in a flowchart format in Fig. S2A, describing how we determined the threshold and proceeded to the drug test. Following this protocol, there was variability in the number of stimulations per day.

      (7) In the second to last paragraph of the discussion, the authors state "However, HPDs are not generalizable across species - they are specific to the mouse model (55)." This statement is inaccurate. The paper cited comes from Dr. Corrine Roucard's lab at Synapcell. In fact, Dr. Rouchard argues the opposite (See Neurochem Res (2017) 42:1919-1925).

      Thank you for pointing out the mistake. On page 16, in the first paragraph, reference 55 (now 58 in the revised version) was intended to refer to 'quickly produce dose-response curves with high confidence.' In the revision, we cited another paper reporting that hippocampal spikes were not reproduced in the rat IHK model. R. Klee, C. Brandt, K. Töllner, W. Löscher, Various modifications of the intrahippocampal kainate model of mesial temporal lobe epilepsy in rats fail to resolve the marked rat-to-mouse differences in type and frequency of spontaneous seizures in this model. Epilepsy Behav. 68, 129–140 (2017).

      (8) In the discussion, Levetiracetam is highlighted as an ASM that would not be detected in acute induced seizure models; the authors point out its lack of effect in MES and PTZ. However, LEV is effective in the 6Hz test (also an acute-induced seizure model). This should be stated.

      Thank you for the comments. We highlighted the discussion on LEV in the 'Application of Model to Testing Multiple Classes of ASMs...' section on page 14.

      (9) The results text indicates that 9 epileptic mice were used to test LEV and DZP. However, the individual data points illustrated in Figure 5B show N=8 mice. Please correct.

      Thank you for the comments. A total of nine epileptic mice were used to assess two drugs, with the animals being re-used as indicated in the schematic. A total of eight assessments were conducted for DZP with six mice and eight assessments for LEV with five mice. Each assessment included hourly ChR2 activations without an ASM and hourly ChR2 activations after ASM injection.

      (10) Figure 4D: Naïve mice are labeled as solid blue circles in the legend while the data points are solid blue triangles. Please correct.

      Thank you. We corrected the marker in Fig.4D.

      Reviewer 2 (Public Review):

      Weaknesses:

      (1) Although the figures provide excellent examples of individual electrographic seizures and compare induced seizures in epileptic and naïve animals, it is unclear which criteria were used to identify an actual seizure induced by the optogenetic stimulus, versus a hippocampal paroxysmal discharge (HPD), an "afterdischarge", an "electrophysiological epileptiform event" (EEE, Ref #36, D'Ambrosio et al., 2010 Epilepsy Currents), or a so-called "spike-wave-discharge" (SWD). Were HPDs or these other non-seizure events ever induced using stimulation in animals with IH-KA? A critical issue is that these other electrical events are not actual seizures, and it is unclear whether they were included in the column showing data on "electrographic afterdischarges" in Figure 5 for the studies on ASDs. This seems to be a problem in other areas of the paper, also.

      Thank you for pointing out the unclear definition of the seizures analyzed. We added sentences at the beginning of the Results section (page 3) to clarify the terminology we used. We analyzed animal behavior during evoked events, and a high percentage of induced electrographic events were accompanied by behavioral seizures with a Racine scale of three or above. We added Supplemental Figure S9, which shows behavioral seizure severity scores observed before and during ASM testing. We hope these changes address the reviewer’s concern and improve the clarity of the manuscript.

      (2) The differences between the optogenetically evoked seizures in IH-KA vs naïve mice are interpreted to be due to the "epileptogenesis" that had occurred, but the lesion from the KA-induced injury would be expected to cause differences in the electrically and behaviorally recorded seizures - even if epileptogenesis had not occurred. This is not adequately addressed.

      Thank you for the comments. IHK-injected mice had spontaneous tonic-clonic seizures before the start of optical stimulation, as shown in Figure S1.

      (3) The authors offer little mention of other research using animal models of TLE to screen ASDs, of which there are many published studies - many of them with other strengths and/or weaknesses. For example, although Grabenstatter and Dudek (2019, Epilepsia) used a version of the systemic KA model to obtain dose-response data on the effects of carbamazepine on spontaneous seizures, that work required use of KA-treated rats selected to have very high rates of spontaneous seizures, which requires careful and tedious selection of animals. The ETSP has published studies with an intra-amygdala kainic acid (IA-KA) model (West et al., 2022, Exp Neurol), where the authors claim that they can use spontaneous seizures to identify ASDs for DRE; however, their lack of a drug effect of carbamazepine may have been a false negative secondary to low seizure rates. The approach described in this paper may help with confounds caused by low or variable seizure rates. These types of issues should be discussed, along with others.

      We appreciate the reviewer’s insights. We added a discussion comparing our model with other existing models in the Discussion section (pages 15 and 16, 'Comparison to Other Seizure Models Used in Pharmacologic Screening' section). In an existing model investigating spontaneous tonic-clonic seizures (such as the intra-amygdala kainate injection model), the time investment is back-loaded, requiring two to three weeks per condition while counting spontaneous seizures, which may occur only once a day. In contrast, our model requires a front-loaded time investment. Once the animals are set up, we can test multiple drugs within a few weeks, providing significant time savings. Additionally, we did not pre-screen animals in our study. Existing models often pre-select mice with high rates of spontaneous seizures, whereas in our model, seizures can be induced even in animals with few spontaneous seizures. We believe that bypassing the need for pre-screening is a key advantage of our induced seizure model.

      (4) The outcome measure for testing LEV and DZP on seizures was essentially the fraction of unsuccessful or successful activations of seizures, where high ASD efficacy is based on showing that the optogenetic stimulation causes fewer seizures when the drug is present. The final outcome measure is thus a percentage, which would still lead to a large number of tests to be assured of adequate statistical power. Thus, there is a concern about whether this proposed approach will have high enough resolution to be more useful than conventional screening methods so that one can obtain actual dose-response data on ASDs.

      Thank you for the comments. In this revision, we added Supplemental Figure S9, showing the severity of behavioral seizures observed before and during ASM testing for each animal. We observed a reduction in behavioral seizure severity for each subject. We would like to explore using behavioral severity as an outcome measure in a follow-up study.

      (5) The authors state that this approach should be used to test for and discover new ASDs for DRE, and also used for various open/closed loop protocols with deep-brain stimulation; however, the paper does not actually discuss rigorously or critically the background literature on other published studies in these areas or how this approach will improve future research for a broader audience than the ETSP and CROs. Thus, it is not clear whether the utility will apply more widely and how extensive a readership will be attracted to this work.

      We appreciate the reviewer’s insights. We revised the manuscript to better emphasize the potential significance of our approach (page 15, second paragraph). The on-demand seizure model can be applied to address biologically and clinically relevant questions beyond its utility in drug screening. For example, crossing the Thy1-ChR2 mouse line with genetic epilepsy models, such as Scn1a mutants, could reveal how optogenetic stimulation differentially induces seizures in mutant versus non-mutant mice, providing insights into seizure generation and propagation in Dravet syndrome. Due to the cellular specificity of optogenetics, we also envision this approach being used to study circuit-specific mechanisms of seizure generation and propagation. Regarding drug-resistant epilepsy (DRE) and anti-seizure drug (ASD) screening, we agree with the reviewer that probing new classes of ASDs for DRE represents a critical goal. However, we believe that a full exploration of additional ASD classes and/or modeling DRE lies outside the scope of this manuscript, and we would like to explore it in a follow-up study.

      Reviewer 2 (Recommendations for the authors):

      (1) The authors should explain why 10 Hz was chosen as the stimulation frequency.

      Thank you for the comment. A frequency of 10 Hz was determined based on previous work using anesthetized animals prepared in an acute in vivo setting. To simplify the paper and avoid confusion, we did not include a discussion on how we determined the frequency. Instead, we added a detailed description of how we optimized the power in a flowchart format in Supplemental Figure S2. We hope this improves reproducibility.

      (2) After micro-injection of KA, morphological changes were observed in the hippocampus, but no comparison of Chr2 expression was made in naïve animals vs KA-injected animals. Presumably, the Thy1-Chr2 mouse expresses GFP in cells that express Chr2. Thus, it may be useful to show the expression of Chr2 in animals with hippocampal sclerosis. This may explain the lack of dramatic difference between stimulation parameters in naïve vs epileptic animals, as shown in supplemental Figure S2.

      Thank you for the suggestion. We added a fluorescence image of ChR2 expression in CA1, ipsilateral to the KA-injected site, in Fig. 2A.

      (3) The authors state that "During epileptogenesis, neural networks in the brain undergo various changes ranging from modification of membrane receptors to the formation of new synapses" and that these changes are critical for successful "on-demand" seizure induction. However, it is not clear or well-discussed whether changes in neuronal cell densities that occur during sclerosis are important for "on-demand" seizure induction as well. Also, the authors showed that naïve animals exhibit a kindling-like effect, but it was unclear whether a similar effect was present in epileptic animals (i.e. do stimulation thresholds to seizure induction change as the animal gets more induction stimulations)? If present, would the secondary kindling affect drug-testing studies (e.g., would the drug effect be different on induced seizure #2 vs induced seizure #20)?

      Thank you for the suggestion. Since this is an important aspect of the model, we would like to address the kindling effect, the secondary kindling effect, and histopathology in a longer-term setting (several weeks) in a follow-up study.

      (4) The authors show that in their model, LEV and DZP were both efficacious. The authors do not seem to mention that, over 25 years ago, LEV was originally missed in the standard ETSP screens; and, it was only discovered outside of the ETSP with the kindling model. The kindling model is now used to screen ASDs. The authors should consider adding this point to the Discussion. It remains unclear, however, if the author's screening strategy shows advantages over kindling and other such approaches in the field.

      Thank you for the suggestion. We added a discussion on LEV in the 'Application of Model to Testing Multiple Classes of ASMs...' section on page 14.

      (5) P8 paragraph 2. The authors state values for naïve animals, but they should also provide values for epileptic animals since they state that the groups were not significantly different (p>0.05). It would be useful to show values for both and state the actual p-value from the test. This issue of stating mean/median values with SD and sample size should be addressed for all data throughout the paper. Additionally, Figure S2 should be added to the manuscript and discussed, as it has data that may be valuable for the reproducibility of the paper.

      Thank you for the suggestion. Figure S2 shows the threshold power required to induce electrographic activity for n = 10 epileptic animals (9.14 ± 4.75 mW) and n = 6 naïve animals (6.17 ± 1.58 mW) (Wilcoxon rank-sum test, p = 0.137). The threshold duration was comparable between the same epileptic animals (6.30 ± 1.64 s) and naïve animals (5.67 ± 1.03 s) (Wilcoxon rank-sum test, p = 0.7133). 

      (6) In addition to the other stated references on synaptic reorganization in the CA1 area, the authors should mention similar studies from Esclapez et al. (1999, J Comp Neurol).

      Thank you. We have included the reference in the revision.

      (7) All of the raw EEG data on the seizures should be accessible to the readers.

      Thank you for the suggestion. We will consider depositing EEG data in a publicly accessible site.

      Reviewer 3 (Public review):

      Weaknesses:

      (1) Evaluation of seizure similarity using the SVM modeling and clustering is not sufficiently explained to show if there are meaningful differences between induced and spontaneous seizures. SVM modeling did not include analysis to assess the overfitting of each classifier since mice were modeled individually for classification.”

      Thank you for the comment. We made text edits to clarify the purpose of the SVM analysis. It was not intended to identify meaningful differences between induced and spontaneous seizures. Rather, it was used to classify EEG epochs as 'seizures' based on spontaneous seizures as the training set, demonstrating the gross similarity between induced and spontaneous seizures.

      (2) The difference between seizures and epileptiform discharges or trains of spikes (which are not seizures) is not made clear.

      Thank you for pointing out the unclear definition of the seizures analyzed. We added sentences at the beginning of the Results section (page 3) to clarify the terminology we used. We analyzed animal behavior during evoked events, and a high percentage of induced electrographic events were accompanied by behavioral seizures with a Racine scale of three or above. We added Supplemental Figure S9 to show the types of seizures observed before and during ASM testing. We hope these changes address the reviewer’s concern and improve the clarity of the manuscript.

      (3) The utility of increasing the number of seizures for enhancing statistical power is limited unless the sample size under evaluation is the number of seizures. However, the standard practice is for the sample size to be the number of mice.

      In this work, we used a linear mixed-effects model to address two levels of variability—between animals and within animals. The interactive linear mixed-effects model shows that most (~90%) of the variability in our data comes from within animals (residual), the random effect that the model accounts for, rather than between animals. Since variability between animals is low, the model identifies common changes in seizure propagation across animals while accounting for the variability in seizures within each animal. Therefore, the results we find reflect changes that occur across animals, not individual seizures. We made text edits to clarify the use of the linear mixed-effects model.

      (4) Seizure burden is not easily tested.

      Thank you for the comment. We added Supplemental Figure S9 to summarize the severity of behavioral seizures before and during ASM testing. This addresses the reviewer’s comment on seizure burden. In a follow-up study, we would like to explore this type of outcome measure for drug screening.

      Reviewer 3 (Recommendations for the authors):

      (1) Provide a stronger rationale to use area CA1. For example, the authors mention that CA1 is active during seizure activity, but can seizures originate from CA1? That would make the approach logical and also explain why induced and spontaneous seizures are similar.

      Thank you for the comment. We discussed it in the Discussion section (page 14, first and second paragraphs).

      (2) Explain the use of SVM classifiers so it is more convincing that induced and spontaneous seizures are similar. Or, if they are not similar, explain that this is a limitation.

      We made text edits to clarify the purpose of the SVM analysis. It was not intended to identify meaningful differences between induced and spontaneous seizures. Rather, it was used to classify EEG epochs as 'seizures' based on spontaneous seizures as the training set, demonstrating the gross similarity between induced and spontaneous seizures.

      (3)If feasible, extend the duration over which seizure induction reliability is assessed so that the long-term utility of the model can be demonstrated.

      Thank you for the suggestion. We would like to assess long-term utility in a follow-up study.

      (4) The GitHub link is not yet active. The authors will be required to supply their relevant code for peer evaluation as well as publication.

      Thank you. The GitHub repository is now active.

      (5) State and assess the impacts of sex as a biological variable.

      Thank you for pointing this out. Both female and male animals were included in this study: Epileptic cohort: 7 males, 3 females; Naïve cohort: 3 males, 4 females.

    1. Author response:

      The following is the authors’ response to the original reviews

      We thank the Reviewers for their constructive comments and the Editor for the possibility to address the Reviewers’ points in this rebuttal. We 

      (1) Conducted new experiments with NP6510-Gal4 and TH-Gal4 lines to address potential behavioral differences due to targeting dopaminergic vs. both dopaminergic and serotonergic neurons

      (2) Conducted novel data analyses to emphasize the strength of sampling distributions of behavioral parameters across trials and individual flies

      (3) Provided Supplementary Movies

      (4) Calculated additional statistics

      (5) Edited and added text to address all points of the Reviewers.

      Please see our point-by-point responses below.

      Public Reviews:

      Reviewer #1 (Public Review):

      Summary:

      Translating discoveries from model organisms to humans is often challenging, especially in neuropsychiatric diseases, due to the vast gaps in the circuit complexities and cognitive capabilities. Kajtor et al. propose to bridge this gap in the fly models of Parkinson's disease (PD) by developing a new behavioral assay where flies respond to a moving shadow by modifying their locomotor activities. The authors believe the flies' response to the shadow approximates their escape response to an approaching predator. To validate this argument, they tested several PD-relevant transgenic fly lines and showed that some of them indeed have altered responses in their assay.

      Strengths:

      This single-fly-based assay is easy and inexpensive to set up, scalable, and provides sensitive, quantitative estimates to probe flies' optomotor acuity. The behavioral data is detailed, and the analysis parameters are well-explained.

      We thank the Reviewer for the positive assessment of our study.

      Weaknesses:

      While the abstract promises to give us an assay to accelerate fly-to-human translation, the authors need to provide evidence to show that this is indeed the case. They have used PD lines extensively characterized by other groups, often with cheaper and easier-to-setup assays like negative geotaxis, and do not offer any new insights into them. The conceptual leap from a low-level behavioral phenotype, e.g. changes in walking speed, to recapitulating human PD progression is enormous, and the paper does not make any attempt to bridge it. It needs to be clarified how this assay provides a new understanding of the fly PD models, as the authors do not explore the cellular/circuit basis of the phenotypes. Similarly, they have assumed that the behavior they are looking at is an escape-from-predator response modulated by the central complex- is there any evidence to support these assumptions? Because of their rather superficial approach, the paper does not go beyond providing us with a collection of interesting but preliminary observations.

      We thank the Reviewer for pointing out some limitations of our study. We would like to emphasize that what we perceive as the main advantage of performing single-fly and single-trial analyses is the access to rich data distributions that provide more fine-scale information compared to bulk assays. We think that this is exactly going one step closer to ‘bridging the enormous conceptual leap from a low-level behavioral phenotype, e.g. changes in walking speed, to recapitulating human PD progression’, and we showcase this in our study by comparing the distributions over the entire repertoire of behavioral responses across fly mutants. Nevertheless, we agree with the Reviewer that many more steps in this direction are needed to improve translatability. Therefore, we toned down the corresponding statements in the Abstract and in the Introduction. Moreover, to further emphasize the strength of sampling distributions of behavioral parameters across trials and individual flies, we complemented our comparisons of central tendencies with testing for potential differences in data dispersion, demonstrated in the novel Supplementary Figure S4.

      Looming stimuli have been used to characterize flies’ escape behaviors. These studies uncovered a surprisingly rich behavioral repertoire (Zacarias et al., 2018), which was modulated by both sensory and motor context, e.g. walking speed at time of stimulus presentation (Card and Dickinson, 2008; Oram and Card, 2022; Zacarias et al., 2018). The neural basis of these behaviors was also investigated, revealing loom-sensitive neurons in the optic lobe and the giant fiber escape pathway (Ache et al., 2019; de Vries and Clandinin, 2012). Although less frequently, passing shadows were also employed as threat-inducing stimuli in flies (Gibson et al., 2015). We opted for this variant of the stimulus so that we could ensure that the shadow reached the same coordinates in all linear track concurrently, aiding data analysis and scalability. Similar to the cited study, we found the same behavioral repertoire as in studies with looming stimuli, with an equivalent dependence on walking speed, confirming that looming stimuli and passing shadows can both be considered as threat-inducing visual stimuli. We added a discussion on this topic to the main text.

      Reviewer #2 (Public Review):

      In this study, Kajtor et al investigated the use of a single-animal trial-based behavioral assay for the assessment of subtle changes in the locomotor behavior of different genetic models of Parkinson's disease of Drosophila. Different genotypes used in this study were Ddc-GAL4>UASParkin-275W and UAS- α-Syn-A53T. The authors measured Drosophila's response to predatormimicking passing shadow as a threatening stimulus. Along with these, various dopamine (DA) receptor mutants, Dop1R1, Dop1R2 and DopEcR were also tested.

      The behavior was measured in a custom-designed apparatus that allows simultaneous testing of 13 individual flies in a plexiglass arena. The inter-trial intervals were randomized for 40 trials within 40 minutes duration and fly responses were defined into freezing, slowing down, and running by hierarchical clustering. Most of the mutant flies showed decreased reactivity to threatening stimuli, but the speed-response behavior was genotype invariant.

      These data nicely show that measuring responses to the predator-mimicking passing shadows could be used to assess the subtle differences in the locomotion parameters in various genetic models of Drosophila.

      The understanding of the manifestation of various neuronal disorders is a topic of active research. Many of the neuronal disorders start by presenting subtle changes in neuronal circuits and quantification and measurement of these subtle behavior responses could help one delineate the mechanisms involved. The data from the present study nicely uses the behavioral response to predator-mimicking passing shadows to measure subtle changes in behavior. However, there are a few important points that would help establish the robustness of this study.

      We thank the Reviewer for the constructive comments and the positive assessment of our study.

      (1) The visual threat stimulus for measuring response behavior in Drosophila is previously established for both single and multiple flies in an arena. A comparative analysis of data and the pros and cons of the previously established techniques (for example, Gibson et al., 2015) with the technique presented in this study would be important to establish the current assay as an important advancement.

      We thank the Reviewer for this suggestion. We included the following discussion on measuring response behavior to visual threat stimuli in the revised manuscript.

      Many earlier studies used looming stimulus, that is, a concentrically expanding shadow, mimicking the approach of a predator from above, to study escape responses in flies (Ache et al., 2019; Card and Dickinson, 2008; de Vries and Clandinin, 2012; Oram and Card, 2022; Zacarias et al., 2018) as well as rodents (Braine and Georges, 2023; Heinemans and Moita, 2024; Lecca et al., 2017). These assays have the advantage of closely resembling naturalistic, ecologically relevant threatinducing stimuli, and allow a relatively complete characterization of the fly escape behavior repertoire. As a flip side of their large degree of freedom, they do not lend themselves easily to provide a fully standardized, scalable behavioral assay. Therefore, Gibson et al. suggested a novel threat-inducing assay operating with moving overhead translational stimuli, that is, passing shadows, and demonstrated that they induce escape behaviors in flies akin to looming discs (Gibson et al., 2015). This assay, coined ReVSA (repetitive visual stimulus-induced arousal) by the authors, had the advantage of scalability, while constraining flies to a walking arena that somewhat restricted the remarkably rich escape types flies otherwise exhibit. Here we carried this idea one step further by using a screen to present the shadows instead of a physically moving paddle and putting individual flies to linear corridors instead of the common circular fly arena. This ensured that the shadow reached the same coordinates in all linear tracks concurrently and made it easy to accurately determine when individual flies encountered the stimulus, aiding data analysis and scalability. We found the same escape behavioral repertoire as in studies with looming stimuli and ReVSA (Gibson et al., 2015; Zacarias et al., 2018), with a similar dependence on walking speed (Oram and Card, 2022; Zacarias et al., 2018), confirming that looming stimuli and passing shadows can both be considered as threat-inducing visual stimuli.  

      (2) Parkinson's disease mutants should be validated with other GAL-4 drivers along with DdcGAL4, such as NP6510-Gal4 (Riemensperger et al., 2013). This would be important to delineate the behavioral differences due to dopaminergic neurons and serotonergic neurons and establish the Parkinson's disease phenotype robustly.

      We thank the Reviewer for point out this limitation. To address this, we repeated our key experiments in Fig.3. with both TH-Gal4 and NP6510-Gal4 lines, and their respective controls. These yielded largely similar results to the Ddc-Gal4 lines reported in Fig.3., reproducing the decreased speed and decreased overall reactivity of PD-model flies. Nevertheless, TH-Gal4 and NP6510-Gal4 mutants showed an increased propensity to stop. Stop duration showed a significant increase not only in α-Syn but also in Parkin fruit flies. These novel results have been added to the text and are demonstrated in Supplementary Figure S3.

      (3) The DopEcR mutant genotype used for behavior analysis is w1118; PBac{PB}DopEcRc02142TM6B, Tb1. Balancer chromosomes, such as TM6B,Tb can have undesirable and uncharacterised behavioral effects. This could be addressed by removing the balancer and testing the DopEcR mutant in homozygous (if viable) or heterozygous conditions.

      We appreciate the Reviewer's comment and acknowledge the potential for the DopEcR balancer chromosome to produce unintended behavioral effects. However, given that this mutant was not essential to our main conclusions, we opted not to repeat the experiment. Nevertheless, we now discuss the possible confounds associated with using the PBac{PB}DopEcRc02142 mutant allele over the balancer chromosome. “We recognize a limitation in using PBac{PB}DopEcRc02142 over the  TM6B, Tb<sup>1</sup> balancer chromosome, as the balancer itself may induce behavioral deficits in flies. We consider this unlikely, as the PBac{PB}DopEcRc02142 mutation demonstrates behavioral effects even in heterozygotes (Ishimoto et al., 2013). Additionally, to our knowledge, no studies have reported behavioral deficits in flies carrying the TM6B, Tb<sup>1</sup> balancer chromosome over a wild-type chromosome.”

      (4) The height of the arena is restricted to 1mm. However, for the wild-type flies (Canton-S) and many other mutants, the height is usually more than 1mm. Also, a 1 mm height could restrict the fly movement. For example, it might not allow the flies to flip upside down in the arena easily. This could introduce some unwanted behavioral changes. A simple experiment with an arena of height at least 2.5mm could be used to verify the effect of 1mm height.

      We thank the Reviewer for this comment, which prompted us to reassess the dimensions of the apparatus. The height of the arena was 1.5 mm, which we corrected now in the text. We observed that the arena did not restrict the flies walking and that flies could flip in the arena. We now include two Supplementary Movies to demonstrate this.

      (5) The detailed model for Monte Carlo simulation for speed-response simulation is not described. The simulation model and its hyperparameters need to be described in more depth and with proper justification.

      We thank the Reviewer for pointing out a lack of details with respect to Monte Carlo simulations. We used a nested model built from actual data distributions, without any assumptions. Accordingly, the stimulation did not have hyperparameters typical in machine learning applications, the only external parameter being the number of resamplings (3000 for each draw). We made these modeling choices clearer and expanded this part as follows.

      “The effect of movement speed on the distribution of behavioral response types was tested using a nested Monte Carlo simulation framework (Fig. S5). This simulation aimed to model how different movement speeds impact the probability distribution of response types, comparing these simulated outcomes to empirical data. This approach allowed us to determine whether observed differences in response distributions are solely due to speed variations across genotypes or if additional behavioral factors contribute to the differences. First, we calculated the probability of each response type at different specific speed values (outer model). These probabilities were derived from the grand average of all trials across each genotype, capturing the overall tendency at various speeds. Second, we simulated behavior of virtual flies (n = 3000 per genotypes, which falls within the same order of magnitude as the number of experimentally recorded trials from different genotypes) by drawing random velocity values from the empirical velocity distribution specific to the given genotype and then randomly selecting a reaction based on the reaction probabilities associated with the drawn velocity (inner model). Finally, we calculated reaction probabilities for the virtual flies and compared it with real data from animals of the same genotype.

      Differences were statistically tested by Chi-squared test.”

      (6) The statistical analysis in different experiments needs revisiting. It wasn't clear to me if the authors checked if the data is normally distributed. A simple remedy to this would be to check the normality of data using the Shapiro-Wilk test or Kolmogorov-Smirnov test. Based on the normality check, data should be further analyzed using either parametric or non-parametric statistical tests. Further, the statistical test for the age-dependent behavior response needs revisiting as well. Using two-way ANOVA is not justified given the complexity of the experimental design. Again, after checking for the normality of data, a more rigorous statistical test, such as split-plot ANOVA or a generalized linear model could be used.

      We thank the Reviewer for this comment. We performed Kolmogorov-Smirnov test for normality on the data distributions underlying Figure 3, and normality was rejected for all data distributions at p = 0.05, which justifies the use of the non-parametric Mann-Whitney U-test. Regarding ANOVA, we would like to point out that the ANOVA hypothesis test design is robust to deviations from normality (Knief and Forstmeier, 2021; Mooi et al., 2018). While the Kruskal-Wallis test is considered a reasonable non-parametric alternative of one-way ANOVA, there is no clear consensus for a non-parametric alternative of two-way ANOVA. Therefore, we left the two-way ANOVA for Figure 5 in place; however, to increase the statistical confidence in our conclusions, we performed Kruskal-Wallis tests for the main effect of age and found significant effects in all genotypes in accordance with the ANOVA, confirming the results (Stop frequency, DopEcR p = 0.0007; Dop1R1, p = 0.004; Dop1R2, p = 9.94 × 10<sup>-5</sup>; w<sup>1118</sup>, p = 9.89 × 10<sup>-13</sup>; y<sup>1</sup> w<sup>67</sup>c<sup>23</sup>, p = 2.54 × 10<sup>-5</sup>; Slowing down frequency, DopEcR, p = 0.0421; Dop1R1, p = 5.77 x 10<sup>-6</sup>; Dop1R2, p = 0.011; w<sup>1118</sup>, p = 2.62 x 10<sup>-5</sup>; y<sup>1</sup> w<sup>67</sup>c<sup>23</sup>, p = 0.0382; Speeding up frequency, DopEcR, p = 0.0003; Dop1R1, p = 2.06 x 10<sup>-7</sup>; Dop1R2, p = 2.19 x 10<sup>-6</sup>; w<sup>1118</sup>, p = 0.0044; y<sup>1</sup> w<sup>67</sup>c<sup>23</sup>, p = 1.36 x 10<sup>-5</sup>). We also changed the post hoc Tukey-tests to post hoc Mann-Whitney tests in the text to be consistent with the statistical analyses for Figure 3. These resulted in very similar results as the Tukey-tests. Of note, there isn’t a straightforward way of correcting for multiple comparisons in this case as opposed to the Tukey’s ‘honest significance’ approach, we thus report uncorrected p values and suggest considering them at p = 0.01, which minimizes type I errors. These notes have been added to the ‘Data analysis and statistics’ Methods section.

      (7) The dopamine receptor mutants used in this study are well characterized for learning and memory deficits. In the Parkinson's disease model of Drosophila, there is a loss of DA neurons in specific pockets in the central brain. Hence, it would be apt to use whole animal DA receptor mutants as general DA mutants rather than the Parkinson's disease model. The authors may want to rework the title to reflect the same.

      We thank the Reviewer for this comment, which suggests that we were not sufficiently clear on the Drosophila lines with DA receptor mutations. We used Mi{MIC} random insertion lines for dopamine receptor mutants, namely y<sup>1</sup> w<sup>*1</sup>; Mi{MIC}Dop1R1<sup>MI04437</sup> (BDSC 43773), y<sup>1</sup> w<sup>*1</sup>; Mi{MIC}Dop1R2<sup>MI08664</sup> (BDSC 51098) (Harbison et al., 2019; Pimentel et al., 2016), and w<sup>1118</sup>; PBac{PB}DopEcR<sup>c02142</sup>/TM6B, Tb<sup>1</sup> (BDSC 10847) (Ishimoto et al., 2013; Petruccelli et al., 2020, 2016). These lines carried reported mutations in dopamine receptors, most likely generating partial knock down of the respective receptors. We made this clearer by including the full names at the first occurrence of the lines in Results (beyond those in Methods) and adding references to each of the lines.

      Recommendations for the authors:

      Reviewer #1 (Recommendations For The Authors):

      (1) Please think about focusing the manuscript either on the escape response or the PD pathology and provide additional evidence to demonstrate that you indeed have a novel system to address open questions in the field.

      As detailed above, we now emphasize more that the main advantage of our single-trial-based approach lies in the appropriate statistical comparison of rich distributions of behavioral data. Please see our response to the ‘Weaknesses’ section for more details.

      (2) Please explain the rationale for choosing the genetic lines and provide appropriate genetic controls in the experiments, e.g. trans-heterozygotes. Why use Ddc-Gal4 instead of TH or other specific Split-Gal4 lines?

      We thank the Reviewer for this suggestion. We repeated our key experiments with TH-Gal4 and NP6510-Gal4 lines. Please see our response to Point #2 of Reviewer #2 for details.

      (3) Please proofread the manuscript for ommissions. e.g. there's no legend for Fig 4b.

      We respectfully point out that the legend is there, and it reads “b, Proportion of a given response type as a function of average fly speed before the shadow presentation. Top, Parkin and α-Syn flies. Bottom, Dop1R1, Dop1R2 and DopEcR mutant flies.”

      Reviewer #2 (Recommendations For The Authors):

      (1) In figure 2(c), representing the average walking speed data for different mutants would be useful to visually correlate the walking differences.

      We thank the Reviewer for this suggestion. The average walking speed was added in a scatter plot format, as suggested in the next point of the Reviewer. 

      (2) The data could be represented more clearly using scatter plots. Also, the color scheme could be more color-blindness friendly.

      We thank the Reviewer for this suggestion. We added scatter plots to Fig.2c that indeed represent the distribution of behavioral responses better. We also changed the color scheme and removed red/green labeling.

      (3) The manuscript should be checked for typos such as in line 252, 449, 484.

      Thank you. We fixed the typos.

      References

      Ache JM, Polsky J, Alghailani S, Parekh R, Breads P, Peek MY, Bock DD, von Reyn CR, Card GM. 2019. Neural Basis for Looming Size and Velocity Encoding in the Drosophila Giant Fiber Escape Pathway. Curr Biol 29:1073-1081.e4. doi:10.1016/j.cub.2019.01.079

      Braine A, Georges F. 2023. Emotion in action: When emotions meet motor circuits. Neurosci Biobehav Rev 155:105475. doi:10.1016/j.neubiorev.2023.105475

      Card G, Dickinson MH. 2008. Visually Mediated Motor Planning in the Escape Response of Drosophila. Curr Biol 18:1300–1307. doi:10.1016/j.cub.2008.07.094

      de Vries SEJ, Clandinin TR. 2012. Loom-Sensitive Neurons Link Computation to Action in the Drosophila Visual System. Curr Biol 22:353–362. doi:10.1016/j.cub.2012.01.007

      Gibson WT, Gonzalez CR, Fernandez C, Ramasamy L, Tabachnik T, Du RR, Felsen PD, Maire MR, Perona P, Anderson DJ. 2015. Behavioral Responses to a Repetitive Visual Threat Stimulus Express a Persistent State of Defensive Arousal in Drosophila. Curr Biol 25:1401– 1415. doi:10.1016/j.cub.2015.03.058

      Harbison ST, Kumar S, Huang W, McCoy LJ, Smith KR, Mackay TFC. 2019. Genome-Wide Association Study of Circadian Behavior in Drosophila melanogaster. Behav Genet 49:60–82. doi:10.1007/s10519-018-9932-0

      Heinemans M, Moita MA. 2024. Looming stimuli reliably drive innate defensive responses in male rats, but not learned defensive responses. Sci Rep 14:21578. doi:10.1038/s41598-02470256-2

      Ishimoto H, Wang Z, Rao Y, Wu C, Kitamoto T. 2013. A Novel Role for Ecdysone in Drosophila Conditioned Behavior: Linking GPCR-Mediated Non-canonical Steroid Action to cAMP Signaling in the Adult Brain. PLoS Genet 9:e1003843. doi:10.1371/journal.pgen.1003843

      Knief U, Forstmeier W. 2021. Violating the normality assumption may be the lesser of two evils. Behav Res Methods 53:2576–2590. doi:10.3758/s13428-021-01587-5

      Lecca S, Meye FJ, Trusel M, Tchenio A, Harris J, Schwarz MK, Burdakov D, Georges F, Mameli M. 2017. Aversive stimuli drive hypothalamus-to-habenula excitation to promote escape behavior. Elife 6:1–16. doi:10.7554/eLife.30697

      Mooi E, Sarstedt M, Mooi-Reci I. 2018. Market Research, Springer Texts in Business and Economics. Singapore: Springer Singapore. doi:10.1007/978-981-10-5218-7

      Oram TB, Card GM. 2022. Context-dependent control of behavior in Drosophila. Curr Opin Neurobiol 73:102523. doi:10.1016/j.conb.2022.02.003

      Petruccelli E, Lark A, Mrkvicka JA, Kitamoto T. 2020. Significance of DopEcR, a G-protein coupled dopamine/ecdysteroid receptor, in physiological and behavioral response to stressors. J Neurogenet 34:55–68. doi:10.1080/01677063.2019.1710144

      Petruccelli E, Li Q, Rao Y, Kitamoto T. 2016. The Unique Dopamine/Ecdysteroid Receptor Modulates Ethanol-Induced Sedation in Drosophila. J Neurosci 36:4647–4657. doi:10.1523/JNEUROSCI.3774-15.2016

      Pimentel D, Donlea JM, Talbot CB, Song SM, Thurston AJF, Miesenböck G. 2016. Operation of a homeostatic sleep switch. Nature 536:333–337. doi:10.1038/nature19055

      Zacarias R, Namiki S, Card GM, Vasconcelos ML, Moita MA. 2018. Speed dependent descending control of freezing behavior in Drosophila melanogaster. Nat Commun 9:1–11. doi:10.1038/s41467-018-05875-1

    1. Note: This preprint has been reviewed by subject experts for Review Commons. Content has not been altered except for formatting.

      Learn more at Review Commons


      Referee #2

      Evidence, reproducibility and clarity

      The manuscript by Metheringham et al. reports on interesting new characterizations of phenotypes caused by genetic inactivation of subunits of the methyl transferase complex responsible for N6-adenosine methylation in (pre)-mRNA ("the m6A writer") in the plant Arabidopsis thaliana. The main claim of the paper is that mutants in these subunits exhibit autoimmunity, a claim that is supported by the following lines of evidence:

      • Transcriptome profiling by mRNA-seq shows a gene expression profile with differential expression of many stress- and defense-related genes.
      • The immunity-like gene expression profile is observed under growth at 17{degree sign}C but not at 27{degree sign}C, consistent with the well-known temperature-sensitivity of some (but not all) innate immunity signaling systems in plants.
      • m6A writer mutants show increased resistance to infection by the virulent Pseudomonas syringae DC3000 strain.
      • The primary biochemical defect in m6A writing is not temperature sensitive, excluding the trivial possibility that the mutant alleles chosen for study are simply ts.

      The observations are important and the manuscript is very well written, a pleasure to read: the problem is clearly presented, the experimental results are presented in a clear, logical succession, and the discussion treats important points.

      The study is valuable pending some manuscript revision on the autoimmunity interpretation of the results obtained, and a few suggested edits that can be included if the authors agree that they would improve the paper.

      The finding that an autoimmune-like state is activated in m6A writer mutants is significant because it provides a warning flag on how such mutants should be used for studying the role of m6A in stress response signaling, including reassessment of previously published work. Whether the stress state really is autoimmunity is subject to some debate, particularly because no genetic evidence to support it has been obtained. The results are nonetheless interesting and constitute an important contribution to the community, even if they remain descriptive and with nearly no insight into molecular mechanisms. My suggestions for improvement are summarized below.

      1. Although the authors do a lot to support the claim that autoimmunity is an element of m6A writer mutant phenotypes, the study does not include genetic evidence to support this claim. This is important, because if the stress/defense gene activation causes some of the morphological phenotypes of m6A writer mutants, one should be able to suppress such defects by mutation of know immune signaling components such as the appropriate nucleotide-binding leucine-rich repeat proteins, or more generic signaling components such as EDS1, PAD4 and SAG1, common to a subset of such intracellular immune receptors. Resistance to pathogens can be observed in mutants with constitutive stress response signaling, and defense-like gene expression can be induced as a secondary of other primary defects, for instance DNA damage. Similarly, while it is true that some types of immune activation are temperature sensitive, others are not 1, and clearly, elevated temperature changes so much of the physiology of the plant that sensitivity to elevated temperature cannot be used as proof of immune activation. Thus, each of the lines of evidence presented is suggestive, not conclusive. Together, they constitute a good argument, but still not a completely satisfactory proof of the main claim. I do not think that this concern means that a lot of genetic work must be undertaken to make this paper publishable, but I think that the authors should be even more careful about how they interpret their observations. I understand that they favor more or less direct activation of autoimmunity, although even if that were true, it would be unclear what the biochemical triggers of such autoimmunity would be (unmethylated RNA, absence or writer components, excess of free m6A-binding proteins etc). However, given the concerns above, I think the authors should dedicate a small paragraph in the discussion to the possibility that the primary cause of stress/defense-gene expression is unclear and may not result from innate immune surveillance of unmethylated mRNA or components of the m6A pathway as favoured by the authors.
      2. It may be of relevance to search promoters of differentially expressed genes for enrichment of cis-elements. This simple approach identified the W-box in the first papers using transcriptome profiling to characterize the immune state in Arabidopsis 2,3, and could perhaps reveal whether a WRKY-driven transcriptional program drives differential expression or whether several other transcription factor classes may also contribute substantially, as may be expected if a more complex stress-related transcriptional program is activated. I do not think that this is a deal breaker, but some additional useful information from the existing data might be gathered in this way.
      3. Stress response activation has also been clearly described in ect2 ect3 ect4 mutants4 and even if the authors find no evidence for PR1 expression in this mutant, it is still of relevance to include a mention of this result in the discussion, together with the discussion of stress response activation seen in writer mutants in earlier reports 5,6. I would not mind the authors being a bit more explicit about what their results mean for studies that try to conclude on the biological relevance of m6A in different types of stress signaling, using phenotypes writer mutants as their primary line of evidence. But this is of course up to the authors to decide on that.
      4. In the introduction on preferred m6A sequence contexts, please clarify that m6A in plants occurs both DRACH in (G)GAU contexts 7,8.
      5. When mentioning convergence on shared signaling components from immune receptors, please include a tiny bit more information for the reader. For instance, EDS1 is mentioned, but this protein is only required for signaling from (some) TIR-NBS-LRRs, not the class of CC-NBS-LRRs. Indeed, signaling by this latter class may not converge on just one to a few components, as their multimerization appears to form the ion channels required for signaling-inducing ion currents.
      6. Please clarify in the introduction and in later parts that only some forms of autoimmunity can be suppressed by elevated temperature. Sentences like "A hallmark of Arabidopsis autoimmunity is temperature sensitivity..." are a bit misleading. Temperature sensitivity has clearly been used to study some forms of EDS1-dependent immunity, to great effect in the TMV-N interaction for instance, but it is not accurate to call temperature sensitivity a "hallmark of autoimmunity".
      7. In the discussion of possible biochemical triggers of autoimmunity in m6A mutants, please consider the following:

      (A) Mention the possibility that the primary trigger may not be immune receptor-surveillance of some defect induced by lack of m6A in mRNA (as discussed above).

      (B) In connection with the consideration that lack of m6A writer components, not m6A in mRNA, may be a signal, you could include the observation from yeast that Ime4 knockouts have a much stronger phenotype than Ime4 catalytically dead mutants or knockouts of the sole yeast YTH-domain Pho92 9. Indeed, it is a bit of an embarrassment to the plant m6A community that we have not yet examined phenotypes of MTA and MTB catalytically dead mutants, and the present report should further urge the community to finally do this important experiment. 8. Just a tiny typo on page 15, Pst DC3000, not Pst D3000 (of no relevance to the overall assessment, just a help to eliminate annoying errors before final submission).

      REFERENCES

      1. Demont, H. et al. Downstream signaling induced by several plant Toll/interleukin-1 receptor-containing immune proteins is stable at elevated temperature. Cell Reports 44(2025).
      2. Petersen, M. et al. Arabidopsis MAP kinase 4 negatively regulates systemic acquired resistance. Cell 103, 1111-1120 (2000).
      3. Maleck, K. et al. The transcriptome of Arabidopsis thaliana during systemic acquired resistance. Nature Genetics 26, 403-410 (2000).
      4. Arribas-Hernández, L. et al. The YTHDF proteins ECT2 and ECT3 bind largely overlapping target sets and influence target mRNA abundance, not alternative polyadenylation. eLife 10, e72377 (2021).
      5. Bodi, Z. et al. Adenosine Methylation in Arabidopsis mRNA is Associated with the 3' End and Reduced Levels Cause Developmental Defects. Front Plant Sci 3, 48 (2012).
      6. Prall, W. et al. Pathogen-induced m6A dynamics affect plant immunity. The Plant Cell 35, 4155-4172 (2023).
      7. Arribas-Hernández, L. et al. Principles of mRNA targeting via the Arabidopsis m6A-binding protein ECT2. eLife 10, e72375 (2021).
      8. Wang, G. et al. Quantitative profiling of m6A at single base resolution across the life cycle of rice and Arabidopsis. Nature Communications 15, 4881 (2024).
      9. Ensinck, I. et al. The yeast RNA methylation complex consists of conserved yet reconfigured components with m6A-dependent and independent roles. eLife 12, RP87860 (2023).

      Significance

      The finding that an autoimmune-like state is activated in m6A writer mutants is significant because it provides a warning flag on how such mutants should be used for studying the role of m6A in stress response signaling, including reassessment of previously published work. Whether the stress state really is autoimmunity is subject to some debate, particularly because no genetic evidence to support it has been obtained. The results are nonetheless interesting and constitute an important contribution to the community, even if they remain descriptive and with nearly no insight into molecular mechanisms. I wish to congratulate the authors on another valuable contribution to the plant m6A field.

    1. Author response:

      The following is the authors’ response to the original reviews

      eLife Assessment

      This important work advances our understanding of the impact of malnutrition on hematopoiesis and subsequently infection susceptibility. Support for the overall claims is convincing in some respects and incomplete in others as highlighted by reviewers. This work will be of general interest to those in the fields of hematopoiesis, malnutrition, and dietary influence on immunity.

      We would like to thank the editors for agreeing to review our work at eLife. We greatly appreciate them assessing this study as important and of general interest to multiple fields, as well as the opportunity to respond to reviewer comments. Please find our responses to each reviewer below.

      Public Reviews:

      Reviewer #1 (Public review):

      Summary:

      In this study, the authors used a chronic murine dietary restriction model to study the effects of chronic malnutrition on controls of bacterial infection and overall immunity, including cellularity and functions of different immune cell types. They further attempted to determine whether refeeding can revert the infection susceptibility and immunodeficiency. Although refeeding here improves anthropometric deficits, the authors of this study show that this is insufficient to recover the impairments across the immune cell compartments.

      Strengths:

      The manuscript is well-written and conceived around a valid scientific question. The data supports the idea that malnutrition contributes to infection susceptibility and causes some immunological changes. The malnourished mouse model also displayed growth and development delays. The work's significance is well justified. Immunological studies in the malnourished cohort (human and mice) are scarce, so this could add valuable information.

      Weaknesses:

      The assays on myeloid cells are limited, and the study is descriptive and overstated. The authors claim that "this work identifies a novel cellular link between prior nutritional state and immunocompetency, highlighting dysregulated myelopoiesis as a major." However, after reviewing the entire manuscript, I found no cellular mechanism defining the link between nutritional state and immunocompetency.

      We thank the reviewer for deeming our work significant and noting the importance of the study. We appreciate the referee’s point regarding the lack of specific cellular functional data for innate immune cells and have modified the conclusions stated in text to more accurately reflect the results presented.

      Reviewer #2 (Public review):

      Summary:

      Sukhina et al. use a chronic murine dietary restriction model to investigate the cellular mechanisms underlying nutritionally acquired immunodeficiency as well as the consequences of a refeeding intervention. The authors report a substantial impact of undernutrition on the myeloid compartment, which is not rescued by refeeding despite rescue of other phenotypes including lymphocyte levels, and which is associated with maintained partial susceptibility to bacterial infection.

      Strengths:

      Overall, this is a nicely executed study with appropriate numbers of mice, robust phenotypes, and interesting conclusions, and the text is very well-written. The authors' conclusions are generally well-supported by their data.

      Weaknesses:

      There is little evaluation of known critical drivers of myelopoiesis (e.g. PMID 20535209, 26072330, 29218601) over the course of the 40% diet, which would be of interest with regard to comparing this chronic model to other more short-term models of undernutrition.

      Further, the microbiota, which is well-established to be regulated by undernutrition (e.g. PMID 22674549, 27339978, etc.), and also well-established to be a critical regulator of hematopoiesis/myelopoiesis (e.g. PMID 27879260, 27799160, etc.), is completely ignored here.

      We thank the reviewer for agreeing that the data presented support the stated conclusions and noting the experimental rigor.  The referee highlights two important areas for future mechanistic investigation that we agree are of great importance and relevant to the submitted study. We have included further discussion of the potential role cytokines and the microbiota might play in our model.

      Reviewer #3 (Public review):

      Summary:

      Sukhina et al are trying to understand the impacts of malnutrition on immunity. They model malnutrition with a diet switch from ad libitum to 40% caloric restriction (CR) in post-weaned mice. They test impacts on immune function with listeriosis. They then test whether re-feeding corrects these defects and find aspects of emergency myelopoiesis that remain defective after a precedent period of 40% CR. Overall, this is a very interesting observational study on the impacts of sudden prolonged exposure to less caloric intake.

      Strengths:

      The study is rigorously done. The observation of lasting defects after a bout of 40% CR is quite interesting. Overall, I think the topic and findings are of interest.

      Weaknesses:

      While the observations are interesting, in this reviewer's opinion, there is both a lack of mechanistic understanding of the phenomena and also some lack of resolution/detail about the phenomena itself. Addressing the following major issues would be helpful towards aspects of both:

      (1) Is it calories, per se, or macro/micronutrients that drive these phenotypes observed with 40% CR. At the least, I would want to see isocaloric diets (primarily protein, fat, or carbs) and then some of the same readouts after 40% CR. Ie does low energy with relatively more eg protein prevent immunosuppression (as is commonly suggested)? Micronutrients would be harder to test experimentally and may be out of the scope of this study. However, it is worth noting that many of the malnutrition-associated diseases are micronutrient deficiencies.

      (2) Is immunosuppression a function of a certain weight loss threshold? Or something else? Some idea of either the tempo of immunosuppression (happens at 1, in which weight loss is detected; vs 2-3, when body length and condition appear to diverge; or 5 weeks), or grade of CR (40% vs 60% vs 80%) would be helpful since the mechanism of immunosuppression overall is unclear (but nailing it may be beyond the scope of this communication).

      (3) Does an obese mouse that gets 40% CR also become immunodeficient? As it stands, this ad libitum --> 40% CR model perhaps best models problems in the industrial world (as opposed to always being 40% CR from weaning, as might be more common in the developing world), and so modeling an obese person losing a lot of weight from CR (like would be achieved with GLP-1 drugs now) would be valuable to understanding generalizability.

      (4) Generalizing this phenomenon as "bacterial" with listeriosis, which is more like a virus in many ways (intracellular phase, requires type I IFN, etc.) and cannot be given by the natural route of infection in mice, may not be most accurate. I would want to see an experiment with E.Coli, or some other bacteria, to test the statement of generalizability (ie is it bacteria, or type I IFN-pathway dominant infections, like viruses). If this is unique listeriosis, it doesn't undermine the story as it is at all, but it would just require some word-smithing.

      (5) Previous reports (which the authors cite) implicate Leptin, the levels of which scale with fat mass, as "permissive" of a larger immune compartment (immune compartment as "luxury function" idea). Is their phenotype also leptin-mediated (ie leptin AAV)?

      (6) The inability of re-feeding to "rescue" the myeloid compartment is really interesting. Can the authors do a bone marrow transplantation (CR-->ad libitum) to test if this effect is intrinsic to the CR-experienced bone marrow?

      (7) Is the defect in emergency myelopoiesis a defect in G-CSF? Ie if the authors injected G-CSF in CR animals, do they equivalently mobilize neutrophils? Does G-CSF supplementation (as one does in humans) rescue host defense against Listeria in the CR or re-feeding paradigms?

      We thank the reviewer for considering our work of interest and noting the rigor with which it was conducted. The referee raises several excellent mechanistic hypotheses and follow-up studies to perform. We agree that defining the specific dietary deficiency driving the phenotypes is of great interest. The relative contribution of calories versus macro- and micronutrients is an area we are interested in exploring in future studies, especially given the literature on the role of micronutrients in malnutrition driven wasting as the referee notes. We also agree that it will be key to determine whether non-hematopoietic cells contribute as well as the role of soluble factors such G-CSF and Leptin in mediating the immunodeficiency all warrant further study. Likewise, it will be important to evaluate how malnutrition impacts other models of infection to determine how generalizable these phenomena are. We have added these points to the discussion section as limitations of this study.

      Regarding how the phenotypes correspond to the timing of the immunosuppression relative to weight loss, we have performed new kinetics studies to provide some insight into this area. We now find that neutropenia in peripheral blood can be detected after as little as one week of dietary restriction, with neutropenia continuing to decline after prolonged restriction. These findings indicate that the impact on myeloid cell production are indeed rapid and proceed maximum weight loss, though the severity of these phenotypes does increase as malnutrition persists. We wholeheartedly agree with the reviewer that it will be interesting to explore whether starting weight impacts these phenotypes and whether similar findings can be made in obese animals as they are treated for weight loss.

      Recommendations for the authors:

      Reviewer #1 (Recommendations for the authors):

      In this study, the authors used a chronic murine dietary restriction model to study the effects of chronic malnutrition on controls of bacterial infection and overall immunity, including cellularity and functions of different immune cell types. They further attempted to determine whether refeeding can revert the infection susceptibility and immunodeficiency. Although refeeding here improves anthropometric deficits, the authors of this study show that this is insufficient to recover the impairments across the immune cell compartments. The authors claim that "this work identifies a novel cellular link between prior nutritional state and immunocompetency, highlighting dysregulated myelopoiesis as a major." However, after reviewing the entire manuscript, I could not find any cellular mechanism defining the link between nutritional state and immunocompetency. The assays on myeloid cells are limited, and the study is descriptive and overstated.

      Major concerns:

      (1) Malnutrition has entirely different effects on adults and children. In this study, 6-8 weeks old C57/Bl6 mice were used that mimic adult malnutrition. I do not understand then why the refeeding strategy for inpatient treatment of severely malnourished children was utilized here.

      (2) Figure 1g shows BM cellularity is reduced, but the authors claim otherwise in the text.

      (3) What is the basis of the body condition score in Figure 1d? It will be good to have it in the supplement.

      (4) Listeria monocytogenes cause systemic infection, so bioload was not determined in tissues beyond the liver.

      (5) Figure 3; T cell functional assays were limited to CD8 T cells and lymphocytes isolated from the spleen.

      (6) Why was peripheral cell count not considered? Discrepancies exist with the absolute cell number and relative abundance data, except for the neutrophil and monocyte data, which makes the data difficult to interpret. For example, for B cells, CD4 and CD8 cells.

      (7) Also, if mice exhibit thymic atrophy, why does % abundance data show otherwise? Overall, the data is confusing to interpret.

      (8) No functional tests for neutrophil or monocyte function exist to explain the higher bacterial burden in the liver or to connect the numbers with the overall pathogen load

      The rationale for examining both innate and adaptive immunity is not clear-it is even more unclear since the exact timelines for examining both innate and adaptive immunity (D0 and D5) were used.

      (9) Figure 2e doesn't make sense - why is spleen cellularity measured when bacterial load is measured in the liver?

      (10) Although it is claimed that emergency myelopoiesis is affected, no specific marker for emergency myelopoiesis other than cell numbers was studied.

      (11) I suggest including neutrophil effector functions and looking for real markers of granulopoiesis, such as Cebp-b. Since the authors attempted to examine the entirety of immune responses, it is better to measure cell abundance, types, and functions beyond the spleen. Consider the systemic spread of m while measuring bioload.

      (12) Minor grammatical errors - please re-read the entire text and correct grammatical errors to improve the flow of the text.

      (13) Sample size details missing

      (14) Be clear on which marks were used to identify monocytes. Using just CD11b and Ly6G is insufficient for neutrophil quantification.

      (15) Also, instead of saying "undernourished patients," say "patients with undernutrition" - change throughout the text. I would recommend numbering citations (as is done for Nature citations) to ease in following the text, as there are areas when there are more than ten citations with author names.

      (16) No line numbers are provided

      (17) Abstract

      -  What does accelerated contraction mean?

      -  "In" is repeated in a sentence

      -  Be clear that the study is done in a mouse model - saying just "animals" is not sufficient

      -  Indicate how malnutrition is induced in these mice

      (18) Introduction

      -  "restriction," "immune organs," - what is this referring to?

      -  You mention lymphoid tissue and innate and adaptive immunity, which doesn't make sense.

      Please correct this.

      -  You mention a lot of lymphoid tissues, i.e. lymphoid mass gain, but how about the bone marrow and spleen, which are responsible for most innate immune compartments?

      (19) Results

      a) Figure 1

      -  Why 40% reduced diet?

      -  It would be interesting to report if the organs are smaller relative to body weight. It makes sense that the organ weight is lower in the 40RD mice, especially since they are smaller, so the novelty of this data is not apparent (Figure 1f).

      -  You say, "We observed a corresponding reduction in the cellularity of the spleen and thymus, while the cellularity of the bone marrow was unaffected (Fig. 1g)." however, your BM data is significant, so this statement doesn't reflect the data you present, please correct.

      b) Figure 2

      - Figure 2d - what tissue is this from, mentioned in the figure? And measure cellularity there. The rationale for why you look only at the spleen here is weak. Also, we would benefit from including the groups without infection here for comparison purposes.

      c) Figure 3

      - The rationale for why you further looked at T cells is weak, mainly because of the following sentence. "Despite this overall loss in lymphocyte number, the relative frequency of each population was either unchanged or elevated, indicating that while malnutrition leads to a global reduction in immune cell numbers, lymphocytes are less impacted than other immune cell populations (Supplemental 1)." Please explain in the main text.

      d) Figure 4

      -  You say the peak of the adaptive immune response, but you never looked at the peak of adaptive immune - when is this? If you have the data, please show it. You also only show d0 and d5 post-infection data for adaptive immunity, so I am unsure where this statement comes from.

      -  How did you identify neutrophils and monocytes through flow cytometry? Indicate the markers used. Also, your text does not match your data; please correct it. i.e. monocyte numbers reduced, and relative abundance increased, but your text doesn't say this.

      -  Show the flow graph first then, followed by the quantification.

      -  The study would benefit from examining markers of emergency myelopoiesis such as Cebpb through qPCR.

      -  Although the number of neutrophils is lower in the BM and spleen, how does this relate to increased bacterial load in the liver? This is especially true since you did not quantify neutrophil numbers in the liver.

      e) Figure 6

      -  Some figures are incorrectly labelled.

      -  For the refeeding data, also include the data from the 40RD group to compare the level of recovery in the outcome measures.

      (20) Discussion

      -  You claim that monocytes are reduced to the same extent as neutrophils, but this is not true.

      Please correct.

      -  Indicate some limitations of your work.

      We thank the reviewer for offering these recommendations and the constructive comments. 

      Several comments raised concerns over the rationale or reasoning behind aspects of the experimental design or the data presented, which we would like to clarify:

      • Regarding the refeeding protocol, we apologize for the confusion for the rationale. We based our methodology on the general guidelines for refeeding protocols for malnourished people. We elected to increase food intake 10% daily to avoid risk of refeeding syndrome or other complications. Our method is by no means replicates the administration of specific vitamins, minerals, electrolytes, nor precise caloric content as would be given to a human patient. The citation provided offers information from the WHO regarding the complications that can arise during refeeding syndrome, which while it is from a document on pediatric care, we did not mean to imply that our method modeled refeeding intervention for children. We have modified the text to avoid this confusion.

      • The reviewer requested more clarity on why we studied both the innate and adaptive immune system as well as why we chose the time points studied. As referenced in the manuscript, prior work has observed that caloric restriction, fasting, and malnutrition all can impact the adaptive immune system. Given these previous findings, we felt it important to evaluate how malnutrition affected adaptive immune cell populations in our model. To this end, we provide data tracking the course of T-cell responses from the start of infection through day 14 at the time that the response undergoes contraction. However, since we find that bacterial burden is not properly controlled at earlier time points (day 5), when it is understood the innate immune system is more critical for mediating pathogen clearance, we elected to better characterize the effect malnutrition had on innate immune populations, something less well described in the literature. As phenotypes both in bacterial burden and within innate immune populations were observable as early as day 5, we chose to focus on that time point rather than later time points when readouts could be further confounded by secondary or compounding effects by the lack of early control of infection. We have tried to make this rationale clear in the text and have made changes to further emphasize this reasoning.

      • The reviewer also requested an explaination over why bacterial burden was measured in the liver and the immune response was measured in the spleen. While the reviewer is correct that our model is a systemic infection, it is well appreciated that bacteria rapidly disseminate to the liver and spleen and these organs serve as major sites of infection. Given the central role the spleen plays in organizing both the innate and adaptive immune response in this model, it is common practice in the field to phenotype immune cell populations in the spleen, while using the liver to quantify bacterial burden (see PMID: 37773751 as one example of many). We acknowledge this does not provide the full scope of bacterial infection or the immune response in every potentially affected tissue, but nonetheless believe the interpretation that malnourished and previously malnourished animals do not properly control infection and their immune responses are blunted compared to controls still stands.

      The reviewer raised several points about di3erences in the results for cell frequency and absolute number and why these may deviate in some circumstances. For example, the reviewer notes that we observe thymic atrophy yet the frequency of peripheral T-cells does not decline. It should be noted that absolute number can change when frequency does not and vice versa, due to changes in other cell types within the studied population of cells. As in the case of peripheral lymphocytes in our study, the frequency can stay the same or even increase when the absolute number declines (Supplemental 1). This can occur if other populations of cells decrease further, which is indeed the case as the loss of myeloid cells is greater than that of lymphocytes. Hence, we find that the frequency of T and B cells is unchanged or elevated, despite the loss in absolute number of peripheral cell, which is our stated interpretation. We believe this is consistent with our overall observations and is why it is important to report both frequency and absolute number, as we have done. 

      We have made the requested changes to the text to address the reviewers concerns as noted to improve clarity and accuracy for the description of experiments, results, and overall conclusions drawn in the manuscript. We have also included a discussion of the limitations of our work as well as additional areas for future investigation that remain open. 

      Reviewer #2 (Recommendations for the authors):

      Regarding the known drivers of myelopoiesis, can the authors quantify circulating levels of relevant immune cytokines (e.g. type I and II IFNs, GM-CSF, etc.)?

      Regarding the microbiota (point #2), how dramatically does this undernutrition modulate the microbiota both in terms of absolute load and community composition, and how effectively/quickly is this rescued by refeeding?

      We thank the reviewer for raising these recommendations. We agree that the role of circulating factors like cytokines and growth factors in contributing to the defects in myelopoiesis is of interest and is the focus of future work. Similarly, the impact of malnutrition on the microbiota is of great interest and has been evaluated by other groups in separate studies. How the known impact of malnutrition on the microbiota affects the phenotypes we observe in myelopoiesis is unclear and warrants future investigation. We have added these points to the discussion section as limitations of this study.

    1. Reviewer #1 (Public review):

      Fombellida-Lopez and colleagues describe the results of an ART intensification trial in people with HIV infection (PWH) on suppressive ART to determine the effect of increasing the dose of one ART drug, dolutegravir, on viral reservoirs, immune activation, exhaustion, and circulating inflammatory markers. The authors hypothesize that ART intensification will provide clues about the degree to which low-level viral replication is occurring in circulation and in tissues despite ongoing ART, which could be identified if reservoirs decrease and/or if immune biomarkers change. The trial design is straightforward and well-described, and the intervention appears to have been well tolerated. The investigators observed an increase in dolutegravir concentrations in circulation, and to a lesser degree in tissues, in the intervention group, indicating that the intervention has functioned as expected (ART has been intensified in vivo). Several outcome measures changed during the trial period in the intervention group, leading the investigators to conclude that their results provide strong evidence of ongoing replication on standard ART. The results of this small trial are intriguing, and a few observations in particular are hypothesis-generating and potentially justify further clinical trials to explore them in depth. However, I am concerned about over-interpretation of results that do not fully justify the authors' conclusions.

      (1) Trial objectives: What was the primary objective of the trial? This is not clearly stated. The authors describe changes in some reservoir parameters and no changes in others. Which of these was the primary outcome? No a priori hypothesis / primary objective is stated, nor is there explicit justification (power calculations, prior in vivo evidence) for the small n, unblinded design, and lack of placebo control. In the abstract (line 36, "significant decreases in total HIV DNA") and conclusion (lines 244-246), the authors state that total proviral DNA decreased as a result of ART intensification. However, in Figures 2A and 2E (and in line 251), the authors indicate that total proviral DNA did not change. These statements are confusing and appear to be contradictory. Regarding the decrease in total proviral DNA, I believe the authors may mean that they observed transient decrease in total proviral DNA during the intensification period (day 28 in particular, Figure 2A), however this level increases at Day 56 and then returns to baseline at Day 84, which is the source of the negative observation. Stating that total proviral DNA decreased as a result of the intervention when it ultimately did not is misleading, unless the investigators intended the day 28 timepoint as a primary endpoint for reservoir reduction - if so, this is never stated, and it is unclear why the intervention would then be continued until day 84? If, instead, reservoir reduction at the end of the intervention was the primary endpoint (again, unstated by the authors), then it is not appropriate to state that the total proviral reservoir decreased significantly when it did not.

      (2) Intervention safety and tolerability: The results section lacks a specific heading for participant safety and tolerability of the intervention. I was wondering about clinically detectable viremia in the study. Were there any viral blips? Was the increased DTG well tolerated? This drug is known to cause myositis, headache, CPK elevation, hepatotoxicity, and headache. Were any of these observed? What is the authors' interpretation of the CD4:8 ratio change (line 198)? Is this a significant safety concern for a longer duration of intensification? Was there also a change in CD4% or only in absolute counts? Was there relative CD4 depletion observed in the rectal biopsy samples between days 0 and 84? Interestingly, T cells dropped at the same timepoints that reservoirs declined... how do the authors rule out that reservoir decline reflects transient T cell decline that is non-specific (not due to additional blockade of replication)?

      (3) The investigators describe a decrease in intact proviral DNA after 84 days of ART intensification in circulating cells (Figure 2D), but no changes to total proviral DNA in blood or tissue (Figures 2A and 2E; IPDA does not appear to have been done on tissue samples). It is not clear why ART intensification would result in a selective decrease in intact proviruses and not in total proviruses if the source of these reservoir cells is due to ongoing replication. These reservoir results have multiple interpretations, including (but not limited to) the investigators' contention that this provides strong evidence of ongoing replication. However, ongoing replication results in the production of both intact and mutated/defective proviruses that both contribute to reservoir size (with defective proviruses vastly outnumbering intact proviruses). The small sample size and well-described heterogeneity of the HIV reservoir (with regard to overall size and composition) raise the possibility that the study was underpowered to detect differences over the 84-day intervention period. No power calculations or prior studies were described to justify the trial size or the duration of the intervention. Readers would benefit from a more nuanced discussion of reservoir changes observed here.

      (4) While a few statistically significant changes occurred in immune activation markers, it is not clear that these are biologically significant. Lines 175-186 and Figure 3: The change in CD4 cells + for TIGIT looks as though it declined by only 1-2%, and at day 84, the confidence interval appears to widen significantly at this timepoint, spanning an interquartile range of 4%. The only other immune activation/exhaustion marker change that reached statistical significance appears to be CD8 cells + for CD38 and HLA-DR, however, the decline appears to be a fraction of a percent, with the control group trending in the same direction. Despite marginal statistical significance, it is not clear there is any biological significance to these findings; Figure S6 supports the contention that there is no significant change in these parameters over time or between groups. With most markers showing no change and these two showing very small changes (and the latter moving in the same direction as the control group), these results do not justify the statement that intensifying DTG decreases immune activation and exhaustion (lines 38-40 in the abstract and elsewhere).

      (5) There are several limitations of the study design that deserve consideration beyond those discussed at line 327. The study was open-label and not placebo-controlled, which may have led to some medication adherence changes that confound results (authors describe one observation that may be evidence of this; lines 146-148). Randomized/blinded / cross-over design would be more robust and help determine signal from noise, given relatively small changes observed in the intervention arm. There does not seem to be a measurement of key outcome variables after treatment intensification ceased - evidence of an effect on replication through ART intensification would be enhanced by observing changes once intensification was stopped. Why was intensification maintained for 84 days? More information about the study duration would be helpful. Table 1 indicates that participants were 95% male. Sex is known to be a biological variable, particularly with regard to HIV reservoir size and chronic immune activation in PWH. Worldwide, 50% of PWH are women. Research into improving management/understanding of disease should reflect this, and equal participation should be sought in trials. Table 1 shows differing baseline reservoir sizes betweenthe control and intervention groups. This may have important implications, particularly for outcomes where reservoir size is used as the denominator.

      (6) Figure 1: the increase in DTG levels is interesting - it is not uniform across participants. Several participants had lower levels of DTG at the end of the intervention. Though unlikely to be statistically significant, it would be interesting to evaluate if there is a correlation between change in DTG concentrations and virologic / reservoir / inflammatory parameters. A positive relationship between increasing DTG concentration and decreased cell-associated RNA, for example, would help support the hypothesis that ongoing replication is occurring.

      (7) Figure 2: IPDA in tissue- was this done? scRNA in blood (single copy assay) - would this be expected to correlate with usCaRNA? The most unambiguous result is the decrease in cell-associated RNA - accompanying results using single-copy assay in plasma would be helpful to bolster this result. The use of the US RNA / Total DNA ratio is not helpful/difficult to interpret since the control and intervention arms were unmatched for total DNA reservoir size at study entry.

    2. Author response:

      Reviewer #1 (Public Review):

      Fombellida-Lopez and colleagues describe the results of an ART intensification trial in people with HIV infection (PWH) on suppressive ART to determine the effect of increasing the dose of one ART drug, dolutegravir, on viral reservoirs, immune activation, exhaustion, and circulating inflammatory markers. The authors hypothesize that ART intensification will provide clues about the degree to which low-level viral replication is occurring in circulation and in tissues despite ongoing ART, which could be identified if reservoirs decrease and/or if immune biomarkers change. The trial design is straightforward and well-described, and the intervention appears to have been well tolerated. The investigators observed an increase in dolutegravir concentrations in circulation, and to a lesser degree in tissues, in the intervention group, indicating that the intervention has functioned as expected (ART has been intensified in vivo). Several outcome measures changed during the trial period in the intervention group, leading the investigators to conclude that their results provide strong evidence of ongoing replication on standard ART. The results of this small trial are intriguing, and a few observations in particular are hypothesis-generating and potentially justify further clinical trials to explore them in depth. However, I am concerned about over-interpretation of results that do not fully justify the authors' conclusions.

      We thank Reviewer #1 for their thoughtful and constructive comments, which will help us clarify and improve the manuscript. Below, we address each of the reviewer’s points and describe the changes that we intend to implement in the revised version. We acknowledge the reviewer’s concern regarding potential over-interpretation of certain findings, and we will take particular care to ensure that all conclusions are supported by the data and framed within the exploratory nature of the study.

      (1) Trial objectives: What was the primary objective of the trial? This is not clearly stated. The authors describe changes in some reservoir parameters and no changes in others. Which of these was the primary outcome? No a priori hypothesis / primary objective is stated, nor is there explicit justification (power calculations, prior in vivo evidence) for the small n, unblinded design, and lack of placebo control. In the abstract (line 36, "significant decreases in total HIV DNA") and conclusion (lines 244-246), the authors state that total proviral DNA decreased as a result of ART intensification. However, in Figures 2A and 2E (and in line 251), the authors indicate that total proviral DNA did not change. These statements are confusing and appear to be contradictory. Regarding the decrease in total proviral DNA, I believe the authors may mean that they observed transient decrease in total proviral DNA during the intensification period (day 28 in particular, Figure 2A), however this level increases at Day 56 and then returns to baseline at Day 84, which is the source of the negative observation. Stating that total proviral DNA decreased as a result of the intervention when it ultimately did not is misleading, unless the investigators intended the day 28 timepoint as a primary endpoint for reservoir reduction - if so, this is never stated, and it is unclear why the intervention would then be continued until day 84? If, instead, reservoir reduction at the end of the intervention was the primary endpoint (again, unstated by the authors), then it is not appropriate to state that the total proviral reservoir decreased significantly when it did not.

      We agree with the reviewer that the primary objective of the study was not explicitly stated in the submitted manuscript. We will clarify this in the revised manuscript. As registered on ClinicalTrials.gov (NCT05351684), the primary outcome was defined as “To evaluate the impact of treatment intensification at the level of total and replication-competent reservoir (RCR) in blood and in tissues”, with a time frame of 3 months. Accordingly, our aim was to explore whether any measurable reduction in the HIV reservoir (total or replication-competent) occurred during the intensification period, including at day 28, 56, or 84. The protocol did not prespecify a single time point for this effect to occur, and the exploratory design allowed for detection of transient or sustained changes within the intensification window.

      We recognize that this scope was not clearly articulated in the original text and may have led to confusion in interpreting the transient drop in total HIV DNA observed at day 28. While total DNA ultimately returned to baseline by the end of intensification, the presence of a transient reduction during this 3-month window still fits within the framework of the study’s registered objective. Moreover, although the change in total HIV DNA was transient, it aligns with the consistent direction of changes observed across the multiple independent measures, including CA HIV RNA, RNA/DNA ratio and intact HIV DNA, collectively supporting a biological effect of intensification.

      We would also like to stress that this is the first clinical trial ever, in which an ART intensification is performed not by adding an extra drug but by increasing the dosage of an existing drug. Therefore, we were more interested in the overall, cumulative, effect of intensification throughout the entire trial period, than in differences between groups at individual time points. We will clarify in the manuscript that this was a proof-of-concept phase 2 study, designed to generate biological signals rather than confirm efficacy in a powered comparison. The absence of a pre-specified statistical endpoint or sample size calculation reflects the exploratory nature of the trial.

      (2) Intervention safety and tolerability: The results section lacks a specific heading for participant safety and tolerability of the intervention. I was wondering about clinically detectable viremia in the study. Were there any viral blips? Was the increased DTG well tolerated? This drug is known to cause myositis, headache, CPK elevation, hepatotoxicity, and headache. Were any of these observed? What is the authors' interpretation of the CD4:8 ratio change (line 198)? Is this a significant safety concern for a longer duration of intensification? Was there also a change in CD4% or only in absolute counts? Was there relative CD4 depletion observed in the rectal biopsy samples between days 0 and 84? Interestingly, T cells dropped at the same timepoints that reservoirs declined... how do the authors rule out that reservoir decline reflects transient T cell decline that is non-specific (not due to additional blockade of replication)?

      We will improve the Methods section to clarify how safety and tolerability were assessed during the study. Safety evaluations were conducted on day 28 and day 84 and included a clinical examination and routine laboratory testing (liver function tests, kidney function, and complete blood count). Medication adherence was also monitored through pill counts performed by the study nurses.

      No virological blips above 50 copies/mL were observed and no adverse events were reported by participants during the 3-month intensification period. Although CPK levels were not included in the routine biological monitoring, no participant reported muscle pain or other symptoms suggestive of muscle toxicity.

      The CD4:CD8 ratio decrease noted during intensification was not associated with significant changes in absolute CD4 or CD8 counts, as shown in Figure 5. We interpret this ratio change as a transient redistribution rather than an immunological risk, therefore we do not consider it to represent a safety concern.

      We would like to clarify that CD4<sup>+</sup> T-cell counts did not significantly decrease in any of the treatment groups, as shown in Figure 5. The apparent decline observed concerns the CD4/CD8 ratio, which transiently dropped, but not the absolute number of CD4<sup>+</sup> T cells.

      (3) The investigators describe a decrease in intact proviral DNA after 84 days of ART intensification in circulating cells (Figure 2D), but no changes to total proviral DNA in blood or tissue (Figures 2A and 2E; IPDA does not appear to have been done on tissue samples). It is not clear why ART intensification would result in a selective decrease in intact proviruses and not in total proviruses if the source of these reservoir cells is due to ongoing replication. These reservoir results have multiple interpretations, including (but not limited to) the investigators' contention that this provides strong evidence of ongoing replication. However, ongoing replication results in the production of both intact and mutated/defective proviruses that both contribute to reservoir size (with defective proviruses vastly outnumbering intact proviruses). The small sample size and well-described heterogeneity of the HIV reservoir (with regard to overall size and composition) raise the possibility that the study was underpowered to detect differences over the 84-day intervention period. No power calculations or prior studies were described to justify the trial size or the duration of the intervention. Readers would benefit from a more nuanced discussion of reservoir changes observed here.

      We sincerely thank the reviewer for this insightful comment. We fully agree that the reservoir dynamics observed in our study raise several possible interpretations, and that its complexity, resulting from continuous cycles of expansion and contraction, reflects the heterogeneity of the latent reservoir.

      Total HIV DNA in PBMCs showed a transient decline during intensification (notably at day 28), ultimately returning to baseline by day 84. This biphasic pattern may reflect the combined effects of suppression of ongoing low-level replication by an increased DTG dosage, followed by the expansion of infected cell clones (mostly harboring defective proviruses). In other words, the transient decrease in total (intact + defective) DNA at day 28 may be due to an initial decrease in newly infected cells upon ART intensification, however at the subsequent time points this effect was masked by proliferation (clonal expansion) of infected cells with defective proviruses. This explains why the intact proviruses decreased, but the total proviruses did not change, between days 0 and 84.

      Importantly, we observed a significant decrease in intact proviral DNA between day 0 and day 84 in the intensification group (Figure 2D). We will highlight this result more clearly in the revised manuscript, as it directly addresses the study’s primary objective: assessing the impact of intensification on the replication-competent reservoir. In comparison, as the reviewer rightly points out, total HIV DNA includes over 90% defective genomes, which limits its interpretability as a biomarker of biologically relevant reservoir changes.

      In addition, other reservoir markers, such as cell-associated unspliced RNA and RNA/DNA ratios, also showed consistent trends supporting a modest but biologically relevant effect of intensification. Even in the absence of sustained changes in total HIV DNA, the coherence across these independent measures suggests a signal indicative of ongoing replication in at least some individuals, and at specific timepoints.

      Regarding tissue reservoirs, the lack of substantial change in total HIV DNA between days 0 and 84 is also in line with the predominance of defective sequences in these compartments. Moreover, the limited increase in rectal tissue dolutegravir levels during intensification (from 16.7% to 20% of plasma concentrations) may have limited the efficacy of the intervention in this site.

      As for the IPDA on rectal biopsies, we attempted the assay using two independent DNA extraction methods (Promega Reliaprep and Qiagen Puregene), but both yielded high DNA Shearing Index values, and intact proviral detection was successful in only 3 of 40 samples. Given the poor DNA integrity and weak signals, these results were not interpretable.

      That said, we fully acknowledge the limitations of our study, especially the small sample size, and we agree with the reviewer that caution is needed when interpreting these findings. In the revised manuscript, we will adopt a more measured tone in the discussion, clearly stating that these observations are exploratory and hypothesis-generating, and require confirmation in larger, more powered studies. Nonetheless, we believe that the convergence of multiple reservoir markers pointing in the same direction constitutes a potentially meaningful biological signal that deserves further investigation.

      (4) While a few statistically significant changes occurred in immune activation markers, it is not clear that these are biologically significant. Lines 175-186 and Figure 3: The change in CD4 cells + for TIGIT looks as though it declined by only 1-2%, and at day 84, the confidence interval appears to widen significantly at this timepoint, spanning an interquartile range of 4%. The only other immune activation/exhaustion marker change that reached statistical significance appears to be CD8 cells + for CD38 and HLA-DR, however, the decline appears to be a fraction of a percent, with the control group trending in the same direction. Despite marginal statistical significance, it is not clear there is any biological significance to these findings; Figure S6 supports the contention that there is no significant change in these parameters over time or between groups. With most markers showing no change and these two showing very small changes (and the latter moving in the same direction as the control group), these results do not justify the statement that intensifying DTG decreases immune activation and exhaustion (lines 38-40 in the abstract and elsewhere).

      We agree with the reviewer that the observed changes in immune activation and exhaustion markers were modest. We will revise the manuscript to reflect this more accurately. We will also note that these differences, while statistically significant (e.g., in TIGIT+ CD4+ T cells and CD38+HLA-DR+ CD8+ T cells), were limited in magnitude. We will explicitly acknowledge these limitations and interpret the findings with appropriate caution.

      (5) There are several limitations of the study design that deserve consideration beyond those discussed at line 327. The study was open-label and not placebo-controlled, which may have led to some medication adherence changes that confound results (authors describe one observation that may be evidence of this; lines 146-148). Randomized/blinded / cross-over design would be more robust and help determine signal from noise, given relatively small changes observed in the intervention arm. There does not seem to be a measurement of key outcome variables after treatment intensification ceased - evidence of an effect on replication through ART intensification would be enhanced by observing changes once intensification was stopped. Why was intensification maintained for 84 days? More information about the study duration would be helpful. Table 1 indicates that participants were 95% male. Sex is known to be a biological variable, particularly with regard to HIV reservoir size and chronic immune activation in PWH. Worldwide, 50% of PWH are women. Research into improving management/understanding of disease should reflect this, and equal participation should be sought in trials. Table 1 shows differing baseline reservoir sizes between the control and intervention groups. This may have important implications, particularly for outcomes where reservoir size is used as the denominator.

      We will expand the limitations section to address several key aspects raised by the reviewer: the absence of blinding and placebo control, the predominantly male study population, and the lack of post-intervention follow-up. While we acknowledge that open-label designs can introduce behavioral biases, including potential changes in adherence, we will now explicitly state that placebo-controlled, blinded trials would provide a more robust assessment and are warranted in future research.

      The 84-day duration of intensification was chosen based on previous studies and provided sufficient time for observing potential changes in viral transcription and reservoir dynamics. However, we agree that including post-intervention follow-up would have strengthened the conclusions, and we will highlight this limitation and future direction in the revised manuscript.

      The sex imbalance is now clearly acknowledged as a limitation in the revised manuscript, and we fully support ongoing efforts to promote equitable recruitment in HIV research. We would like to add that, in our study, rectal biopsies were coupled with anal cancer screening through HPV testing. This screening is specifically recommended for younger men who have sex with men (MSM), as outlined in the current EACS guidelines (see: https://eacs.sanfordguide.com/eacs-part2/cancer/cancer-screening-methods). As a result, MSM participants had both a clinical incentive and medical interest to undergo this procedure, which likely contributed to the higher proportion of male participants in the study.

      Lastly, although baseline total HIV DNA was higher in the intensified group, our statistical approach is based on a within-subject (repeated-measures) design, in which the longitudinal change of a parameter within the same participant during the study was the main outcome. In other words, we are not comparing absolute values of any marker between the groups, we are looking at changes of parameters from baseline within participants, and these are not expected to be affected by baseline imbalances.

      (6) Figure 1: the increase in DTG levels is interesting - it is not uniform across participants. Several participants had lower levels of DTG at the end of the intervention. Though unlikely to be statistically significant, it would be interesting to evaluate if there is a correlation between change in DTG concentrations and virologic / reservoir / inflammatory parameters. A positive relationship between increasing DTG concentration and decreased cell-associated RNA, for example, would help support the hypothesis that ongoing replication is occurring.

      We agree with the reviewer that assessing correlations between DTG concentrations and virological, immunological, or inflammatory markers would be highly informative. In fact, we initially explored this question in a preliminary way by examining whether individuals who showed a marked increase in DTG levels after intensification also demonstrated stronger changes in the viral reservoir. While this exploratory analysis did not reveal any clear associations, we would like to emphasize that correlating biological effects with DTG concentrations measured at a single timepoint may have limited interpretability. A more comprehensive understanding of the relationship between drug exposure and reservoir dynamics would ideally require multiple pharmacokinetic measurements over time, including pre-intensification baselines. This is particularly important given that DTG concentrations vary across individuals and over time, depending on adherence, metabolism, and other individual factors. We will clarify these points in the revised manuscript.

      (7) Figure 2: IPDA in tissue- was this done? scRNA in blood (single copy assay) - would this be expected to correlate with usCaRNA? The most unambiguous result is the decrease in cell-associated RNA - accompanying results using single-copy assay in plasma would be helpful to bolster this result.

      As mentioned in our response to point 3, we attempted IPDA on tissue samples, but technical limitations prevented reliable detection of intact proviruses. Regarding residual viremia, we did perform ultra-sensitive plasma HIV RNA quantification but due to a technical issue (an inadvertent PBMC contamination during plasma separation) that affected the reliability of the results we felt uncomfortable including these data in the manuscript.

      The use of the US RNA / Total DNA ratio is not helpful/difficult to interpret since the control and intervention arms were unmatched for total DNA reservoir size at study entry.

      We respectfully disagree with this comment. The US RNA / Total DNA ratio is commonly used to assess the relative transcriptional activity of the viral reservoir, rather than its absolute size. While we acknowledge that the total HIV-1 DNA levels differed at baseline between the two groups, the US RNA / Total DNA ratio specifically reflects the relationship between transcriptional activity and reservoir size within each individual, and is therefore not directly confounded by baseline differences in total DNA alone.

      Moreover, our analyses focus on within-subject longitudinal changes from baseline, not on direct between-group comparisons of absolute marker values. As such, the observed changes in the US RNA / Total DNA ratio over time are interpreted relative to each participant's baseline, mitigating concerns related to baseline imbalances between groups.

      Reviewer #2 (Public Review):

      Summary:

      An intensification study with a double dose of 2nd generation integrase inhibitor with a background of nucleoside analog inhibitors of the HIV retrotranscriptase in 2, and inflammation is associated with the development of co-morbidities in 20 individuals randomized with controls, with an impact on the levels of viral reservoirs and inflammation markers. Viral reservoirs in HIV are the main impediment to an HIV cure, and inflammation is associated with co-morbidities.

      Strengths:

      The intervention that leads to a decrease of viral reservoirs and inflammation is quite straightforward forward as a doubling of the INSTI is used in some individuals with INSTI resistance, with good tolerability.

      This is a very well documented study, both in blood and tissues, which is a great achievement due to the difficulty of body sampling in well-controlled individuals on antiretroviral therapy. The laboratory assays are performed by specialists in the field with state-of-the art quantification assays. Both the introduction and the discussion are remarkably well presented and documented.

      The findings also have a potential impact on the management of chronic HIV infection.

      Weaknesses:

      I do not think that the size of the study can be considered a weakness, nor the fact that it is open-label either.

      We thank Reviewer #2 for their constructive and supportive comments. We appreciate their positive assessment of the study design, the translational relevance of the intervention, and the technical quality of the assays. We also take note of their perspective regarding sample size and study design, which supports our positioning of this trial as an exploratory, hypothesis-generating phase 2 study.

      Reviewer #3 (Public Review):

      The introduction does a very good job of discussing the issue around whether there is ongoing replication in people with HIV on antiretroviral therapy. Sporadic, non-sustained replication likely occurs in many PWH on ART related to adherence, drug interactions and possibly penetration of antivirals into sanctuary areas of replication and as the authors point out proving it does not occur is likely not possible and proving it does occur is likely very dependent on the population studied and the design of the intervention. Whether the consequences of this replication in the absence of evolution toward resistance have clinical significance challenging question to address.

      It is important to note that INSTI-based therapy may have a different impact on HIV replication events that results in differences in virus release for specific cell type (those responsible for "second phase" decay) by blocking integration in cells that have completed reverse transcription prior to ART initiation but have yet to be fully activated. In a PI or NNRTI-based regimen, those cells will release virus, whereas with an INSTI-based regimen, they will not.

      Given the very small sample size, there is a substantial risk of imbalance between the groups in important baseline measures. Unfortunately, with the small sample size, a non-significant P value is not helpful when comparing baseline measures between groups. One suggestion would be to provide the full range as opposed to the inter-quartile range (essentially only 5 or 6 values). The authors could also report the proportion of participants with baseline HIV RNA target not detected in the two groups.

      We thank Reviewer #3 for their thoughtful and balanced review. We are grateful for the recognition of the strength of the Introduction, the complexity of evaluating residual replication, and the technical execution of the assays. We also appreciate the insightful suggestions for improving the clarity and transparency of our results and discussion.

      We will revise the manuscript to address several of the reviewer’s key concerns. We agree that the small sample size increases the risk of baseline imbalances. We will acknowledge these limitations in the revised manuscript. We will provide both the full range and the IQR in Table 1 in the revised manuscript.

      A suggestion that there is a critical imbalance between groups is that the control group has significantly lower total HIV DNA in PBMC, despite the small sample size. The control group also has numerically longer time of continuous suppression, lower unspliced RNA, and lower intact proviral DNA. These differences may have biased the ability to see changes in DNA and US RNA in the control group.

      We acknowledge the significant baseline difference in total HIV DNA between groups, which we have clearly reported. However, the other variables mentioned, duration of continuous viral suppression, unspliced RNA levels, and intact proviral DNA, did not differ significantly between groups at baseline, despite differences in the median values. These numerical differences do not necessarily indicate a critical imbalance.

      Notably, there was no significant difference in the change in US RNA/DNA between groups (Figure 2C).

      The nonsignificant difference in the change in US RNA/DNA between groups is not unexpected, given the significant between-group differences for both US RNA and total DNA changes. Since the ratio combines both markers, it is likely to show attenuated between-group differences compared to the individual components. However, while the difference did not reach statistical significance (p = 0.09), we still observed a trend towards a greater reduction in the US RNA/Total DNA ratio in the intervention group.

      The fact that the median relative change appears very similar in Figure 2C, yet there is a substantial difference in P values, is also a comment on the limits of the current sample size.

      Although we surely agree that in general, the limited sample size impacts statistical power, we would like to point out that in Figure 2C, while the medians may appear similar, the ranges do differ between groups. At days 56 and 84, the median fold changes from baseline are indeed close but the full interquartile range in the DTG group stays below 1, while in the control group, the interquartile range is wider and covers approximately equal distance above and below 1. This explains the difference in p values between the groups.

      The text should report the median change in US RNA and US RNA/DNA when describing Figures 2A-2C.

      These data are already reported in the Results section (lines 164–166): "By day 84, US RNA and US RNA/total DNA ratio had decreased from day 0 by medians (IQRs) of 5.1 (3.3–6.4) and 4.6 (3.1–5.3) fold, respectively (p = 0.016 for both markers)."

      This statistical comparison of changes in IPDA results between groups should be reported. The presentation of the absolute values of all the comparisons in the supplemental figures is a strength of the manuscript.

      In the assessment of ART intensification on immune activation and exhaustion, the fact that none of the comparisons between randomized groups were significant should be noted and discussed.

      We would like to point out that a statistically significant difference between the randomized groups was observed for the frequency of CD4<sup>+</sup> T cells expressing TIGIT, as shown in Figure 3A and reported in the Results section (p = 0.048).

      The changes in CD4:CD8 ratio and sCD14 levels appear counterintuitive to the hypothesis and are commented on in the discussion.

      Overall, the discussion highlights the significant changes in the intensified group, which are suggestive. There is limited discussion of the comparisons between groups where the results are less convincing.

      We will temper the language accordingly and add commentary on the limited and modest nature of these changes. Similarly, we will expand our discussion of counterintuitive findings such as the CD4:CD8 ratio and sCD14 changes.

      The limitations of the study should be more clearly discussed. The small sample size raises the possibility of imbalance at baseline. The supplemental figures (S3-S5) are helpful in showing the differences between groups at baseline, and the variability of measurements is more apparent. The lack of blinding is also a weakness, though the PK assessments do help (note 3TC levels rise substantially in both groups for most of the time on study (Figure S2).

      The many assays and comparisons are listed as a strength. The many comparisons raise the possibility of finding significance by chance. In addition, if there is an imbalance at baseline outcomes, measuring related parameters will move in the same direction.

      We agree that the multiple comparisons raise the possibility of chance findings but would like to stress that in an exploratory study like this it is very important to avoid a type II error. In addition, the consistent directionality of the most relevant outcomes (US RNA and intact DNA) lends biological plausibility to the observed effects.

      The limited impact on activation and inflammation should be addressed in the discussion, as they are highlighted as a potentially important consequence of intermittent, not sustained replication in the introduction.

      The study is provocative and well executed, with the limitations listed above. Pharmacokinetic analyses help mitigate the lack of blinding. The major impact of this work is if it leads to a much larger randomized, controlled, blinded study of a longer duration, as the authors point out.

      Finally, we fully endorse the reviewer’s suggestion that the primary contribution of this study lies in its value as a proof-of-concept and foundation for future randomized, blinded trials of greater scale and duration. We will highlight this more clearly in the revised Discussion.

    1. Reviewer #2 (Public review):

      This paper introduces a framework for modeling individual differences in decision-making by learning a low-dimensional representation (the "individuality index") from one task and using it to predict behaviour in a different task. The approach is evaluated on two types of tasks: a sequential value-based decision-making task and a perceptual decision task (MNIST). The model shows improved prediction accuracy when incorporating this learned representation compared to baseline models.

      The motivation is solid, and the modelling approach is interesting, especially the use of individual embeddings to enable cross-task generalization. That said, several aspects of the evaluation and analysis could be strengthened.

      (1) The MNIST SX baseline appears weak. RTNet isn't directly comparable in structure or training. A stronger baseline would involve training the GRU directly on the task without using the individuality index-e.g., by fixing the decoder head. This would provide a clearer picture of what the index contributes.

      (2) Although the focus is on prediction, the framework could offer more insight into how behaviour in one task generalizes to another. For example, simulating predicted behaviours while varying the individuality index might help reveal what behavioural traits it encodes.

      (3) It's not clear whether the model can reproduce human behaviour when acting on-policy. Simulating behaviour using the trained task solver and comparing it with actual participant data would help assess how well the model captures individual decision tendencies.

      (4) Figures 3 and S1 aim to show that individuality indices from the same participant are closer together than those from different participants. However, this isn't fully convincing from the visualizations alone. Including a quantitative presentation would help support the claim.

      (5) The transfer scenarios are often between very similar task conditions (e.g., different versions of MNIST or two-step vs three-step MDP). This limits the strength of the generalization claims. In particular, the effects in the MNIST experiment appear relatively modest, and the transfer is between experimental conditions within the same perceptual task. To better support the idea of generalizing behavioural traits across tasks, it would be valuable to include transfers across more structurally distinct tasks.

      (6) For both experiments, it would help to show basic summaries of participants' behavioural performance. For example, in the MDP task, first-stage choice proportions based on transition types are commonly reported. These kinds of benchmarks provide useful context.

      (7) For the MDP task, consider reporting the number or proportion of correct choices in addition to negative log-likelihood. This would make the results more interpretable.

      (8) In Figure 5, what is the difference between the "% correct" and "% match to behaviour"? If so, it would help to clarify the distinction in the text or figure captions.

      (9) For the cognitive model, it would be useful to report the fitted parameters (e.g., learning rate, inverse temperature) per individual. This can offer insight into what kinds of behavioural variability the individuality index might be capturing.

      (10) A few of the terms and labels in the paper could be made more intuitive. For example, the name "individuality index" might give the impression of a scalar value rather than a latent vector, and the labels "SX" and "SY" are somewhat arbitrary. You might consider whether clearer or more descriptive alternatives would help readers follow the paper more easily.

      (11) Please consider including training and validation curves for your models. These would help readers assess convergence, overfitting, and general training stability, especially given the complexity of the encoder-decoder architecture.

    2. Reviewer #3 (Public review):

      Summary:

      This work presents a novel neural network-based framework for parameterizing individual differences in human behavior. Using two distinct decision-making experiments, the authors demonstrate the approach's potential and claims it can predict individual behavior (1) within the same task, (2) across different tasks, and (3) across individuals. While the goal of capturing individual variability is compelling and the potential applications are promising, the claims are weakly supported, and I find that the underlying problem is conceptually ill-defined.

      Strengths:

      The idea of using neural networks for parameterizing individual differences in human behavior is novel, and the potential applications can be impactful.

      Weaknesses:

      (1) To demonstrate the effectiveness of the approach, the authors compare a Q-learning cognitive model (for the MDP task) and RTNet (for the MNIST task) against the proposed framework. However, as I understand it, neither the cognitive model nor RTNet is designed to fit or account for individual variability. If that is the case, it is unclear why these models serve as appropriate baselines. Isn't it expected that a model explicitly fitted to individual data would outperform models that do not? If so, does the observed superiority of the proposed framework simply reflect the unsurprising benefit of fitting individual variability? I think the authors should either clarify why these models constitute fair control or validate the proposed approach against stronger and more appropriate baselines.

      (2) It's not very clear in the results section what it means by having a shorter within-individual distance than between-individual distances. Related to the comment above, is there any control analysis performed for this? Also, this analysis appears to have nothing to do with predicting individual behavior. Is this evidence toward successfully parameterizing individual differences? Could this be task-dependent, especially since the transfer is evaluated on exceedingly similar tasks in both experiments? I think a bit more discussion of the motivation and implications of these results will help the reader in making sense of this analysis.

      (3) The authors have to better define what exactly he meant by transferring across different "tasks" and testing the framework in "more distinctive tasks". All presented evidence, taken at face value, demonstrated transferring across different "conditions" of the same task within the same experiment. It is unclear to me how generalizable the framework will be when applied to different tasks.

      (4) Conceptually, it is also unclear to me how plausible it is that the framework could generalize across tasks spanning multiple cognitive domains (if that's what is meant by more distinctive). For instance, how can an individual's task performance on a Posner task predict task performance on the Cambridge face memory test? Which part of the framework could have enabled such a cross-domain prediction of task performance? I think these have to be at least discussed to some extent, since without it the future direction is meaningless.

      (5) How is the negative log-likelihood, which seems to be the main metric for comparison, computed? Is this based on trial-by-trial response prediction or probability of responses, as what usually performed in cognitive modelling?

      (6) None of the presented evidence is cross-validated. The authors should consider performing K-fold cross-validation on the train, test, and evaluation split of subjects to ensure robustness of the findings.

      (7) The authors excluded 25 subjects (20% of the data) for different reasons. This is a substantial proportion, especially by the standards of what is typically observed in behavioral experiments. The authors should provide a clear justification for these exclusion criteria and, if possible, cite relevant studies that support the use of such stringent thresholds.

      (8) The authors should do a better job of creating the figures and writing the figure captions. It is unclear which specific claim the authors are addressing with the figure. For example, what is the key message of Figure 2C regarding transfer within and across participants? Why are the stats presentation different between the Cognitive model and the EIDT framework plots? In Figure 3, it's unclear what these dots and clusters represent and how they support the authors' claim that the same individual forms clusters. And isn't this experiment have 98 subjects after exclusion, this plot has way less than 98 dots as far as I can tell. Furthermore, I find Figure 5 particularly confusing, as the underlying claim it is meant to illustrate is unclear. Clearer figures and more informative captions are needed to guide the reader effectively.

      (9) I also find the writing somewhat difficult to follow. The subheadings are confusing, and it's often unclear which specific claim the authors are addressing. The presentation of results feels disorganized, making it hard to trace the evidence supporting each claim. Also, the excessive use of acronyms (e.g., SX, SY, CG, EA, ES, DA, DS) makes the text harder to parse. I recommend restructuring the results section to be clearer and significantly reducing the use of unnecessary acronyms.

    1. Reviewer #3 (Public review):

      Summary:

      This manuscript investigates the conditions under which representational distances estimated from brain-activity measurements accurately mirror the true geometry of the underlying neural representations. Using a theoretical framework and simulations, the authors show that (i) random weighted sampling of individual neurons preserves representational distances; (ii) the non-negative pooling characteristic of fMRI stretches the geometry along the population-mean dimension; and (iii) subtracting the across-channel mean from each activity pattern removes this distortion, explaining the well-known success of correlation-based RSA. They further argue that a mean-centred, squared Euclidean (or Mahalanobis) distance retains this corrective benefit while avoiding some pitfalls of variance normalisation.

      Strengths:

      (1) Theoretical clarity and novelty:<br /> The paper offers an elegant and convincing proof of how linear measurement models affect representational geometry and pinpoints the specific condition (non-zero-mean sampling weights) under which voxel pooling introduces a systematic bias. This quantitative explanation of why mean removal is effective in RSA is new and valuable.

      (2) Simulations:<br /> Experiments on both synthetic high-dimensional fMRI data and macaque-IT-inspired embeddings corroborate the mathematics, providing practical insights into the theoretical reasoning outlined by the authors.

      (3) Actionable recommendations:<br /> The work summarises the results into clear guidelines: random single-unit sampling is "safe" (the estimated geometry is undistorted); fMRI voxel data with unstructured or single-scale codes should be mean-centred; and multi-scale cortical maps require explicit forward modelling. These guidelines are clear, and useful for future research.

      Weaknesses:

      (1) Simplistic assumptions:<br /> The assumption that measurement-channel weights are drawn independently and identically distributed (i.i.d.) from a univariate distribution is a significant idealisation for fMRI data. Voxels have spatially structured responses (and noise), meaning they do not sample neurons with i.i.d. weights. The extent to which the conclusions (especially the "exact recovery" with mean centring) hold when this assumption is violated needs more discussion. While the paper states that the non-negative IWLCS model is a best-case scenario, the implications of deviations from this best case could be elaborated.

      (2) Random-subpopulation model for electrophysiology:<br /> Similarly, the "random subpopulation model" is presented as an idealisation of single-cell recordings. In reality, electrophysiological sampling is often biased (e.g., towards larger, more active neurons or neurons in accessible locations). The paper acknowledges biased sampling as a challenge that requires separate modelling, but the gap between this idealised model and actual practice should be highlighted more strongly when interpreting the optimistic results.

      (3) Noise as an "orthogonal issue":<br /> The theoretical derivations largely ignore measurement noise, treating it as an orthogonal problem solvable by cross-validation. Although bias from noise is a well-known problem, interactions between noise and sampling-induced distortions (especially the down-scaling of orthogonal dimensions) could complicate the picture. For instance, if a dimension is already heavily down-scaled by averaging, it might become more susceptible to being obscured by noise. Addressing or highlighting these points more explicitly would make the limitations of this theoretical framework more transparent.

      (4) Simulation parameters and generalizability:<br /> The random ground-truth geometries were generated from a Gaussian mixture in 5-D and then embedded into 1,024-D, with ≈25 % of the variance coming from the mean dimension. The sensitivity of the findings to these specific parameters (initial dimensionality, geometry complexity, proportion of mean variance, and sample size) could be discussed. How would the results change if the true neural geometry had a much higher or lower intrinsic dimensionality, or if the population-mean component were substantially smaller or larger? If the authors' claims are to generalise, more scenarios should be considered.

      (5) Mean addition to the neural-data simulation:<br /> In simulations based on neural data from Kiani et al., a random mean was added to each pattern to introduce variation along the mean dimension. This was necessary because the original patterns had identical mean activation. However, the procedure might oversimplify how population means vary naturally and could influence the conclusions, particularly regarding the impact of the population-mean dimension. While precisely modelling how the mean varies across conditions is beyond the manuscript's scope, this point should be stated and discussed more clearly.

      (6) Effect of mean removal on representational geometry:<br /> As noted, the benefits of mean removal hold "under ideal conditions". Real data often violates these assumptions. A critical reader might ask: What if conditions differ in overall activation and in more complex ways (e.g., differing correlation structures across neurons)? Is it always desirable to remove population-mean differences? For example, if a stimulus truly causes a global increase in firing across the entire population (perhaps reflecting arousal or salience), subtracting the mean would treat this genuine effect as a nuisance and eliminate it from the geometry. Prior literature has cautioned that one should interpret RSA results after demeaning carefully. For instance, Ramírez (2017) dubbed this problem "representational confusion", showing that subtracting the mean pattern can change the relationships between conditions in non-intuitive ways. These potential issues and previous results should be discussed and properly referenced by the authors.

      Appraisal, Impact, and Utility:

      The authors set out to identify principled conditions under which measured representational distances faithfully reflect the underlying neural geometry and to provide practical guidance for RSA across modalities. Overall, I believe they achieved their goals. Theoretical derivations identify the bias-inducing factors in linear measurement models, and the simulations verify the analytic claims, demonstrating that mean-pattern subtraction can indeed correct some mean-related geometric distortions. These conclusions strongly rely on idealised assumptions (e.g., i.i.d. sampling weights and negligible noise), but the manuscript is explicit about them, and the reasoning from evidence to claim is sound. A deeper exploration of how robust each conclusion is to violations of these assumptions, particularly correlated voxel weights and realistic noise, would make the argument even stronger.

      Beyond their immediate aims, the authors offer contributions likely to shape future work. Its influence is likely to influence both analysis decisions and the design of future studies exploring the geometry of brain representations. By clarifying why correlation-based RSA seems to work so robustly, they help demystify a practice that has so far been adopted heuristically. Their proposal to adopt mean-centred Euclidean or Mahalanobis distances promises a straightforward alternative that better aligns representational geometry with decoding-based interpretations.

      In sum, I see this manuscript as a significant and insightful contribution to the field. The theoretical work clarifying the impact of sampling schemes and the role of mean removal is highly valuable. However, the identified concerns, primarily regarding the idealized nature of the models (especially for fMRI), the treatment of noise, and the need for more nuanced claims, suggest that some revisions are necessary. Addressing these points would substantially strengthen the paper's conclusions and enhance its impact on the neuroscience community by ensuring the proposed methods are robustly understood and appropriately applied in real-world research settings.

    1. Reviewer #1 (Public review):

      Kaller et al. (2025) explore the impact of environmental enrichment (EE) on the developing mouse brain, specifically during the perinatal period. The authors use high-resolution MRI to examine structural brain changes in neonates (postnatal day 7, P7) and compare these changes to those observed in adulthood. A key aspect of the study is the investigation of maternal care as a potential mediating factor in the effects of perinatal EE on neonatal brain development.

      The work exhibits the following notable strengths:

      (1) The study addresses a significant gap in the literature by investigating the effects of perinatal EE on whole-brain structure in neonates. Previous research has primarily focused on the effects of EE on the adult brain or specific aspects of early development, such as the visual system.

      (2) The authors employ a combination of high-resolution MRI and behavioral analysis of maternal care, providing a comprehensive view of the effects of EE.

      (3) The study reveals that EE affects brain structure as early as P7, with distinct regional changes compared to adulthood. The finding that maternal care influences neonatal brain structure and correlates with the effects of EE is particularly noteworthy.

      (4) The paper is clearly written, well-organized, and easy to follow. The figures and tables are informative and effectively illustrate the key findings.

      However, some weaknesses should be addressed to improve the quality of this study:

      (1) While the study includes an assessment of maternal care, the observational period is relatively short. A more extended or continuous assessment of maternal behavior could provide a more comprehensive understanding of its role in mediating the effects of EE.

      (2) The study primarily focuses on structural brain changes. Investigating the functional consequences of these changes could provide further insights into the long-term impact of perinatal EE.

      (3) The study demonstrates a correlation between maternal care and neonatal brain structure but does not elucidate the underlying mechanisms. Future studies could explore potential molecular or cellular mechanisms involved in these effects.

    2. Reviewer #2 (Public review):

      This paper by Kaller and colleagues combines an interesting replication of findings on the importance of maternal behavior on brain development in the offspring with a state-of-the-art MRI analysis and a novel comparison between such perinatal and early postnatal enrichment via the activity of the mother and a classical enriched environment in the adult. In general, the observations are as one would have expected. Early postnatal enrichment and adult enrichment have differential effects, which is plausible because, as the source of these changes is environmental, and environmental means very different things at these different stages. The three data sets presented are really interesting, and while the comparison between them might not always be as straightforward as it seems, the cross-sectional phenotyping with MRI already provides very important material and allows for interesting insight. Most interesting is possibly the massive effect of housing conditions at P7.

      In particular, the role of individual behavior differs. The authors highlight this role of the interaction with the environment, rather than the environment alone. Maternal care is a process that involves the pup.

      Importantly, the study shows that being born into an enriched environment predates certain changes that are still available after exposure at a later stage, but that there are also important differences. Detailed interpretation of these effects is not easy, however.

      Notably, the study does not include a condition of enrichment from birth into adulthood, and no analysis of the perinatal enrichment effects at an adult age. The timeline can be guessed from Figure 1b, but the authors might in places be more explicit about the fact that, indirectly and sometimes directly, animals of different ages (young adult versus adult) are compared. There is obviously no experience of maternal care in adulthood and no active exploration, etc in childhood. In part, this is what this paper is about, but it requires some thought for the reader to separate the more trivial from the more profound conclusions. Some more guidance would probably be welcome here. In general, Figure 4 is a great idea (and visually very appealing), but the content is not quite clear. "Adults born in EE vs. switched to EE in adulthood": this has, as far as I can tell, not been studied. What is compared are EE effects at two different time-points with two supposedly different mechanisms.

      From such a more mechanistic side, the authors might, for example, want to relate the observed patterns to what is known about the developmental (and plastic) dynamics in the respective brain regions at the given time. But age is a confounder here.

      There is another interesting point that the authors might discuss more prominently. The inter-individual differences in Z-score are dramatic within essentially all groups. So while the mean effects might still be statistically different, a large proportion of animals are within a range of values that could be found in either experimental group. The same is also true for the effects of maternal care, as depicted in Figure 3. While there is, for this ROI, a clear trend that overall relative volume decreases with maternal contact time at each time point, there is a large range of values for each maternal contact time bin. Consequently, neither genetics nor maternal care per se can be the driver of this variation. Part of it will be technical, but the trend in the data indicates that certainly not all of this is noise and technical error.

      This study has some open ends but also provides a very important and interesting direction for future study, corroborating the idea that behavior, maternal and own, does matter.

    3. Reviewer #3 (Public review):

      Summary:

      This study aimed to investigate the effect of environmental enrichment (EE) during the critical perinatal period on the developing brain structure and compare it with other periods. Different datasets of mice with EE or standard housing (SH) were compared with post-mortem MRI: dataset A (MRI at P96; 13 animals in EE during adulthood P53-P96, 14 animals in SH), dataset P (MRI at P43; 24 animals in EE during perinatal period and adulthood E17-P43, 25 animals in SH) and dataset N (MRI at P7; 52 animals in EE during perinatal period E13-P7, 67 animals in SH / resulting from 5 dams with 2 litters: 4 dams in EE and 6 dams in SH). The study replicated the effects observed during adulthood (main neuroanatomical EE/SH difference in datasets A and P: increase in the hippocampus volume) but also showed that volumetric changes for some regions differ between datasets A and P, suggesting different mechanisms of brain responses to enrichment depending on the period when EE was applied. Results on dataset N further showed that EE leads to lower brain size and differences for various regions: volume reduction in striatum, frontal, parietal, and occipital regions, hippocampus; volume increase for a few thalamic nuclei and hindbrain, suggesting different patterns of perinatal EE effects in datasets P and N. Since mice at P7 show little engagement with their environment, the authors further explored the hypothesis that the dams' behavior and interaction with neonates could be a mediator of brain differences observed at P7 between EE and SH animals. Maternal contact time was related to the P7 volumes for some regions (striatum, brainstem), but the variability and low sample size prevented a clear separation between EE and SH in terms of maternal behaviors.

      Strengths:

      (1) The question raised by this article is important at a fundamental level for our understanding of the complex interactions between the brain, behavior, and the environment.

      (2) This study replicates previous observations on the effects of EE in adult mice.

      (3) While some studies have been performed on neonates of dams exposed to EE during gestation, it is the first time that the effects of perinatal EE are investigated, in both the developing and mature brains with MRI. From a translational perspective, this is crucial for our understanding of human neurodevelopment in interaction with the environment.

      (4) The analyses carried out are numerous and detailed.

      Weaknesses:

      (1) The analyses carried out do not allow us to fully assess whether differences in maternal care mediate the effects of EE on brain structure during development. The observations support this causal hypothesis, but a complete mediation analysis would be useful if permitted by the sample size and the variability observed between litters.

      (2) The article is quite dense to read, given the number of analyses carried out. It is difficult at first reading to get a global view of the results. Figure 4 could be highlighted earlier to present the hypotheses and tests carried out.

      (3) The figures could be more explicit in terms of legends (particularly the supplementary figures).

    1. Reviewer #1 (Public review):

      Summary:

      The study investigated how individuals living in urban slums in Salvador, Brazil, interact with environmental risk factors, particularly focusing on domestic rubbish piles, open sewers, and a central stream. The study makes use of the step selection functions using telemetry data, which is a method to estimate how likely individuals move towards these environmental features, differentiating among groups by gender, age, and leptospirosis serostatus. The results indicated that women tended to stay closer to the central stream while avoiding open sewers more than men. Furthermore, individuals who tested positive for leptospirosis tended to avoid open sewers, suggesting that behavioral patterns might influence exposure to risk factors for leptospirosis, hence ensuring more targeted interventions.

      Strengths:

      (1) The use of step selection functions to analyze human movement represents an innovative adaptation of a method typically used in animal ecology. This provides a robust quantitative framework for evaluating how people interact with environmental risk factors linked to infectious diseases (in this case, leptospirosis).

      (2) Detailed differentiation by gender and serological status allows for nuanced insights, which can help tailor targeted interventions and potentially improve public health measures in urban slum settings.

      (3) The integration of real-world telemetry data with epidemiological risk factors supports the development of predictive models that can be applied in future infectious disease research, helping to bridge the gap between environmental exposure and health outcomes.

      Weaknesses:

      (1) The sample size for the study was not calculated, although it was a nested cohort study.

      (2) The step‐selection functions, though a novel method, may face challenges in fully capturing the complexity of human decision-making influenced by socio-cultural and economic factors that were not captured in the study.

      (3) The study's context is limited to a specific urban slum in Salvador, Brazil, which may reduce the generalizability of its findings to other geographical areas or populations that experience different environmental or socio-economic conditions.

      (4) The reliance on self-reported or telemetry-based movement data might include some inaccuracies or biases that could affect the precision of the selection coefficients obtained, potentially limiting the study's predictive power.

      (5) Some participants with less than 50 relocations within the study area were excluded without clear justification, see line 149.

      (6) Some figures are not clear (see Figure 4 A & B).

      (7) No statement on conflict of interest was included, considering sponsorship of the study.

    1. Reviewer #3 (Public review):

      In this manuscript, Nishi et al. propose a new model to explain the previously reported myeloid-biased hematopoiesis associated with aging. Traditionally, this phenotype has been explained by the expansion of myeloid-biased hematopoietic stem cell (HSC) clones during aging. Here, the authors question this idea and show how their Hoxb5 reporter model can discriminate long-term (LT) and short-term (ST) HSC and characterized their lineage output after transplant. From these analyses, the authors conclude that changes during aging in the LT/ST HSC proportion explain the myeloid bias observed.

      Comments on revisions:

      I appreciate the authors' reply to some of my comments. However, there are some key aspects that remain unresolved. Please see below.

      - The authors propose a critical change in the way we consider the mechanisms leading to lineage biased hematopoiesis during aging. As Reviewer 2 mentioned, such a strong claim needs to be supported by solid experimental data. Unfortunately, the level of variability in key in vivo experiments (Figure 2 and 3) diminishes the robustness of these results.

      The authors argue that even with the low number of mice used in some of these experiments and the high level of variability, differences still reach (or not) statistical significance according to their analysis. I am not an expert on statistics but the only test that is mentioned is their methodology is a Welch's t test, which is only appropriate for data following a normal distribution. A more rigorous statistical analysis should be performed to sustain the claims included in the current manuscript.

      - The chosen irradiation regiment might contribute to the uncertainty of the data and influence their interpretation. As the authors show in their response to my "comment to our #3-4 response", there is a considerable (and variable) amount of "radioresistant" CD45.1+CD45.2- cells in their primary recipients, which become concerningly high in the secondary transplant. This is not found in previous publications focused on this topic and, therefore, it makes it difficult to compare those studies with the present manuscript. The inclusion of this aspect in the text is appreciated but definitely reduces the impact of their claims.

      - The correction introduced in the main text as an answer to the original comment #3-6 is still misleading. There is an assumption for GMP, CMP and MEP to increase with age if myeloid-biased HSC clones increase with age ("in contrast to what we anticipated"). Again, the link between these two changes could be more complex than just a direct correlation.

    1. Reviewer #1 (Public review):

      Summary:

      Taber et al report the biochemical characterization of 7 mutations in PHD2 that induce erythrocytosis. Their goal is to provide a mechanism for how these mutations cause the disease. PHD2 hydroxylates HIF1a in the presence of oxygen at two distinct proline residues (P564 and P402) in the "oxygen degradation domain" (ODD). This leads to the ubiquitylation of HIF1a by the VHL E3 ligase and its subsequent degradation. Multiple mutations have been reported in the EGLN1 gene (coding for PHD2), which are associated with pseudohypoxic diseases that include erythrocytosis. Furthermore, 3 mutations in PHD2 also cause pheochromocytoma and paraganglioma (PPGL), a neuroendocrine tumour. These mutations likely cause elevated levels of HIF1a, but their mechanisms are unclear. Here, the authors analyze mutations from 152 case reports and map them on the crystal structure. They then focus on 7 mutations, which they clone in a plasmid and transfect into PHD2-KO to monitor HIF1a transcriptional activity via a luciferase assay. All mutants show impaired activation. Some mutants also impaired stability in pulse chase turnover assays (except A228S, P317R, and F366L). In vitro purified PHD2 mutants display a minor loss in thermal stability and some propensity to aggregate. Using MST technology, they show that P317R is strongly impaired in binding to HIF1a and HIF2a, whereas other mutants are only slightly affected. Using NMR, they show that the PHD2 P317R mutation greatly reduces hydroxylation of P402 (HIF1a NODD), as well as P562 (HIF1a CODD), but to a lesser extent. Finally, BLI shows that the P317R mutation reduces affinity for CODD by 3-fold, but not NODD.

      Strengths:

      (1) Simple, easy-to-follow manuscript. Generally well-written.

      (2) Disease-relevant mutations are studied in PHD2 that provide insights into its mechanism of action.

      (3) Good, well-researched background section.

      Weaknesses:

      (1) Poor use of existing structural data on the complexes of PHD2 with HIF1a peptides and various metals and substrates. A quick survey of the impact of these mutations (as well as analysis by Chowdhury et al, 2016) on the structure and interactions between PHD2 peptides of HIF1a shows that the P317R mutation interferes with peptide binding. By contrast, F366L will affect the hydrophobic core, and A228S is on the surface, and it's not obvious how it would interfere with the stability of the protein.

      (2) To determine aggregation and monodispersity of the PHD2 mutants using size-exclusion chromatography (SEC), equal quantities of the protein must be loaded on the column. This is not what was done. As an aside, the colors used for the SEC are very similar and nearly indistinguishable.

      (3) The interpretation of some mutants remains incomplete. For A228S, what is the explanation for its reduced activity? It is not substantially less stable than WT and does not seem to affect peptide hydroxylation.

      (4) The interpretation of the NMR prolyl hydroxylation is tainted by the high concentrations used here. First of all, there is a likely a typo in the method section; the final concentration of ODD is likely 0.18 mM, and not 0.18 uM (PNAS paper by the same group in 2024 reports using a final concentration of 230 uM). Here, I will assume the concentration is 180 uM. Flashman et al (JBC 2008) showed that the affinity of the NODD site (P402; around 10 uM) for PHD2 is 10-fold weaker than CODD (P564, around 1 uM). This likely explains the much faster kinetics of hydroxylation towards the latter. Now, using the MST data, let's say the P317R mutation reduces the affinity by 40-fold; the affinity becomes 400 uM for NODD (above the protein concentration) and 40 uM for CODD (below the protein concentration). Thus, CODD would still be hydroxylated by the P317R mutant, but not NODD.

      (5) The discrepancy between the MST and BLI results does not make sense, especially regarding the P317R mutant. Based on the crystal structures of PHD2 in complex with the ODD peptides, the P317R mutation should have a major impact on the affinity, which is what is reported by MST. This suggests that the MST is more likely to be valid than BLI, and the latter is subject to some kind of artefact. Furthermore, the BLI results are inconsistent with previous results showing that PHD2 has a 10-fold lower affinity for NODD compared to CODD.

      (6) Overall, the study provides some insights into mutants inducing erythrocytosis, but the impact is limited. Most insights are provided on the P317R mutant, but this mutant had already been characterized by Chowdhury et al (2016). Some mutants affect the stability of the protein in cells, but then no mechanism is provided for A228S or F366L, which have stabilities similar to WT, yet have impaired HIF1a activation.

    2. Reviewer #2 (Public review):

      Summary:

      Mutations in the prolyl hydroxylase, PHD2, cause erythrocytosis and, in some cases, can result in tumorigenesis. Taber and colleagues test the structural and functional consequences of seven patient-derived missense mutations in PHD2 using cell-based reporter and stability assays, and multiple biophysical assays, and find that most mutations are destabilizing. Interestingly, they discover a PHD2 mutant that can hydroxylate the C-terminal ODD, but not the N-terminal ODD, which suggests the importance of N-terminal ODD for biology. A major strength of the manuscript is the multidisciplinary approach used by the authors to characterize the functional and structural consequences of the mutations. However, the manuscript had several major weaknesses, such as an incomplete description of how the NMR was performed, a justification for using neighboring residues as a surrogate for looking at prolyl hydroxylation directly, or a reference to the clinical case studies describing the phenotypes of patient mutations. Additionally, the experimental descriptions for several experiments are missing descriptions of controls or validation, which limits their strength in supporting the claims of the authors.

      Strengths:

      (1) This manuscript is well-written and clear.

      (2) The authors use multiple assays to look at the effects of several disease-associated mutations, which support the claims.

      (3) The identification of P317R as a mutant that loses activity specifically against NODD, which could be a useful tool for further studies in cells.

      Weaknesses:

      Major:

      (1) The source data for the patient mutations (Figure 1) in PHD2 is not referenced, and it's not clear where this data came from or if it's publicly available. There is no section describing this in the methods.

      (2) The NMR hydroxylation assay.

      A. The description of these experiments is really confusing. The authors have published a recent paper describing a method using 13C-NMR to directly detect proly-hydroxylation over time, and they refer to this manuscript multiple times as the method used for the studies under review. However, it appears the current study is using 15N-HSQC-based experiments to track the CSP of neighboring residues to the target prolines, so not the target prolines themselves. The authors should make this clear in the text, especially on page 9, 5th line, where they describe proline cross-peaks and refer to the 15N-HSQC data in Figure 5B.<br /> B. The authors are using neighboring residues as reporters for proline hydroxylation, without validating this approach. How well do CSPs of A403 and I566 track with proline hydroxylation? Have the authors confirmed this using their 13C-NMR data or mass spec?<br /> C. Peak intensities. In some cases, the peak intensities of the end point residue look weaker than the peak intensities of the starting residue (5B, PHD2 WT I566, 6 ct lines vs. 4 ct lines). Is this because of sample dilution (i.e., should happen globally)? Can the authors comment on this?

      (3) Data validating the CRISPR KO HEK293A cells is missing.

      (4) The interpretation of the SEC data for the PHD2 mutants is a little problematic. Subtle alterations in the elution profiles may hint at different hydrodynamic radii, but as the samples were not loaded at equal concentrations or volumes, these data seem more anecdotal, rather than definitive. Repeating this multiple times, using matched samples, followed by comparison with standards loaded under identical buffer conditions, would significantly strengthen the conclusions one could make from the data.

      Minor:

      (1) Justification for picking the seven residues is not clearly articulated. The authors say they picked 7 mutants with "distinct residue changes", but no further rationale is provided.

      (2) A major finding of the paper is that a disease-associated mutation, P317R, can differentially affect HIF1 prolyhydroxylation, however, additional follow-up studies have not been performed to test this in cells or to validate the mutant in another method. Is it the position of the proline within the catalytic core, or the identity of the mutation that accounts for the selectivity?

    3. Author response:

      Public Reviews: 

      Reviewer #1 (Public review): 

      Summary: 

      Taber et al report the biochemical characterization of 7 mutations in PHD2 that induce erythrocytosis.

      Their goal is to provide a mechanism for how these mutations cause the disease. PHD2 hydroxylates HIF1a in the presence of oxygen at two distinct proline residues (P564 and P402) in the "oxygen degradation domain" (ODD). This leads to the ubiquitylation of HIF1a by the VHL E3 ligase and its subsequent degradation. Multiple mutations have been reported in the EGLN1 gene (coding for PHD2), which are associated with pseudohypoxic diseases that include erythrocytosis. Furthermore, 3 mutations in PHD2 also cause pheochromocytoma and paraganglioma (PPGL), a neuroendocrine tumour. These mutations likely cause elevated levels of HIF1a, but their mechanisms are unclear. Here, the authors analyze mutations from 152 case reports and map them on the crystal structure. They then focus on 7 mutations, which they clone in a plasmid and transfect into PHD2-KO to monitor HIF1a transcriptional activity via a luciferase assay. All mutants show impaired activation. Some mutants also impaired stability in pulse chase turnover assays (except A228S, P317R, and F366L). In vitro purified PHD2 mutants display a minor loss in thermal stability and some propensity to aggregate. Using MST technology, they show that P317R is strongly impaired in binding to HIF1a and HIF2a, whereas other mutants are only slightly affected. Using NMR, they show that the PHD2 P317R mutation greatly reduces hydroxylation of P402 (HIF1a NODD), as well as P562 (HIF1a CODD), but to a lesser extent. Finally, BLI shows that the P317R mutation reduces affinity for CODD by 3-fold, but not NODD.  

      Strengths: 

      (1) Simple, easy-to-follow manuscript. Generally well-written. 

      (2) Disease-relevant mutations are studied in PHD2 that provide insights into its mechanism of action. 

      (3) Good, well-researched background section. 

      Weaknesses: 

      (1) Poor use of existing structural data on the complexes of PHD2 with HIF1a peptides and various metals and substrates. A quick survey of the impact of these mutations (as well as analysis by Chowdhury et al, 2016) on the structure and interactions between PHD2 peptides of HIF1a shows that the P317R mutation interferes with peptide binding. By contrast, F366L will affect the hydrophobic core, and A228S is on the surface, and it's not obvious how it would interfere with the stability of the protein. 

      Thank you for the comment.  We will further analyze the mutations on the available PHD2 crystal structures in complex with HIFa to discern how these substitution mutations may impact PHD2 structure and function.  

      (2) To determine aggregation and monodispersity of the PHD2 mutants using size-exclusion chromatography (SEC), equal quantities of the protein must be loaded on the column. This is not what was done. As an aside, the colors used for the SEC are very similar and nearly indistinguishable. 

      Agreed.  We will perform additional experiment as suggested by the reviewer to further assess aggregation and hydrodynamic size.  The colors used in the graph will be changed for a clearer differentiation between samples.

      (3) The interpretation of some mutants remains incomplete. For A228S, what is the explanation for its reduced activity? It is not substantially less stable than WT and does not seem to affect peptide hydroxylation. 

      We agree with the reviewer that the causal mechanism for some of the tested disease-causing mutants remain unclear.  The negative findings also raise the notion, perhaps considered controversial, that there may be other substrates of PHD2 that are impacted by certain mutations, which contribute to disease pathogenesis.  We will expand our discussion accordingly. 

      (4) The interpretation of the NMR prolyl hydroxylation is tainted by the high concentrations used here. First of all, there is a likely a typo in the method section; the final concentration of ODD is likely 0.18 mM, and not 0.18 uM (PNAS paper by the same group in 2024 reports using a final concentration of 230 uM). Here, I will assume the concentration is 180 uM. Flashman et al (JBC 2008) showed that the affinity of the NODD site (P402; around 10 uM) for PHD2 is 10-fold weaker than CODD (P564, around 1 uM). This likely explains the much faster kinetics of hydroxylation towards the latter. Now, using the MST data, let's say the P317R mutation reduces the affinity by 40-fold; the affinity becomes 400 uM for NODD (above the protein concentration) and 40 uM for CODD (below the protein concentration). Thus, CODD would still be hydroxylated by the P317R mutant, but not NODD. 

      The HIF1α concentration was indeed an oversight, which will be corrected to 0.18 mM.  The study by Flashman et al.[1] showing PHD2 having a lower affinity to the NODD than CODD likely contributes to the differential hydroxylation rates via PHD2 WT.  We showed here via MST that PHD2 P317R had Kd of 320 ± 20 uM for HIF1αCODD, which should have led to a severe enzymatic defect, even at the high concentrations used for NMR (180 uM).  However, we observed only a subtle reduction in hydroxylation efficiency in comparison to PHD2 WT.  Thus, we performed another binding method using BLI that showed a mild binding defect on CODD by PHD2 P317R, consistent with NMR data.  The perplexing result is the WT-like binding to the NODD by PHD2 P317R, which appears inconsistent with the severe defect in NODD hydroxylation via PHD2 P317R as measured via NMR.  These results suggest that there are supporting residues within the PHD2/NODD interface that help maintain binding to NODD but compromise the efficiency of NODD hydroxylation upon PHD2 P317R mutation. We will perform additional binding experiments to further interrogate and validate the binding affinity of PHD2 P317R to NODD and CODD.

      (5) The discrepancy between the MST and BLI results does not make sense, especially regarding the P317R mutant. Based on the crystal structures of PHD2 in complex with the ODD peptides, the P317R mutation should have a major impact on the affinity, which is what is reported by MST. This suggests that the MST is more likely to be valid than BLI, and the latter is subject to some kind of artefact. Furthermore, the BLI results are inconsistent with previous results showing that PHD2 has a 10-fold lower affinity for NODD compared to CODD. 

      The reviewer’s structural prediction that P317R mutation should cause a major binding defect, while agreeable with our MST data, is incongruent with our NMR and the data from Chowdhury et al.[2] that showed efficient hydroxylation of CODD via PHD2 P317R.  Moreover, we have attempted to model NODD and CODD on apo PHD2 P317R structure and found that the mutation had no major impact on CODD while the mutated residue could clash with NODD, causing a shifting of peptide positioning on the protein.  However, these modeling predictions, like any in silico projections, would need experimental validation.  As mentioned in our preceding response, we also performed BLI, which showed that PHD2 P317R had a minor binding defect for CODD, consistent with the NMR results and findings by Chowdhury et al[2].  NODD binding was also measured with BLI as purified NODD peptides were not amenable for soluble-based MST assay, which showed similar K<sub>d</sub>’s for PHD2 WT and P317R.  Considering the absence of NODD hydroxylation via PHD2 P317R as measured by NMR and modeling on apo PHD2 P317R, we posit that P317R causes deviation of NODD from its original orientation that may not affect binding due to the other interactions from the surrounding elements but unfortunately disallows NODD from turnover.  Further study would be required to validate such notion, which we feel is beyond the scope of this manuscript.  However, we will perform additional binding experiments to further interrogate PHD2 P317R binding to NODD.   

      (6) Overall, the study provides some insights into mutants inducing erythrocytosis, but the impact is limited. Most insights are provided on the P317R mutant, but this mutant had already been characterized by Chowdhury et al (2016). Some mutants affect the stability of the protein in cells, but then no mechanism is provided for A228S or F366L, which have stabilities similar to WT, yet have impaired HIF1a activation. 

      We thank the reviewer for raising these and other limitations.  We will expand on the shortcomings of the present study but would like to underscore that the current work using the recently described NMR assay along with other biophysical analyses suggests a previously under-appreciated role of NODD hydroxylation in the normal oxygen-sensing pathway.  

      Reviewer #2 (Public review): 

      Summary: 

      Mutations in the prolyl hydroxylase, PHD2, cause erythrocytosis and, in some cases, can result in tumorigenesis. Taber and colleagues test the structural and functional consequences of seven patientderived missense mutations in PHD2 using cell-based reporter and stability assays, and multiple biophysical assays, and find that most mutations are destabilizing. Interestingly, they discover a PHD2 mutant that can hydroxylate the C-terminal ODD, but not the N-terminal ODD, which suggests the importance of N-terminal ODD for biology. A major strength of the manuscript is the multidisciplinary approach used by the authors to characterize the functional and structural consequences of the mutations. However, the manuscript had several major weaknesses, such as an incomplete description of how the NMR was performed, a justification for using neighboring residues as a surrogate for looking at prolyl hydroxylation directly, or a reference to the clinical case studies describing the phenotypes of patient mutations. Additionally, the experimental descriptions for several experiments are missing descriptions of controls or validation, which limits their strength in supporting the claims of the authors. 

      Strengths: 

      (1) This manuscript is well-written and clear. 

      (2) The authors use multiple assays to look at the effects of several disease-associated mutations, which support the claims. 

      (3) The identification of P317R as a mutant that loses activity specifically against NODD, which could be a useful tool for further studies in cells. 

      Weaknesses: 

      Major: 

      (1) The source data for the patient mutations (Figure 1) in PHD2 is not referenced, and it's not clear where this data came from or if it's publicly available. There is no section describing this in the methods.

      Clinical and patient information on disease-causing PHD2 mutants was compiled from various case reports and summarized in an excel sheet found in the Supplementary Information.  The case reports are cited in this excel file.  A reference to the supplementary data will be added to the Figure 1 legend and in the introduction.

      (2) The NMR hydroxylation assay. 

      A. The description of these experiments is really confusing. The authors have published a recent paper describing a method using 13C-NMR to directly detect proly-hydroxylation over time, and they refer to this manuscript multiple times as the method used for the studies under review. However, it appears the current study is using 15N-HSQC-based experiments to track the CSP of neighboring residues to the target prolines, so not the target prolines themselves. The authors should make this clear in the text, especially on page 9, 5th line, where they describe proline cross-peaks and refer to the 15N-HSQC data in Figure 5B. 

      As the reviewer mentioned, the assay that we developed directly measures the target proline residues.  This assay is ideal when mutations near the prolines are studied, such as A403, Y565 (He et al[3]).  In this previous work, we observed that the shifting of the target proline cross-peaks due to change in electronegativity on the pyrrolidine ring of proline in turn impacted the neighboring residues[3], which meant that the neighboring residues can be used as reporter residues for certain purposes.  In this study, we focused on investigating the mutations on PHD2 while leaving the sequence of the HIF-1α unchanged by using solely 15N-HSQC-based experiments without the need for double-labeled samples.  Nonetheless, we thank the reviewer for pointing out the confusion in the text and we will correct and clarify our description of this assay.

      B. The authors are using neighboring residues as reporters for proline hydroxylation, without validating this approach. How well do CSPs of A403 and I566 track with proline hydroxylation? Have the authors confirmed this using their 13C-NMR data or mass spec? 

      For previous studies, we performed intercalated 15N-HSQC and 13C-CON experiments for the kinetic measurements of wild-type HIF-1α and mutants.  We observed that the shifting pattern of A403 and I566 in the 15N-HSQC spectra aligned well with the ones of P402 and P564, respectively, in the 13C-CON spectra.  Representative data will be added to Supplemental Data.

      C. Peak intensities. In some cases, the peak intensities of the end point residue look weaker than the peak intensities of the starting residue (5B, PHD2 WT I566, 6 ct lines vs. 4 ct lines). Is this because of sample dilution (i.e., should happen globally)? Can the authors comment on this? 

      This is an astute observation by the reviewer.  We checked and confirmed that for all kinetic datasets, the peak intensities of the end point residue are always slightly lower than the ones of the starting.  This includes the cases for PHD2 A228S and P317R in 5B, although not as obvious as the one of PHD2 WT.  We agree with the reviewer that the sample dilution is a factor as a total volume of 16 microliters of reaction components was added to the solution to trigger the reaction after the first spectrum was acquired.  It is also likely that rate of prolyl hydroxylation becomes extremely slow with only a low amount of substrate available in the system.  Therefore, the reaction would not be 100% complete which was detected by the sensitive NMR experimentation.

      (3) Data validating the CRISPR KO HEK293A cells is missing. 

      We thank the reviewer for noting this oversight.  Western blots validating PHD2 KO in HEK293A cells will be added to the Supplementary Data file.

      (4) The interpretation of the SEC data for the PHD2 mutants is a little problematic. Subtle alterations in the elution profiles may hint at different hydrodynamic radii, but as the samples were not loaded at equal concentrations or volumes, these data seem more anecdotal, rather than definitive. Repeating this multiple times, using matched samples, followed by comparison with standards loaded under identical buffer conditions, would significantly strengthen the conclusions one could make from the data. 

      Agreed.  We will perform additional experiments as suggested with equal volume and concentration of each PHD2 construct loaded onto the SEC column for better assessment of aggregation.

      Minor: 

      (1) Justification for picking the seven residues is not clearly articulated. The authors say they picked 7 mutants with "distinct residue changes", but no further rationale is provided. 

      Additional justification for the selection of the mutants will be added to the ‘Mutations across the PHD2 enzyme induce erythrocytosis’ section.  Briefly, some mutants were chosen based on their frequency in the clinical data and their presence in potential mutational hot spots.  Various mutations were noted at W334 and R371, while F366L was identified in multiple individuals.  Additionally, 9 cases of PHD2-driven disease were reported to be caused from mutations located between residues 200 to 210 while 13 cases were reported between residues 369-379, so G206C and R371H were chosen to represent potential hot spots.  To examine a potential genotype-phenotype relationship, two of the mutants responsible for neuroendocrine tumor development, A228S and H374R, were also selected.  Finally, mutations located close or on catalytic core residues (P317R, R371H, and H374R) were chosen to test for suspected defects.   

      (2) A major finding of the paper is that a disease-associated mutation, P317R, can differentially affect HIF1 prolyhydroxylation, however, additional follow-up studies have not been performed to test this in cells or to validate the mutant in another method. Is it the position of the proline within the catalytic core, or the identity of the mutation that accounts for the selectivity? 

      This is the very question that we are currently addressing but as a part of a follow-up study.  Indeed, one thought is that the preferential defect observed could be the result of the loss of proline, an exceptionally rigid amino acid that makes contact with the backbone twice, or the addition of a specific amino acid, namely arginine, a flexible amino acid with an added charge at this site.  Although beyond the scope of this manuscript, we will investigate whether such and other characteristics in this region of PHD2/HIF1α interface contribute to the differential hydroxylation. 

      Reviewer #3 (Public review): 

      Summary: 

      This is an interesting and clinically relevant in vitro study by Taber et al., exploring how mutations in PHD2 contribute to erythrocytosis and/or neuroendocrine tumors. PHD2 regulates HIFα degradation through prolyl-hydroxylation, a key step in the cellular oxygen-sensing pathway. 

      Using a time-resolved NMR-based assay, the authors systematically analyze seven patient-derived PHD2 mutants and demonstrate that all exhibit structural and/or catalytic defects. Strikingly, the P317R variant retains normal activity toward the C-terminal proline but fails to hydroxylate the N-terminal site. This provides the first direct evidence that N-terminal prolyl-hydroxylation is not dispensable, as previously thought. 

      The findings offer valuable mechanistic insight into PHD2-driven effects and refine our understanding of HIF regulation in hypoxia-related diseases. 

      Strengths: 

      The manuscript has several notable strengths. By applying a novel time-resolved NMR approach, the authors directly assess hydroxylation at both HIF1α ODD sites, offering a clear functional readout. This method allows them to identify the P317R variant as uniquely defective in NODD hydroxylation, despite retaining normal activity toward CODD, thereby challenging the long-held view that the N-terminal proline is biologically dispensable. The work significantly advances our understanding of PHD2 function and its role in oxygen sensing, and might help in the future interpretation and clinical management of associated erythrocytosis. 

      Weaknesses: 

      (1) There is a lack of in vivo/ex vivo validation. This is actually required to confirm whether the observed defects in hydroxylation-especially the selective NODD impairment in P317R-are sufficient to drive disease phenotypes such as erythrocytosis. 

      We thank the reviewer for this comment, and while we agree with this statement, the objective of this study per se was to elucidate the structural and/or functional defect caused by the various diseaseassociated mutations on PHD2. The subsequent study would be to validate whether the identified defects, in particular the selective NODD impairment, would lead to erythrocytosis in vivo.  However, we feel that such study would be beyond the scope of this manuscript.

      (2) The reliance on HRE-luciferase reporter assays may not reliably reflect the PHD2 function and highlights a limitation in the assessment of downstream hypoxic signaling. 

      Agreed.  All experimental assays and systems have limitations. The HRE-luciferase assay used in the present manuscript also has limitations such as the continuous expression of exogenous PHD2 mutants driven via CMV promoter. Thus, we performed several additional biophysical methodologies to interrogate the disease-causing PHD2 mutants. The limitations of the luciferase assay will be expanded in the revised manuscript. 

      (3) The study clearly documents the selective defect of the P317R mutant, but the structural basis for this selectivity is not addressed through high-resolution structural analysis (e.g., cryo-EM). 

      We thank the reviewer for the comment.  While solving the structure of PHD2 P317R in complex with HIFα substrate is beyond the scope for this study, a structure of PHD2 P317R in complex with a clinically used inhibitor has been solved (PDB:5LAT).  In analyzing this structure and that of PHD2 WT in complex with NODD, Chowdhury et al[2] stated that P317 makes hydrophobic contacts with LXXLAP motif on HIFα and R317 is predicted to interact differently with this motif. While this analysis does not directly elucidate the reason for the preferential NODD defect, it supports the possibility that P317R substitution may be more detrimental for enzymatic activity on NODD than CODD. We will discuss this notion in the revised manuscript. 

      (4) Given the proposed central role of HIF2α in erythrocytosis, direct assessment of HIF2α hydroxylation by the mutants would have strengthened the conclusions. 

      We thank the reviewer for this comment, but we feel that such study would be beyond the scope of the present study. We observed that the PHD2 binding patterns to HIF1α and HIF2α were similar, and we have previously assigned >95% of the amino acids in HIF1α ODD for NMR study[3]. Thus, we first focused on the elucidation of possible defects on disease-associated PHD2 mutants using HIF1α as the substrate with the supposition that an identified deregulation on HIF1α could be extended to HIF2α paralog. 

      However, we agree with the reviewer that future studies should examine the impact of PHD2 mutants directly on HIF2α.  

      References:

      (1) Flashman, E. et al. Kinetic rationale for selectivity toward N- and C-terminal oxygen-dependent degradation domain substrates mediated by a loop region of hypoxia-inducible factor prolyl hydroxylases. J Biol Chem 283, 3808-3815 (2008).

      (2) Chowdhury, R. et al. Structural basis for oxygen degradation domain selectivity of the HIF prolyl hydroxylases. Nat Commun 7, 12673 (2016).

      (3) He, W., Gasmi-Seabrook, G.M.C., Ikura, M., Lee, J.E. & Ohh, M. Time-resolved NMR detection of prolyl-hydroxylation in intrinsically disordered region of HIF-1alpha. Proc Natl Acad Sci U S A 121, e2408104121 (2024).

    1. Reviewer #1 (Public review):

      Summary:

      The authors have investigated the role of FMRP in the formation and function of RNA granules in mouse brain/cultured hippocampal neurons. Most of their results indicate that FMRP does not have a role in the formation or function of RNA granules with specific mRNAs, but may have some role in distal RNA granules in neurons and their response to synaptic stimulation. This is an important work (though the results are mostly negative) in understanding the composition and function of neuronal RNA granules. The last part of the work in cultured neurons is disjointed from the rest of the manuscript, and the results are neither convincing nor provide any mechanistic insight.

      Strengths:

      (1) The study is quite thorough, the methods and analysis used are robust, and the conclusion and interpretation are diligent.

      (2) The comparative study of Rat and Mouse RNA granules is very helpful for future studies.

      (3) The conclusion that the absence of FMRP does not affect the RNA granule composition and many of its properties in the system the authors have chosen to study is well supported by the results.

      (4) The difference in the response to DHPG stimulation concerning RNA granules described here is very interesting and could provide a basis for further studies, though it has some serious technical issues.

      Weaknesses:

      (1) The system used for the study (P5 mouse brain or DIV 8-10 cultured neuron) is surprising, as the majority of defects in the absence of FMRP are reported in later stages (P30+ brain and DIV 14+ neurons). It is important to test if the conclusions drawn here hold good at different developmental stages.

      (2) The term 'distal granules' is very vague. Since there is no structural or biochemical characterization of these granules, it is difficult to understand how they are different from the proximal granules and why FMRP has an effect only on these granules.

      (3) Since the manuscript does not find any effect of FMRP on neuronal RNA granules, it does not provide any new molecular insight with respect to the function of FMRP

    2. Reviewer #2 (Public review):

      In the present manuscript, Li et al. use biochemical fractionation of "RNA granules" from P5 wildtype and FMR1 knock-out mouse brains to analyze their protein/RNA content, determine a single particle cryo-EM structure of contained ribosomes, and perform ribo-seq analysis of ribosome-protected RNA fragments (RPFs). The authors conclude from these that neither the composition of the ribosome granules, nor the state of their contained ribosomes, nor the mRNA positions with high ribosome occupancy change significantly. Besides minor changes in mRNA occupancy, the one change the authors identified is a decrease in puromycylated punctae in distal neurites of cultured primary neurons of the same mice, and their enhanced resistance to different pharmacological treatments. These results directly build on their earlier work (Anadolu et al., 2023) using analogous preparations of rat brains; the authors now perform a very similar study using WT and FMR1-KO mouse brains. This is an important topic, aiming to identify the molecular underpinnings of the FMRP protein, which is the basis of a major neurological disease. Unfortunately, several limitations of this study prevent it from being more convincing in its present form.

      In order to improve this study, our main suggestions are as follows:

      (1) The authors equate their biochemically purified "RG" fraction with their imaging-based detection of puromycin-positive punctae. They claim essentially no differences in RGs, but detect differences in the latter (mostly their abundance and sensitivity to DHPG/HHT/Aniso). In the discussion the authors acknowledge the inconsistency between these two modalities: "An inconsistency in our findings is the loss of distal RPM puncta coupled with an increase in the immunoreactivity for S6 in the RG." and "Thus, it may be that the RG is not simply made up of ribosomes from the large liquid-liquid phase RNA granules."

      How can the authors be sure that they are analysing the same entities in both modalities? A more parsimonious explanation of their results would be that, while there might be some overlap, two different entities are analyzed. Much of the main message rests on this equivalence, and I believe the authors should show its validity.

      (2) The authors show that increased nuclease digestion (and magnesium concentration) led to a reduction of their RPF sizes down to levels also seen by other researchers. Analyzing these now properly digested RPFs, the authors state that the CDS coverage and periodicity drastically improved, and that spurious enrichments of secretory mRNAs, which made up one of the major fractions in their previous work, are now reduced. In my opinion, this would be more appropriately communicated as a correction to their previous work, not as a main Figure in another manuscript.

      (3) The fold changes reported in Figure 7 (ranging between log2(-0.2) and log2(+0.25)) are all extremely small and in my opinion should not be used to derive claims such as "The loss of FMRP significantly affected the abundance and occupancy of FMRP-Clipped mRNAs in WT and FMR1-KO RG (Fig 7A, 7B), but not their enrichment between RG and RCs".

      (4) Figure 8 / S8-1 - The authors show that ~2/3 of their reads stem from PCR duplicates, but that even after removing those, the majority of peaks remain unaltered. At the same time, Figure S8-1 shows the total number of peaks to be 615 compared with 1392 before duplicate removal. Can the authors comment on this discrepancy? In addition, the dataset with properly removed artefacts should be used for their main display item instead of the current Figure 8.

      (5) Figure 9 / S9-1, the density of punctae in both WT and FMR1-KO actually increases after treatment of HHT or Anisomycin (Figure S9-1 B-C). Even if a large fraction would now be "resistant to run-off", there should not be an increase. While this effect is deemed not significant, a much smaller effect in Figure 9C is deemed significant. Can the authors explain this? Given how vastly different the sample sizes are (ranging from 23 neurites in Figures S9-1 to 5,171 neurites in Figure 9), the authors should (randomly) sample to the same size and repeat their statistical analysis again, to improve their credibility.

    3. Reviewer #3 (Public review):

      Summary: Li et al describe a set of experiments to probe the role of FMRP in ribosome stalling and RNA granule composition. The authors are able to recapitulate findings from a previous study performed in rats (this one is in mice).

      Strengths:

      1) The work addresses an important and challenging issue, investigating mechanisms that regulate stalled ribosomes, focusing on the role of FMRP. This is a complicated problem, given the heterogeneity of the granules and the challenges related to their purification. This work is a solid attempt at addressing this issue, which is widely understudied.

      2) The interpretation of the results could be interesting, if supported by solid data. The idea that FMRP could control the formation and release of RNA granules, rather than the elongation by stalled ribosomes is of high importance to the field, offering a fresh perspective into translational regulation by FMRP.

      3) The authors focused on recapitulating previous findings, published elsewhere (Anadolu et al., 2023) by the same group, but using rat tissue, rather than mouse tissue. Overall, they succeeded in doing so, demonstrating, among other findings, that stalled ribosomes are enriched in consensus mRNA motifs that are linked to FMRP. These interesting findings reinforce the role of FMRP in formation and stabilization of RNA granules. It would be nice to see extensive characterization of the mouse granules as performed in Figure 1 of Anadolu and colleagues, 2023.

      4) Some of the techniques incorporated aid in creating novel hypotheses, such as the ribopuromycilation assay and the cryo-EM of granule ribosomes.

      Weaknesses:

      1) The RNA granule characterization needs to be more rigorous. Coomassie is not proper for this type of characterization, simply because protein weight says little about its nature. The enrichment of key proteins is not robust and seems to not reach significance in multiple instances, including S6 and UPF1. Furthermore, S6 is the only proxy used for ribosome quantification. Could the authors include at least 3 other ribosomal proteins (2 from small, 2 from large subunit)?

      2) Page 12-13 - The Gene Ontology analysis is performed incorrectly. First, one should not rank genes by their RPKM levels. It is well known that housekeeping genes such as those related to actin dynamics, molecular transport and translation are highly enriched in sequencing datasets. It is usually more informative when significantly different genes are ranked by p adjust or log2 Fold Change, then compared against a background to verify enrichment of specific processes. However, the authors found no DEGs. I would suggest the removal of this analysis, incorporation of a gene set enrichment analyses (ranked by p adjust). I further suggest that the authors incorporate a dimensionality reduction analysis to demonstrate that the lack of significance stems from biology and not experimental artifacts, such as poor reproducibility across biological replicates.

    4. Author response:

      Reviewer #1 (Public review):

      Summary:

      The authors have investigated the role of FMRP in the formation and function of RNA granules in mouse brain/cultured hippocampal neurons. Most of their results indicate that FMRP does not have a role in the formation or function of RNA granules with specific mRNAs, but may have some role in distal RNA granules in neurons and their response to synaptic stimulation. This is an important work (though the results are mostly negative) in understanding the composition and function of neuronal RNA granules. The last part of the work in cultured neurons is disjointed from the rest of the manuscript, and the results are neither convincing nor provide any mechanistic insight.

      Strengths:

      (1) The study is quite thorough, the methods and analysis used are robust, and the conclusion and interpretation are diligent.

      (2) The comparative study of Rat and Mouse RNA granules is very helpful for future studies.

      (3) The conclusion that the absence of FMRP does not affect the RNA granule composition and many of its properties in the system the authors have chosen to study is well supported by the results.

      (4) The difference in the response to DHPG stimulation concerning RNA granules described here is very interesting and could provide a basis for further studies, though it has some serious technical issues.

      Weaknesses:

      (1) The system used for the study (P5 mouse brain or DIV 8-10 cultured neuron) is surprising, as the majority of defects in the absence of FMRP are reported in later stages (P30+ brain and DIV 14+ neurons). It is important to test if the conclusions drawn here hold good at different developmental stages.

      (2) The term 'distal granules' is very vague. Since there is no structural or biochemical characterization of these granules, it is difficult to understand how they are different from the proximal granules and why FMRP has an effect only on these granules.

      (3) Since the manuscript does not find any effect of FMRP on neuronal RNA granules, it does not provide any new molecular insight with respect to the function of FMRP

      Thank you for your comments and for pointing out the strengths of the manuscript. Unfortunately, we will not be able to respond to point #1. The protocol for purification of the ribosomes from RNA granules does not work in older brains (See Khandjian et al, 2004 PNAS 101:13357), presumably due to the presence of large concentrations of myelin. While it would be possible to repeat our results later in culture, we have no expectation that it would be different since we do observe DHPG induction of elongation dependent, initiation independent mGLUR-LTD in later cultures (Graber et al, 2017 J. Neuroscience 37:9116)..We will strengthen this caveat in the discussion that our results are only at a snapshot of development and that it is certainly possible that different results may be seen at different times. We agree with point 2 that ‘distal granules’ is a vague term. We will remove the term and clarify that we only quantified granules larger than 50 microns from the cell soma. We do not know if these granules are distinct. We would respectfully disagree with point #3 that the study does not provide molecular insight into the function of FMRP, as disproving that FMRP is important for stalling and determining the position of stalling removes a major hypothesis about the function of FMRP, and showing that something is not true, is at least to me, providing insight.

      Reviewer #2 (Public review):

      In the present manuscript, Li et al. use biochemical fractionation of "RNA granules" from P5 wildtype and FMR1 knock-out mouse brains to analyze their protein/RNA content, determine a single particle cryo-EM structure of contained ribosomes, and perform ribo-seq analysis of ribosome-protected RNA fragments (RPFs). The authors conclude from these that neither the composition of the ribosome granules, nor the state of their contained ribosomes, nor the mRNA positions with high ribosome occupancy change significantly. Besides minor changes in mRNA occupancy, the one change the authors identified is a decrease in puromycylated punctae in distal neurites of cultured primary neurons of the same mice, and their enhanced resistance to different pharmacological treatments. These results directly build on their earlier work (Anadolu et al., 2023) using analogous preparations of rat brains; the authors now perform a very similar study using WT and FMR1-KO mouse brains. This is an important topic, aiming to identify the molecular underpinnings of the FMRP protein, which is the basis of a major neurological disease. Unfortunately, several limitations of this study prevent it from being more convincing in its present form.

      In order to improve this study, our main suggestions are as follows:

      (1) The authors equate their biochemically purified "RG" fraction with their imaging-based detection of puromycin-positive punctae. They claim essentially no differences in RGs, but detect differences in the latter (mostly their abundance and sensitivity to DHPG/HHT/Aniso). In the discussion the authors acknowledge the inconsistency between these two modalities: "An inconsistency in our findings is the loss of distal RPM puncta coupled with an increase in the immunoreactivity for S6 in the RG." and "Thus, it may be that the RG is not simply made up of ribosomes from the large liquid-liquid phase RNA granules."

      How can the authors be sure that they are analysing the same entities in both modalities? A more parsimonious explanation of their results would be that, while there might be some overlap, two different entities are analyzed. Much of the main message rests on this equivalence, and I believe the authors should show its validity.

      (2) The authors show that increased nuclease digestion (and magnesium concentration) led to a reduction of their RPF sizes down to levels also seen by other researchers. Analyzing these now properly digested RPFs, the authors state that the CDS coverage and periodicity drastically improved, and that spurious enrichments of secretory mRNAs, which made up one of the major fractions in their previous work, are now reduced. In my opinion, this would be more appropriately communicated as a correction to their previous work, not as a main Figure in another manuscript.

      (3) The fold changes reported in Figure 7 (ranging between log2(-0.2) and log2(+0.25)) are all extremely small and in my opinion should not be used to derive claims such as "The loss of FMRP significantly affected the abundance and occupancy of FMRP-Clipped mRNAs in WT and FMR1-KO RG (Fig 7A, 7B), but not their enrichment between RG and RCs".

      (4) Figure 8 / S8-1 - The authors show that ~2/3 of their reads stem from PCR duplicates, but that even after removing those, the majority of peaks remain unaltered. At the same time, Figure S8-1 shows the total number of peaks to be 615 compared with 1392 before duplicate removal. Can the authors comment on this discrepancy? In addition, the dataset with properly removed artefacts should be used for their main display item instead of the current Figure 8.

      (5) Figure 9 / S9-1, the density of punctae in both WT and FMR1-KO actually increases after treatment of HHT or Anisomycin (Figure S9-1 B-C). Even if a large fraction would now be "resistant to run-off", there should not be an increase. While this effect is deemed not significant, a much smaller effect in Figure 9C is deemed significant. Can the authors explain this? Given how vastly different the sample sizes are (ranging from 23 neurites in Figures S9-1 to 5,171 neurites in Figure 9), the authors should (randomly) sample to the same size and repeat their statistical analysis again, to improve their credibility.

      Thank you for your comments. We agree with the issue in point #1 that the equivalence of RPM puncta with the RG fraction is an issue and while we believe that we show in a number of ways that the two are related (anisomycin-resistant puromycylation, puromyclation only at high concentrations consistent with the hybrid state, etc), we would respectfully disagree that our main message results from the equivalence of the RPM-labeled RNA granules in neurites and the ribosomes isolated by sedimentation. We will make this point clearer in our revision. For point #2, we agree that the changes with increased nuclease is somewhat out of place in a narrative sense, but it is clearly relevant to this work. Whether or not one sees this as a ‘correction’ or an interesting point will depend on a better characterization of the structures of the stalled polysomes. My personal view is that the nuclease resistance of cleavage near the RNA entrance site is quite interesting. Since we reproduce our results with a similar nuclease treatment in mice, as reported in our previous publication, I believe the comparison could be of interest in the future and would like to retain it. We agree with point #3 and will temper these claims in our revised version. For point #4, we will determine more carefully why the number of peaks differs and switch the main and supplemental figures. We apologize for the typo in the figure legend in Figure 9, 171, not 5171. The box plot line shows the median not the average and the data is clearly skewed such that the median and average are different (i.e. there is a two-fold decrease in the average density of distal puncta between WT and FMRP, but the average density is actually slightly decreased with HHT and A, although the median increases slightly. We will now report the results in distinct modalities to clarify this, and we will reexamine the statistics to better address the skewed distribution of values in the revised version.

      Summary:

      Li et al describe a set of experiments to probe the role of FMRP in ribosome stalling and RNA granule composition. The authors are able to recapitulate findings from a previous study performed in rats (this one is in mice).

      Strengths:

      (1) The work addresses an important and challenging issue, investigating mechanisms that regulate stalled ribosomes, focusing on the role of FMRP. This is a complicated problem, given the heterogeneity of the granules and the challenges related to their purification. This work is a solid attempt at addressing this issue, which is widely understudied.

      (2) The interpretation of the results could be interesting, if supported by solid data. The idea that FMRP could control the formation and release of RNA granules, rather than the elongation by stalled ribosomes is of high importance to the field, offering a fresh perspective into translational regulation by FMRP.

      (3) The authors focused on recapitulating previous findings, published elsewhere (Anadolu et al., 2023) by the same group, but using rat tissue, rather than mouse tissue. Overall, they succeeded in doing so, demonstrating, among other findings, that stalled ribosomes are enriched in consensus mRNA motifs that are linked to FMRP. These interesting findings reinforce the role of FMRP in formation and stabilization of RNA granules. It would be nice to see extensive characterization of the mouse granules as performed in Figure 1 of Anadolu and colleagues, 2023.

      (4) Some of the techniques incorporated aid in creating novel hypotheses, such as the ribopuromycilation assay and the cryo-EM of granule ribosomes.

      Weaknesses:

      (1) The RNA granule characterization needs to be more rigorous. Coomassie is not proper for this type of characterization, simply because protein weight says little about its nature. The enrichment of key proteins is not robust and seems to not reach significance in multiple instances, including S6 and UPF1. Furthermore, S6 is the only proxy used for ribosome quantification. Could the authors include at least 3 other ribosomal proteins (2 from small, 2 from large subunit)?

      (2) Page 12-13 - The Gene Ontology analysis is performed incorrectly. First, one should not rank genes by their RPKM levels. It is well known that housekeeping genes such as those related to actin dynamics, molecular transport and translation are highly enriched in sequencing datasets. It is usually more informative when significantly different genes are ranked by p adjust or log2 Fold Change, then compared against a background to verify enrichment of specific processes. However, the authors found no DEGs. I would suggest the removal of this analysis, incorporation of a gene set enrichment analyses (ranked by p adjust). I further suggest that the authors incorporate a dimensionality reduction analysis to demonstrate that the lack of significance stems from biology and not experimental artifacts, such as poor reproducibility across biological replicates.

      Thank you for your comments on the strengths of the manuscript. We agree with point #1 that the mouse RNA granule characterization needs to be more rigorous and we plan to accomplish this in our revised version. Similarly, we will incorporate the additional statistical analysis suggested by the reviewer in a revised version.

    1. Reviewer #2 (Public review):

      This study seeks to understand how the Rhino factor knows how to localize to specific transposon loci and to specific piRNA clusters to direct the correct formation of specialized heterochromatin that promotes piRNA biogenesis in the fly germline. In particular, these dual-strand piRNA clusters with names like 42AB, 38C, 80F, and 102F generate the bulk of ovarian piRNAs in the nurse cells of the fly ovary, but the evolutionary significance of these dual-strand piRNA clusters remains mysterious since triple null mutants of these dual-strand piRNA clusters still allows fly ovaries to develop and remain fertile. Nevertheless, mutants of Rhino and its interactors Deadlock, Cutoff, Kipferl and Moonshiner, etc, causes more piRNA loss beyond these dual-strand clusters and exhibit the phenotype of major female infertility, so the impact of proper assembly of Rhino, the RDC, Kipferl etc onto proper piRNA chromatin is an important and interesting biological question that is not fully understood.

      This study tries to first test ectopic expression of Rhino via engineering a Dox-inducible Rhino transgene in the OSC line that only expresses the primary Piwi pathway that reflects the natural single pathway expression the follicle cells and is quite distinct from the nurse cell germline piRNA pathway that is promoted by Rhino, Moonshiner, etc. The authors present some compelling evidence that this ectopic Rhino expression in OSCs may reveal how Rhino can initiate de novo binding via ADMA histone marks, a feat that would be much more challenging to demonstrate in the germline where this epigenetic naïve state cannot be modeled since germ cell collapse would likely ensue. In the OSC, the authors have tested the knockdown of four of the 11 known Drosophila PRMTs (DARTs), and comparing to ectopic Rhino foci that they observe in HP1a knockdown (KD), they conclude DART1 and DART4 are the prime factors to study further in looking for disruption of ADMA histone marks. The authors also test KD of DART8 and CG17726 in OSCs, but in the fly, the authors only test Germ Line KD of DART4 only, they do not explain why these other DARTs are not tested in GLKD, the UAS-RNAi resources in Drosophila strain repositories should be very complete and have reagents for these knockdowns to be accessible.

      The authors only characterize some particular ADMA marks of H3R17me2a as showing strong decrease after DART4 GLKD, and then they see some small subset of piRNA clusters go down in piRNA production as shown in Figure 6B and Figure 6F and Supplementary Figure 7. This small subset of DART4-dependent piRNA clusters does lose Rhino and Kipferl recruitment, which is an interesting result.

      However, the biggest issue with this study is the mystery that the set of the most prominent dual-strand piRNA clusters. 42AB, 38C, 80F, and 102F, are the prime genomic loci subjected to Rhino regulation, and they do not show any change in piRNA production in the GLKD of DART4. The authors bury this surprising negative result in Supplementary Figure 5E, but this is also evident in no decrease (actually an n.s. increase) in Rhino association in Figure 5D. Since these main piRNA clusters involve the RDC, Kipferl, Moonshiner, etc, and it does not change in ADMA status and piRNA loss after DART4 GLKD, this poses a problem with the model in Figure 7C. In this study, there is only a GLKD of DART4 and no GLKD of the other DARTs in fly ovaries.

      One way the authors rationalize this peculiar exception is the argument that DART4 is only acting on evolutionarily "young" piRNA clusters like the bx, CG14629, and CG31612, but the lack of any change on the majority of other piRNA clusters in Figure 6F leaves upon the unsatisfying concern that there is much functional redundancy remaining with other DARTs not being tested by GLKD in the fly that would have a bigger impact on the other main dual-strand piRNA clusters being regulated by Rhino and ADMA-histone marks.

      Also, the current data does not provide convincing enough support for the model Figure 7C and the paper title of ADMA-histones being the key determinant in the fly ovary for Rhino recognition of the dual-strand piRNA clusters. Although much of this study's data is well constructed and presented, there remains a large gap that no other DARTs were tested in GLKD that would show a big loss of piRNAs from the main dual-strand piRNA clusters of 42AB, 38C, 80F, and 102F, where Rhino has prominent spreading in these regions.

      As the manuscript currently stands, I do not think the authors present enough data to conclude that "ADMA-histones [As a Major new histone mark class] does play a crucial role in the initial recognition of dual-strand piRNA cluster regions by Rhino" because the data here mainly just show a small subset of evolutionarily young piRNA clusters have a strong effect from GLKD of DART4. The authors could extensively revise the study to be much more specific in the title and conclusion that they have uncovered this very unique niche of a small subset of DART4-dependent piRNA clusters, but this niche finding may dampen the impact and significance of this study since other major dual-strand piRNA clusters do not change during DART4 GLKD, and the authors do not show data GLKD of any other DARTs. The niche finding of just a small subset of DART-4-dependent piRNA clusters might make another specialized genetics forum a more appropriate venue.

    1. Reviewer #1 (Public review):

      The manuscript by Shan et al seeks to define the role of the CHI3L1 protein in macrophages during the progression of MASH. The authors argue that the Chil1 gene is expressed highly in hepatic macrophages. Subsequently, they use Chil1 flx mice crossed to Clec4F-Cre or LysM-Cre to assess the role of this factor in the progression of MASH using a high-fat, high-fructose diet (HFFC). They found that loss of Chil1 in KCs (Clec4F Cre) leads to enhanced KC death and worsened hepatic steatosis. Using scRNA seq, they also provide evidence that loss of this factor promotes gene programs related to cell death. From a mechanistic perspective, they provide evidence that CHI3L serves as a glucose sink and thus loss of this molecule enhances macrophage glucose uptake and susceptibility to cell death. Using a bone marrow macrophage system and KCs they demonstrate that cell death induced by palmitic acid is attenuated by the addition of rCHI3L1. While the article is well written and potentially highlights a new mechanism of macrophage dysfunction in MASH, there are some concerns about the current data that limit my enthusiasm for the study in its current form. Please see my specific comments below.

      Major:

      (1) The authors' interpretation of the results from the KC ( Clec4F) and MdM KO (LysM-Cre) experiments is flawed. For example, in Figure 2 the authors present data that knockout of Chil1 in KCs using Clec4f Cre produces worse liver steatosis and insulin resistance. However, in supplemental Figure 4, they perform the same experiment in LysM-Cre mice and find a somewhat different phenotype. The authors appear to be under the impression that LysM-Cre does not cause recombination in KCs and therefore interpret this data to mean that Chil1 is relevant in KCs and not MdMs. However, LysM-Cre DOES lead to efficient recombination in KCs and therefore Chil1 expression will be decreased in both KCs and MdM (along with PMNs) in this line.

      Therefore, a phenotype observed with KC-KO should also be present in this model unless the authors argue that loss of Chil1 from the MdMs has the opposite phenotype of KCs and therefore attenuates the phenotype. The Cx3Cr1 CreER tamoxifen inducible system is currently the only macrophage Cre strategy that will avoid KC recombination. The authors need to rethink their results with the understanding that Chil1 is deleted from KCs in the LysM-Cre experiment. In addition, it appears that only one experiment was performed, with only 5 mice in each group for both the Clec4f and LysM-Cre data. This is generally not enough to make a firm conclusion for MASH diet experiments.

      (2) The mouse weight gain is missing from Figure 2 and Supplementary Figure 4. This data is critical to interpret the changes in liver pathology, especially since they have worse insulin resistance.

      (3) Figure 4 suggests that KC death is increased with KO of Chil1. However, this data cannot be concluded from the plots shown. In Supplementary Figure 6 the authors provide a more appropriate gating scheme to quantify resident KCs that includes TIM4. The TIM4 data needs to be shown and quantified in Figure 4. As shown in Supplementary Figure 6, the F4/80 hi population is predominantly KCs at baseline; however, this is not true with MASH diets. Most of the recruited MoMFs also reside in the F4/80 hi gate where they can be identified by their lower expression of TIM4. The MoMF gate shown in this figure is incorrect. The CD11b hi population is predominantly PMNs, monocytes, and cDC,2 not MoMFs (PMID:33997821). In addition, the authors should stain the tissue for TIM4, which would also be expected to reveal a decrease in the number of resident KCs.

      (4) While the Clec4F Cre is specific to KCs, there is also less data about the impact of the Cre system on KC biology. Therefore, when looking at cell death, the authors need to include some mice that express Clec4F cre without the floxed allele to rule out any effects of the Cre itself. In addition, if the cell death phenotype is real, it should also be present in LysM Cre system for the reasons described above. Therefore, the authors should quantify the KC number and dying KCs in this mouse line as well.

      (5) I am somewhat concerned about the conclusion that Chil1 is highly expressed in liver macrophages. Looking at our own data and those from the Liver Atlas it appears that this gene is primarily expressed in neutrophils. At a minimum, the authors should address the expression of Chil1 in macrophage populations from other publicly available datasets in mouse MASH to validate their findings (several options include - PMID: 33440159, 32888418, 32362324). If expression of Chil1 is not present in these other data sets, perhaps an environmental/microbiome difference may account for the distinct expression pattern observed. Either way, it is important to address this issue.

    2. Reviewer #3 (Public review):

      This paper investigates the role of Chi3l1 in regulating the fate of liver macrophages in the context of metabolic dysfunction leading to the development of MASLD. I do see value in this work, but some issues exist that should be addressed as well as possible.

      Here are my comments:

      (1) Chi3l1 has been linked to macrophage functions in MASLD/MASH, acute liver injury, and fibrosis models before (e.g., PMID: 37166517), which limits the novelty of the current work. It has even been linked to macrophage cell death/survival (PMID: 31250532) in the context of fibrosis, which is a main observation from the current study.

      (2) The LysCre-experiments differ from experiments conducted by Ariel Feldstein's team (PMID: 37166517). What is the explanation for this difference? - The LysCre system is neither specific to macrophages (it also depletes in neutrophils, etc), nor is this system necessarily efficient in all myeloid cells (e.g., Kupffer cells vs other macrophages). The authors need to show the efficacy and specificity of the conditional KO regarding Chi3l1 in the different myeloid populations in the liver and the circulation.

      (3) The conclusions are exclusively based on one MASLD model. I recommend confirming the key findings in a second, ideally a more fibrotic, MASH model.

      (4) Very few human data are being provided (e.g., no work with own human liver samples, work with primary human cells). Thus, the translational relevance of the observations remains unclear.

    1. Reviewer #1 (Public review):

      Summary:

      The article by Zdraljevic et al. reports the discovery of a third toxin-antidote (TA) element in C. elegans, composed of the genes mll-1 (toxin) and smll-1 (antidote). Unlike previously characterized TA systems in C. elegans, this element induces larval arrest rather than embryonic lethality. The study identifies three distinct haplotypes at the TA locus, including a hyper-divergent version in the standard laboratory strain N2, which retains a functional toxin but lacks a functional antidote. The authors propose that small RNA-mediated silencing mechanisms, dependent on MUT-16 and PRG-1, suppress the toxicity of the divergent toxin allele. This work provides insights into the evolutionary dynamics of TA elements and their regulation through RNA interference (RNAi).

      Overall, there are many things to like about this paper and only a few small quibbles, which will not require more than a little rewriting or relatively minor analyses.

      Strengths:

      (1) The discovery of a maternally deposited TA element with delayed toxicity due to delayed mRNA translation of the maternally deposited toxin mRNA is a significant addition to the literature on selfish genetic elements in metazoans.

      (2) Identifying three haplotypes at the TA locus provides a snapshot of potential evolutionary trajectories for these elements, which are often inferred but rarely demonstrated in naturally occurring strains. The genomic analysis of 550 wild isolates contextualizes the findings within natural populations, revealing geographic clustering and evolutionary pressures acting on the TA locus.

      (3) The study employs various techniques, including CRISPR/Cas9 knockouts, FISH, long-read RNA sequencing, and population genomics. The use of inducible systems to confirm toxicity and antidote functionality is particularly robust. This multifaceted approach strengthens the validity of the findings.

      (4) The authors provide compelling evidence that small RNA pathways suppress toxin activity in strains lacking a functional antidote. This highlights an alternative mechanism for neutralizing selfish genetic elements.

      Weaknesses:

      (1) The introduction focuses strongly (for good reason) on bacterial TA systems and then jumps to TA systems in C. elegans. It's unclear why TA systems in other eukaryotes are not discussed.

      (2) Similarly, there is a missed opportunity to discuss an analogy between the suppressor mechanism discovered here and the hairpin RNA suppressors of meiotic drive identified by Eric Lai and colleagues. Discussing these will provide a fuller context of the present study's findings and will not affect their novelty.

      (3) While the evidence for RNAi-mediated suppression is strong, the claim that positive selection drove diversification at piRNA binding sites requires further discussion and clarification. The elevated dN and dS are unusual (how unusual relative to other genes in vicinity? What is hyper-divergent statistically speaking?), but there is no a priori reason that there would be selection on piRNA binding sites within the mll-1 transcript to facilitate its recognition by endogenous RNAi machinery; what is the selective pressure for mll-1 to do so? Most TA systems would like to avoid being suppressed by the host. One cannot make the argument that this was motivated by the loss of the antidote because the loss of the antidote would be instantly suicidal, so the cadence of events described requiring hypermutation of the mll-1 transcript does not work.

    1. Document de synthèse : Temps long et urgences climatiques – Perspectives croisées

      Ce document de synthèse vise à analyser les thèmes principaux et les idées ou faits les plus importants issus de la conférence "Troisième conférence : temps long et urgences climatiques", organisée dans le cadre du rapport annuel du Conseil d'État sur l'État stratège et le temps long dans les politiques publiques.

      Les interventions de

      • Valérie Masson-Delmotte (scientifique climatologue),
      • Antoine Pellion (Secrétaire général à la planification écologique) et
      • Florence Lustman (Présidente de France Assureurs)

      ont offert des perspectives complémentaires sur l'urgence climatique, la planification écologique, la participation citoyenne et le rôle du secteur de l'assurance.

      Thèmes principaux et idées clés :

      1. L'Urgence Climatique et la Rupture Anthropique (Perspective Scientifique)

      Valérie Masson-Delmotte, climatologue, souligne la rupture fondamentale que représente l'influence humaine sur le climat, visible à travers l'analyse des carottages glaciaires remontant à 800 000 ans.

      Elle met en évidence une "augmentation brutale et rapide par rapport aux variations naturelles de la teneur des principaux gaz à effet de serre dans l'atmosphère, notamment le dioxyde de carbone émis par la combustion d'énergie fossile".

      • Bases scientifiques solides et historiques : La compréhension de l'effet de serre remonte au XIXe siècle (Arrhenius), avec les premières mesures de réchauffement en 1938 et les premières modélisations climatiques dans les années 1960. Le GIEC, créé dans les années 1990, fournit des évaluations rigoureuses et non prescriptives.
      • Science de l'attribution : La science permet aujourd'hui d'attribuer "comme un fait scientifique que l'ensemble des caractéristiques observées dont le réchauffement de surface est la conséquence des activités humaines", et d'évaluer l'influence humaine sur l'occurrence et l'intensité des événements extrêmes.
      • Aggravation rapide des impacts : Les vulnérabilités et l'aggravation rapide des impacts négatifs ont été sous-estimées. Le réchauffement planétaire a atteint 1,2°C au cours de la dernière décennie, et devrait dépasser 1,5°C vers 2030-2035. Les conséquences sont multiples : "augmentation de la mortalité des arbres", "blanchissement des coraux", "difficulté d'approvisionnement en eau", "choc sur la production alimentaire", "augmentation de la morbidité de la mortalité liée à la chaleur".
      • Limites à l'adaptation : Un réchauffement de 2°C au niveau mondial se traduirait par +3°C en France d'ici 2050, et 3°C mondial par +4°C en France d'ici 2100, exposant à des "limites à l'adaptation" dans les régions les plus vulnérables (climats méditerranéens, zones côtières, grands deltas, villes).
      • Décalage juridique et urgence : Le cadre juridique actuel est en décalage avec l'état des connaissances scientifiques, notamment sur la montée du niveau de la mer et la nécessité de scénarios "pire physiquement plausible" pour l'aménagement du territoire et la dimension des infrastructures critiques.

      2. La Planification Écologique et ses Défis (Perspective de l'État)

      Antoine Pellion, Secrétaire général à la planification écologique, détaille la démarche française pour coordonner l'action publique face aux enjeux écologiques, en lien avec le Premier ministre.

      • Périmètre large de la planification : La planification écologique ne se limite pas aux émissions de gaz à effet de serre, mais englobe l'adaptation au changement climatique, la protection de la biodiversité, la gestion durable des ressources naturelles (eau, forêt, matériaux critiques), et les enjeux de santé environnementale. Elle est également "indissociable d'enjeux économique extrêmement structurant" et de "dimension sociale".
      • Cohérence et transversalité : L'objectif est de "casser les silos" entre les ministères et les acteurs, et de concilier "des enjeux très long terme avec une action immédiate de court terme". La décarbonation est aussi un "plan de résilience économique" majeur pour la France, réduisant la dépendance aux énergies fossiles.
      • Un chemin "possible" mais "difficile" : Un plan d'action opérationnel a été élaboré, montrant qu'il existe "un chemin pour que la France effectivement baisse ses émissions de -55 % entre 1990 et 2030 sans avoir de rupture absolument majeure". Cependant, des "gains un peu faciles" liés à la sobriété forcée par les prix ont été réalisés, et la tendance pour 2025 n'est "pas bonne" dans certains secteurs.
      • Répartition de l'effort et justice sociale : La planification vise une répartition de l'effort : "la moitié des baisses, on attend à ce qu'elle soit faite par les gros acteurs les entreprises notamment 75 % par les gros je dis les gros c'est les pouvoirs publics au sens large". Le dernier quart est entre les mains des citoyens, avec "15 % de la population qui a besoin d'avoir des changements assez drastiques dans ses modes de vie".
      • Défi du financement : L'investissement annuel public et privé doit être augmenté de 50 % (+60 milliards d'euros par an) d'ici 2030. Un quart des investissements est rentable, mais le reste nécessite de "nouveaux modèles de financement" et une "optimisation un peu fine pour que la ressource publique soit vraiment investie là où il y a pas vraiment aucune autre alternative".

      3. Le Rôle Crucial de la Démocratie Environnementale (Perspective de la Société Civile)

      Antoine Gaté, représentant de France Nature Environnement, insiste sur le rôle des associations dans la protection de l'environnement et met en garde contre un "backlash écologique".

      • Conception de l'État : Pour la société civile, l'État est le "cadre du pouvoir d'action publique dans un système démocratique", fondé sur le respect des droits humains (droit à l'environnement), la "prééminence du droit" (sécurité juridique, force jugée) et une "démocratie véritable" (partage du pouvoir, participation citoyenne).
      • Démocratie environnementale : La Convention d'Aarhus (2005) est essentielle : "afin d'être en mesure de faire valoir ce droit et de s'acquitter de ce devoir, les citoyens doivent avoir accès à l'information, être habilité à participer au processus décisionnel et avoir accès à la justice en matière d'environnement". La participation du public conduit à "de meilleures décisions" et une "application plus efficace".
      • Planifications existantes et manque de systémique : De nombreuses planifications sectorielles existent depuis 50 ans (loi sur l'eau, l'air, déchets, etc.), souvent "robustes d'un point de vue juridique" et construites avec des "procédures participatives". Cependant, la planification écologique actuelle "manque aussi une vision systémique de la chose" en se focalisant trop sur le carbone au détriment des interdépendances (biodiversité, pollutions).
      • Besoin d'un débat social et d'un changement transformateur : Face à une "triple crise" (climatique, biodiversité, pollutions), il est urgent d'avoir un "débat social et sociétal global sur quel monde de demain on veut construire par rapport à ces scénarios qu'on nous propose". Les solutions exigent des "changements transformateurs profonds" et une "prise en compte de la dette écologique".
      • Backlash écologique et remises en cause : La période actuelle est marquée par un "backlash écologique" avec des "attaques sans précédent" contre les associations environnementales, la "remise en cause de la science", et une "criminalisation" de la contestation. L'État doit retrouver son "exemplarité sur la défense de l'État de droit" et assumer des décisions respectueuses de la légalité environnementale.

      4. Le Secteur de l'Assurance face aux Risques Climatiques (Perspective Économique)

      Florence Lustman, Présidente de France Assureurs, partage la vision des assureurs, à la fois gestionnaires de risques à long terme et acteurs de la réparation immédiate.

      • Augmentation et interdépendance des risques : Le risque climatique est perçu comme l'un des risques majeurs, partageant la première place avec le risque cyber dans leur cartographie. Il est un "risque maître" qui peut déclencher "40 % des autres risques", y compris la santé mentale (éco-anxiété).
      • Coût croissant des sinistres : Les coûts des sinistres climatiques sont en forte progression : la moyenne annuelle est passée de 1,5 milliard d'euros dans les années 1980 à 6 milliards d'euros sur les quatre premières années de la décennie en cours. L'année 2022 a coûté 10,6 milliards d'euros.
      • Projections futures : Le coût cumulé des sinistres climatiques pourrait doubler sur les 30 prochaines années (2020-2050), atteignant 143 milliards d'euros. Le risque de "retrait-gonflement des argiles" (sécheresse) est le "péril le plus dynamique", pouvant tripler son coût.
      • Régime "Catastrophes Naturelles" (CatNat) : La France bénéficie d'un régime CatNat "universel et solidaire" (partenariat public-privé) qui mutualise les risques et assure une couverture pour un coût modéré (passé de 25 à 40€ par an en moyenne). Ce système est unique en Europe et essentiel pour l'assurabilité des biens.
      • Levi- leviers d'action et domaines de progrès : Les assureurs ont des leviers d'action :
      • Réparation durable : Inciter à l'utilisation de matériaux recyclés et de pièces de réemploi, et développer des filières et des labels pour des réparations plus durables.
      • Prévention et résilience : Poursuivre les actions de prévention (SMS d'alerte, journée de la résilience), tester de nouvelles technologies pour l'amélioration de la résilience du bâti (initiative sécheresse), et encourager les plans de prévention des risques naturels au niveau des communes.
      • Investissement durable : Les assureurs gèrent 2500 milliards d'euros d'actifs, dont une grande partie finance les entreprises et les infrastructures, avec une part croissante dans les investissements durables. Des contraintes réglementaires limitent toutefois leur capacité à financer des projets moins rentables ou plus risqués.
      • Points de convergence et de tension :
      • Nécessité de la science et de l'anticipation : Tous les intervenants s'accordent sur l'importance des données scientifiques pour comprendre les phénomènes climatiques et anticiper leurs conséquences. La nécessité d'une "adaptation par anticipation" est soulignée par la climatologue et appuyée par les assureurs.
      • Temps long vs. Urgence : Un paradoxe est mis en lumière : les phénomènes climatiques évoluent sur le temps long, mais l'urgence des impacts actuels nécessite des actions immédiates. La planification doit intégrer ces deux échelles.
      • Interconnexion des crises : L'approche systémique est cruciale. La climatologue et le représentant de FNE soulignent que le climat ne peut être séparé de la biodiversité, de la santé, de l'eau et de l'alimentation. Les assureurs constatent également les interdépendances entre les risques.
      • Défi de la mise en œuvre et du financement : Malgré l'existence de plans et de stratégies, la traduction en actions concrètes et leur financement restent un défi majeur. La question de la rentabilité des investissements pour la transition est cruciale.
      • Place de la délibération et de la participation citoyenne : La nécessité d'une "démocratie environnementale" et d'un "débat social et sociétal" est fortement mise en avant par FNE, qui déplore le manque de véritable discussion sur des choix politiques majeurs. La frustration des citoyens est un risque si les processus participatifs ne sont pas clairs et respectés.
      • Responsabilité et redevabilité de l'État : FNE appelle à une plus grande "redevabilité" de l'action publique et à l'"exemplarité de l'État" dans le respect de la légalité environnementale.
      • Conflit et désinformation : La montée des "nouvelles conflictualités" liées au changement climatique, l'obstruction à l'action climatique et la désinformation représentent un défi majeur pour nos démocraties.
      • Questions en suspens et pistes de réflexion :
      • Optimisation du cadre juridique : Comment le cadre juridique peut-il mieux intégrer les scénarios climatiques les plus extrêmes et les plus récents pour guider l'aménagement du territoire et la dimension des infrastructures ?
      • Renforcement des mécanismes de suivi et d'évaluation : La mise en place d'un observatoire national des impacts et des pertes permettrait de mieux évaluer l'efficacité des politiques d'adaptation.
      • Innovation en financement : Comment développer des mécanismes de financement innovants (au-delà de la subvention) pour flécher l'épargne vers les investissements dans les transitions, en conciliant rentabilité et impact ?
      • Débat sur les "changements transformateurs" : Comment engager un véritable débat sociétal sur les choix fondamentaux nécessaires pour une transition écologique juste et efficace, en impliquant tous les acteurs ?
      • Articulation entre les différentes échelles : Comment mieux coordonner l'action entre le niveau national, européen et local, en respectant les spécificités biogéographiques des territoires ?
      • Défis de l'adaptation : Comment éviter la "maladaptation" et assurer que les solutions mises en œuvre ne créent pas de nouveaux risques à long terme, notamment en privilégiant les solutions fondées sur la nature ?
      • Éducation et connaissance de la nature : Comment restaurer une meilleure connexion et connaissance de la nature au sein de la société, des décideurs aux citoyens, pour fonder les décisions sur une compréhension plus juste des écosystèmes ?

      En conclusion, cette conférence a mis en évidence l'ampleur et la complexité des défis posés par l'urgence climatique. Si des outils et des stratégies sont en place, leur efficacité dépendra de la capacité à surmonter les tensions (entre temps long et court, entre objectifs sectoriels et systémiques, entre choix politiques et délibération citoyenne) et à mobiliser l'ensemble de la société autour d'une vision partagée et d'actions concrètes, en s'appuyant sur la science et en renforçant la démocratie environnementale.

    1. Author response:

      The following is the authors’ response to the original reviews.

      Reviewer #1 (Public review):

      Summary:

      The authors report a study on how stimulation of receptive-field surround of V1 and LGN neurons affects their firing rates. Specifically, they examine stimuli in which a grey patch covers the classical RF of the cell and a stimulus appears in the surround. Using a number of different stimulus paradigms they find a long latency response in V1 (but not the LGN) which does not depend strongly on the characteristics of the surround grating (drifting vs static, continuous vs discontinuous, predictable grating vs unpredictable pink noise). They find that population responses to simple achromatic stimuli have a different structure that does not distinguish so clearly between the grey patch and other conditions and the latency of the response was similar regardless of whether the center or surround was stimulated by the achromatic surface. Taken together they propose that the surround-response is related to the representation of the grey surface itself. They relate their findings to previous studies that have put forward the concept of an ’inverse RF’ based on strong responses to small grey patches on a full-screen grating. They also discuss their results in the context of studies that suggest that surround responses are related to predictions of the RF content or figure-ground segregation. Strengths:

      I find the study to be an interesting extension of the work on surround stimulation and the addition of the LGN data is useful showing that the surround-induced responses are not present in the feedforward path. The conclusions appear solid, being based on large numbers of neurons obtained through Neuropixels recordings. The use of many different stimulus combinations provides a rich view of the nature of the surround-induced responses.

      Weaknesses:

      The statistics are pooled across animals, which is less appropriate for hierarchical data. There is no histological confirmation of placement of the electrode in the LGN and there is no analysis of eye or face movements which may have contributed to the surround-induced responses. There are also some missing statistics and methods details which make interpretation more difficult.

      We thank the reviewer for their positive and constructive comments, and have addressed these specific issues in response to the minor comments. For the statistics across animals, we refer to “Reviewer 1 recommendations” point 1. For the histological analysis, we refer to “Reviewer 1 recommendations point 2”. For the eye and facial movements, we refer to “Reviewer 1 recommendations point 5”. Concerning missing statistics and methods details, we refer to various responses to “Reviewer 1 recommendations”. We thoroughly reviewed the manuscript and included all missing statistical and methodological details.

      Reviewer #2 (Public review):

      Cuevas et al. investigate the stimulus selectivity of surround-induced responses in the mouse primary visual cortex (V1). While classical experiments in non-human primates and cats have generally demonstrated that stimuli in the surround receptive field (RF) of V1 neurons only modulate activity to stimuli presented in the center RF, without eliciting responses when presented in isolation, recent studies in mouse V1 have indicated the presence of purely surround-induced responses. These have been linked to prediction error signals. In this study, the authors build on these previous findings by systematically examining the stimulus selectivity of surround-induced responses.

      Using neuropixels recordings in V1 and the dorsal lateral geniculate nucleus (dLGN) of head-fixed, awake mice, the authors presented various stimulus types (gratings, noise, surfaces) to the center and surround, as well as to the surround only, while also varying the size of the stimuli. Their results confirm the existence of surround-induced responses in mouse V1 neurons, demonstrating that these responses do not require spatial or temporal coherence across the surround, as would be expected if they were linked to prediction error signals. Instead, they suggest that surround-induced responses primarily reflect the representation of the achromatic surface itself.

      The literature on center-surround effects in V1 is extensive and sometimes confusing, likely due to the use of different species, stimulus configurations, contrast levels, and stimulus sizes across different studies. It is plausible that surround modulation serves multiple functions depending on these parameters. Within this context, the study by Cuevas et al. makes a significant contribution by exploring the relationship between surround-induced responses in mouse V1 and stimulus statistics. The research is meticulously conducted and incorporates a wide range of experimental stimulus conditions, providing valuable new insights regarding center-surround interactions.

      However, the current manuscript presents challenges in readability for both non-experts and experts. Some conclusions are difficult to follow or not clearly justified.

      I recommend the following improvements to enhance clarity and comprehension:

      (1) Clearly state the hypotheses being tested at the beginning of the manuscript.

      (2) Always specify the species used in referenced studies to avoid confusion (esp. Introduction and Discussion).

      (3) Briefly summarize the main findings at the beginning of each section to provide context.

      (4) Clearly define important terms such as “surface stimulus” and “early vs. late stimulus period” to ensure understanding.

      (5) Provide a rationale for each result section, explaining the significance of the findings.

      (6) Offer a detailed explanation of why the results do not support the prediction error signal hypothesis but instead suggest an encoding of the achromatic surface.

      These adjustments will help make the manuscript more accessible and its conclusions more compelling.

      We thank the reviewer for their constructive feedback and for highlighting the need for improved clarity regarding the hypotheses and their relation to the experimental findings.

      • We have strongly improved the Introduction and Discussion section, explaining the different hypotheses and their relation to the performed experiments.

      • In the Introduction, we have clearly outlined each hypothesis and its predictions, providing a structured framework for understanding the rationale behind our experimental design. • In the Discussion, we have been more explicit in explaining how the experimental findings inform these hypotheses.

      • We explicitly mentioned the species used in the referenced studies.

      • We provided a clearer rationale for each experiment in the Results section.

      We have also always clearly stated the species that previous studies used, both in the Introduction and Discussion section.

      Reviewer #3 (Public review):

      Summary:

      This paper explores the phenomenon whereby some V1 neurons can respond to stimuli presented far outside their receptive field. It introduces three possible explanations for this phenomenon and it presents experiments that it argues favor the third explanation, based on figure/ground segregation.

      Strengths:

      I found it useful to see that there are three possible interpretations of this finding (prediction error, interpolation, and figure/ground). I also found it useful to see a comparison with LGN responses and to see that the effect there is not only absent but actually the opposite: stimuli presented far outside the receptive field suppress rather than drive the neurons. Other experiments presented here may also be of interest to the field.

      Weaknesses:

      The paper is not particularly clear. I came out of it rather confused as to which hypotheses were still standing and which hypotheses were ruled out. There are numerous ways to make it clearer.

      We thank the reviewer for their constructive feedback and for highlighting the need for improved clarity regarding the hypotheses and their relation to the experimental findings.

      • We have strongly improved the Introduction and Discussion section, explaining the different hypotheses and their relation to the performed experiments.

      • In the Introduction, we have clearly outlined each hypothesis and its predictions, providing a structured framework for understanding the rationale behind our experimental design. • In the Discussion, we have been more explicit in explaining how the experimental findings inform these hypotheses.

      ** Recommendations for the Authors:**

      Reviewer #1 (Recommendations for the Authors):

      (1) Given the data is hierarchical with neurons clustered within 6 mice (how many recording sessions per animal?) I would recommend the use of Linear Mixed Effects models. Simply pooling all neurons increases the risk of false alarms.

      To clarify: We used the standard method for analyzing single-unit recordings, by comparing the responses of a population of single neurons between two different conditions. This means that the responses of each single neuron were measured in the different conditions, and the statistics were therefore based on the pairwise differences computed for each neuron separately. This is a common and standard procedure in systems neuroscience, and was also used in the previous studies on this topic (Keller et al., 2020; Kirchberger et al., 2023). We were not concerned with comparing two groups of animals, for which hierarchical analyses are recommended. To address the reviewer’s concern, we did examine whether differences between baseline and the gray/drift condition, as well as the gray/drift compared to the grating condition, were consistent across sessions, which was indeed the case. These findings are presented in Supplementary Figure 6.

      (2) Line 432: “The study utilized three to eight-month-old mice of both genders”. This is confusing, I assume they mean six mice in total, please restate. What about the LGN recordings, were these done in the same mice? Can the authors please clarify how many animals, how many total units, how many included units, how many recording sessions per animal, and whether the same units were recorded in all experiments?

      We have now clarified the information regarding the animals used in the Methods section.

      • We state that “We included female and male mice (C57BL/6), a total of six animals for V1 recordings between three and eight months old. In two of those animals, we recorded simultaneously from LGN and V1.”

      • We state that“For each animal, we recorded around 2-3 sessions from each hemisphere, and we recorded from both hemispheres.”

      • We noted that the number of neurons was not mentioned for each figure caption. We apologize for this omission. We have now added the number for all of the figures and protocols to the revised manuscript. We note that the same neurons were recorded for the different conditions within each protocol, however because a few sessions were short we recorded more units for the grating protocol. Note that we did not make statistical comparisons between protocols.

      (3) I see no histology for confirmation of placement of the electrode in the LGN, how can they be sure they were recording from the LGN? There is also little description of the LGN experiments in the methods.

      For better clarity, we have included a reconstruction of the electrode track from histological sections of one animal post-experiment (Figure S4). The LGN was targeted via stereotactical surgery, and the visual responses in this area are highly distinct. In addition, we used a flash protocol to identify the early-latency responses typical for the LGN, which is described in the Methods section: “A flash stimulus was employed to confirm the locations of LGN at the beginning of the recording sessions, similar to our previous work in which we recorded from LGN and V1 simultaneously (Schneider et al., 2023). This stimulus consisted of a 100 ms white screen and a 2 s gray screen as the inter-stimulus interval, designed to identify visually responsive areas. The responses of multi-unit activity (MUA) to the flash stimulus were extracted and a CSD analysis was then performed on the MUA, sampling every two channels. The resulting CSD profiles were plotted to identify channels corresponding to the LGN. During LGN recordings, simultaneous recordings were made from V1, revealing visually responsive areas interspersed with non-responsive channels.”

      (4) Many statements are not backed up by statistics, for example, each time the authors report that the response at 90degree sign is higher than baseline (Line 121 amongst other places) there is no test to support this. Also Line 140 (negative correlation), Line 145, Line 180.

      For comparison purposes, we only presented statistical analyses across conditions. However, we have now added information to the figure captions stating that all conditions show values higher than the baseline.

      (5) As far as I can see there is no analysis of eye movements or facial movements. This could be an issue, for example, if the onset of the far surround stimuli induces movements this may lead to spurious activations in V1 that would be interpreted as surround-induced responses.

      To address this point, we have included a supplementary figure analyzing facial movements across different sessions and comparing them between conditions (Supplementary Figure 5). A detailed explanation of this analysis has been added to the Methods section. Overall, we observed no significant differences in face movements between trials with gratings, trials with the gray patch, and trials with the gray screen presented during baseline. Animals exhibited similar face movements across all three conditions, supporting the conclusion that the observed neural firing rate increases for the gray-patch condition are not related to face movements.

      (6) The experiments with the rectangular patch (Figure 3) seem to give a slightly different result as the responses for large sizes (75, 90) don’t appear to be above baseline. This condition is also perceptually the least consistent with a grey surface in the RF, the grey patch doesn’t appear to occlude the surface in this condition. I think this is largely consistent with their conclusions and it could merit some discussion in the results/discussion section.

      While the effect is maybe a bit weaker, the total surround stimulated also covers a smaller area because of the large rectangular gray patch. Furthermore, the early responses are clearly elevated above baseline, and the responses up to 70 degrees are still higher than baseline. Hence we think this data point for 90 degrees does not warrant a strong interpretation.

      Minor points:

      (1) Figure 1h: What is the statistical test reported in the panel (I guess a signed rank based on later figures)? Figure 4d doesn’t appear to be significantly different but is reported as so. Perhaps the median can be indicated on the distribution?

      We explained that we used a signed rank test for Figure 1h and now included the median of the distributions in Figure 4d.

      (2) What was the reason for having the gratings only extend to half the x-axis of the screen, rather than being full-screen? This creates a percept (in humans at least) that is more consistent with the grey patch being a hole in the grating as the grey patch has the same luminance as the background outside the grating.

      We explained in the Methods section that “We presented only half of the x-axis due to the large size of our monitor, in order to avoid over-stimulation of the animals with very large grating stimuli.”. Perceptually speaking, the gray patch appears as something occluding the grating, not as a “hole”.

      (3) Line 103: “and, importantly, had less than 10degree sign (absolute) distance to the grating stimulus’ RF center.” Re-phrase, a stimulus doesn’t have an RF center.

      We corrected this to “We included only single units into the analysis that met several criteria in terms of visual responses (see Methods) and, importantly, the RF center had less than 10(absolute) distance to the grating stimulus’ center. ”.

      (4) Line 143: “We recorded single neurons LGN” - should be “single LGN neurons”.

      We corrected this to “we recorded single LGN neurons”.

      (5) Line 200: They could spell out here that the latency is consistent with the latency observed for the grey patch conditions in the previous experiments. (6) Line 465: This is very brief. What criteria did they use for single-unit assignation? Were all units well-isolated or were multi-units included?

      We clarified in the Methods section that “We isolated single units with Kilosort 2.5 (Steinmetz et al., 2021) and manually curated them with Phy2 (Rossant et al., 2021). We included only single units with a maximum contamination of 10 percent.”

      (7) Line 469: “The experiment was run on a Windows 10”. Typo.

      We corrected this to “The experiment was run on Windows 10”.

      (9) Line 481: “We averaged the response over all trials and positions of the screen”. What do they mean by ’positions of the screen’?

      We changed this to “We computed the response for each position separately right, by averaging the response across all the trials where a square was presented at a given position.”

      (9) Line 483: “We fitted an ellipse in the center of the response”. How?

      We additionally explain how we preferred the detection of the RF using an ellipse fitting: “A heatmap of the response was computed. This heatmap was then smoothed, and we calculated the location of the peak response. From the heatmap we calculated the centroid of the response using the function regionprops.m that finds unique objects, we then selected the biggest area detected. Using the centroids provided as output. We then fitted an ellipse centered on this peak response location to the smoothed heatmap using the MATLAB function ellipse.m.“

      (10) Line 485 “...and positioned the stimulus at the response peak previously found”. Unclear wording, do you mean the center of the ellipse fit to the MUA response averaged across channels or something else? (11) Line 487: “We performed a permutation test of the responses inside the RF detected vs a circle from the same area where the screen was gray for the same trials.”. The wording is a bit unclear here, can they clarify what they mean by the ’same trials’, what is being compared to what here?

      We used a permutation test to compare the neuron’s responses to black and white squares inside the RF to the condition where there was no square in the RF (i.e. the RF was covered by the gray background).

      (12) Was the pink noise background regenerated on each trial or as the same noise pattern shown on each trial?

      We explain that “We randomly presented one of two different pink noise images”

      (13) Line 552: “...used a time window of the Gaussian smoothing kernel from-.05 to .05”. Missing units.

      We explained that “we used a time window of the Gaussian smoothing kernel from -.05 s to .05 s, with a standard deviation of 0.0125 s.”

      (14) Line 565: “Additionally, for the occluded stimulus, we included patch sizes of 70 degree sign and larger.”. Not sure what they’re referring to here.

      We changed this to: “For the population analyses, we analyzed the conditions in which the gray patch sizes were 70 degrees and 90 degrees”.

      (15) Line 569: What is perplexity, and how does changing it affect the t-SNE embeddings?

      Note that t-SNE is only used for visualization purposes. In the revised manuscript, we have expanded our explanation regarding the use of t-SNE and the choice of perplexity values. Specifically, we have clarified that we used a perplexity value of 20 for the Gratings with circular and rectangular occluders and 100 for the black-and-white condition. These values were empirically selected to ensure that the groups in the data were clearly separable while maintaining the balance between local and global relationships in the projected space. This choice allowed us to visually distinguish the different groups while preserving the meaningful structure encoded in the dissimilarity matrices. In particular, varying the perplexity values would not alter the conclusions drawn from the visualization, as t-SNE does not affect the underlying analytical steps of our study.

      (16) Line 572: “We trained a C-Support Vector Classifier based on dissimilarity matrices”. This is overly brief, please describe the construction of the dissimilarity matrices and how the training was implemented. Was this binary, multi-class? What conditions were compared exactly?

      In the revised manuscript, we have expanded our explanation regarding the construction of the dissimilarity matrices and the implementation of the C-Support Vector Classification (C-SVC) model (See Methods section).

      The dissimilarity matrices were calculated using the Euclidean distance between firing rate vectors for all pairs of trials (as shown in Figure 6a-b). These matrices were used directly as input for the classifier. It is important to note that t-SNE was not used for classification but only for visualization purposes. The classifier was binary, distinguishing between two classes (e.g., Dr vs St). We trained the model using 60% of the data for training and used 40% for testing. The C-SVC was implemented using sklearn, and the classification score corresponds to the average accuracy across 20 repetitions.

      Reviewer #2 (Recommendations for the Authors):

      The relationship between the current paper and Keller et al. is challenging to understand. It seems like the study is critiquing the previous study but rather implicitly and not directly. I would suggest either directly stating the criticism or presenting the current study as a follow-up investigation that further explores the observed effect or provides an alternative function. Additionally, defining the inverse RF versus surround-induced responses earlier than in the discussion would be beneficial. Some suggestions:

      (1) The introduction is well-written, but it would be helpful to clearly define the hypotheses regarding the function of surround-induced responses and revisit these hypotheses one by one in the results section.

      Indeed, we have generally improved the Introduction of the manuscript, and stated the hypotheses and their relationships to the Experiments more clearly.

      (2) Explicitly mention how you compare classic grating stimuli of varying sizes with gray patch stimuli. Do the patch stimuli all come with a full-field grating? For the full-field grating, you have one size parameter, while for the patch stimuli, you have two (size of the patch and size of the grating).

      We now clearly describe how we compare grating stimuli of varying sizes with gray patch stimuli.

      (3) The third paragraph in the introduction reads more like a discussion and might be better placed there.

      We have moved content from the third paragraph of the Introduction to the Discussion, where it fits more naturally.

      (4) Include 1-2 sentences explaining how you center RFs and detail the resolution of your method.

      We have added an explanation to the Methods: “To center the visual stimuli during the recording session, we averaged the multiunit activity across the responsive channels and positioned the stimulus at the center of the ellipse fit to the MUA response averaged across channels.”.

      (5) Motivate the use of achromatic stimuli. This section is generally quite hard to understand, so try to simplify it.

      We explained better in the Introduction why we performed this particular experiment.

      (6) The decoding analysis is great, but it is somewhat difficult to understand the most important results. Consider summarizing the key findings at the beginning of this section.

      We now provide a clearer motivation at the start of the Decoding section.

      Reviewer #3 (Recommendations for the Authors):

      I have a few suggestions to improve the clarity of the presentation.

      Abstract: it lists a series of observations and it ends with a conclusion (“based on these findings...”). However, it provides little explanation for how this conclusion would arise from the observations. It would be more helpful to introduce the reasoning at the top and show what is consistent with it.

      We have improved the abstract of the paper incorporating this feedback.

      To some extent, this applies to Results too. Sometimes we are shown the results of some experiment just because others have done a similar experiment. Would it be better to tell us which hypotheses it tests and whether the results are consistent with all 3 hypotheses or might rule one or more out? I came out of the paper rather confused as to which hypotheses were still standing and which hypotheses were ruled out.

      We have strongly improved our explanation of the hypotheses and the relationships to the experiments in the Introduction.

      It would be best if the Results section focused on the results of the study, without much emphasis on what previous studies did or did not measure. Here, instead, in the middle of Results we are told multiple times what Keller et al. (2020) did or did not measure, and what they did or did not find. Please focus on the questions and on the results. Where they agree or disagree with previous papers, tell us briefly that this is the case.

      We have revised the Results section in the revised manuscript, and ensured that there is much less focus on what previous studies did in the Results. Differences to previous work are now discussed in the Discussion section.

      The notation is extremely awkward. For instance “Gc” stands for two words (Gray center) but “Gr” stands for a single word (Grating). The double meaning of G is one of many sources of confusion.

      This notation needs to be revised. Here is one way to make it simpler: choose one word for each type of stimulus (e.g. Gray, White, Black, Drift, Stat, Noise) and use it without abbreviations. To indicate the configuration, combine two of those words (e.g. Gray/Drift for Gray in the center and Drift in the surround).

      We have corrected the notation in the figures and text to enhance readability and improve the reader’s understanding.

      Figure 1e and many subsequent ones: it is not clear why the firing rate is shown in a logarithmic scale. Why not show it in a linear scale? Anyway, if the logarithmic scale is preferred for some reason, then please give us ticks at numbers that we can interpret, like 0.1,1,10,100... or 0.5,1,2,4... Also, please use the same y-scale across figures so we can compare.

      To clarify: it is necessary to normalize the firing rates relative to baseline, in order to pool across neurons. However such a divisive normalization would be by itself problematic, as e.g. a change from 1 to 2 is the same as a change from 1 to 0.5, on a linear scale. Furthermore such division is highly outlier sensitive. For this reason taking the logarithm (base 10) of the ratio is an appropriate transformation. We changed the tick labels to 1, 2, 4 like the reviewer suggested.

      Figure 3: it is not clear what “size” refers to in the stimuli where there is no gray center. Is it the horizontal size of the overall stimulus? Some cartoons might help. Or just some words to explain.

      Figure 3: if my understanding of “size” above is correct, the results are remarkable: there is no effect whatsoever of replacing the center stimulus with a gray rectangle. Shouldn’t this be remarked upon?

      We have added a paragraph under figure 3 and in the Methods section explaining that the sizes represent the varying horizontal dimensions of the rectangular patch. In this protocol, the classical condition (i.e. without gray patch) was shown only as full-field gratings, which is depicted in the plot as size 0, indicating no rectangular patch was present.

      DETAILS The word “achromatic” appears many times in the paper and is essentially uninformative (all stimuli in this study are achromatic, including the gratings). It could be removed in most places except a few, where it is actually used to mean “uniform”. In those cases, it should be replaced by “uniform”.

      Ditto for the word “luminous”, which appears twice and has no apparent meaning. Please replace it with “uniform”.

      We have replaced the words achromatic and luminous with “uniform” stimuli to improve the clarity when we refer to only black or white stimuli.

      Page 3, line 70: “We raise some important factors to consider when describing responses to only surround stimulation.” This sentence might belong in the Discussion but not in the middle of a paragraph of Results.

      We removed this sentence.

      Neuropixel - Neuropixels (plural)

      “area LGN” - LGN

      We corrected for misspellings.

      References

      Keller, A.J., Roth, M.M., Scanziani, M., 2020. Feedback generates a second receptive field in neurons of the visual cortex. Nature 582, 545–549. doi:10.1038/s41586-020-2319-4.

      Kirchberger, L., Mukherjee, S., Self, M.W., Roelfsema, P.R., 2023. Contextual drive of neuronal responses in mouse V1 in the absence of feedforward input. Science Advances 9, eadd2498. doi:10. 1126/sciadv.add2498.

      Rossant, C., et al., 2021. phy: Interactive analysis of large-scale electrophysiological data. https://github.com/cortex-lab/phy.

      Schneider, M., Tzanou, A., Uran, C., Vinck, M., 2023. Cell-type-specific propagation of visual flicker. Cell Reports 42.

      Steinmetz, N.A., Aydin, C., Lebedeva, A., Okun, M., Pachitariu, M., Bauza, M., Beau, M., Bhagat, J., B¨ohm, C., Broux, M., Chen, S., Colonell, J., Gardner, R.J., Karsh, B., Kloosterman, F., Kostadinov, D., Mora-Lopez, C., O’Callaghan, J., Park, J., Putzeys, J., Sauerbrei, B., van Daal,R.J.J., Vollan, A.Z., Wang, S., Welkenhuysen, M., Ye, Z., Dudman, J.T., Dutta, B., Hantman, A.W., Harris, K.D., Lee, A.K., Moser, E.I., O’Keefe, J., Renart, A., Svoboda, K., H¨ausser, M., Haesler, S., Carandini, M., Harris, T.D., 2021. Neuropixels 2.0: A miniaturized high-density probe for stable, long-term brain recordings. Science 372, eabf4588. doi:10.1126/science.abf4588.

    1. Reviewer #3 (Public review):

      Smit and Robbins' manuscript investigates the dynamics of aggression among female groupmates across five gorilla groups. The authors utilize longitudinal data to examine how reproductive state, group size, presence of males, and resource availability influence patterns of aggression and overall dominance rankings as measured by Elo scores. The findings underscore the important role of group composition and reproductive status, particularly pregnancy, in shaping dominance relationships in wild gorillas. While the study addresses a compelling and understudied topic, I have several comments and suggestions that may enhance clarity and improve the reader's experience.

      (1) Clarification of longitudinal data - The manuscript states that 25 years of behavioral data were used, but this number appears unclear. Based on my calculations, the maximum duration of behavioral observation for any one group appears to be 18 years. Specifically: - ATA: 6 years - BIT: 8 years - KYA: 18 years - MUK: 6 years - ORU: 8 years I recommend that the authors clarify how the 25-year duration was derived.

      (2) Consideration of group size - The authors mention that group size was excluded from analyses to avoid conflating the opposing effects of female and male group members. While this is understandable, it may still be beneficial to explore group size effects in supplementary analyses. I suggest reporting statistics related to group size and potentially including a supplementary figure. Additionally, given that the study includes both mountain and wild gorillas, it would be helpful to examine whether any interspecies differences are apparent.

      (3) Behavioral measures clarification - Lines 112-116 describe the types of aggressive behaviors observed. It would be helpful to clarify how these behaviors differ from those used to calculate Elo scores, or whether they overlap. A brief explanation would improve transparency regarding the methodology.

      (4) Aggression rates versus Elo scores - The manuscript uses aggression rates rather than dominance rank (as measured by Elo scores) as the main outcome variable, but there is no explanation on why. How would the results differ if aggression rates were replaced or supplemented with Elo scores? The current justification for prioritizing aggression rates over dominance rank needs to be more clearly supported.

    2. Author response:

      Public Reviews:

      Reviewer #1 (Public review):

      Summary:

      This work aims to improve our understanding of the factors that influence female-on-female aggressive interactions in gorilla social hierarchies, using 25 years of behavioural data from five wild groups of two gorilla species. Researchers analysed aggressive interactions between 31 adult females, using behavioural observations and dominance hierarchies inferred through Elo-rating methods. Aggression intensity (mild, moderate, severe) and direction (measured as the rank difference between aggressor and recipient) were used as key variables. A linear mixed-effects model was applied to evaluate how aggression direction varied with reproductive state (cycling, trimester-specific pregnancy, or lactation) and sex composition of the group. This study highlights the direction of aggressive interactions between females, with most interactions being directed from higher- to lower-ranking adult females close in social rank. However, the results show that 42% of these interactions are directed from lower- to higher-ranking females. Particularly, lactating and pregnant females targeted higher-ranking individuals, which the authors suggest might be due to higher energetic needs, which increase risk-taking in lactating and pregnant females. Sex composition within the group also influenced which individuals were targeted. The authors suggest that male presence buffers female-on-female aggression, allowing females to target higher-ranking females than themselves. In contrast, females targeted lower-ranking females than themselves in groups with a larger ratio of females, which supposes a lower risk for the females since the pool of competitors is larger. The findings provide an important insight into aggression heuristics in primate social systems and the social and individual factors that influence these interactions, providing a deeper understanding of the evolutionary pressures that shape risk-taking, dominance maintenance, and the flexibility of social strategies in group-living species.

      The authors achieved their aim by demonstrating that aggression direction in female gorillas is influenced by factors such as reproductive condition and social context, and their results support the broader claim that aggression heuristics are flexible. However, some specific interpretations require further support. Despite this, the study makes a valuable contribution to the field of behavioural ecology by reframing how we think about intra-sexual competition and social rank maintenance in primates.

      Strengths:

      One of the study's major strengths is the use of an extensive dataset that compiles 25 years of behavioural data and 6871 aggressive interactions between 31 adult females in five social groups, which allows for a robust statistical analysis. This study uses a novel approach to the study of aggression in social groups by including factors such as the direction and intensity of aggressive interactions, which offers a comprehensive understanding of these complex social dynamics. In addition, this study incorporates ecological and physiological factors such as the reproductive state of the females and the sex composition of the group, which allows an integrative perspective on aggression within the broader context of body condition and social environment. The authors successfully integrate their results into broader evolutionary and ecological frameworks, enriching discussions around social hierarchies and risk sensitivity in primates and other animals.

      Thank you for the positive assessment of our work and the nice summary of the manuscript!

      Weaknesses:

      Although the paper has a novel approach by studying the effect of reproductive state and social environment on female-female aggression, the use of observational data without experimental manipulation limits the ability to establish causation. The authors suggest that the difference observed in female aggression direction between groups with different sex composition might be indicative of male presence buffering aggression, which seems speculative, as no direct evidence of male intervention or support was reported. Similarly, the use of reproductive state as a proxy for energetic need is an indirect measure and does not account for actual energy expenditure or caloric intake, which weakens the authors' claims that female energetic need induces risk-taking. Overall, this paper would benefit from stronger justification and empirical support to strengthen the conclusions of the study about the mechanisms driving female aggression in gorillas.

      We agree that experimental manipulation would allow us to extend our work. Unfortunately, this is not possible with wild, endangered gorillas.

      We have now added more references (Watts 1994; Watts 1997) and enriched our arguments regarding male presence buffering aggression. Previous research suggests that male gorillas may support lower-ranking females and they may intervene in female-female conflicts (Sicotte 2002). Unfortunately, our dataset did not allow us to test for male protection. We conduct proximity scans every 10 minutes and these scans are not associated to each interaction, meaning that we cannot reliably test if proximity to a male influence the likelihood to receive aggression.

      We have now clearly stated that reproductive state is an indirect proxy for energetic needs. We agree with your point about energy intake and expenditure, but unfortunately, we do not have data on energy expenditure or caloric intake to allow us to delve into more fine-grained analyses.

      Overall, we have tried to enrich the justification and empirical support to strengthen our conclusions by clarifying the text and adding more examples and references.

      Reviewer #2 (Public review):

      Summary:

      The authors' aim in this study is to assess the factors that can shift competitive incentives against higher- or lower-ranking groupmates in two gorilla species.

      Strengths:

      This is a relevant topic, where important insights could be gained. The authors brought together a substantial dataset: a long-term behavioral dataset representing two gorilla species from five social groups.

      Weaknesses:

      The authors have not fully shown the data used in the model and explored the potential of the model. Therefore, I remain cautious about the current results and conclusions.

      Some specific suggestions that require attention are

      (1) The authors described how group size can affect aggression patterns in some species (line 54), using a whole paragraph, but did not include it as an explanation variable in their model, despite that they stated the overall group size can "conflate opposing effects of females and males" (line 85). I suggest underlining the effects of numbers of males or/and females here and de-emphasizing the effect of group size in the Introduction.

      We did not use group size as a main predictor, as has been commonly done in other species, because of potentially conflating opposing effects of males and females. To further stress this point, we have specifically added in the introduction: “group size, the overall number of individuals in the group, might not be a good predictor of aggression heuristics, as it can conflate the effects of different kinds of individuals on aggression (see Smit & Robbins 2024 for an example of opposing effects of the number of females and number of males on female gorilla aggression).”

      We also “ran our analysis testing for group size (number of weaned individuals in the group), instead of the numbers of females and males, [and] its influence on interaction score was not significant (estimate=-0.001, p-value=0.682).”

      (2) There should be more details given about how the authors calculated individual Elo-ratings (line 98). It seems that authors pooled all avoidance/displacement behaviors throughout the study period. But how often was the Elo-rating they included in the model calculated? By the day or by the month? I guess it was by the day, as they "estimate female reproductive state daily" (line 123). If so, it should be made clear in the text.

      We rephrased accordingly: “We used all avoidance and displacement interactions throughout the study period and we used the function elo.seq from R package EloRating to infer daily individual female Elo-scores”. We also clarified that “This method takes into account the temporal sequence of interactions and updates an individual’s Elo-scores each day the individual interacted with another...”

      In addition, all groups were long-term studied, and the group composition seems fluctuant based on the Table 1 in Reference 11. When an individual enters/leaves the group with a stable hierarchy, it takes time before the hierarchy turns stable again. If the avoidance/displacement behaviors used for the rank relationship were not common, it would take a few days or maybe longer. Also, were the aggressive behaviors more common during rank fluctuations? In other words, if avoidance/displacement behaviors and aggressive behaviors occur simultaneously during rank fluctuations, how did the authors deal with it and take it into consideration in the analysis?

      We have shown in Reference 25 (Smit & Robbins 2025) after Reference 11 (Smit & Robbins 2024) that females form highly stable hierarchies, and that dyadic dominance relationships are not influenced by dispersal or death of third individuals. Notably, new immigrant females usually start at and remain low ranking, without large fluctuations in rank. Therefore, the presence of any fluctuation periods have limited influence in the aggressive interactions in our study system.

      The authors emphasized several times in the text that gorillas "form highly stable hierarchical relationships". Also, in Reference 25, they found very high stabilities of each group's hierarchy. However, the number of females involved in that analysis was different from that used here. They need to provide more basic info on each group's dominance hierarchy and verify their statement. I strongly suggest that the authors display Elo-rating trajectories and necessary relevant statistics for each group throughout the study period as part of the supplementary materials.

      In fact, the females involved in the present analysis and the analysis of Smit & Robbins 2025 are the same. Our present analysis is based on the hierarchies of Smit & Robbins 2025. Note that female gorillas disperse and occasionally immigrate to another study group. This is why some females may appear in the hierarchies of more than one group, giving the impression that there are more females involved in the analysis of Smit & Robbins 2025 (e.g. by counting the lines in the Elo-rating plots). We now specifically state that “We present these interactions and hierarchies in detail in Smit & Robbins 2025”, to clarify that the hierarchies are the same.

      (3) The authors stated why they differentiated the different stages based on female reproductive status. They also referred to the differences in energetic needs between stages of pregnancy and lactation (lines 127-128). However, in the mixed model, they only compared the interaction score between the female cycling stage and other stages. The model was not well explained, and the results could be expanded. I suggest conducting more pairwise comparisons in the model and presenting the statistics in the text, if there are significant results. If all three pregnancy stages differed significantly from cycling and lactating stages but not from each other, they may be merged as one pregnancy stage. More in-depth analysis would help provide better answers to the research questions.

      Thank you for pointing this out. First, when we considered one pregnancy stage, pregnant females showed indeed a significantly greater interaction score than females in other reproductive stages. We have now included that in the manuscript. However, we still find relevant to test for the different stages of pregnancy, given the difference of energetic needs in these stages. We have now included the pairwise comparisons in a new table (Table 2).

      Reviewer #3 (Public review):

      Smit and Robbins' manuscript investigates the dynamics of aggression among female groupmates across five gorilla groups. The authors utilize longitudinal data to examine how reproductive state, group size, presence of males, and resource availability influence patterns of aggression and overall dominance rankings as measured by Elo scores. The findings underscore the important role of group composition and reproductive status, particularly pregnancy, in shaping dominance relationships in wild gorillas. While the study addresses a compelling and understudied topic, I have several comments and suggestions that may enhance clarity and improve the reader's experience.

      (1) Clarification of longitudinal data - The manuscript states that 25 years of behavioral data were used, but this number appears unclear. Based on my calculations, the maximum duration of behavioral observation for any one group appears to be 18 years. Specifically:

      • ATA: 6 years

      • BIT: 8 years

      • KYA: 18 years

      • MUK: 6 years

      • ORU: 8 years

      I recommend that the authors clarify how the 25-year duration was derived.

      Indeed none of the five study “groups” has been studied for 25 years in a row. However, MUK emerged from a fission of group KYA in early 2016. So, from the start of group KYA in October 1998 to the end of group MUK in December 2023, there are 25 years and 2 months. We have now rephrased to “...starting in 1998 in one of the mountain gorilla groups” in the introduction, and to “We use a long-term behavioural dataset on five wild groups of the two gorilla species, starting in 1998” in the abstract.

      (2) Consideration of group size - The authors mention that group size was excluded from analyses to avoid conflating the opposing effects of female and male group members. While this is understandable, it may still be beneficial to explore group size effects in supplementary analyses. I suggest reporting statistics related to group size and potentially including a supplementary figure. Additionally, given that the study includes both mountain and wild gorillas, it would be helpful to examine whether any interspecies differences are apparent.

      We have now added the suggested extra test: “When we ran our analysis testing for group size (number of weaned individuals in the group), instead of the numbers of females and males, its influence on interaction score was not significant (estimate=-0.001, p-value=0.682).”

      Regarding species differences: In our analysis, we test for species (mountain vs western) and we find no significant differences between the two. This is stated in the results.

      (3) Behavioral measures clarification - Lines 112-116 describe the types of aggressive behaviors observed. It would be helpful to clarify how these behaviors differ from those used to calculate Elo scores, or whether they overlap. A brief explanation would improve transparency regarding the methodology.

      We now added short explanations into brackets for behaviours that are not obvious. We also added a sentence in the text to clarify the difference with the behaviours used to calculate Elo scores: “These two behaviours [avoidance and displacement] are ritualized, occurring in absence of aggression, they are considered a more reliable proxy of power relationships over aggression, and they are typically used to infer gorilla hierarchical relationships”.

      (4) Aggression rates versus Elo scores - The manuscript uses aggression rates rather than dominance rank (as measured by Elo scores) as the main outcome variable, but there is no explanation on why. How would the results differ if aggression rates were replaced or supplemented with Elo scores? The current justification for prioritizing aggression rates over dominance rank needs to be more clearly supported.

      The sentence we added above (“These two behaviours [avoidance and displacement] are ritualized, occurring in absence of aggression, they are considered a more reliable proxy of power relationships over aggression, and they are typically used to infer gorilla hierarchical relationships”) and the first paragraph of the results hopefully clarify that ritualized agonistic interactions are generally directionally consistent and more reliably capture the highly stable dominance relationships of female gorillas. This approach has been used to calculate dominance rank in gorillas in all studies that have considered it, dating back to the 1970s (namely in studies by Harcourt and Watts). On the other hand, aggression can be context dependent (we now clearly note that in the beginning of the Methods paragraph on aggressive interactions). Therefore, we use Eloscores inferred from ritualized interactions as base and a reliable proxy of power relationships; then we test if the direction of aggression within these relationships is driven also by energetic needs or the social environment.

    1. Compte Rendu Détaillé : Le Handicap et l'École Inclusive en France

      Ce document est un compte rendu détaillé des thèmes principaux et des faits marquants abordés lors d'un débat radiophonique sur France Culture, intitulé "Handicap : l'école est-elle la clé de l'inclusion ?".

      Les intervenantes,

      • Sonia Ainou (Première Vice-présidente de l'UNAPEI),
      • Servane Hug (Députée, co-présidente du groupe d'étude handicap et inclusion) et
      • Isabelle Keval (Philosophe, professeure des universités à l'INSEI),

      explorent les défis et les perspectives de l'inclusion des élèves en situation de handicap dans le système éducatif français.

      1. La Loi de 2005 et la Réalité de l'Inclusion

      La discussion s'ouvre sur le constat que, malgré la loi de 2005 affirmant le droit de chaque enfant à une scolarisation en milieu ordinaire, la réalité est loin d'être satisfaisante.

      Une étude récente de la Fédération UNAPEI révèle que "3/4 des enfants en situation de handicap n'ont pas accès à une scolarité normale, 23 % d'entre eux n'ayant même aucune heure de scolarisation par semaine."

      Ce chiffre contraste avec l'annonce présidentielle de 430 000 élèves handicapés scolarisés à la dernière rentrée, soulevant la question de la "qualité de l'accueil de ces élèves."

      2. Définition et Ambivalence de l'École Inclusive

      Les intervenantes s'accordent sur l'idée que l'expression "école inclusive" devrait être redondante, car l'école, par essence et mission, se doit d'être inclusive.

      Isabelle Keval : "Déjà, l'école inclusive, c'est une expression qui devrait être redondante parce que l'école dans ses textes, dans son histoire et dans ses missions, elle est inclusive.

      Or, dans la réalité des faits, comme on vient de l'entendre et comme le rappelle de nombreuses enquêtes chaque année à la rentrée, elle ne l'est pas. Voilà. Donc, l'école inclusive, c'est une école qui accueille tout le monde."

      Sonia Ainou : L'école inclusive est "celle qui permet d'accueillir tous les élèves quel qu'ils soient, qu'ils s'appuient sur les leviers sur lesquels ils peuvent progresser, gagner en autonomie et c'est celle qui va mettre en œuvre tous les moyens et les ressources nécessaires pour que l'élève puisse rentrer dans les apprentissages, grandir comme tous les autres élèves parmi tout le monde."

      Servane Hug met l'accent sur la "l'accessibilité pédagogique des pratiques des enseignants" comme levier essentiel pour une réelle inclusion.

      Une difficulté soulignée par Isabelle Keval est l'ambivalence inhérente à la notion d'inclusion : "la difficulté de l'inclusion, c'est qu'au fond, dans la notion, il y a cette ambivalence que pour pouvoir inclure, il faut pouvoir identifier et que dès lors qu'on identifie, on risque de stigmatiser."

      3. La "Jungle de Sigles" et la Nécessité de Dispositifs Adaptés

      Le vocabulaire complexe (dispositifs d'autorégulation, professeurs ressources, unités d'enseignement, Ulis, AESH, MDPH) est évoqué.

      Sonia Ainou clarifie que ces termes désignent les diverses formes d'accompagnement nécessaires aux élèves ayant des besoins spécifiques : "c'est que cet élève-là a besoin qu'on intervienne de façon plus ou moins intensive auprès de lui parce qu'il a des des compétences, mais on a besoin d'accompagner ses compétences, de les renforcer.

      Ça peut être des aides humaines comme les AESH, mais ça peut aussi être des aides techniques. Ça peut être aussi un aménagement pédagogique par l'enseignant. Ça peut être la formation des AESH."

      4. Le Rôle Crucial de la Formation des Enseignants et la Coopération Médico-Sociale

      Les trois intervenantes s'accordent sur le fait que l'augmentation du nombre d'accompagnants (AESH) ne suffit pas.

      Le point central de l'avancement vers une école réellement inclusive réside dans la formation des enseignants et une coopération renforcée entre le monde médico-social et l'Éducation Nationale.

      Servane Hug insiste sur la nécessité pour les enseignants de "se rendre compte aujourd'hui que accueillir un enfant en situation de handicap dans sa classe, ce n'est pas essayer de faire disparaître la différence mais au contraire c'est de se de de de rendre accessible ces pratiques."

      Elle ajoute : "je crois que c'est c'est sur ça qu'il faut appuyer, c'est cette coopération entre les enseignants et les professionnels du médico-social, les éducateurs, ce qui permettra réellement, je pense, une avancée." Isabelle Keval corrobore en pointant un "déficit de formation" dans le cursus des enseignants, soulignant l'augmentation des demandes de formation continue sur ces questions à l'INSEI.

      Cette appréhension des enseignants est liée à la "variété de handicap" et aux "résistances des parents des autres enfants".

      5. Les Chiffres et les Avancées Gouvernementales

      • Servane Hug défend l'action gouvernementale, mentionnant un budget de "3 milliards 8 d'euros en 2022" pour le handicap, soit une augmentation de "36 % depuis 2017".

      Elle souligne le déploiement des "unités d'enseignement externalisé" et les futurs "dispositifs intégrés médico-éducatifs (DIY)" d'ici 2027, visant à prendre en charge les enfants polyhandicapés ou "lourdement handicapés" qui ne peuvent actuellement pas intégrer l'école ordinaire.

      Cependant, Sonia Ainou tempère en affirmant qu'il ne s'agit pas d'une "amélioration" mais plutôt d'"engagements" et d'"annonces", et que la plateforme marentree.org continue de recueillir de nombreux témoignages d'enfants sans solution de scolarisation.

      Le manque de places en établissements spécialisés reste criant, avec "12000 enfants qui n'ont pas de place".

      6. L'Accessibilité au-delà du Technique : Sociale et Intellectuelle

      Isabelle Keval élargit la notion d'accessibilité au-delà de la simple installation de rampes ou ascenseurs.

      Pour elle, l'accessibilité doit aussi être "développé au niveau social, sociétal, intellectuel dans le regard qu'on porte sur les enfants en situation de handicap".

      Il s'agit de les considérer comme des "sujets, des personnes qui ont la possibilité de choisir quelque chose, de décider", plutôt que de les stigmatiser par un "fléchage" technique.

      7. L'Inclusion Hors Scolaire et la Communauté d'Expérience

      Le débat explore également l'importance de l'inclusion dans les activités extrascolaires. Servane Hug ne croit pas que l'école soit "l'outil ultime de l'inclusion" en raison de l'attente de performances cognitives.

      Elle suggère d'investir les centres de loisirs, les colonies, et les activités sportives et artistiques, où les enfants n'ont pas à s'évaluer les uns les autres.

      Sonia Ainou renchérit en affirmant qu'il faut "saisir tous les leviers dans tous les lieux de vie et d'apprentissage des enfants", car l'école est la "porte d'entrée de l'avenir", mais l'endossement du statut d'élève se fait aussi "dans les temps hors scolaires."

      Isabelle Keval insiste sur la "similarité d'expérience" comme levier d'inclusion, en utilisant des contextes comme l'eau ou l'air où les différences s'estompent au profit d'un point commun : "ce que nous partageons c'est l'eau. Voilà.

      Et nous avons là un point commun. Nous sommes deux humains dans ce milieu aquatique."

      L'objectif est de viser l'"universel" et non de "continuer à distinguer ceux qui sont dehors et ceux qui sont dedans."

      8. Le Cas Belge : Un Modèle de Coopération

      Servane Hug, dans le cadre de sa mission d'information parlementaire, a étudié le modèle belge.

      Elle note que "1500 enfants sont aujourd'hui accueillis en Belgique" faute de solutions en France. La réussite belge s'explique par un "renforcement entre la coopération éducation nationale en Belgique et professionnel du médico-social."

      En Belgique, les éducateurs sortent des IME et il y a l'équivalent d'une unité d'enseignement externalisée par groupe scolaire.

      Sonia Ainou questionne pourquoi la France finance ces départs plutôt que d'investir dans une transformation du système national.

      9. Les Freins et la "Plasticité" du Système

      Les freins à l'inclusion sont multiples : les résistances des parents d'autres élèves, l'appréhension des professionnels, et la difficulté de modifier les habitudes. Isabelle Keval introduit le concept de "plasticité" : l'école inclusive et la société inclusive ne sont pas des touts déjà constitués dans lesquels on essaie de faire rentrer un élément.

      Il s'agit plutôt d'"adapter ce système, le faire changer pour que finalement il y ait plus de cette frontière".

      Sonia Ainou utilise le terme d'"agilité" pour décrire la capacité du système à répondre à toute forme de vulnérabilité.

      Elle insiste sur la nécessité de faire travailler ensemble tous les acteurs (collectivités, financeurs, professionnels de l'éducation nationale, AESH, cuisiniers, professionnels médico-sociaux et libéraux), avec une attention particulière aux personnes concernées et aux familles, qui doivent être des "acteurs principaux".

      10. Conclusion : Un Long Chemin à Parcourir Le débat se termine sur la reconnaissance du "long chemin à parcourir" pour atteindre une inclusion véritable.

      La "plasticité" et l'"agilité" du système, la formation continue des enseignants, et une coopération intersectorielle sont identifiées comme les clés de cette transformation.

      Servane Hug, en tant que députée, s'engage à œuvrer pour un "changement de paradigme" lors du prochain projet de loi de financement.

      L'objectif ultime est de donner à tous les enfants en situation de handicap une "véritable chance [...] de rentrer dans les apprentissages et dans la vie tout simplement."

    1. Dossier de briefing : Faire face à l'inceste et au silence

      Source : Extraits de "France Inter - Faire face à l'inceste 16173-13.10.2021-ITEMA_22805012-2021F26104S0286-22.mp3"

      Thèmes Principaux et Idées Essentielles

      Ce briefing aborde la problématique de l'inceste en France, en soulignant l'ampleur du phénomène, les mécanismes du silence qui l'entourent, les conséquences dévastatrices pour les victimes et les voies de prévention et de réparation.

      1. L'ampleur de l'inceste et la conspiration du silence

      • Prévalence alarmante : Selon un sondage Ipsos, un Français sur 10 déclare avoir été victime d'inceste.

      Cependant, Bruno Clavier, psychanalyste et psychologue clinicien, estime que ce chiffre est largement sous-estimé en raison du déni et de l'amnésie des victimes. Il suggère que le chiffre réel pourrait être de trois à quatre personnes sur dix. * Le silence comme arme : Le silence est décrit comme une "arme de destruction massive" érigée par les agresseurs, entraînant de graves dégâts collatéraux. Ce silence est imposé par les abuseurs et les violeurs, qui sont dans l'écrasante majorité des hommes. * Complicité sociétale : La société est interrogée sur sa complicité dans cette "conspiration du silence".

      Charlotte Pudlovski, cofondatrice de Louis Media, souligne que la société a longtemps ignoré ou minimisé le problème, comme en témoignent les réticences des médias à aborder le sujet avant des événements médiatisés.

      • Amnésie et déni : Bruno Clavier met en lumière deux types de silence encore plus profonds : le déni (refuser la réalité des faits) et l'amnésie (oubli total des événements traumatiques).

      L'amnésie est particulièrement fréquente chez les victimes, et peut durer des décennies, le cerveau cherchant à se protéger de la violence. Certains patients disent même : "Si je me souviens, je meurs."

      2. Le traumatisme et ses conséquences

      • Mémoire traumatique : L'inceste est décrit comme un "crime qui défigure des enfances", laissant une "mémoire traumatique tatouée dans le corps et l'esprit", une "onde choc qui bouleverse toute une vie".
      • Difficulté à nommer l'innommable : Grégoire de la Cour, écrivain, explique la difficulté de "mettre des mots sur des choses qu'on ne peut pas formuler quand on est très petit". Les mots comme "abus", "attouchement", "violence sexuelle" "cisaillent la bouche".
      • Honte et culpabilité de la victime : Les victimes se demandent souvent si c'est de leur faute, pourquoi la personne qui devait les aimer le plus a pu les détruire. "On a peur de pas être recueilli, de pas être accueilli avec nos chagrins, avec nos souillures. Et alors, on se tait. Et puis il y a la honte, cette honte de nous-même."
      • Conséquences physiques et psychiques : L'inceste est un "fléau de santé publique" avec des conséquences très graves sur le psychisme et le corps. On observe des souffrances psychiques importantes, des addictions, des tentatives de suicide, des scarifications.

      Grégoire de la Cour témoigne de douleurs physiques inexpliquées (mal au ventre pendant 55 ans) dues à ce traumatisme.

      Le corps devient un "pire ennemi", un "traître", dont on a honte. Bruno Clavier compare les violences sexuelles à une "déflagration", un "incendie" qui brûle les circuits nerveux et laisse des "traces multiples" invisibles aux médecins.

      • Le rôle des mères : La réaction des mères est un point sensible.

      Beaucoup de victimes leur en veulent d'abord pour ne pas les avoir protégées. Cependant, les experts soulignent que ces mères ont souvent elles-mêmes été victimes d'abus, reproduisant un "formatage" familial du silence. "Elles donnent la soupe qu'elles ont mangé."

      3. La libération de la parole et les défis persistants

      • Libération progressive mais fragile : Charlotte Pudlovski observe une "véritable libération" de la parole ces dernières années, notamment après la sortie du livre de Camille Kouchner, "La Familia Grande". Cependant, elle craint un "recommencement permanent" et le retour du silence, un "backlash" du féminisme.
      • La question du recueil de la parole : Goénal Boulet, journaliste, insiste sur l'importance de savoir accueillir la parole des victimes. "La double punition c'est quand on a réussi à parler et qu'on n'est pas entendu ou que notre parole elle va dans les limbes de on ne sait quelle justice qui n'a pas le temps de le traiter."
      • Le déni institutionnel : Eva Thomas, première personne à témoigner à visage découvert à la télévision en 1986, exprime son découragement face aux politiques qui ne s'emparent pas suffisamment du sujet. Elle raconte avoir été sollicitée pour une commission sur la protection de l'enfance, où la première chose demandée était "de ne pas en parler tout de suite", symbolisant la persistance du silence institutionnel.

      4. Prévention et chemins de réparation

      • Prévention précoce : Bruno Clavier souligne l'importance de la prévention dès l'âge de 4 ans, moment où les enfants sont dans la découverte sexuelle. Jenny, une victime, témoigne de l'importance d'avoir été éduquée très jeune par son père sur comment réagir face à ce type d'événements, ce qui lui a permis de comprendre et d'agir lors de son agression.
      • Rôle des parents : Les parents doivent affronter le sujet calmement, parler à leurs enfants de leur corps, des gestes autorisés ou non, et de la notion de "bon" ou "mauvais" secret. Il s'agit de ne pas paniquer mais de faire preuve de vigilance, en ouvrant le dialogue et en autorisant la parole de l'enfant.
      • La guérison comme réparation : La guérison n'est pas totale, mais la réparation est possible. Grégoire de la Cour parle de "reprendre possession de qui j'allais être". Il faut "redresser ce corps de traviol" et apprendre à "rendre gracieux notre boîtement pour rester humain".
      • Thérapies multiples et temps long : Bruno Clavier compare les victimes à des "grands brûlés" ou des "grands accidentés de la route", nécessitant "plusieurs thérapies" et "beaucoup de temps". Des outils comme l'EMDR, l'hypnose, ou même des activités physiques (escrime) sont mentionnés pour gérer les émotions.
      • L'importance de l'amour et de la reconnaissance : L'amour est un facteur essentiel de réparation. Charlotte Pudlovski insiste sur le fait que "des cicatrices restent mais que c'est pas une condamnation au malheur". L'amour peut être une "réparation formidable", même si le concept d'amour est rendu problématique par la nature même de l'inceste.
      • Numéro d'aide : Le 119 est un numéro destiné aux victimes d'abus sexuel sur mineur.
    1. Compte rendu détaillé : "Y a-t-il une culture de l'inceste en France ?" (France Culture, 12.10.2022)

      • Ce compte rendu explore les thèmes principaux et les idées essentielles abordées lors du débat sur France Culture, en s'appuyant sur les propos des intervenants.

      L'émission, en se basant sur le rapport de la CIVISE (Commission Indépendante sur l'Inceste et les Violences Sexuelles), questionne l'existence d'une "culture de l'inceste" en France, remettant en cause le mythe du tabou anthropologique et soulignant la réalité omniprésente de ces violences.

      1. L'ampleur et la sous-estimation de l'inceste en France

      Le débat s'ouvre sur un chiffre choc issu du rapport de la CIVISE : "160 000 enfants subissent des violences sexuelles chaque année en France."

      Ce chiffre, longtemps "sous-estimé voire complètement négligé", contredit l'idée reçue d'un tabou anthropologique sur ce crime.

      Au contraire, les enquêtes récentes montrent que "ce crime touche un français ou une française sur 10 et est présent dans toutes les classes sociales."

      • Juliette Drouard, thérapeute et co-directrice de l'ouvrage collectif "La culture de l'inceste", cite cette phrase percutante : "s'il est tabou de dire l'inceste, il n'est pas tabou de le faire."

      Cette affirmation résume la dissonance entre la perception publique de l'inceste comme un interdit absolu et sa réalité fréquente et dissimulée.

      Édouard Duran, juge des enfants et co-président de la CIVISE, confirme que "16 500 personnes sont venues [à la CIVISE], nous ont fait confiance [...] toutes nous disent cela, que les violences commencent quelques jours après la naissance ou qu'elles durent jusqu'à la majorité ou au-delà de la majorité." Il insiste sur le fait que "la maison est pour beaucoup le lieu du danger, de la confrontation à la terreur et à la mort même."

      2. Le mythe du tabou anthropologique et la réalité de la "culture de l'inceste"

      • Juliette Drouard et les autres auteurs de "La culture de l'inceste" remettent en question la notion de tabou suprême héritée de l'anthropologie classique (notamment Claude Lévi-Strauss).

      Ils affirment que cette idée, véhiculée par des "anthropologues depuis leur position située, c'est-à-dire d'hommes blancs qui sont arrivés sans vouloir parler de violence sexuelle mais simplement en voulant étudier les règles du mariage", a conforté le silence autour de l'inceste.

      Pour eux, le concept de tabou du mariage "n'a rien à voir avec les pratiques d'inceste. Marier ou pas marier avec certaines personnes, ça n'empêche pas d'incester ces certaines personnes."

      Le terme de "culture de l'inceste" est utilisé dans plusieurs sens par Juliette Drouard :

      • Un phénomène propre à l'espèce humaine : contrairement aux animaux, les humains utilisent la sexualité pour la domination.
      • Une culture spécifique au sein des cultures humaines : cela se produit dans certaines sociétés, mais "il n'est pas nécessaire pour les êtres humains pour vivre et pour exister ou pour fonder une culture d'agresser sexuellement d'autres personnes."
      • Les productions culturelles : celles-ci "vont soutenir la systématicité de l'inceste en permettant de ne pas le parler en tant que violence sexuelle."

      Elles peuvent "romantiser l'inceste comme dans Game of Thrones avec le frère, la sœur" ou, comme dans le porno, où le "stepmom" est un hashtag très recherché.

      D'autres œuvres "n'adoptent pas le point de vue de la victime" ou reprennent des mythes comme celui de Lolita, où "ce serait la personne victime qui vient séduire l'agresseur."

      3. L'évolution historique et juridique de la perception de l'inceste

      Julie Doyon, historienne, apporte un éclairage diachronique sur la question. Elle souligne que l'inceste, dans l'Ancien Régime, était "beaucoup dit, montré, écrit" dans la littérature et était un crime considéré comme tel dans la doctrine pénale.

      Cependant, il n'était "pas du tout la même signification qu'aujourd'hui.

      C'est-à-dire qu'il n'est pas indexé à une forme de violence ni spécifiquement à la catégorie de l'enfance." L'inceste était alors un "crime sans victime.

      Un crime avec deux coupables", considéré comme un crime de mœurs et de péché entre personnes apparentées.

      Le "point de bascule" se situe entre le 18e et le 19e siècle, où l'inceste passe d'une conception de "couple incestueux" à celle d'"acte d'agression sexuelle commis par un adulte sur un enfant dans le cadre familial."

      La Révolution française, en voulant séculariser le droit pénal, a supprimé le crime d'inceste, le considérant comme relevant de la sphère religieuse et de la "vie privée".

      Aujourd'hui, Édouard Duran déplore cette persistance de l'idée que "la maison est éminemment essentiellement le lieu du privé."

      Il insiste sur la nécessité que "ce qui doit régner dans la maison, c'est la loi commune et pas la loi d'un seul, pas la loi du dominant."

      4. La spécificité de la violence incestueuse et la vulnérabilité des enfants

      Édouard Duran insiste sur la vulnérabilité des enfants : "les agresseurs recherchent toujours une proie en raison de sa vulnérabilité.

      Et l'enfant parmi les êtres vulnérables dans la société est le plus vulnérable et parmi les enfants vulnérables, il y a les enfants handicapés, plus vulnérables et plus invisibilisés encore."

      • Il récuse l'argument souvent avancé par les agresseurs : "Je n'ai jamais entendu en audience, en cours d'assise, au tribunal correctionnel ou au tribunal pour enfants un agresseur dire autre chose que c'est l'enfant qui m'a séduit." Édouard Duran refuse de "chercher à comprendre" dans le sens de "chercher dans la psychologie de l'agresseur ce qui pourrait l'excuser." Pour lui, l'impératif moral est de "mettre en sécurité les enfants victimes d'inceste et les personnes victimes de violence."

      • Juliette Drouard souligne l'importance de parler de "pédocriminalité de manière générale", car "les adultes qui commettent des agressions sur des enfants, les commettent aussi bien sur leurs enfants que sur les enfants des autres."

      Elle met en évidence une "communauté de traumatisme" et de destruction pour toutes les victimes, avec seulement une "différence de degré dans l'échelle de la trahison éthologique" selon Sortnaf.

      Édouard Duran, citant Christine Ang, décrit l'inceste comme un "crime absolument spécifique, un crime contre l'humanité du sujet, un crime généalogique."

      Il explique que "en venant à elle sexuellement, il se refuse à elle comme père.

      C'est une humiliation sociale avant tout par laquelle l'enfant n'a plus de place dans l'histoire des humains."

      Il n'y a "pas d'amour dans l'inceste," comme le souligne Juliette Drouard : "L'excitant ça n'est pas l'amour mais le pouvoir et les fractions."

      5. Le silence, la prescription et la difficile écoute de la parole des victimes

      Le silence est présenté comme un facteur mortifère : "Ce qui tue c'est le silence. C'est de ne pas parler. C'est de ne pas dire, de ne pas pouvoir dire."

      L'extrait du documentaire "Inceste, le dire et l'entendre" illustre le ressenti des victimes : "On t'a juste dit que l'agression sexuelle c'est dehors que ça se passe.

      C'est des étrangers qui peuvent t'attaquer. C'est des étrangers. C'est jamais dedans la famille. Et que tu pressens, tu ressens que quand il t'arrive un truc à l'intérieur de la famille, il faut fermer sa gueule."

      La question de la prescription est abordée. Le ministre de la Justice, Éric Dupond-Moretti, évoque l'allongement du délai de 20 à 30 ans à compter de la majorité depuis 2018.

      Édouard Duran souligne l'importance de cet allongement, car les traumatismes générés par ces violences "ne sont pas cachés dans un passé lointain.

      C'est un présent perpétuel qui s'immisce dans toutes les sphères de l'existence, des plus sociales au plus intimes." Il insiste sur "l'aspiration profonde à ce que justice soit rendue."

      L'expression d'Iris Bray, "Mon corps est une archive vivante de mon inceste," résonne avec cette idée de persistance du traumatisme.

      Malgré une apparente "libération de la parole" dans l'espace public, Juliette Drouard et Édouard Duran soulignent que le tabou reste "absolu" là où l'inceste a lieu.

      Seulement "1000 condamnations" pour "160 000 enfants victimes de violence sexuelle chaque année" révèlent un "système d'impunité des agresseurs."

      Les enfants n'ont pas les outils pour décrire ce qui leur arrive et sont souvent "tués ou resilenciés" lorsqu'ils parlent.

      Édouard Duran révèle que "dans 9 cas sur 10, le confident de l'enfant ne fait rien." Le processus de "silenciation" est au cœur de la stratégie de l'agresseur, qui vise à "imposer le silence à l'enfant victime" et à "contaminer le groupe."

      Julie Doyon nuance l'idée d'un silence absolu en soulignant l'existence de moments passés où l'inceste a été discuté publiquement, comme la fin des années 1980 avec les "dossiers de l'écran."

      Elle insiste sur le fait que le vrai problème n'est peut-être "pas tant de le parler que de l'entendre."

      Elle met en lumière les dynamiques complexes au sein des familles, où le "silence familial n'est pas un bloc monolithique" et où les rôles et statuts des individus influencent la manière dont la parole circule ou est étouffée.

      Conclusion

      Le débat met en lumière une réalité complexe et souvent douloureuse de l'inceste en France.

      Loin d'être un tabou universellement respecté, il est une violence omniprésente, souvent dissimulée par des mécanismes de silence, d'impunité et une certaine "culture" qui minimise ou romantise la souffrance des victimes.

      Les intervenants appellent à une meilleure compréhension historique, juridique et sociétale de l'inceste, une protection accrue des enfants victimes, et une capacité collective à écouter et croire la parole de ceux qui osent briser le silence.

      Numéro de téléphone Inceste : 0805 802 804 (anonyme et gratuit)

    1. Compte Rendu Détaillé : "La culture de l'inceste" sur France Inter

      • Ce document de synthèse analyse les thèmes principaux et les idées clés abordées lors de l'émission de France Inter intitulée "France inter Iris Brey et Juliet Drouar: existe-t-il une culture de l'inceste", diffusée le 8 septembre 2022. L'émission présente l'ouvrage collectif "La culture de l'inceste", un livre rouge décrit comme un "traité, un manifeste, un brûlot", co-écrit par Iris Brey, Juliette Drouar, Sorna Fal, Wendy de Lorn, Dorothée Dussy, Tal Piter Bro Merx et Ovidi.

      1. L'Inceste : Non une Déviance Individuelle, mais un Phénomène Culturel et Systémique

      Le thème central de l'émission et de l'ouvrage est la remise en question de la vision traditionnelle de l'inceste comme une "déviance, d'exception pathologiques, de monstres à la marge".

      Au contraire, les invitées soutiennent que l'inceste est un phénomène "massif" et "systématique" ancré au "cœur même de notre organisation sociale".

      • Statistiques Éffarantes et Témoignages Affluents : Les statistiques sont présentées comme "effarantes", avec "une personne sur 10 en France" victime d'inceste, ce qui représente "7 millions de victimes". Cette ampleur remet en question la notion d'exception.
      • De l'Individu au Système : Iris Brey et Juliette Drouar insistent sur le fait que "les monstres, ça n'existe pas.

      C'est notre société, c'est nous, c'est nos amis, c'est nos pères. C'est ça qu'on doit regarder." La responsabilité est ainsi déplacée de l'individu "monstrueux" vers le collectif et le système social. * Continuité avec la Culture du Viol : Juliette Drouar explique que le terme "culture de l'inceste" est décalqué de l'expression "culture du viol", visant à souligner un aspect "culturel" et non une "exception, une pathologie, une monstruosité". * L'Inceste comme Outil de Domination Patriarcale : L'ouvrage postule que l'inceste est "une expression, c'est une reconduction d'un fonctionnement social qui s'appuie sur l'idée de domination". Iris Brey affirme que c'est un "système qui est mis en place pour que le corps des enfants et que le corps des femmes continue à être dominé par le patriarcat et par les hommes". Les agresseurs, à 76% des hommes, se sentent "autorisé[s] partout et depuis toujours" à agresser le corps "le plus faible".

      2. Le Tabou de l'Inceste : Ne pas Parler, Plutôt que Ne pas Exister

      Les auteures déconstruisent l'idée reçue selon laquelle l'inceste serait un interdit social fondamental.

      Elles affirment que l'inceste n'est pas un tabou dans sa pratique, mais plutôt un tabou dans sa discussion et sa reconnaissance.

      • Critique de Lévi-Strauss : Le célèbre anthropologue Claude Lévi-Strauss est cité pour sa conception de l'interdit de l'inceste comme "socle du contrat social". Cependant, Juliette Drouar rectifie que Lévi-Strauss parlait de l'interdit du mariage avec certains membres de la famille, et non de l'interdit des violences sexuelles. Elle ajoute : "on peut tout à fait se ne pas se marier avec certains membres de sa famille et les violer."
      • L'Omerta et l'Inaccessibilité de la Pensée : Iris Brey souligne l' "omerta et une impossibilité de penser ça" qui rend même les textes de chercheurs sur l'inceste "pas disponibles".
      • Les Enfants Parlent, les Parents n'Entendent pas : Le véritable tabou n'est pas le silence des enfants victimes – "les enfants en parlent" – mais plutôt l'incapacité des adultes à les entendre : "C'est que les parents ne veulent pas entendre ou ne peuvent pas entendre."

        1. La Condition de l'Enfant et le Mythe de la Famille Protectrice

      L'ouvrage met en lumière la vulnérabilité intrinsèque des enfants dans le système social et familial, où leur dépendance est naturalisée et leurs droits sont "déprivés".

      • L'Enfant comme Catégorie Sociale Constituée : Le livre, notamment à travers l'article de Tal Piter Bro Merx, introduit l'idée que les "enfants sont pas une catégorie qui est les mineurs en tout cas sont pas une catégorie naturelle. C'est une catégorie qui a été constituée". Cette catégorie est "complètement déprivée de droit et posé dans une position d'absolue dépendance par rapport aux adultes et leur famille."
      • Privation de Droits et de Crédibilité : Les enfants sont "privé[s] de paroles, privé[s] de crédibilité, privé[s] d'individualité, privé[s] de légitimité". Cette condition de "dépendance matérielle", d'absence de droit de vote ou de représentation, crée les "meilleures conditions pour pouvoir disposer des corps de l'autre".
      • La Famille, Lieu de Risque et non de Protection Naturelle : Contrairement au "mythe qui entoure la famille qui serait extrêmement bienveillante, extrêmement chaleureuse" et "naturellement protect[rice]", les études concordent : "c'est très majoritairement au sein de la famille qu'on lieu ces violences et ses abus sexuels."

      4. Représentations Médiatiques et Culturelles de l'Inceste : Banalisation et Distorsion

      Une part importante de la discussion est consacrée à la manière dont l'inceste est représenté ou non représenté dans la culture populaire, contribuant à sa banalisation et à la culpabilisation des victimes.

      • Le "Séisme Médiatique" et le #MeToo Inceste : Les auteures reviennent sur l'impact des témoignages de personnalités comme Vanessa Springora, Camille Kouchner et Adèle Haenel. Le #MeToo Inceste en France a commencé par des récits de violences sexuelles dans l'enfance, impliquant des "femmes mais aussi d'hommes et aussi de lesbienne, de personnes gay, de personnes trans", comme Mathieu Fouchet avec le #MeToo gay.
      • L'Héritage de "Lolita" : Iris Brey analyse le film de Kubrick, "Lolita", comme une "bascule" culturelle. Le terme "Lolita" est passé dans l'imaginaire collectif, rendant la "jeune fille ... responsable du fait que son beau-père ait envie de coucher avec elle". L'image iconique de Lolita avec ses lunettes en cœur, bien que non issue du film, a contribué à "infuser dans toute la culture populaire" l'idée que l'inceste est "érisé" et souvent imputé à la victime.

      Elle rappelle que la Lolita de Nabokov était "une enfant violée par son beau-père". * Distorsion des Représentations de l'Inceste :Inceste père-fille : Souvent présenté avec la culpabilisation de la jeune fille. * Inceste mère-fils : Souvent "montré comme une démarche d'émancipation, comme une relecture du d'Œdipe". * Inceste frère-sœur : Bien que les plus rares dans la réalité, ils sont "montrés beaucoup dans les séries et notamment dans Game of Thrones comme quelque chose d'érotisé et de normal". * L'Inceste et le Pornographie Grand Public : Ovidi (co-auteure) et Juliette Drouar abordent l'infiltration de l'inceste dans le porno grand public, notamment via le mythe de la "MILF" (Mother I'd Like to F***) qui a évolué vers la "Stepmom" (belle-mère) comme hashtag principal.

      Ce phénomène, initialement américain, s'est "très largement diffusé", banalisant une "représentation érotisée de l'inceste" où les violences sont déniées au profit d'une sexualisation "sexy" et "fun".

      Les auteures déplorent que ces représentations "ne représente[nt] jamais l'inceste comme un acte de violence et de domination".

      5. Une Lutte Collective pour une Pensée Collective

      L'écriture de ce livre est présentée comme une "lutte, un combat", rendue possible uniquement par un effort collectif.

      • Nécessité du Collectif : Iris Brey a eu l'idée du livre en lisant un article de Juliette Drouar sur "la culture de l'inceste" mais ne voulait pas "déplier" ce terme seule. Le collectif était essentiel pour "pousser nos propres réflexions" et pour "se soutenir" face à un sujet "difficile". La "pensée collective est pour moi la seule solution pour qu'on mette les mains un peu dans le camboui et qu'on réfléchisse à qu'est-ce qu'on fait maintenant".
      • Implication Personnelle des Auteures : Iris Brey ouvre l'ouvrage en se présentant comme victime d'inceste, soulignant l'importance de comprendre "d'où je parle" pour les lecteurs.

      Le suicide de Tal Piter Bro Merx pendant l'écriture du livre témoigne de l'épreuve que représente l'engagement sur ce sujet, même dans une approche théorique.

      En conclusion, "La culture de l'inceste" est un ouvrage politique et théorique qui vise à déconstruire les mythes entourant l'inceste, le présentant non pas comme un fait divers isolé, mais comme un symptôme d'un système de domination patriarcale et d'une invisibilisation de la vulnérabilité et des droits des enfants.

      L'émission met en lumière la nécessité d'une prise de conscience collective et d'une relecture critique des représentations culturelles pour démanteler ce système.

    1. Note de Synthèse : Réussite à l'École, Réussite de l'École

      Cette note de synthèse analyse les thèmes principaux et les idées ou faits les plus importants extraits des interventions du Conseil économique, social et environnemental (CESE) sur le sujet de la réussite à l'école et la réussite de l'école.

      Elle met en lumière les constats, les défis et les préconisations du CESE et des différents groupes de la société civile.

      1. Le CESE : Rôle, Composition et Missions

      Le CESE est présenté comme la troisième assemblée citée dans la Constitution française, après l'Assemblée Nationale et le Sénat.

      Il est composé de 175 conseillers et conseillères, désignés pour 5 ans par des organisations représentatives de la société civile (entreprises, syndicats, associations, ONG, organisations étudiantes, mouvements de jeunesse, etc.).

      C'est un "mini France réunie dans un hémicycle où tous les points de vue se rencontrent", un des rares endroits où "des chasseurs peuvent discuter et débattre avec des défenseurs des oiseaux".

      Ses quatre missions principales sont :

      • Conseiller et éclairer le gouvernement et le Parlement dans l'élaboration des politiques publiques.
      • Favoriser le dialogue social et la recherche d'un consensus exigeant.
      • Contribuer à évaluer l'efficacité des politiques publiques.
      • Prendre le pouls des régions en lien constant avec les CESE régionaux.
      • Une mission cruciale du CESE est de renforcer la démocratie participative, en permettant aux citoyens de faire entendre leur voix. Cela se concrétise par des méthodes participatives telles que le tirage au sort de citoyens, l'organisation de conventions citoyennes, et les consultations en ligne. Les citoyens peuvent directement saisir le CESE via une pétition qui, si elle recueille plus de 150 000 signatures (dès 16 ans), doit être étudiée par le Conseil. Des exemples concrets de préconisations du CESE ayant eu un impact incluent la Garantie Jeune et les dispositifs d'alerte pour lutter contre les violences faites aux femmes.

      2. Le Contexte Politique Actuel et l'Urgence de Faire Entendre la Voix de la Société Civile

      Plusieurs interventions soulignent le contexte politique troublé en France, marqué par la dissolution de l'Assemblée nationale et la montée de l'extrême droite.

      La société civile organisée exprime une vive inquiétude face à cette situation, considérant l'arrivée de l'extrême droite au pouvoir comme un "véritable danger pour notre démocratie et pour le monde du travail".

      Les craintes exprimées incluent :

      • La remise en cause du dialogue social et des syndicats.
      • La suppression des subventions aux associations.
      • Une liberté de la presse menacée.
      • Des discriminations basées sur le principe de "préférence nationale" dans les entreprises, administrations et écoles.
      • L'abandon ou la privatisation des services publics.
      • Le recul des droits des femmes.
      • La CFDT, la CGT, l'UNSA, le groupe des associations et le groupe santé et citoyenneté appellent à la mobilisation et au vote pour faire "tout sauf l'extrême droite". La CGT, tout en affirmant son indépendance, soutient l'appel à voter pour le nouveau programme du Front Populaire, dénonçant le Rassemblement National comme une "imposture électoraliste" qui a toujours défendu "les intérêts des plus riches et des multinationales". Les associations mettent en garde contre la suppression des subventions et l'utilisation d'outils de restriction associative.

      Le bureau du CESE insiste sur la nécessité de mieux associer la société civile à l'action publique, estimant que "la mécanique de nos institutions s'est rigidifiée et a fini par faire perdre la culture du dialogue et du débat".

      Le CESE se positionne comme un "lieu de résistance par le respect des divergences et des différences" et un "lieu de recueil de toutes les voix des espoirs et des préoccupations".

      3. L'École Française : Constats d'Inégalités et Défis

      Le CESE aborde en profondeur le sujet de l'école, reconnaissant son rôle fondamental dans la République.

      Malgré un budget important et un taux d'alphabétisation et d'éducation sans précédent, l'école française "peine à faire réussir tous les jeunes". Plusieurs constats alarmants sont mis en évidence :

      • Inégalités scolaires persistantes : L'école française est "un des plus inégalitaires d'Europe", ne parvenant pas à "enrayer la reproduction sociale".

      La corrélation entre les inégalités scolaires et sociales est forte : "le facteur essentiel de la difficulté scolaire et de l'échec scolaire provient des inégalités sociales".

      L'enquête PISA montre que "l'école française réussit aux élèves les plus favorisés". 30% des élèves issus de milieux populaires sont en difficulté.

      • Filiarisation ségrégative : 70% des enfants d'ouvriers obtiennent un bac professionnel ou technologique, contre 75% des enfants de cadres qui obtiennent un bac général. Seuls 2% des ouvriers sont étudiants à l'École Polytechnique.
      • Manque de moyens et conditions de travail difficiles : Les témoignages d'enseignantes de Marseille soulignent des locaux dégradés ("peinture arrachée, fissures dans les murs, chauffage défectueux, présence de cafards"), un sentiment d'être "oublié, seul sans moyen", et un rôle multiple des enseignants ("professeur, psychologue, assistante sociale, infirmier, médecin, médiateur social, orthophoniste et parfois même policiers").
      • Manque d'attractivité du métier d'enseignant : Formation "baclée", diplôme "dévalorisé", peu d'inspections, évolution de salaire non basée sur le mérite, absence de médecine du travail.
      • Problèmes d'adaptation et de stabilité : Les élèves témoignent de "changements soudains" dans les programmes et les modalités d'examen (bac), d'une "charge de travail trop chargée", et d'un apprentissage souvent basé sur la mémorisation plutôt que la compréhension. L'école est perçue comme "impersonnelle" et ne s'intéresse pas toujours à ce qui est bon pour l'élève.
      • Manque de mixité sociale : La ségrégation socio-résidentielle se reflète dans les établissements scolaires, amplifiée par la possibilité d'échapper à la sectorisation via le privé ou des stratégies résidentielles. Les familles "fuient le quartier" et la mixité sociale se réduit.
      • Spécificités des Outre-mer : Confrontés à une forte croissance démographique, des difficultés d'accès à l'école, des sorties précoces du système scolaire, un taux d'illettrisme élevé (double de la moyenne nationale aux Antilles et à la Réunion, 5 à 7 fois plus élevé en Guyane et à Mayotte), et des déficits d'infrastructures.

      4. Philosophie de la Réussite : De l'Égalité des Chances à la Réussite de Tous

      Le CESE prône un changement de paradigme, passant du concept d'«égalité des chances» à celui de la «réussite de toutes et tous».

      • L'égalité des chances est jugée une "promesse trompeuse" car elle ne garantit pas l'effectivité du droit à l'éducation, renvoyant les difficultés à la responsabilité individuelle de l'élève (vision méritocratique).
      • La réussite de toutes et tous implique que l'école "ne s'arrête pas avec la fin de la scolarité", et que "un niveau d'éducation élevé a un impact sur le revenu des personnes tout au cours de la leur carrière" (Éric Morin : "une année supplémentaire d'étude apporte 14% de revenus en plus"). L'équité et la performance sont liées : "les systèmes éducatifs les plus équitables... sont également les plus performants".
      • Faire réussir tous les élèves est bénéfique non seulement pour l'individu, mais aussi pour la "cohésion sociale, notre démocratie et notre économie".

      5. Axes de Préconisations du CESE

      Le projet d'avis du CESE s'articule autour de quatre axes majeurs :

      A. Redéfinir les finalités de l'école et mieux articuler l'ensemble des politiques publiques

      Préconisation 1 : Organiser un grand débat démocratique pour clarifier et redéfinir collectivement les finalités de l'école. L'école a été historiquement construite pour former une élite, non pour faire réussir tous les élèves. Préconisation 15 : Améliorer la concertation et l'articulation des politiques publiques complémentaires (logement, transport, santé, culture, sport) qui concourent à l'éducation, car "l'école seule n'arrivera pas à faire de l'égalité".

      B. Favoriser l'égalité et la mixité dans les territoires

      • Préconisation 5 : Mettre en place des observatoires de la mixité sociale et scolaire et de la réussite éducative pour diagnostiquer et recommander des actions.
      • Préconisation 4 : Agir sur la ségrégation scolaire par un plan pluriannuel pour une réelle mixité sociale inter et intra-établissements (publics et privés), avec un objectif de réduction des écarts d'indices de position sociale (IPS).
      • Préconisation 7 : Engager l'enseignement privé dans cette dynamique de mixité par un contrat d'objectifs et de moyens.
      • Spécificités Outre-mer (Préconisation 9) : Donner aux recteurs davantage de marges d'adaptation, créer des réseaux d'échange, faciliter l'accès à la langue française, développer l'offre post-bac sur place, et améliorer les conditions de vie des élèves (bâtiments, restauration scolaire).

      C. Conforter les acteurs de la communauté éducative et en priorité les élèves

      • Reconnaître et entendre les élèves : Les témoignages d'élèves soulignent le besoin de stabilité, de méthodes d'apprentissage basées sur la compréhension, et de prise en compte de la santé mentale et de la diversité. "L'école de mes rêves ce serait une école où la santé mentale des élèves passerait avant leur réussite scolaire".
      • Préconisation 10 : Organiser une concertation pour améliorer le bien-être des élèves et leurs conditions de scolarisation.
      • Préconisation 8 : Étendre les fonds sociaux élèves de l'école primaire au lycée et en faciliter le recours.
      • Préconisation 11 : Faire un bilan des pratiques de la vie démocratique au sein des écoles pour la renforcer.
      • Rôle des parents : L'importance du rôle des parents est soulignée, car l'élève apprend mieux s'il y a un partage de la nécessité d'apprendre entre l'école et la famille.
      • Préconisation 14 : Renforcer la place des parents à l'école via des "espaces parents".

      D. Transformer l'école et conforter le rôle des personnels

      • Revaloriser le métier d'enseignant : La "qualité des enseignants est le premier levier d'amélioration de l'efficacité des systèmes d'éducation".
      • Préconisation 12 et 13 : Mettre l'accent sur la formation initiale et continue des enseignants pour s'adapter à la diversité des élèves et rompre avec les logiques discriminantes.
      • Préconisation 19 : Voter une loi de programmation et de revalorisation des rémunérations des enseignants.
      • Renforcer les équipes : Augmenter le nombre d'assistants sociaux, infirmières, médecins, psychologues scolaires, etc.
      • Liberté pédagogique : Doit être préservée et exercée dans le cadre du projet d'école.
      • Utilisation de la technologie : Les élèves suggèrent l'utilisation des téléphones pour une meilleure adaptation aux nouvelles technologies.

      6. Perspectives et Appel à l'Action

      Le CESE insiste sur l'urgence d'un message positif et d'espoir pour les jeunes. L'école est vue comme un "moyen pour chacun et chacune de se construire, de s'émanciper, de surmonter ses difficultés, de grandir, d'apprendre, d'imaginer le monde de demain pour faire société ensemble".

      Malgré des réserves de certains groupes (entreprises, agriculture) sur des points spécifiques (financement, applicabilité de certaines mesures, pertinence de redéfinir les finalités pour l'agriculture), le projet d'avis "Réussite à l'école, réussite de l'école" a été adopté avec 97 voix pour, 1 contre et 23 abstentions.

      Le CESE s'engage à porter et prolonger cet avis, réaffirmant son rôle d'assemblée de combat et de solution face aux défis sociaux et éducatifs.

    1. Note de synthèse détaillée : Vivre dans les Territoires Ruraux

      Date : 19 juin 2024 Sujet : Synthèse des thèmes majeurs et faits marquants de l'événement "Vivre dans les territoires ruraux" organisé par la Commission Territoire, Agriculture et Alimentation.

      Introduction

      • La séance plénière consacrée à l'événement "Vivre dans les territoires ruraux" a mis en lumière la place centrale et souvent sous-estimée des zones rurales dans l'identité, l'économie et l'avenir de la France et de l'Europe.

      Loin d'être une "diagonale du vide uniforme", ces territoires regorgent d'initiatives et sont essentiels pour relever les défis sociétaux actuels et futurs. Cette réunion a permis de confronter des analyses sociologiques historiques et contemporaines aux témoignages concrets d'acteurs de terrain, offrant une vision nuancée des défis et des opportunités.

      1. La Ruralité : Une Entité Complexe et en Évolution

      Historiquement perçue comme un résidu voué à l'uniformisation face à l'urbanisation, la ruralité a connu une "disparition des écrans radars des politiques publiques nationales" avant de revenir au cœur du débat public, notamment avec la crise des gilets jaunes et la crise sanitaire.

      Évolution Sociologique et Démographique :

      • Déclin de la population agricole : La population agricole est devenue minoritaire dans l'essentiel des espaces ruraux français.
      • Popularisation des campagnes : Les mondes ouvriers et employés sont de plus en plus surreprésentés en dehors des villes. "On est tout l'inverse, les mondes ouvriers sont surreprésentés en dehors des villes."
      • Diversité des ruralités : Au lieu d'une ruralité unique, il existe une "très grande diversité" de territoires ruraux (productivistes, industriels, récréatifs, gentrifiés, balnéaires, naturels protégés).
      • Flux de population et multirésidentialité : Une part croissante de la population est multirésidentielle, ce qui rend la définition de "rural" complexe. Les flux immobiliers montrent une tendance à l'accumulation d'espaces de travail et de récréation, notamment dans les zones côtières et montagneuses.
      • Ségrégation sociale : Plutôt qu'une simple distinction urbain/rural, le territoire se structure de plus en plus par des "territoires de classe supérieure et des territoires de classe populaire". Ces dynamiques créent des "conflictualités de plus en plus fortes" entre usages récréatifs et productifs des espaces.

      Enjeux et Attributs des Territoires Ruraux :

      • Rôle central dans les défis sociétaux : La ruralité est "au cœur des enjeux de notre société", notamment pour répondre aux enjeux environnementaux (réchauffement climatique, biodiversité, transition énergétique) et de souveraineté alimentaire et de réindustrialisation.
      • Atouts intrinsèques : Cadre de vie, grands espaces, nature préservée, qualité de vie (air pur, faible délinquance, éducation protectrice), dimension humaine (proximité avec les acteurs locaux), valeurs (travail, respect).
      • Opportunités liées au changement climatique : Les zones rurales, notamment la moyenne montagne, attirent des populations fuyant les fortes chaleurs estivales des villes. L'eau est également un "véritable enjeu" et un atout fondamental.

      2. Freins et Défis Majeurs

      Malgré leur dynamisme, les territoires ruraux font face à des contraintes importantes qui entravent leur plein développement :

      • Déficit démographique : Population insuffisante et vieillissante, exode des jeunes.
      • Enclavement et accessibilité : Éloignement des pôles urbains, manque de transports en commun, absence de liaisons aériennes, usage impératif de la voiture.
      • Problématiques de recrutement : Taux de chômage très faible (4,7% en Lozère, par exemple), plein emploi, forte proportion d'emplois publics. Difficulté à attirer et loger les talents.
      • Crise du logement : Forte proportion de résidences secondaires (32% en Lozère) et de logements inoccupés (12%), posant un problème crucial pour les habitants et les saisonniers. "On peut même imaginer que des entreprises ou des des sites pourrait fermer par manque de logement pour les saisonniers."
      • Inertie administrative et difficultés de financement : La "longueur des dossiers" et l'inertie des processus administratifs sont des freins majeurs pour les chefs d'entreprise qui nécessitent "rapidité" et "réactivité". Les dispositifs nationaux (France Ruralité Revitalisation, Petites Villes de Demain, Villages d'Avenir) répondent "partiellement" aux besoins, mais nécessitent plus de réactivité et une adaptation aux réalités locales.
      • Déclin des productions locales et des services de proximité : La perte de production à l'usage des habitants entraîne une disparition des services essentiels (boulangerie, épicerie, médecin), augmentant la solitude et les coûts pour les collectivités.

      3. Initiatives et Modèles de Réussite

      Les témoignages des acteurs de terrain ont mis en évidence la capacité des territoires ruraux à innover et à se développer grâce à des initiatives locales fortes et à la coopération :

      Société d'Économie Mixte (SEM) en Lozère (Roger Cruis) :

      • Modèle pluridisciplinaire : Activités diversifiées (tourisme, portage immobilier professionnel, accompagnement des collectivités).
      • Synergie élus-économique : La SEM "allie la compétence et la proximité des élus et la performance et la recherche de performance des dirigeants et du monde économique".
      • Coopération locale : Nécessité d'une "ligne de conduite partagée par tous les acteurs" (services de l'État, collectivités, chambres de commerce).
      • Proactivité : Initiatives de la SEM pour le logement étudiant, la formation aux métiers du thermalisme et la construction de bâtiments partagés.
      • Atout de la fibre optique : La Lozère, fibrée à 99%, voit la fibre comme un "vrai atout et une vraie valeur ajoutée" pour attirer entreprises et habitants.
      • Entreprise INFACO dans le Tarn (David Elmas) :
      • Ancrage territorial fort : "On a des racines qui nous poussent sous les pieds", fierté de développer l'économie locale et de participer à la vie du village.
      • Innovation et fabrication locale : Inventeur du sécateur électrique, l'entreprise innove, fabrique et assemble 100% de ses sécateurs à Caylusac-sur-Vère.
      • Philosophie d'achats locaux : Priorité aux entreprises locales, régionales et nationales.
      • Défis transformés en opportunités : Malgré les difficultés de foncier et d'internet, l'entreprise a investi (fibre optique, bornes électriques) pour maintenir et développer son activité, soulignant l'importance de "faciliter la tâche" aux entreprises.
      • Culture d'entreprise familiale : Forte relation avec les collaborateurs, climat de confiance et d'écoute, "vie d'entreprise simple, vraie, véritable".
      • Conseil de Développement de Beaujovalley (Dominique Alombus) :
      • Démocratie participative : Le Codev, "un petit CES", proactif dans l'élaboration du Plan Climat Air Énergie Territorial (PCAET).
      • Projet d'Alimentation Territoriale (PAT) : Réduction de l'empreinte carbone, soutien à l'emploi et au savoir-faire locaux, commande publique (cantines scolaires) pour soutenir les filières locales.
      • Mobilisation des acteurs : Travail avec la Chambre de Commerce, la Chambre d'Agriculture, l'hôpital, les communes, les associations, les habitants.
      • Participation citoyenne : Réunions et visites à l'initiative du Codev, diagnostic partagé, création d'un guide des producteurs, forums professionnels, ateliers anti-gaspillage.
      • Origine des initiatives : "C'est vraiment partie des habitants et particulièrement d'un agriculteur en bio". Le Codev vise à "anticiper pour ne pas subir".
      • Le Jeu de la Dombe (Monique Michel) :
      • Objectif de lien social : Favoriser l'interconnaissance des habitants sur un territoire morcelé (36 communes, 39 000 habitants).
      • Conception participative : "Tous les habitants ont construit les jeux, les questions du jeu", lors de réunions participatives qui ont elles-mêmes créé du lien.
      • Diffusion large : Distribution gratuite dans les écoles, médiathèques, centres sociaux, mairies, pour toucher tous les publics et notamment les nouveaux arrivants.
      • Le Jardin d'Arvieux, Tiers-Lieu Villageois en Aveyron (Perrine Vigrou) :
      • Démarche participative "Harvieux 2020" : Démarrée en 2014 par la mairie pour relancer l'attractivité et faire face au déclin démographique.
      • Coopération public-privé : Partenariat entre la mairie et la coopérative LITiS (entreprise numérique installée dès 1998) pour créer et gérer le tiers-lieu.
      • Services intégrés : Médiathèque, cyberbase, inclusion numérique, Maison France Services, services aux associations, offre de coworking, formation, habitat passerelle, séjours immersifs pour les candidats à la vie rurale.
      • Synergie entre anciens et nouveaux habitants : Les nouveaux arrivants sont "force de proposition et porteur de ces nouveaux projets".
      • Animation territoriale : Nécessité d'animateurs sur le terrain pour "produire les bonnes conditions de coopération entre des acteurs différents" et réguler les conflits.
      • Projet Terra en Lot-et-Garonne (Frédéric Bosquet) :
      • Expérimentation sur 10 ans : Visant la revitalisation des "12 000 communes rurales en train de mourir".
      • Approche intégrée : Relocalisation de la production (ferme en permaculture), distribution (épicerie de producteurs), énergies renouvelables (SCIC), mobilité partagée, écoconstruction.
      • "Quartier rural en transition pilote" : Construction avec des matériaux locaux, centre d'écoconstruction et de formation pour reproduire le modèle.
      • Financement patient et solidaire : Processus allant des dons de temps des volontaires aux dons défiscalisables, subventions des collectivités, puis investissements à "capitaux patients, intérêts modérés" pour réinjecter les bénéfices dans le territoire.
      • Gouvernance partagée : SCIC (Société Coopérative d'Intérêt Collectif) avec collectivités, entreprises, associations, partenaires financiers.

      4. Recommandations et Perspectives

      Plusieurs pistes de réflexion et d'action émergent de ces échanges :

      • Développer la coopération et la concertation : Renforcer les dispositifs de démocratie participative (Conseils de Développement) en amont des projets pour partager les visions et renforcer l'acceptabilité.
      • Adapter les politiques publiques : Les territoires ruraux "doivent être des vrais laboratoires" et "être traités différemment" des milieux urbains, avec des dispositifs fiscaux, immobiliers et administratifs spécifiques, plus réactifs et moins "inertiels".
      • Soutenir l'économie locale diversifiée : Encourager la réindustrialisation maîtrisée, valoriser les productions locales, faciliter la transmission des entreprises.
      • Investir dans les services de proximité : La question des services (santé, éducation, mobilité, culture, commerces) est "au centre de l'avenir des territoires ruraux". Les Maisons France Services sont un exemple positif de "remettre de l'humain au cœur des services".
      • Changer le récit de la ruralité : Sortir du "récit de l'abandon" et de la "culture de handicap" pour promouvoir l'attractivité et le dynamisme des territoires ruraux, essentiels pour attirer et retenir les talents.
      • Favoriser les modèles de financement innovants : Rechercher des capitaux "patients à intérêt modéré" pour soutenir des projets à long terme qui génèrent de la valeur économique, sociale et écologique.
      • Prendre en compte les enjeux de ségrégation sociale : Les conflits d'usage dans les territoires ruraux sont de plus en plus liés à des dynamiques de classes sociales. Une meilleure compréhension de ces dynamiques est nécessaire pour une gestion apaisée du "bien vivre ensemble".

      Conclusion

      La ruralité française n'est ni figée ni uniforme, mais un "cœur battant de notre économie et de notre souveraineté alimentaire", un "atout puissant pour permettre la transition écologique".

      Les initiatives citoyennes et la coopération entre tous les acteurs locaux sont les moteurs essentiels de son dynamisme. Il appartient aux politiques publiques de les soutenir efficacement en adaptant les cadres existants et en facilitant l'émergence de nouveaux modèles, pour que la ruralité puisse pleinement jouer son rôle dans la société de demain. "Le pays a besoin de sa ruralité."

    1. Ce document est un compte rendu détaillé des discussions et des propositions issues de la session du Conseil Économique, Social et Environnemental (CESE) consacrée aux violences faites aux femmes, en particulier dans les Outre-mer. Il met en lumière les rôles du CESE, l'ampleur du problème des violences, les obstacles à leur éradication, les initiatives de la société civile, et les axes d'amélioration des politiques publiques.

      Rôle et Missions du CESE Le CESE est présenté comme la "troisième assemblée citée dans la Constitution" après l'Assemblée Nationale et le Sénat. Sa mission principale est de "conseiller le gouvernement et le Parlement dans l'élaboration des lois et des politiques publiques". Plus récemment, il est également devenu la "chambre de la participation citoyenne", agissant comme un "trait d'union entre les pouvoirs publics et la société civile".

      Les quatre missions principales du CESE sont :

      Conseiller et éclairer le gouvernement et le Parlement. Favoriser le dialogue social et la recherche de consensus. Contribuer à évaluer l'efficacité des politiques publiques. Prendre le pouls des régions en lien constant avec les CESER. Le CESE a également pour mission de "renforcer la démocratie participative en permettant aux citoyens de faire entendre leur voix". Les citoyens peuvent saisir le CESE via pétition, et si elle recueille plus de 150 000 signatures, le Conseil est "obligatoirement" tenu d'étudier le sujet.

      Ampleur et Spécificités des Violences dans les Outre-mer Les statistiques et témoignages révèlent une situation alarmante :

      En 2023, 96 féminicides sur 119 décès au sein des couples et 451 tentatives d'homicide en France, chiffres en "hausse constante depuis 2019". Un viol ou une tentative de viol "toutes les 2 minutes et demi" en France. Les violences faites aux femmes sont "toujours aussi prégnantes dans le monde et en France", et les Outre-mer ne font "pas exception, bien au contraire". Entre 2017 et 2023, le nombre de féminicides a augmenté dans les Outre-mer, tout comme les violences sexuelles et psychologiques, y compris dans la sphère professionnelle. "11% des féminicides interviennent dans les territoires ultramarins qui ne concentrent que 4% de la population". Les taux de morts violentes au sein du couple placent la Guyane, la Nouvelle-Calédonie, et la Polynésie française comme "les territoires ayant les niveaux de violence les plus élevés en France". Forte augmentation des violences psychologiques, pour lesquelles les campagnes de prévention sont "quasi inexistantes". Un enfant est tué "tous les 6 jours au sein de sa famille" en France, et "160 000 sont agressés sexuellement chaque année". Plusieurs facteurs aggravants et spécificités sont soulignés pour les Outre-mer :

      Contexte socio-économique : "creusement des inégalités familiales, sociales et économiques", "taux des familles monoparentales", "revenus très bas". "Un enfant sur deux à la Réunion vit dans un foyer pauvre, 37% de la population vit en dessous du seuil de pauvreté." Culture patriarcale : "culture patriarcale de domination masculine toujours très enracinée", "tabou" autour de l'éducation à la vie affective, relationnelle et sexuelle. Spécificités géographiques et sociales : "interconnaissances plus fortes" sur les îles rendant la dissimulation des violences plus facile, difficultés de fuite dues à l'éloignement ("océan tout autour"). Poids des coutumes : En Nouvelle-Calédonie, le "statut civil coutumier" rend la situation des femmes particulièrement difficile. Une femme mariée coutumièrement "est mariée à un clan", et si elle part, c'est "sans ses enfants parce qu'en fait ses enfants appartiennent au clan". Le divorce est également complexe, nécessitant l'accord des deux clans. Méconnaissance des formes de violence : Beaucoup de femmes ne réalisent pas qu'elles sont victimes, surtout pour les violences psychologiques et économiques. Obstacles et Défis à la Lutte Plusieurs obstacles majeurs sont identifiés :

      Manque de financement : Les associations sont le "premier acteur de terrain", mais manquent cruellement de moyens financiers et de "visibilité à moyen terme". Des exemples concrets sont donnés sur l'annulation de formations faute d'inscrits, ou l'absence de versement des subventions annuelles. Manque de cohérence et de coordination : Les actions sont souvent "ponctuelles", il manque une "grosse dose de cohérence, coordination, coopération". Données lacunaires : Les données sur les violences sont "trop éparses et incomplètes", ce qui "montre en creux l'absence de vision globale et de coordination des politiques publiques". Accès insuffisant aux droits et à la protection : Les victimes ont un "accès insuffisant au droit". Le manque de places d'hébergement est criant, forçant des femmes à "dormir dans leur voiture". Le 115 est "saturé". Méconnaissance des outils existants : Les "lois sont méconnues", y compris des acteurs de terrain. L'ordonnance de protection est "très peu utilisée". Implication inégale des élus locaux : "La prise de conscience des élus [...] est très inégale et elle est souvent insuffisante pour faire bouger les choses". Formation insuffisante des professionnels : Malgré des formations dispensées, elles restent "très inégales d'un territoire à l'autre". Les encadrants d'enfants, par exemple, ne sont pas toujours formés, ce qui "dilue" l'impact des actions de sensibilisation. Adaptation des outils nationaux : Des dispositifs comme le 3919 sont "totalement inadaptés à la diversité des populations ultra-marines" (langue, horaires, interconnaissance). Initiatives et Solutions Proposées Plusieurs pistes et actions sont suggérées :

      Soutien aux associations : Reconnaître leur rôle "primordial" et leur accorder des "moyens pérennes" et des "financements à hauteur des besoins", connus "tôt dans l'année". Prévention et éducation : Développer la "prévention dès le plus jeune âge", notamment via l'éducation à la vie affective, relationnelle et sexuelle (EVARS), obligatoire mais non appliquée partout. Il faut "rompre avec les stéréotypes sexistes" et "adapter les messages aux populations locales". Amélioration des données et observatoires : Étendre les enquêtes "Virage" à l'ensemble des territoires et alimenter un "observatoire national dédié aux violences faites aux femmes dans les Outre-mer" pour disposer de "chiffres fiables et homogènes". Renforcement de la coordination : Création de "référents dans un peu toutes les administrations et aussi des associations qui montent en compétence sur l'écoute des femmes victimes de violence". Importance des "délégations régionales aux droits des femmes" si elles sont dotées de moyens suffisants. Formation des professionnels : Renforcer la "formation initiale et continue des professionnels" (gendarmes, intervenants sociaux, magistrats, personnel de santé, élus). Décloisonnement de la justice : Les "pôles violences intrafamiliales" visent à spécialiser les magistrats et à favoriser les échanges entre les différents acteurs judiciaires pour une prise en charge globale. Lois et politiques publiques ambitieuses : Nécessité d'une "loi cadre" similaire à la loi intégrale espagnole pour une approche globale et coordonnée. Les plans pluriannuels d'investissement ("PPI") et les "contrats de convergence et de transformation" devraient inclure des "financements pluriannuels fléchés" pour la lutte contre les violences. Mobilisation de la société civile : Impliquer davantage les élus locaux, les organisations patronales, syndicales, et les associations. Le CESE lui-même peut servir de lieu de "débat avec les représentants de la société civile organisée et avec les citoyens". Innovation technologique et outils de protection : Utilisation d'outils comme "Mémo de vie" (coffre-fort numérique), le "bouton Monchérif" (alerte géolocalisée), le "sifflet anti-relou" (interpellation de l'entourage). Sensibilisation et médiatisation : L'importance de montrer la "cruauté" des violences pour "faire comprendre l'ampleur" et inciter à la dénonciation. Conclusion Le CESE, sept ans après son premier avis en 2017, réitère son appel aux pouvoirs publics. La résolution actuelle, fruit d'un travail collaboratif et de l'écoute des acteurs de terrain, souligne l'urgence d'une "volonté politique" forte et de "moyens dédiés" pour enrayer ce fléau. Le consensus général est que les violences faites aux femmes sont "un coût humain individuel et collectif aussi dramatique qu'inacceptable", et qu'il est "l'affaire de toutes et de tous" de les combattre. La résolution, adoptée à l'unanimité (111 votants, 111 voix pour), est un appel clair à l'action.

    1. Synthèse : La Restauration de la Nature – Face à l'Urgence, Donnons l'Envie d'Agir * Ce briefing se base sur les discussions et le projet d'avis du Conseil Économique, Social et Environnemental (CESE) intitulé "La restauration de la nature : face à l'urgence, donnons l'envie d'agir". Il met en lumière le rôle du CESE, les enjeux cruciaux de la restauration de la nature, les défis et les propositions concrètes pour une action efficace, ainsi que les divers points de vue exprimés par les groupes d'intérêts.

      1. Le CESE : Un Trait d'Union et un Moteur de Démocratie Participative

      • Le CESE est présenté comme un acteur clé de la démocratie française, servant de "trait d'union entre les pouvoirs publics et la société civile". Composé de 175 conseillers issus de divers horizons (entreprises, syndicats, associations, ONG), il est une "sorte de mini France réunie dans un hémicycle où tous les points de vue se rencontrent", permettant des débats inattendus, comme entre "des chasseurs [qui peuvent] discuter et débattre avec des défenseurs des oiseaux".

      Ses missions principales sont :

      • Conseil et éclairage : Conseiller et éclairer le gouvernement et le Parlement dans l'élaboration des politiques publiques.
      • Dialogue social : Favoriser le dialogue social et la recherche de consensus.
      • Évaluation : Contribuer à évaluer l'efficacité des politiques publiques.
      • Lien territorial : Prendre le pouls des régions via les CESE régionaux.
      • Démocratie participative : Renforcer la démocratie participative, notamment par le tirage au sort de citoyens, l'organisation de conventions citoyennes ou les consultations en ligne.

      Les citoyens peuvent saisir le CESE via une pétition de plus de 150 000 signatures. * Des exemples concrets de l'impact du CESE sont cités, tels que la "garantie jeune" ou les "dispositifs d'alerte pour lutter contre les violences faites aux femmes".

      2. L'Urgence de la Restauration de la Nature : Constats et Enjeux

      • Le projet d'avis sur la restauration de la nature est une réponse directe à une urgence environnementale majeure et aux objectifs du règlement européen de 2024.

      Constats alarmants :

      • Perte de biodiversité : La perte de biodiversité se poursuit à un rythme alarmant, sous l'effet du réchauffement climatique, de la fragmentation des habitats, de l'artificialisation des sols, de la surexploitation et de la pollution.
      • Chiffres clés : "le nombre d'oiseaux a diminué de 25 % en 40 ans dans l'Union européenne et les données sont encore plus dramatique pour les insectes".

      Plus de "80 % des habitats européens sont dégradés". "85 % des zones humides ont disparu" dans le monde.

      La France a perdu "70 % de ses haies depuis 1950 [et] la moitié de ces zones humides entre 1960 et 1990". * Dépendance économique : Près de "50 % du PIB mondial repose sur la nature", et "80 % des emplois en France dépendent directement ou indirectement de la nature". * Santé humaine : Selon l'OMS, "23 % des décès et 25 % des pathologies chroniques dans le monde peuvent être attribués à des facteurs environnementaux et comportementaux."

      Objectifs et Définition de la Restauration :

      • Le règlement européen de 2024 fixe des objectifs "quantitatifs et contraignants" : "restaurer au moins 30 % des terres et des mers dégradées d'ici 2030 et l'ensemble des écosystèmes d'ici 2050".
      • La restauration vise un "état fonctionnel" plutôt qu'un "état originel" ou pré-industriel. "un chirurgien il ne va pas chercher à restaurer un état originel un os d'avant la fracture il va chercher à restaurer un état fonctionnel une capacité à marcher à nouveau bah pour la restauration de la nature c'est peu ou prou la même chose."
      • Elle comprend des actions "passives" (limitation des pressions comme le zéro artificialisation nette) et "actives" (actions ciblées).

      3. Les Défis et Freins à l'Action

      • Plusieurs obstacles entravent la mise en œuvre de la restauration :

      • Faible appropriation et fragmentation : Le plan national se heurte à une "faible appropriation [des enjeux], à une fragmentation des responsabilités et à un manque de moyens".

      • Moyens insuffisants : Les moyens financiers et humains pour la recherche, la mise en œuvre et le contrôle sont jugés insuffisants.
      • Absence de données : Le manque de données agrégées et de connaissances, notamment sur le milieu marin, est un défi, bien que "ce que l'on sait est suffisant pour agir".
      • Réticences des acteurs : Certains acteurs, comme les agriculteurs (concernant Natura 2000), expriment des réticences liées à la liberté entrepreneuriale ou à la méconnaissance des objectifs.
      • Financements problématiques : Les financements sont souvent insuffisants, et la CFDT s'oppose à la création de "nouvelles niches fiscales réduisant d'autant les recettes indispensables au services publics et bénéficiant aussi à de grands propriétaires fonciers".
      • Politiques incohérentes : "Il ne peut y avoir de politique de restauration de la nature efficace si en parallèle les pressions sur la nature ne sont pas durablement et significativement diminué." Des exemples de projets nuisibles (A69, Lyon-Turin) sont cités.

      4. Préconisations du CESE : Une Approche Pragmaticque et Collaborative

      • Le CESE propose 16 préconisations articulées autour de trois axes, privilégiant la mobilisation de l'existant plutôt que la création de nouvelles structures : "nous ne proposons pas de créer de nouvelles institutions, agences, de mettre en place un paquet de nouvelles réglementations non pour réussir ce vaste projet on s'est rendu compte que beaucoup de choses existait et presque tout était disponible déjà mais que il manquait de coordination de moyens et de diffusion sur le terrain".

      Axe 1 : Donner le cap et accompagner

      • Clarification et portage politique : L'État doit fournir un "cap clair" et un "renforcement de l'Association des parties prenantes".
      • Rôle des régions : Les régions doivent intégrer la restauration de la nature dans leurs outils de planification et de financement.
      • Guichet unique : Créer des "guichets uniques" locaux (via les agences régionales de la biodiversité ou leur équivalent) pour accompagner les porteurs de projets (diagnostic, mise en relation avec professionnels).

      Axe 2 : Embarquer les acteurs en faveur de la restauration de la nature

      • Partage de la corresponsabilité : "Embarquer ça veut dire être tous dans le même bateau face à l'urgence et travailler ensemble pour aboutir à quelque chose."
      • Sensibilisation et formation : Lancer une "grande campagne de communication et d'information" dès l'école, et développer des formations professionnelles.
      • Réduction des pressions : Réduire "durablement et significativement" les pressions sur la nature, notamment via la loi ZAN (Zéro Artificialisation Nette) et une meilleure application de la séquence "éviter, réduire, compenser".
      • Reconnaissance et valorisation : Mettre en place un label pour reconnaître le travail des acteurs de terrain (particuliers, propriétaires fonciers, entreprises, associations, collectivités).

      Axe 3 : Mobiliser outils et moyens

      • Outils existants : Rendre plus attractifs les outils juridiques et contractuels existants (contrats Natura 2000, Obligations Réelles Environnementales (ORE), baux ruraux à clause environnementale).
      • Différenciation et incitation : Différencier compensation et engagement volontaire, en incitant ce dernier.
      • Financements dédiés : Flécher des financements dédiés, notamment en abondant le Fonds Vert national, et explorer les financements privés (paiements pour services environnementaux, mécénat, certificats/crédits biodiversité).

      5. Messages Clés et Perspectives

      • Optimisme et action concrète : Malgré l'ampleur des défis, l'avis se veut optimiste : "La restauration de la nature ça fonctionne, ça se voit et ça peut embarquer les gens à cette objectif à cet engagement collectif."

      • Rôle du CESE : Le CESE prouve sa capacité à "co-construire avec les acteurs, par les acteurs, à partir du terrain", et à faire discuter des points de vue divergents.

      • Aller au-delà de l'utilité : Pour certains groupes, la nature ne doit pas être réduite à son utilité pour les humains : "elle possède une valeur intrinsèque non quantifiable en euros ou en pourcentage du PIB."
      • Cohérence des politiques publiques : Nécessité d'une "cohérence avec les territoires" et d'un "pilotage interministériel".
      • L'adoption de cet avis par une large majorité des votants (118 pour, 1 contre) souligne le consensus sur l'urgence et la pertinence des propositions, malgré quelques nuances ou désaccords sur des points spécifiques (ex: zonage Natura 2000, exemptions fiscales). La restauration de la nature est présentée comme "une stratégie sans regret" et une opportunité de construire "un monde plus juste, plus prospère et plus respectueux des générations futures".
    1. Compte-rendu détaillé de la matinée : L'IA, la voie citoyenne Date : [Non précisé, mais fait référence à des événements de 2023 et 2024] Lieu : Palais d'Iéna, siège du Conseil Économique Social et Environnemental (CESE) Organisateurs : CESE, Conseil National du Numérique (CNNum), en partenariat avec Make.org, The Future Society, Sciences Po, ENS.

      1. Introduction et Objectifs de la Matinée La matinée, organisée au CESE, assemblée de la société civile et de la participation citoyenne, vise à discuter de la place du citoyen dans l'intelligence artificielle (IA). L'événement s'inscrit dans la perspective du Sommet Mondial de Paris sur l'IA, avec pour ambition de donner la parole aux citoyens sur les impacts et les enjeux de l'IA.

      Points clés :

      • Rôle du CESE et du CNNum : Le CESE, en tant qu'assemblée de la société civile et de la participation citoyenne, est le lieu "tout à fait naturel" pour cet événement. Le CNNum prolonge ses "cafés IA" initiés en 2024, des moments d'écoute et de débat sur les enjeux de l'IA.
      • Objectif de l'événement : Donner la voix à ceux qu'on n'entend pas toujours, pour "exprimer leurs espérances et leurs craintes face au déploiement de l'IA et de regarder par le débat si nous pouvons trouver des réponses communes."
      • Contexte global de l'IA : L'IA est comparée à l'arrivée d'Internet dans les années 2000 et de l'électricité dans les années 1900, suscitant "les mêmes passions".
      • Nature de l'IA : L'IA est présentée comme "un objet social et politique résultant de choix collectif et humains avant même d'être un objet technologique", n'étant "ni porteuse de miracle ni de danger" en soi.
      • Enjeux des travaux du CESE : Mettre le sujet de l'IA "à hauteur de la société civile" en examinant les problématiques sociales : risques d'atteinte aux droits fondamentaux et libertés individuelles, empreinte environnementale, autonomie stratégique et souveraineté, impacts sur l'emploi, l'intégration en entreprise, les services publics, l'éducation, la santé, le handicap, et la garantie d'un accès au non-numérique.
      • Expertise d'usage : Nécessité d'apporter une "expertise d'usage" pour compléter les savoirs spécialisés et les stratégies politiques/commerciales, cruciale pour l'acceptabilité des mutations par les concitoyens.
      • Mission commune : L'IA ne doit pas se substituer à l'intelligence collective. L'objectif est de rendre l'IA "plus démocratique", pour que "les citoyens, les salariés, les administrés aient un poids dans les décisions et les calculs".
        1. Perspectives Gouvernementales et Institutionnelles
      • Clara Chappaz, Ministre déléguée chargée à l'Intelligence Artificielle et au Numérique :
      • Inclusivité du Sommet de Paris : Souligne l'importance de rendre le Sommet de Paris sur l'IA "le plus inclusif possible", en "embarquant la société civile" et en répondant aux questions des citoyens.
      • IA au service de l'intérêt général : L'objectif principal est de mettre cette technologie "au service de l'intérêt général".
      • IA : une question démocratique et politique : L'IA n'est pas seulement économique ou de compétitivité, mais une "question absolument démocratique et même politique".
      • Confiance comme ciment : "La confiance doit être le ciment du développement de cette technologie". Sans confiance, il n'y aura pas d'adoption de l'innovation.
      • Responsabilité collective : Nécessité d'une "responsabilité absolument collective" pour que l'IA ne devienne pas une source de "fracture sociale", "frustration" ou "fracture territoriale", mais un "outil de progrès".
      • Écoute des citoyens : Mentionne les "Cafés IA" du CNNum et les ateliers "élu.ai" comme exemples d'initiatives d'écoute et d'échange avec les Français sur leurs perceptions et craintes de l'IA.
      • Équilibre : Trouver un équilibre entre le développement de l'écosystème technologique (pour la souveraineté) et l'accompagnement des citoyens à l'adoption de l'IA, dans le respect des droits fondamentaux, des libertés individuelles, de l'égalité et des limites planétaires.
      • Valeurs françaises et européennes : Faire de la France une puissance de l'IA compatible avec son "socle de valeur" et les "spécificités de notre culture française et européenne".
        1. Témoignages Citoyens et Expériences Locales
      • Martine (citoyenne ayant participé à la commission temporaire sur l'IA au CESE) :
      • Expérience formatrice : Souligne une expérience "formatrice et révélatrice", malgré un sentiment initial d'"illégitimité".
      • Importance du dialogue : Les échanges enrichissants et la diversité des perspectives ont permis une meilleure compréhension des enjeux.
      • Rôle du CESE : Le CESE est une "passerelle où décideurs publics et de citoyens... peuvent se réunir et échanger équitablement", favorisant un dialogue inclusif et renforçant la légitimité des décisions.
      • IA comme outil : Réaffirme que l'IA "n'est ni une entité autonome ni véritablement intelligente", mais "un outil façonné par des humains".
      • Responsabilité collective : Insiste sur l'immense responsabilité des créateurs et utilisateurs de l'IA, et le rôle des décideurs publics dans la régulation et l'anticipation des dérives.
      • Axel Docher (Make.org) et Constance (The Future Society) sur la consultation publique :
      • Large participation : Plus de 11 000 participants et 120 000 votes, montrant un "haut niveau de compréhension" et des "points de convergence assez forts".
      • Vigilance active : Les citoyens sont "ouverts à l'IA" mais réclament une "vigilance très active sur son mise en application".
      • IA dans les services publics : Acceptation de l'IA dans les services publics (ex: diagnostics de santé), mais "point de rupture" sur la "décision humaine" : l'IA doit être un outil au service de la décision, non une substitution.
      • Rationalisation vs. Contribution : L'IA ne doit pas être exclusivement au service de la rationalisation des services, mais un élément contributeur.
      • Peurs démocratiques : Peur de l'IA utilisée pour la désinformation et la fragilisation de la démocratie.
      • Opportunité pour la démocratie : L'IA peut "renforcer le lien entre les citoyens et les processus démocratiques", notamment en "décomplexifiant le monde pour les citoyens".
      • Lien IA-Démocratie : "Il n'y aura pas d'innovation ouverte" et "pas d'IA au service du bien commun" sans démocratie.
      • Alice Rousset (Ville de Paris) :
      • Démarche progressive : La Ville de Paris a abordé l'IA par l'expérimentation pour améliorer les services publics (analyse espace public, information aides sociales, urbanisme).
      • Démarche participative : Face à l'essor de l'IA générative, adoption d'une démarche "participative et inclusive" (auditions experts, consultation citoyenne, journée citoyenne).
      • Enseignements : Les Parisiens souhaitent que la ville se saisisse de l'IA "à son niveau" de manière "responsable", avec un "réel encadrement".
      • Axes prioritaires : Nécessité d'un "cadre de transparence et de contrôle des projets IA" (évaluation préalable, suivi déploiement avec société civile) et un "effort de formation et de sensibilisation".
      • Rappel : L'IA ne doit pas "se substituer à la décision humaine".
      • Pierre Jannin (Ville de Rennes) :
      • IA : un sujet politique : L'IA doit être "au service des transitions sociales, écologiques et démocratiques de l'intérêt général".
      • Voie alternative : Créer une "voie alternative qui contrôle, qui régule" face à un modèle "ultralibéraliste et dérégulé".
      • Conseil Citoyen du Numérique Responsable : Création d'une instance de 30 citoyens tirés au sort travaillant sur les enjeux de l'IA (impact sur métiers, IA au service du territoire, enjeux éthiques, liberté, sécurité, justice).
      • Points de vigilance : Les citoyens de Rennes ont identifié des points de vigilance cohérents avec les rapports nationaux : contrôle, transparence, régulation, risques sur l'emploi, lien public-privé, opportunités.
      • Concertations territoriales : Initiative nationale "Concertations territoriales de l'intelligence artificielle" (bottom-up) avec 33 villes, pour extraire des grands enjeux et recommandations.
      • Co-construction et reddition de comptes : "Nous sommes convaincus que nous devons construire la technologie avec les citoyennes et les citoyens", en les formant, les consultant, et surtout en "rendant des comptes sur la manière dont leurs recommandations... sont pris en compte".
      • Didier Mino (Changer de Cap) sur l'IA dans les services publics (CAF) :
      • Problèmes de l'automatisation : Témoignage alarmant sur la dématérialisation à la CAF, générant "maltraitance institutionnelle" et "non accès au droit" pour les plus précaires.
      • Pratiques illégales/discriminatoires : Suspension de droits sans préavis, qualification d'erreurs en fraude, contrôles ciblés par algorithmes discriminatoires, absence de questions ouvertes dans les formulaires, complexité de la réglementation.
      • Perte de maîtrise technique : Les services informatiques ont perdu la maîtrise du code (Crystal, écrit en Cobol dans les années 90), entraînant des décalages avec la loi et des décisions inexplicables.
      • Conséquences humaines : "Graves conséquences pour la santé physique et mentale des personnes en difficulté", basculement dans la pauvreté, perte de sens pour les agents.
      • Injonctions politiques : Les réformes budgétaires (ex: aides au logement) ont provoqué des "catastrophes informatiques".
      • Appel à l'action : Actions en justice contre l'algorithme ciblant les contrôles sur les plus fragiles.
      • Solution : "Possibilité d'un libre choix des usagers dans leur mode de relation avec les services publics", et nécessité de transparence et dialogue.
      • Soasick Penico et Estelle Hary (Observatoire des Algorithmes Publics - ODAP) :
      • Transparence des algorithmes : Nécessité de visibiliser et de rendre transparents les algorithmes utilisés par l'administration, car ils sont "fondamentalement politique".
      • Non-neutralité des algorithmes : Les algorithmes ne sont "absolument pas des objets objectifs" mais résultent de "choix humain et institutionnel" (décision de déploiement, critères, ressources, prestataires privés).
      • Manque de documentation : Absence de panorama exhaustif des algorithmes, les administrations les documentent "très peu publiquement".
      • Inventaire citoyen : Création d'un inventaire de 72 algorithmes à partir de sources publiques, montrant un "très peu de transparence" et une évaluation rare (4% d'évaluations internes publiées).
      • IA et automatisation : L'IA est "l'arbre qui cache la forêt de l'histoire longue de l'automatisation du service public". Les systèmes critiques anciens (ex: calcul impôts) sont aussi importants dans le débat démocratique.
      • Transparence au service de la justice sociale : La transparence est un "outil au service d'autres individus et d'autres collectifs qui luttent pour la justice sociale, pour les droits humains, pour les droits des travailleurs et des travailleuses et pour la justice environnementale".
      • Lutte essentielle : Essentiel que la société civile s'empare du sujet de l'IA comme "partenaire de débat mais aussi comme contre-pouvoir fort", car "tout le monde est légitime à le faire" même sans connaissances techniques, car c'est un "sujet politique avant tout".
      • Gabrielle Dubois (Défenseur des Droits) :
      • Rapport sur l'IA et service public : Rappelle le rapport du Défenseur des Droits de novembre dernier sur les décisions administratives automatisées.
      • Enjeux clés : L'intervention humaine et la transparence sont cruciales.
      • Enjeu individuel : Respecter le principe constitutionnel de transparence et le rendre appropriable par les personnes concernées.
      • Enjeu collectif : Concrétiser l'obligation de publication des règles des traitements algorithmiques pour permettre la compréhension et la contestation.
      • Intelligibilité de l'administration : S'assurer que les agents comprennent le fonctionnement des outils qu'ils utilisent.
      • Recommandations : Respect des obligations de publication, consécration d'un "droit à l'explication des décisions individuelles administratives" (au-delà des IA à haut risque), et association des usagers du service public à tous les niveaux.
      • Thomas Peron (Professeur de droit) sur le service public coopératif :
      • Repenser les services publics par les communs : Réfléchir à la structure de pouvoir dans les services publics à travers les communautés.
      • Jury populaire : Le jury populaire est le seul cas où une décision publique est prise par des citoyens tirés au sort.
      • Numérique et démocratisation : Le numérique offre un accès à la décision et la possibilité de décider en temps réel, permettant une démocratisation des services publics.
      • Métier de citoyen : Le métier de citoyen devrait s'apprendre d'abord dans les services publics.
      • Démocratisation des services publics : La question de l'IA démocratique doit être accompagnée d'une réflexion sur la démocratisation des services publics.
      • Décentralisation radicale : Implique une "décentralisation radicale des lieux de pouvoir et des processus de décision" au plus près de la relation.
      • Sid Sako et Hélène Mazela (citoyens de la consultation Make.org) :
      • Convention Citoyenne sur l'IA : Proposition de lancer une convention citoyenne de l'IA pour embrasser tous les défis contemporains (écologie, équité, justice sociale, éducation, emploi, santé, éthique).
      • Prendre le temps de comprendre : Les citoyens n'ont jamais été vraiment consultés sur la numérisation. La convention permettrait de prendre ce temps pour aligner les enjeux informatiques et IA avec l'intérêt général.
      • Partager la responsabilité : Embarquer les citoyens, c'est partager la responsabilité des décisions futures, car le sujet n'est pas seulement technique mais politique ("quelle société voulons-nous ?").
      • Normes IA environnementales et RSE : Proposer la mise en place de normes IA environnementales et RSE (responsabilité sociale des entreprises) pour encourager des modèles économes (IA frugale), favoriser la transparence énergétique, intégrer les critères éthiques d'inclusion et d'accessibilité.
      • Souveraineté : Favoriser des protocoles de collaboration pour éviter la domination des IA internationales.
        1. Débat public sur l'IA et le travail
      • Thomas Fournaise (Nantes, organisateur salon Data IA) :
      • Transparence des décisions : Le problème de la transparence des décisions est antérieur aux algorithmes et à l'IA. Le numérique permet de mettre en évidence ce manque de transparence historique.
      • Responsabilité humaine : Les décisions de priorisation (ex: couples mariés vs. paxés) sont prises par des humains. "Il faut rendre l'IA éthique, moi ça pose un problème, c'est qu'on la rend humaine, on l'anthropomorphise et quelque part on se déresponsabilise."
      • IA comme outil : L'IA est un outil qui répond à des questions. L'importance réside dans "les questions qu'on lui pose, la manière dont on le pose".
      • Usage sociétal : L'enjeu est "quel usage sociétal on veut l'utiliser".
      • Marine André (Mère de famille et Designer d'IA) :
      • Risque d'anthropomorphisme : Confirme le risque de penser qu'il y a une personne derrière l'IA.
      • Éducation à l'IA : S'inquiète de l'absence d'éducation à l'usage de l'IA dans les lycées et le manque de formation à l'esprit critique des jeunes.
      • Laure Lucchesi (Ex-directrice Etalab) :
      • Obligations légales de transparence : Insiste sur l'importance de la transparence des traitements algorithmiques dans le service public et le rôle d'Etalab dans l'accompagnement des administrations.
      • Démantèlement des équipes dédiées : Regrette le démantèlement des équipes chargées d'accompagner les administrations sur ces questions éthiques.
      • Droit d'accès aux documents administratifs : Rappelle l'importance de ce droit, qui date de 1978, pour la société civile et les journalistes pour interroger la conception des algorithmes et la communication des codes sources.
      • Guilaine Giersau (Les Petits Débrouillards) :
      • Éducation et esprit critique : Souligne l'importance de l'éducation aux sciences et à l'esprit critique, surtout dans les territoires ruraux et d'Outre-Mer, malgré le manque de moyens.
      • Rôle des associations : Les associations jouent un rôle crucial dans cette éducation hors les murs de l'école.
      • Connaissance des entreprises : Nécessité que les entreprises comprennent aussi ces enjeux.
      • Cohérence des dispositifs : Manque de pérennité et de cohérence dans les dispositifs d'éducation numérique.
      • Urgence : L'approche démocratique est d'autant plus urgente au vu des événements mondiaux.
      • Didier Cornel (Juriste, institution publique belge) :
      • Problème non lié à l'IA : Quand la législation est appliquée, les droits sont plus faciles à octroyer avec les outils informatiques qu'sans. Le problème est le non-respect des règles existantes.
      • Obligation d'aide : Propose une obligation légale d'aide avec une obligation de résultat pour les personnes n'arrivant pas à accomplir les formalités.
      • Risques existentiels : Exprime sa "surprise et déception" face à l'absence de discussion sur les risques existentiels de l'IA, citant une probabilité moyenne de 10% de "fatale issue pour l'humanité" selon les spécialistes.
      • Volonté d'arrêter l'IA : S'étonne que la consultation citoyenne ait révélé une proposition d'arrêter l'usage de l'IA (49% pour, 39% contre) sans que cela soit plus discuté.
      • Franck Bataille (Président Loir et Cher Tech) :
      • Cafés IA sur les territoires : Témoigne du succès des "cafés IA" en Loir-et-Cher, ayant touché 300 personnes en 2024 et visant 1000 en 2025, notamment auprès de jeunes en décrochage scolaire.
      • Inclusion numérique : Son association, active depuis 10 ans dans la culture et l'inclusion numérique, a embrassé l'IA avec divers publics.
      • Patrick Allard (Ex-entrepreneur, citoyen) :
      • Souveraineté : Pose la question de la souveraineté face aux acteurs américains et chinois, et de l'action de la France.
      • Aziz Kizou (Fondateur iPublic) :
      • IA privées dans les industries de réseau : Interroge sur le "angle mort" des IA privées dans les industries de réseau (énergie, transport) qui, malgré leur taille, peuvent avoir un pouvoir systémique sur la vie des citoyens.
      • Cadre normatif insuffisant : En dehors du RGPD et de l'AI Act, il n'y a pas de cadre normatif suffisant pour contrôler ces plateformes.
      • Nationalisation ? : Se demande si la société civile sera suffisante ou s'il faudra envisager des nationalisations de plateformes IA.
      • Eden Carou (Data Scientist) :
      • Compréhension du fonctionnement : Une IA démocratique n'est efficace que si les citoyens comprennent son fonctionnement et ses enjeux.
      • Éducation et sensibilisation : L'éducation à l'IA, au-delà de sa dimension technique, doit concerner son interaction avec les individus et la société.
      • Étienne Brevet (Gouvernance des données, Agglomération du Pays Basque) :
      • Importance de la donnée : Insiste sur la qualité de la donnée qui alimente l'IA. "Aucun algorithme ne sera efficace si derrière la donnée qu'on récupère n'est pas bonne."
      • Masse de données : Réflexion sur les quantités astronomiques de données stockées et le faible pourcentage réellement utilisé.
      • Cadre réglementaire : Nécessité d'une réflexion sur le cadre réglementaire de la donnée.
        1. L'IA au travail : Impacts et Dialogue Social
      • Caroline Jeanmaire (Consultation Make.org) :
      • Urgence d'agir : 200 organisations de la société civile alertent sur l'urgence d'agir pour comprendre et prévenir les risques de l'IA pour le futur du travail.
      • Protéger concrètement les emplois : L'IA risque d'aggraver les inégalités. Solutions : observatoire international pour anticiper les bouleversements, accords d'entreprise innovants (ex: Volkswagen zéro licenciement IA), kit de protection des travailleurs (guides pratiques, normes surveillance humaine).
      • Développer formation numérique et esprit critique : Plateforme gratuite multilingue, laboratoires pour l'équité sur l'IA.
      • Investir dans les talents de demain : Accès inégal aux métiers de l'IA. Programme mondial de formations avec acteurs locaux, bourses, mentorat, soutien aux communautés sous-représentées.
      • IA au service de tous : "Agissons maintenant pour une IA au service de tous et pour réduire les inégalités au lieu de les creuser."
      • Eric Meyer (Conseiller CESE, syndicaliste) et Solidaire Finances Publiques :
      • Déploiement de l'IA à la DGFiP (Direction Générale des Finances Publiques) : Exemples du projet CFVR (ciblage fraude et valorisation requêtes) pour détecter la fraude fiscale.
      • Coût et efficacité : 34,5 millions d'euros, 52% des contrôles entreprises en 2022, mais seulement 13,6% des sommes récupérées.
      • Suppression d'emplois : "Gains de productivité" de 500 emplois, soit 1/4 des effectifs dédiés au contrôle fiscal.
      • Impacts sur les missions et conditions de travail :Réduction du périmètre de mission : Moins de lien avec le terrain, traitement prioritaire de listes générées par l'IA au détriment du reste.
      • Perte d'autonomie et de technicité : Travail "monotâche, très répétitif", plus de latitude pour les agents.
      • Erreurs de l'IA : Les agents passent du temps à justifier pourquoi des contrôles proposés par l'IA ne peuvent être engagés.
      • Pas de tâches plus intéressantes : 85,4% des agents estiment que l'IA ne permet pas de se consacrer à des tâches plus intéressantes.
      • Perte de sens au travail.
      • Opacité et absence de dialogue social : Déploiement "à marche forcée", absence totale d'information, de concertation, peu de formations. Bilans d'expérimentations non discutés.
      • Boîte noire et externalisation : Conception souvent externalisée à des cabinets privés, renforçant l'inexplicabilité.
      • Réinvention du syndicalisme : Utilisation de moyens juridiques (saisine CADA), partenariats (journalistes, chercheurs), alertes politiques, enquêtes internes. Obtention d'un comité éthique interne après refus de participation à l'externe.
      • Discours technocritique : Les agents doivent être systématiquement associés à la conception de leurs outils dans une démarche transparente.
      • David Gaborio (Sociologue) sur les ouvriers de la logistique :
      • Outil : la commande vocale (Voice Picking) : Logiciel dictant toutes les tâches via un casque et micro.
      • Bilan : Perte d'autonomie, intensification du travail (10 à 15% d'accélération), individualisation, hausse du contrôle.
      • Taylorisme moderne : Travail contraint, répétitif, physique, avec une "usure accélérée des corps". Explosion des accidents du travail et maladies professionnelles.
      • Manque d'anticipation et promesses déçues : Promesse d'un travail plus qualifié et libéré non tenue.
      • Contrôle inefficace : Les rapports de la CNIL sur la surveillance n'ont pas empêché une standardisation extrême du travail.
      • Discours sur l'automatisation : Produit des effets d'invisibilisation du travail et de perte de légitimité des ouvriers.
      • Très faible encadrement : Manque de contrôle citoyen et démocratique dans l'entreprise (ex: disparition des CHSCT).
      • Dominance des discours d'en haut : Très faible présence des discours des classes populaires.
      • Polarisation du travail : Les nouvelles technologies ne feront pas disparaître les métiers pénibles, mais entraîneront une "polarisation très forte" entre métiers qualifiés et classes populaires subissant les conséquences.
      • Eric Drouin (CNIL) sur la régulation :
      • Régulation : La régulation peut fonctionner, comme dans le cas d'Amazon Logistique France. Le RGPD est "pleinement d'actualité" et "très robuste" grâce à sa "neutralité technologique".
      • Mission de la CNIL : "L'informatique doit être au service de chaque citoyen. Elle ne doit porter atteinte ni à l'identité humaine, ni aux droits de l'homme, ni à la vie privée, ni aux libertés individuelles ou publiques."
      • Cas Amazon Logistique France : Amende de 32 millions d'euros (déc. 2023) pour un système de surveillance excessif (mesure interruptions, vitesse d'utilisation du scanner, conservation des données trop longue).
      • Pas de blocage de l'innovation : Le RGPD n'est pas une "loi bloc" mais un cadre qui "ralentit" les usages excessifs pour un développement cohérent avec les droits fondamentaux.
      • Principe de proportionnalité : Équilibre entre les objectifs de performance de l'entreprise et les atteintes aux droits et libertés fondamentales.
      • Garantie complémentaire : Le RGPD (et l'AI Act) est une garantie face aux dérives des technologies traitant massivement les données personnelles, notamment dans le secteur du travail.
      • Frank Fasalina Madinier (Avis à Bruxelles sur le management algorithmique) :
      • Démocratie et dialogue social : La démocratie au travail, c'est un dialogue avec les travailleurs, surtout quand ils sont impactés.
      • Rôle des syndicats : L'organisation collective est un "véritable contre-pouvoir" pour assurer que les outils se déploient de manière juste et choisie, sans supprimer ni aggraver les conditions de travail.
      • Management algorithmique : Ce phénomène se diffuse au-delà des plateformes uberisées.
      • Dialogue social renforcé : Nécessité d'un dialogue social renforcé, car les acteurs ne sont pas toujours préparés.
      • Réglementations adaptées : Les réglementations européennes existent mais ne sont pas toujours adaptées au monde du travail (ex: consentement dans le RGPD).
      • Transparence des algorithmes : Exigences de transparence (inspirées de la directive plateformes) devraient s'étendre à tous les travailleurs.
      • Négociation et discussion : Adapter la législation pour aider les acteurs du dialogue social à négocier et discuter ces questions.
        1. Échanges et Perspectives du Débat public
      • Christophe Moraux (FSU Emploi à France Travail) :
      • Faux libre choix de l'usage : Les objectifs inatteignables et la réduction des moyens conduisent à l'imposition de l'IA aux agents.
      • IA générative et réponses complexes : Les IA prenant en charge les tâches simples, les agents se retrouvent avec des cas exclusivement complexes, conduisant à une "surprécarisation des publics".
      • Normalisation des réponses : L'IA impose une normalisation des réponses complexes.
      • Exemple Match FT et ChatDoc : Outils de mise en relation et de recherche documentaire qui masquent le manque de moyens humains et le temps laissé aux agents.
      • Perte d'autonomie et de sens : L'IA conduit à une perte d'autonomie, de sens au travail et un contrôle accru.
      • Refus de participation : Refus de la direction d'inclure les syndicats dans le comité éthique externe de l'IA, nécessitant la création d'un comité éthique interne.
      • Margaux Prod (Traductrice, collectif En Chair et en Os) :
      • IA non neutre, insoutenable écologiquement, basée sur l'exploitation : Rappelle que l'IA n'est pas neutre, est gourmande en énergie et eau, et repose sur l'exploitation de travailleurs (clic, mine) dans le monde.
      • IA dans la traduction : la post-édition : Un "sabotage" des savoir-faire et une "ubérisation" des métiers. Consiste à corriger des textes générés par machine (souvent fautifs, lissés, standardisés) pour une rémunération 30 à 50% inférieure.
      • Absence d'intention humaine : Le texte généré manque "d'épaisseur intellectuelle" et d'intention artistique.
      • Opposition des artistes : La majorité des artistes-auteurs s'oppose à l'utilisation de leurs œuvres pour alimenter les logiciels d'IA, même avec compensation financière.
      • IA : pas un progrès : Pour la traduction, l'IA est une "automatisation désastreuse des métiers de la culture".
      • Alice Dragon (Indépendante, ex-interministérielle) :
      • Déficit de management : Souligne un "gros déficit de management" dans les ministères et administrations, antérieur à l'IA.
      • Invisibilité des 15 ans d'optimisation : Demande plus de visibilité sur les suppressions d'effectifs et l'optimisation numérique des 15 dernières années.
      • Opportunités de l'IA générative : Potentiel de "mobilité sociale extraordinaire" et d'accès à la formation pour la classe moyenne.
      • Valorisation des savoir-faire invisibles : Comment mieux valoriser les savoir-faire invisibilisés par l'IA.
      • France et régulation : Fière de la position française sur la régulation (ex: CNIL sur Amazon).
      • Expérience citoyenne et autonomie : L'embarquement des citoyens se fera si l'IA leur laisse "l'autonomie de mettre la techno à leur service et pas à l'autre sens".
      • Agnès de Tamarana (Unbias, Twisting) :
      • Implication des syndicats : Invite les syndicats à s'emparer des questions techniques de l'IA, car c'est une technologie "pas si compliquée à comprendre".
      • Exiger transparence : Exiger des registres algorithmiques, même si l'ingénierie passée n'a pas tout documenté.
      • Structuration des institutions : Les institutions et entreprises doivent se structurer pour gérer ces risques techniques.
      • Formation des salariés : Exiger une formation des salariés qui soit "interne" et non "poussée par les providers de solutions tels que Microsoft ou Google".
      • Combat dans les entreprises : Le "push commercial" des entreprises américaines attaque les entreprises européennes en leur faisant croire qu'elles manqueront une opportunité si elles ne s'équipent pas rapidement.
      • IA et augmentation collective : L'IA est formidable pour "augmenter une puissance collective, une action collective, un dialogue collectif, mais certainement pas au niveau individuel".
      • Sandra Lem (Indépendante, accompagnement entreprises) :
      • Course aux outils digitaux : Constat d'une "course aux outils digitaux" avec une mise en place en deux temps (dirigeant-travailleur, dirigeant-technicien) oubliant le lien "technicien-utilisateur final".
      • Manque d'accompagnement : Pas de temps pour les utilisateurs de changer leurs pratiques, entraînant isolement, surcharge de travail et perte d'intelligence collective.
      • Marc Malenfer (INRS) :
      • Dialogue social et prévention des risques : Le dialogue social est crucial en matière de prévention des risques professionnels.
      • Écoute des salariés : Rappelle le rapport du CESE (Assises du travail 2023) qui proposait d'ajouter l'écoute des salariés comme principe général de prévention.
      • Consultation des instances : Les dispositifs modifiant l'organisation du travail doivent faire l'objet de consultations des IRP et d'une expression directe des travailleurs.
      • Inégalité entre entreprises : Les petites entreprises sont "plus démunies" face à la pression commerciale des solutions IA.
      • Formation des développeurs : Nécessité de former les développeurs d'IA aux enjeux de santé au travail.
      • Arthur Talan (Doctorant en Philosophie) :
      • Non-neutralité de la technologie : Il y a un consensus philosophique sur le fait que la technologie n'est jamais neutre. L'IA ne peut être prise indépendamment de sa conception, de ses usages et de ses finalités.
      • Excuse de la neutralité : La promotion de la neutralité est une "excuse pour justifier le développement" de ces technologies et déresponsabiliser.
      • Responsabilités identifiées : Le développement de l'IA engage des responsables et des responsabilités qui doivent être bien identifiées.
      • Christophe Gernet (Radical Exchange) :
      • IA totalitaire vs. autres formes : L'IA n'est pas neutre, mais il existe d'autres manières de la développer que le modèle totalitaire.
      • Responsabilité du déploiement : Importance de la responsabilité dans le choix des projets IA.
      • Management algorithmique : Les managers se retrouvent aussi sous les ordres d'une IA.
      • Négociation collective des données : Milite pour que les données fassent partie de la négociation collective, car leur valeur n'est pas partagée.
      • Eden Carou (Data Scientist) :
      • IA et expertise : "L'IA n'a pas sa place partout" surtout sans collaboration avec les utilisateurs, car "une IA sans l'expertise, elle est une IA pourrie".
      • Dialogue professionnel : Nécessité d'un dialogue entre ceux qui utilisent l'outil et ceux qui le développent.
      • Quentin Pignon (Conseiller numérique) :
      • Web et émancipation vs. algorithmes de recommandation : Le web est émancipateur mais les algorithmes de recommandation invisibilisent le contenu non monétisable.
      • "Bullshitisation" du web : L'IA générative permet de multiplier les vidéos "bullshit" (influenceurs perte de poids, développement personnel), rendant le web "invivable" et plus difficile à repérer pour la vulgarisation scientifique ou artistique.
      • Dépendance et perte de repères : Les repères deviendront plus difficiles pour le travail de conseil numérique.
      • Antoine Lata (Étudiant en sociologie) :
      • Risque de l'arrêt : Qu'arrive-t-il si l'IA s'arrête ou ne fonctionne plus ?
      • Dépossession des savoirs : L'IA peut entraîner une dépossession des savoirs et une dépendance aux outils.
      • Marline de Banque (The Shift Project) :
      • Implications énergétiques et climatiques : Interroge sur les gigawatts et térawatts nécessaires pour l'IA et le numérique, et les nouvelles émissions de GES.
      • Pollution : Quels secteurs peuvent polluer moins pour permettre au numérique de polluer plus ?
      • Guilaine Giersau (Les Petits Débrouillards) :
      • Merci l'Europe : Remercie l'Europe pour ses valeurs digitales mais appelle à ne pas être naïfs.
      • Responsabilité sociale et environnementale : Insiste sur la responsabilité sociale et environnementale, notamment sur l'eau, l'énergie et la pression sur les travailleurs (plateformes, mineurs).
      • Consommateurs : Importance de la responsabilité du consommateur.
      • Connaissance et diffusion des savoirs : La connaissance est essentielle et la diffusion des savoirs est une priorité.
      • Fanny Legal (SNMI) :
      • Impact dans les Missions Locales : L'arrivée d'un "tout petit bout d'IA" depuis le 20 janvier dans les Missions Locales a des conséquences directes : impossibilité de travailler, l'outil devient un "écran" entre le conseiller et le jeune.
      • Manque d'accompagnement : Les collègues n'ont pas été accompagnés ni formés.
      • Sabine Vannek (Avocate, Docteur en droit) :
      • Souveraineté des données : Interroge sur la volonté de la Chine et des États-Unis de capter les données européennes et françaises, transformant l'Europe en "jumeau numérique", posant une "question essentielle de notre souveraineté" avant de s'engager dans la "course effrénée" à l'IA.
        1. Conclusion de la Matinée
      • Eric Meyer :
      • Livre Blanc du CESE : Rappelle la publication du livre blanc "Pour une intelligence artificielle au service de l'intérêt général", voté très largement par la société civile, avec 30 préconisations.
      • Questions clés : Les questions du débat recoupent les travaux du CESE sur la démocratie et la "prise" des travailleurs sur l'outil IA.
      • IA : un outil politique : L'IA n'est pas un outil comme les autres, mais "un outil très politique".
      • Enjeux pour les entreprises : L'IA n'est pas neutre, nécessite des investissements, peut faire perdre la souveraineté et le pouvoir de décision.
      • Impacts sur l'emploi : Suppression ou transformation du travail, inégalités femmes-hommes (métiers féminins potentiellement les plus impactés), intensification, perte de sens et de reconnaissance.
      • Recommandations : Discussions rapides entre partenaires sociaux et gouvernement pour un accord national interprofessionnel sur l'IA. Privilégier le dialogue social avant toute introduction d'IA en entreprise, avec études d'impact et grilles de maturité.
      • Régulation : La société civile doit faire plus et plus fort sur la régulation et l'encadrement pour éviter que la "bigtech" ou des "politico-financiers" imposent leur loi.
      • [Intervenant non identifié, conclusion intermédiaire] :
      • Vivacité de la société civile : L'ensemble des témoignages montre une "vivacité du monde de la société civile", une "lucidité" et une "expertise".
      • IA : un leurre ou un vivier d'énergie ? : L'IA peut être un leurre masquant des structures de pouvoir, mais en assemblée citoyenne, elle devient un "vivier d'énergie et de force indépassable".
      • Action citoyenne sur le pouvoir politique : L'IA mène à l'action citoyenne sur le pouvoir politique, car ce ne sont pas seulement les technologies qui sont politiques, mais les décisions et les actions.
      • Remerciements : Remerciements aux équipes du CESE et du CNNum.
      • Stéphane Brelman (Anthropologue du numérique) :
      • Regarder dans le détail : L'expérience montre qu'il faut regarder "dans le détail" ce que l'IA introduit au niveau du travail et des pratiques.
      • Ne pas craindre les aspects techniques : Comprendre les aspects techniques est essentiel pour intervenir.
      • Exemple de l'opérateur de centrale nucléaire : L'histoire de l'opérateur qui "sent dans le pif" sa décision illustre l'importance de comprendre les micro-décisions et les facteurs non explicites.
      • Manque d'études approfondies : Regrette le manque d'études approfondies sur les micro-décisions et les impacts concrets de l'IA.
      • Granularité détaillée : Nécessité de descendre à un "niveau de granularité très très très très détaillé" pour comprendre les enjeux et les impacts.
      • Tradition française d'analyse : La tradition française d'analyse des activités précises peut être exploitée pour l'IA.
      • Lever les craintes et fantasmes : Comprendre le détail permettra d'enlever "pas mal de craintes et de fantasmes".
      • Remerciements finals : L'ensemble des intervenants et organisateurs se remercient mutuellement pour la qualité des échanges et l'orientation des travaux futurs.
    1. Document de Synthèse : Les Politiques Publiques en Faveur de la Jeunesse – Constats, Défis et Recommandations

      Source Principale : Extraits de la "Présentation du rapport annuel de la Cour des comptes - En direct", par Pierre Moscovici, Premier Président de la Cour des comptes, et compléments par Jacques Cressel, Président de la Commission Économie et Finances du CE.

      • Introduction : Ce document de synthèse présente les thèmes principaux et les idées les plus importantes issues de la présentation du rapport annuel 2025 de la Cour des comptes, axé sur les politiques publiques en faveur de la jeunesse, ainsi que les réactions et compléments du Conseil Économique, Social et Environnemental (CE).

      Ce rapport, fruit d'un travail collectif des chambres de la Cour et des Chambres Régionales et Territoriales des Comptes (CRTC), est enrichi par l'éclairage d'un groupe d'experts universitaires et chercheurs spécialistes de la jeunesse.

      Il s'inscrit dans une nouvelle approche de la Cour, caractérisée par une publication thématique annuelle et une transparence accrue, avec 180 rapports publiés par an.

      I. La Jeunesse en France : Portrait et Enjeux Démographiques

      • Définition et Importance : La jeunesse, définie pour ce rapport comme la tranche d'âge des 15-25 ans, représente un investissement stratégique pour l'avenir de la société. Bien qu'il n'existe pas de définition juridique unique de la jeunesse, cette période est marquée par des étapes clés (croissance, puberté, parcours scolaires, acquisition de droits) et par la construction identitaire.
      • Données Démographiques (15-25 ans) :En 2024, ils sont 9 millions en France, soit 13,2% de la population.
      • Perspective Démographique Alerte : D'ici une quinzaine d'années, cette proportion sera inférieure à celle des plus de 75 ans, ce qui est qualifié d'"hiver démographique" et aura des "conséquences gigantesques dans tous les domaines". Les zones rurales seront les plus affectées.
      • Accès à l'Autonomie Globalement Réussi mais des Défis Persistants :Les jeunes achèvent leurs études en moyenne à 21 ans et demi, et plus de la moitié sont diplômés du supérieur (au-dessus de la moyenne européenne de 42%).
      • Ils quittent le domicile parental à 23 ans et demi (moins élevé que chez certains partenaires européens).
      • À 25 ans, 88,5% des 15-24 ans sont en étude, formation ou emploi. Le taux de jeunes "NEET" (ni en emploi, ni en étude, ni en formation) est de 5,8% pour le chômage et 5,7% pour l'inactivité.
      • Malgré ces succès, la France est "quasiment du simple au double" par rapport à l'Allemagne en termes de NEETs, ce qui "montre en tout cause que l'accès des jeunes à l'emploi demeure en France plus difficile qu'ailleurs".

      II. Coût et Défis des Politiques Publiques en Faveur de la Jeunesse

      • Coût Massif : Les dépenses de l'État spécifiquement dédiées aux 15-25 ans sont estimées à 53,4 milliards d'euros, soit 12% du budget de l'État (et 12% du PIB). Ce montant n'inclut pas les dépenses des collectivités locales et des organismes de sécurité sociale.
      • L'éducation représente les 4/5e de cette dépense (plus de 40 milliards d'euros).
      • Viennent ensuite les politiques de travail et d'emploi, les aides personnalisées au logement, et la protection judiciaire de la jeunesse.
      • Inégalités Accrues : Le rapport met en évidence de profondes inégalités, le "fil rouge" de l'analyse :
      • Pauvreté : Le taux de pauvreté des 18-25 ans est de 10% en France.
      • Territoriales : Les jeunes ruraux sont 20% à accéder à l'enseignement supérieur contre 32% des jeunes urbains, malgré de meilleurs résultats éducatifs. L'accès aux transports collectifs, à la pratique sportive et à l'emploi est également inégal.
      • Information et Accès aux Droits : Un taux important de non-recours aux droits des jeunes est observé.
      • Fragmentations des Politiques Publiques :Il existe une multitude de dispositifs et d'acteurs, mais une "approche structurée et coordonnée" manque, conduisant à une "gouvernance assez fragmentée". Il y a "plutôt des politiques publiques en faveur de la jeunesse qu'une politique de et pour la jeunesse".
      • Les politiques, longtemps centrées sur l'insertion professionnelle, se sont élargies depuis 2009 à l'autonomie, l'égalité des chances, et la participation à la vie publique.

      III. Principaux Enseignements et Recommandations par Domaine

      Le rapport se structure autour de 16 enquêtes réparties en quatre parties :

      • Accès des Jeunes à l'Éducation et à la Formation :
      • Orientation : Coût élevé (400 millions d'euros) mais inefficace pour dépasser les déterminismes et inégalités. Recommandations : modules obligatoires pour les enseignants, adaptation des emplois du temps, réflexion sur un début d'orientation plus précoce.
      • Obligation de Formation (16-18 ans) : Objectif non atteint pour 150 000 jeunes en décrochage. Manque d'indicateurs et de cibles. Recommandations : améliorer le repérage et le suivi, diversifier les solutions, renforcer la collaboration.
      • Échec en Premier Cycle Universitaire : Taux de réussite en 3 ans de seulement 36% (inférieur à la moyenne OCDE). Coût annuel des redoublements et sorties sans diplôme estimé à 534 millions d'euros. Dispositifs de remédiation (1,4 milliard depuis 2017) aux effets non démontrés. Recommandations : mieux identifier les causes, suivre les parcours, évaluer les dispositifs.
      • Accès des Jeunes Ruraux à l'Enseignement Supérieur : Accès moins fréquent et offre moins développée. Recommandations : favoriser la mobilité, réexaminer l'attribution des bourses pour tenir compte de l'éloignement géographique.
      • Aide à l'Entrée des Jeunes dans la Vie Active et l'Autonomie :
      • Emploi des Jeunes : Amélioration depuis 2017 grâce à l'alternance, mais coût des dispositifs a "explosé" (7,3 milliards d'euros en 2023) sans lien de causalité confirmé entre moyens et résultats. Part des NEETs élevée. Recommandations : formaliser une stratégie cyclique, mieux articuler avec le droit commun, cibler les jeunes les plus éloignés de l'emploi.
      • Accès au Logement : Vulnérabilité des jeunes due aux petites surfaces en ville, mobilités fréquentes, revenus faibles. Politique fragmentée, bénéficiant surtout aux étudiants. Recommandations : agir à l'échelle territoriale, renforcer la coordination locale, désigner un chef de file national.
      • Mobilité en Transport Collectif : 38% des jeunes ruraux renoncent à des entretiens d'embauche par difficulté de déplacement. Les réductions tarifaires sont privilégiées sans cibler les plus défavorisés. Recommandations : meilleure connaissance des besoins, ciblage tarifaire sur les ressources, coordination de l'offre.
      • Prise en Charge des Jeunes Majeurs Sortant de l'Aide Sociale à l'Enfance (ASE) : 32 000 jeunes concernés en 2023. Modalités "trop hétérogènes" selon les départements (taux de prise en charge variant de 38% à 83%). Recommandations : garantir un socle de base, mieux insérer dans des dispositifs de droit commun.
      • Politiques de Prévention à Destination de la Jeunesse :
      • Accès au Sport : 80% des jeunes Français sont des sportifs réguliers, mais fort décrochage entre 15 et 25 ans. Politiques orientées vers la performance, négligeant les profils éloignés de la pratique (jeunes femmes, handicapés, difficultés socio-économiques). Recommandations : cibler ces profils dans une stratégie État-collectivités-acteurs privés.
      • Maisons des Adolescents (MDA) : 123 structures accompagnent 100 000 jeunes pour un coût inférieur à 100 millions d'euros. Demande en forte augmentation (mal-être des jeunes). Recommandations : clarifier les attentes, rationaliser les missions, fusionner avec d'autres dispositifs.
      • Addictions (Drogues illicites et Alcool) : "Enjeu crucial" où la France est "moins bonne que dans le reste de l'Union européenne". 1 jeune sur 10 s'estime dépendant ; 2,6% consomment de l'alcool quotidiennement. Cerveau des jeunes (jusqu'à 25 ans) particulièrement vulnérable. Recommandations : efforts de prévention à la hauteur des enjeux, réponse sanitaire insuffisante, approche plus volontaire et transversale (monde éducatif, campagnes, prix minimum de l'unité d'alcool).
      • Obésité : Taux de prévalence alarmants dans les Outre-mer (38% en Nouvelle-Calédonie, 45% en Polynésie française contre 15% en métropole). Causes : alimentation déséquilibrée, sédentarité, précarité. Politiques de prévention non prioritaires. Recommandations : faire de la prévention une priorité.
      • Politiques d'Apprentissage à la Citoyenneté et à la Vie dans la Cité :
      • Journée Défense et Citoyenneté (JDC) : Obligation légale pour 800 000 jeunes/an (coût 100 millions d'euros). Objectifs divers mais dispositif "soumis à de très fortes tensions", raccourci, sur base juridique "fragile". Recommandations : rationaliser les objectifs, le contenu et la base juridique, "remilitariser".
      • Entrée dans l'Impôt sur le Revenu : Seulement 1/4 des moins de 25 ans paient l'impôt ; 1/3 rattachés au foyer parental. Sondage : plus d'un quart des jeunes interrogés jugent "justifié de tricher sur ses impôts". Recommandations : renforcer la sensibilisation à l'impôt avant la majorité fiscale, simplifier la déclaration, envoyer un courrier d'information à 18 ans.
      • Jeunes et Justice Pénale : Surreprésentation des jeunes dans la délinquance (12% de la population, mais 26% des mis en cause, 34% des poursuivis, 35% des condamnés en 2023). Efficacité limitée malgré au moins 2 milliards d'euros/an. Taux de récidive stable depuis 2010. Recommandations : améliorer les outils de compréhension du phénomène, déployer une action précoce auprès des familles, renforcer la coopération entre acteurs.
      • Éducation Artistique et Culturelle (EAC) : Dépense de 3,5 milliards d'euros en 2023. Mise en œuvre hétérogène (dépend de l'initiative des enseignants), qualité variable. Référencement et contrôle minimalistes. Recommandations : garantir un parcours effectif, cohérent, de qualité, piloté par le chef d'établissement ; évaluation régulière des intervenants externes financés par le Pass Culture.

      IV. Messages Transversaux et Orientations Stratégiques de la Cour des Comptes

      • Non la Quantité, mais la Qualité et l'Efficience de la Dépense : "Le problème n'est pas d'abord la quantité d'indépendance notre jeunesse n'est pas sacrifiée elle n'est pas oubliée elle n'est pas abandonnée mais c'est que la qualité de la dépense et son efficience peuvent être améliorées."
      • Mieux Cibler les Politiques Publiques : Renforcer la cohérence et l'efficacité par un meilleur ciblage.
      • Six Grandes Orientations :Mieux différencier les soutiens et les mesures en fonction des publics ciblés (jeunes ruraux, urbains, quartiers prioritaires, ultramarins).
      • Repenser l'organisation et le contenu des parcours de formation initiale pour mieux préparer l'autonomie sociale et économique (l'orientation est une clé).
      • Élaborer une nouvelle stratégie nationale de lutte contre les addictions et promouvoir la santé et le bien-être des jeunes.
      • Renforcer la lisibilité des dispositifs publics pour les jeunes (face au "non-recours" et à la "méconnaissance du système fiscal").
      • Mieux coordonner les actions des acteurs publics et privés, clarifier les rôles et responsabilités.
      • Mettre en place des outils de suivi et d'évaluation rigoureux pour les politiques jeunesse.
      • Nécessité d'un Plan Stratégique : "Doter la France peut-être pour vous y réfléchir d'un plan stratégique en faveur des jeunes en un mot de planifier", pour donner une "colonne vertébrale" aux politiques éclatées.

      V. La Situation des Finances Publiques (Constat Général de la Cour)

      • "Extraordinairement préoccupante" : Taux d'endettement parmi les plus élevés de la zone euro (115%, derrière l'Italie et la Grèce, loin devant l'Allemagne à 60%).
      • Déficit Public : Reste "pas éloigné de 6%", loin des 3% visés et de la moyenne européenne.
      • Enjeux de Financement : Transition écologique, innovation, recherche, défense.
      • Problèmes de Crédibilité, Soutenabilité, Souveraineté : L'augmentation de la charge de la dette réduit les marges de manœuvre pour les services publics essentiels.

      VI. Compléments du CE et Perspectives

      • Convergence des Constats : Le CE, à travers son Président de la commission Économie et Finances, Jacques Cressel, souligne les nombreux points communs avec ses propres travaux, notamment sur l'importance de l'éducation, les inégalités (sociales, éducatives, territoriales), la coordination des politiques publiques et des acteurs, et l'engagement des jeunes.
      • Impact de la Démographie : L'"hiver démographique" est un facteur d'urgence, avec des conséquences "gigantesques" sur les territoires, les régimes sociaux (retraites) et les modes de consommation.
      • Vitesse de Transformation des Compétences : Le système éducatif doit s'adapter à la "vitesse de transformation des besoins de compétences" due notamment à l'intelligence artificielle, qui peut aussi être une "potentialité pour renforcer l'égalité des chances".
      • Enjeu de l'Orientation : Crucial pour limiter les échecs et mieux faire correspondre offre et demande d'emploi, face à une "assez forte insatisfaction des jeunes" et un coût de 4 milliards d'euros par an lié aux dysfonctionnements.
      • Vision Globale et Évaluation : La complexité des enjeux liés à la jeunesse (emploi, logement, transports, éducation) nécessite une "vision globale de l'ensemble de ces politiques". Le CE insiste sur la nécessité de renforcer l'évaluation des politiques publiques en France, un domaine "assez largement en pauvre".
      • Renforcement de la Collaboration : Les deux institutions expriment leur volonté de renforcer leur partenariat pour travailler sur l'évaluation et l'égalité des chances, qui sera le thème du prochain rapport annuel du CE sur l'état de la France.

      Conclusion : Le rapport de la Cour des comptes, tout en dressant un état des lieux lucide des défis posés par les inégalités et la fragmentation des politiques, insuffle une note d'optimisme.

      Il ne s'agit pas de déplorer un manque d'investissement, mais bien d'améliorer la "qualité de la dépense" et son "ciblage".

      La jeunesse française est perçue comme un "atout", une "ressource inestimable" et "porteuse d'un dynamisme", justifiant ainsi un "témoignage de confiance".

      Les recommandations visent à structurer une véritable "politique de et pour la jeunesse", intégrant planification, coordination et évaluation rigoureuse pour garantir une meilleure égalité des chances.

    1. Compte-rendu détaillé : La prévention en santé, passons aux actes !

      • Ce document de synthèse est basé sur les discussions et présentations tenues lors de la séance plénière du CESE consacrée à la prévention en santé, avec un accent particulier sur la santé au travail.

      Il vise à identifier les thèmes principaux, les idées clés et les faits marquants soulevés par les différents intervenants, en incluant des citations pertinentes.

      1. La Prévention : Un Enjeu Sociétal Majeur et Sous-Estimé

      • L'ensemble des intervenants s'accorde sur l'importance cruciale de la prévention en santé, qui dépasse largement le seul cadre médical pour englober la société dans son ensemble. Malgré cette évidence, la prévention demeure trop souvent le "parent pauvre des politiques publiques".

      1.1 Prévenir Plutôt que Guérir : Une Évidence non Appliquée

      Le constat est unanime : "Prévenir plutôt que guérir, voilà qui semble évident et pourtant la prévention est encore trop souvent le parent pauvre des politiques publiques." (Déclaration introductive).

      Il est souligné que la santé ne se limite pas aux hôpitaux, médecins et médicaments, mais est une affaire de société.

      1.2 Un Investissement, non un Coût

      • Investir dans la prévention est présenté comme une "stratégie d'avenir", non un coût. Les bénéfices sont multiples : "moins de souffrance évitable, moins de dépenses publiques sur le long terme, plus de qualité de vie". (Déclaration introductive).

      De plus, elle redonne aux citoyens un "pouvoir sur leur propre santé", les plaçant comme "acteur de tout" plutôt que comme patient.

      1.3 Historique et Concepts : Prévention vs Promotion de la Santé

      • Le Professeur Emmanuel Ruche, Président de la Conférence Nationale de Santé, met en lumière une spécificité française : une approche historiquement "très centrée sur la prévention et peut-être un peu moins sur la promotion de la santé". Il insiste sur la complémentarité de ces deux approches, qu'il faut "articuler". Il cite le Directeur Général de l'OMS : "La santé ne commence pas dans les cliniques ou les hôpitaux pas plus que la justice ne commence dans les tribunaux ou que la paix ne commence sur le champ de bataille. La santé commence dans les conditions dans lesquelles nous sommes nés et avons grandi dans les écoles les rues les lieux de travail…". Cette vision élargie souligne que la santé est façonnée par les "déterminants commerciaux" (tabac, alcool, aliments transformés, combustibles fossiles), qui sont responsables d'un tiers des décès dans le monde.

      1.4 Efficacité et Retour sur Investissement

      • L'efficacité des actions de prévention n'est "plus à démontrer" (Professeur Ruche), s'appuyant sur des "données probantes bien établies".

      Le retour sur investissement est "une évidence" pour les études scientifiques, l'exemple de la prévention du tabagisme montrant "1900 % de retour sur investissement".

      Malgré cela, le financement reste difficile, nécessitant des "dispositifs de financement incitatifs et pérennes" et pluriannuels.

      2. Les Déterminants de la Santé et les Inégalités

      La discussion met en évidence la multiplicité des déterminants qui influencent la santé, soulignant leur rôle dans la création et l'aggravation des inégalités.

      2.1 Déterminants Sociaux et Économiques

      • Emmanuel Cambois, Directrice de recherche à l'INED, explique que les inégalités de santé se créent non seulement par des comportements individuels mais aussi par des facteurs "qui s'imposent en quelque sorte aux individus et qui peuvent se combiner à d'autres". Ces facteurs incluent la "situation socio-économique", l'"entourage, soutien social, et à contrario l'isolement", la "charge mentale", les "traumatismes" et les "phénomènes d'exclusion". Les inégalités se manifestent aussi dans l'accès aux soins et dans les parcours professionnels (pénibilités, carrières hachées). L'approche en "parcours de vie" est essentielle, car les risques "se cumulent au cours de la vie" rendant certains groupes "beaucoup plus à risque de problème de santé et beaucoup moins en capacité de lutter contre ces risques". La prévention doit donc "couvrir les différentes sphères d'activité qu'elle soit domestique professionnelle ou social et surtout suivre l'ensemble de des âges de la vie".

      2.2 Déterminants Environnementaux et Risques Émergents

      • Jean-François Guégan, Directeur de recherche à l'INRAE, aborde l'impact de l'environnement sur la santé, notamment face aux "évolutions climatiques". Il souligne une "confusion impressionnante" et un "manque de culture" sur les liens entre biodiversité et santé. Les activités humaines, comme la déforestation et l'élevage, sont identifiées comme des facteurs majeurs dans l'émergence de pandémies zoonotiques. Il met en garde contre une vision "naïve, idyllique et tronquée" de la nature, illustrant que même la "réintroduction de la nature en ville" peut introduire des "dangers microbiologiques" (moustiques, rongeurs, germes pathogènes). Le risque infectieux est un produit entre "des aléas" (micro-organismes) et "l'exposition humaine et la vulnérabilité des populations".

      2.3 Déterminants Commerciaux et Influence de l'Industrie

      • Karine Galopel Morvent, Professeure à l'EHESP, met en lumière le rôle des "acteurs commerciaux" qui "influencent de manière délétaire la santé et l'équité de la population". Elle cite le marketing et le lobbying comme des pratiques commerciales préoccupantes, en particulier pour les industries du tabac, de l'alcool, des aliments ultra-transformés et des combustibles fossiles, responsables d'environ "un tiers des décès". Elle dénonce le "pouvoir accru des multinationales" et la sous-estimation des budgets marketing par rapport aux campagnes de prévention (ex: 250 millions d'euros par an pour l'alcool contre 3 millions pour la prévention). Le lobbying est "très fort", bloquant des avancées comme la hausse des taxes sur le tabac ou la généralisation du Nutri-Score. Les solutions incluent l'"encadrement des conflits d'intérêt", la "transparence sur le lobbying", l'"interdiction de publicité" et l'"information et éducation sur ces déterminants commerciaux".

      2.4 L'Approche Genrée en Santé

      • La question de l'approche genrée dans les politiques de santé est soulevée.

      Emmanuel Cambois et Lormier soulignent que la santé des femmes et les défis auxquels elles sont confrontées (troubles musculosquelettiques, troubles anxiodépressifs, carrières hachées) sont souvent sous-estimés ou mal compris.

      Il est crucial d'adopter des "approches différenciées entre les hommes et les femmes" dans la prévention et la personnalisation des soins, car les symptômes et les parcours de vie peuvent varier considérablement.

      3. Innovations et Défis dans la Prévention

      La discussion explore les nouvelles méthodes et outils, notamment le numérique, tout en identifiant les freins persistants à une prévention efficace.

      3.1 Le Numérique : Opportunité et Défi

      • Lormier, experte à l'Institut Montaigne, présente le numérique comme une "réponse indispensable au défi actuel de la prévention", offrant "personnalisation", "ciblage amélioré", "meilleure adhésion du patient" et "anticipation des risques".

      Les données de santé massives et l'intelligence artificielle permettent une "détection précoce" (ex: radiologie), un "soutien personnalisé" (applications mobiles, chatbots) et une "télésurveillance" des paramètres vitaux.

      Cependant, des "freins" persistent : un "décalage culturel et organisationnel" du système de santé axé sur le curatif, la nécessité de "former" les professionnels de santé, et les "déterminants numériques de la santé" (accès, connectivité, confiance). L'objectif est de passer "d'une médecine épisodique à un suivi continu".

      3.2 Financement et Volonté Politique

      • Pierre-Louis Bra, Inspecteur général des affaires sociales, nuance la question du financement, affirmant que la prévention n'est pas "simplement des financements" mais "la capacité à mettre en cause des intérêts privés".

      Le succès de la lutte contre le tabagisme, principalement par l'augmentation des taxes, en est la preuve. Il souligne que "ça ne demande pas de financement public, au contraire, c'est des taxes, ça apporte des financements publics".

      Il critique le recours au "bon sens" plutôt qu'aux "données probantes" pour certaines initiatives de prévention coûteuses (ex: bilans de santé périodiques).

      Il insiste sur la nécessité d'investir dans les réseaux de prévention de base (médecine scolaire, PMI, médecine du travail), qui sont "en difficulté".

      3.3 Gouvernance et Coordination

      • Plusieurs intervenants appellent à une meilleure gouvernance et coordination des politiques publiques.

      Le Professeur Ruche et Emmanuel Cambois insistent sur la nécessité d'une "intersectorialité et interministérialité" au niveau national, et d'une "déclinaison territoriale au plus près des territoires et des populations".

      La promotion de la santé plaide pour "introduire la santé dans toutes les politiques publiques".

      La CNS recommande une "stratégie nationale de santé" sur 10 ans et des "feuilles de route prévention promotion de la santé" au niveau territorial avec un "rendu de compte".

      4. La Santé au Travail : Un Pilier de la Prévention

      La deuxième partie de la séance est spécifiquement dédiée à la santé au travail, soulignant ses défis et les pistes d'amélioration.

      4.1 Des Chiffres Alarmants

      • Les chiffres présentés par Cécile Gondard Lalane et Jean-Christophe Repont sont frappants : "1287 décès liés au travail par an", "5800 maladies professionnelles accidents et 47400 maladies professionnelles" en 2022.

      Cela montre que "malgré un accord interprofessionnel national sur la prévention au travail une loi en décembre 2020 une loi en août 2021 sur la prévention au travail, on est à un niveau qui stagne en terme de prise en charge de prévention primaire au travail".

      4.2 Des Bouleversements qui Pèsent

      Le monde du travail est confronté à des "bouleversements" majeurs :

      • Réchauffement climatique : La chaleur a des "effets physiologiques" et des "conséquences mortelles", entraînant des "pertes de productivité" et des "risques psychosociaux".
      • Approche genrée : La santé au travail est encore "trop centrée sur les hommes". Alors que les accidents du travail ont baissé de 27% pour les hommes sur 20 ans, ils ont augmenté de "plus de 41 %" pour les femmes.

      Les troubles musculosquelettiques, première cause de maladie professionnelle, touchent "trois femmes sur 5 et un homme sur deux". La "répartition genrée du travail domestique" impacte aussi la santé mentale des femmes. * Santé mentale : Les principaux facteurs de risque sont le "stress chronique" (80%, surcharge mentale, burnout, troubles du sommeil, suicide) et les "violences internes ou externes" (20%, incivilités, harcèlement, discrimination).

      La "fatigue liée aux outils et à l'utilisation des outils numériques" est un nouveau défi. * Pratiques managériales : Elles sont "déterminantes" mais apparaissent "trop verticales et trop hiérarchiques" en France, avec un manque de "confiance au salariés" et un "besoin de maîtrise et de contrôle encore très important" (Dr. Florence Bénichou).

      4.3 Les Nouveaux Visages du Travail

      • L'étude met en lumière la situation des travailleurs indépendants et des plateformes. Les livreurs et VTC subissent des "risques forts" (accidents, TMS, problèmes de santé mentale dus à la "pression" des algorithmes et à l'angoisse de la perte de revenus). L'accès aux assurances est "très peu connu" et utilisé.

      • 4.4 Pistes d'Amélioration : Vers une Prévention Primaire Renforcée

      Les rapporteurs proposent trois axes pour améliorer la prévention au travail :

      • Former et sensibiliser : Renforcer la formation des étudiants en médecine à la santé du travail et environnementale pour attirer de jeunes professionnels. Étendre la formation à la santé du travail aux "acteurs du dialogue social", salariés et employeurs, avec des "formations communes".
      • Identifier et prévenir : Accompagner les dirigeants de TPE dans la mise en œuvre du "document unique". Souligner le rôle des "services de prévention en santé au travail" et des "branches professionnelles". Insister sur l'"approche genrée" et l'intégration du "management" dans la prévention.
      • Anticiper par le dialogue social et l'écoute : Inscrire l'"écoute des salariés" dans les principes généraux de prévention du Code du travail, car "ce sont bien les travailleurs qui connaissent mieux les risques et auxquels ils s'exposent". Prendre en compte l'"articulation des temps de vie" et le "déploiement de l'IA" dans le dialogue social.

      4.5 Des Exemples de Succès et une Volonté Politique

      • Bernard Tibba, co-président de la charte sociale des JO 2024, témoigne du succès de cette initiative qui a permis de diviser par quatre l'accidentalité sur un "chantier énorme".

      Cette approche, qui combine "volonté politique, des moyens, une mobilisation des différents acteurs publics comme privés", montre qu'il n'y a "pas de fatalité en matière d'accidentologie".

      Madame Astrid Panosian Bouvet, Ministre chargée du travail et de l'emploi, salue le rapport et confirme l'importance du sujet. Elle rappelle que la santé au travail n'est pas "assez haut sur l'agenda public".

      Elle insiste sur la "lutte contre les accidents du travail grave et mortel", un phénomène qui n'est "pas une fatalité" et dont beaucoup sont "évitables".

      Elle confirme la volonté de "capitaliser sur ce succès" des JO et de "dupliquer la méthode" notamment via le "dialogue social au sein des branches" et une "meilleure coopération interministérielle".

      Elle souligne que la prévention doit être au "cœur des préoccupations" et non un "codicille au contrat de travail".

      5. Conclusion Générale

      • La prévention en santé est un impératif stratégique, économique et social. Elle exige un changement de paradigme, passant d'une logique curative à une culture proactive.

      Cela implique une approche globale et transversale, intégrant les déterminants sociaux, environnementaux et commerciaux.

      Le numérique offre des outils prometteurs, mais leur déploiement doit être inclusif et accompagné.

      Le financement n'est pas le seul obstacle ; la capacité à remettre en question des intérêts privés et la volonté politique sont primordiales.

      La santé au travail, avec ses défis liés aux changements climatiques, aux inégalités de genre et aux nouvelles formes de travail, est un exemple criant de la nécessité d'une prévention primaire renforcée, basée sur le dialogue social et l'écoute des travailleurs.

    1. Synthèse du Briefing : L'Accès à une Alimentation de Qualité et la Précarité Alimentaire en France

      • Le Conseil Économique, Social et Environnemental (CESE) a mené une discussion plénière cruciale sur le projet d'avis intitulé "Permettre à tous de bénéficier d’une alimentation de qualité en quantité suffisante".

      Cet avis met en lumière une situation alarmante en France où l'accès à une alimentation saine et équilibrée, en quantité suffisante, qui est un droit fondamental, n'est pas pleinement effectif.

      La précarité alimentaire s'aggrave, touchant près de 16% de la population, soit 8 millions de personnes ayant eu recours à l'aide alimentaire en 2023, un chiffre ayant triplé en 10 ans.

      De plus, les conséquences sanitaires sont préoccupantes, avec un tiers des adultes et plus d'un enfant sur dix en surpoids, et une augmentation des maladies chroniques liées à une alimentation déséquilibrée, représentant un coût de 11 milliards d'euros par an pour l'assurance maladie.

      L'avis propose une approche systémique, interministérielle, et territoriale pour adresser ces défis majeurs.

      Thèmes Principaux et Idées Clés :

      Constat Alarmant de la Précarité Alimentaire et de ses Conséquences Sanitaires et Économiques :

      • Augmentation de la précarité : "la précarité alimentaire ne cesse de s'aggraver elle touche aujourd'hui près de 16 % de la population ce sont 8 millions de personnes qui ont eu recours à l'aide alimentaire en 2023 un chiffre qui a presque triplé en 10 ans."
      • Impact sur la santé : "un/tiers des adultes et plus d'un enfant sur 10 sont en surpoids l'obésité les maladies cardio-vasculaires le diabète certaines formes de cancer liées à une alimentation déséquilibrée se développe de façon préoccupante."

      Le Professeur Daniel Nizeri, président du comité de suivi du Plan National Nutrition Santé (PNNS), souligne que l'alimentation déséquilibrée est "directement impliquée dans le développement des principales pathologies chroniques", coûtant "55 milliards d'euros" et entraînant "plus de 50000 décès par an".

      • Coût financier considérable : "plus de 11 milliards d'euros par an pour les seules pathologies liées à la nutrition."
      • Dépendance économique et choix contraints : La hausse durable des prix alimentaires (+12% en 2023) force les ménages modestes à privilégier des produits moins chers et souvent ultra-transformés, au détriment des produits bruts, frais et locaux. "88 % des consommateurs disent comparer systématiquement les prix pour 68 % c'est même le premier critère d'achat."
      • Perte de souveraineté alimentaire : "près de 40 % de notre alimentation est aujourd'hui importée avec des pics de dépendance atteignant 75 % pour la volaille en restauration hors domicile et plus de 50 % pour les fruits et légumes."

      Rôle des Banques Alimentaires et Aggravation de la Précarité :

      • Action et Objectifs : Le réseau des banques alimentaires est le premier réseau national d'aide alimentaire, accompagnant près de 2,4 millions de personnes.

      Leurs objectifs sont de "lutter simultanément contre la précarité alimentaire et le gaspillage alimentaire, utiliser l'aide alimentaire comme créatrice de lien social, participer à l'amélioration de l'alimentation distribuée, s'adapter constamment à l'évolution des besoins." * Impact de l'inflation : La crise inflationniste est la "première cause du recours à l'aide alimentaire." * Profil des personnes aidées : 42% touchent un revenu mensuel inférieur ou égal à 1000 €, une personne sur deux vit en logement social, et un tiers des personnes en emploi vit en milieu rural, signe de l'aggravation de la précarité en milieu rural et de l'émergence des "travailleurs pauvres". * Problèmes de santé et renoncement aux soins : "78 % déclarent au moins un problème de santé" et "déclare avoir renoncé à ses soins pour des raisons financières." * Amélioration de la qualité de l'aide alimentaire : Les banques alimentaires ont progressé de 8 points en 10 ans pour les fruits et légumes et intègrent l'accompagnement social via des ateliers (anti-gaspi, activité physique, nutrition santé, etc.) pour favoriser l'autonomie et la participation.

      Propositions et Préconisations du CESE (16 au total) :

      • Axe 1 : Gouvernance et Priorisation Faire de l'alimentation une grande cause nationale : "mobiliser et sensibiliser le plus largement possible."
      • Gouvernance interministérielle : Mettre en place un "pilotage centralisé au plus haut niveau de l'État" pour coordonner les politiques publiques (agriculture, santé, solidarité, environnement).
      • Généralisation et soutien des Projets Alimentaires Territoriaux (PAT) : Assurer leur "généralisation sur tout le territoire" avec des moyens financiers pérennes, en associant tous les acteurs.
      • Axe 2 : Alimentation Équilibrée et Qualité des ProduitsGénéralisation du Nutri-score : Rendre le Nutri-score "obligatoire au niveau européen", tout en précisant qu'un mauvais score n'est pas une interdiction de consommer, mais une incitation à la modération et à un régime équilibré.
      • Réduction des substances nocives : Fixer des objectifs de "réduction de la teneur en sel, en sucre, en matière grasse des produits transformés et ultra transformés" avec un calendrier. Les produits ne respectant pas ces objectifs pourraient faire l'objet d'une taxation.
      • Évolution des réglementations : Faire évoluer les réglementations "plus systématiquement et rapidement" dès que des études scientifiques prouvent la nocivité de substances (additifs chimiques, résidus de pesticides, ultra-transformation).
      • Encadrement de la publicité : Renforcer l'encadrement de la publicité ciblée sur les jeunes pour les produits posant problème.
      • Interdiction des produits "snacking" près des caisses : Mettre fin à la présence de "produits sucrés salés ou gras de type snacking près des caisses des magasins."
      • Interdiction des publicités axées uniquement sur les prix : Interdire les publicités de la grande distribution qui "ne portent que sur les prix sans prendre en compte la qualité des produits", qui dégradent l'image de la nourriture et impactent les revenus des agriculteurs.
      • Obligation d'indication d'origine : Étendre l'obligation d'indiquer le pays d'origine aux "principaux ingrédients végétaux dans les produits transformés et dans les plats servies hors domicile."
      • Soutien aux filières locales : Fédérer les plans de soutien aux filières locales de fruits, légumes et légumineuses.
      • Éducation à la cuisine : Former dès le plus jeune âge à la préparation et à la cuisine des produits bruts.
      • Simplification du programme européen lait et fruit à l'école : Simplifier les modalités pour une meilleure utilisation des budgets alloués.
      • Axe 3 : Lutte contre la Précarité Alimentaire Pérennisation des dispositifs : Rembourser la TVA sur les achats de denrées des associations d'aide alimentaire et maintenir/renforcer les financements publics. Le produit de la taxation des produits trop gras, salés, ou sucrés pourrait abonder ces financements.
      • Organisation des Assises Nationales : Organiser des "assises nationales de la lutte contre la précarité alimentaire" pour recenser, évaluer et diffuser les initiatives efficaces et assurer une bonne couverture territoriale.
      • Axe 4 : Restauration Collective et Filières Locales Soutien aux petits acteurs économiques : Systématiser l'accompagnement et la formation des agriculteurs pour répondre aux marchés publics (réponses groupées).
      • Développement des plateformes régionales : Faciliter la mise en relation entre acheteurs et producteurs.
      • Assouplissement des règles de marché public : Relever les seuils de dispense des règles de marché public (ex: de 40 000 à 100 000 € HT) et renforcer la formation des acheteurs sur les pratiques existantes.

      Points de Débat et de Divergence au sein du CESE :

      • Taxation des produits : L'idée de taxer les produits trop gras, salés ou sucrés a suscité des débats. Certains groupes comme "Artisanat et profession libérale" s'y opposent, jugeant cette approche "ni constructive ni réaliste", et craignant la suppression ou la taxation de produits du terroir. D'autres, comme la CFDT, la soutiennent comme une mesure "courageuse et pragmatique".
      • Transparence des prix et des marges : Des groupes comme "Alternative sociale et écologique" regrettent que "la commission a refusée de formuler une préconisation sur la transparence des prix", la considérant comme un "levé essentiel pour limiter les surmarche et surtout pour reconstruire la confiance entre tous les acteurs." Le groupe des "Non inscrits" note également que le sujet de la formation des prix, où "règne l'opacité la plus complète sur les marges des intermédiaires", a été évoqué mais n'a pas donné lieu à des préconisations concrètes.
      • Interdiction de la publicité : La proposition d'interdiction pure et simple de la publicité pour les produits gras/sucrés/salés auprès des enfants a été adoucie en "encadrement renforcé" pour tenir compte de la difficulté de mise en œuvre et de la nécessité de transition, bien que certains membres l'auraient souhaitée plus stricte.
      • La "Sécurité Sociale de l'Alimentation" (SSA) : Le sujet, bien que mentionné comme potentiellement prometteur et en cours d'expérimentation, n'a pas été traité directement dans l'avis en raison de sa complexité et de la nécessité de dispositifs financiers dépassant le champ de compétence du CESE. Certains groupes, comme "Alternative sociale et écologique" et "Organisations étudiantes et mouvements de jeunesse", souhaitent un soutien plus affirmé à ces "expérimentations des caisses alimentaires communes".
      • Produits ultra-transformés : Le groupe des entreprises s'oppose à la notion d'"aliment ultra transformé", citant un rapport de l'Anses soulignant les limites de la classification NOVA.
      • Vision générale de l'industrie : Le groupe des entreprises regrette le manque de reconnaissance des progrès déjà réalisés par la filière et l'absence de soutien aux acteurs, s'opposant aux "sanctions ou des taxes supplémentaires", craignant que cela affaiblisse l'industrie agroalimentaire française. Ils votent contre.
      • Inauguration de l'Exposition "La Belle Gamelle" :
      • En marge de la discussion, une exposition est consacrée à "La Belle Gamelle", une société coopérative d'insertion qui propose de la restauration en formant et employant principalement des personnes réfugiées.

      Cette initiative, saluée comme "une très belle entreprise" et "une œuvre une action qui s'inscrit directement dans la volonté de se placer ailleurs et même de combattre ces remugles insupportables", met en lumière la capacité de l'entrepreneuriat social à concilier qualité alimentaire et insertion professionnelle.

      Elle est présentée comme un exemple des valeurs civiques fortes et de la démocratie sociale.

      Conclusion du Vote :

      Le projet d'avis "Permettre à tous de bénéficier d’une alimentation de qualité en quantité suffisante" a été adopté avec 94 votes pour, 17 contre et 11 abstentions.

      Ce vote témoigne d'un consensus large sur l'urgence d'agir face à la précarité alimentaire et aux enjeux de santé publique, malgré des divergences notables sur les moyens et l'étendue des mesures à prendre.

      Le CESE réaffirme ainsi son rôle dans l'éclairage de la décision publique sur des sujets de société fondamentaux.

    1. Briefing Document : Désenclaver pour un espace de vie apaisé - Quartiers urbains populaires #2 : En direct

      Date : 14 juin 2024 (référence aux dates mentionnées dans les sources)

      • Contexte : Ce document synthétise les discussions et les témoignages présentés lors du deuxième rendez-vous du Conseil économique, social et environnemental (CESE) sur les quartiers urbains populaires, intitulé "Parlons solution".

      L'événement fait suite aux violences de 2023 et s'inscrit dans une démarche d'écoute active et d'immersion dans la réalité de ces quartiers. L'objectif principal est de "désenclaver les quartiers pour y faire advenir des espaces de vie apaisés".

      Thèmes Majeurs et Idées Clés :

      1. Revalorisation et Reconnaissance des Quartiers Populaires :

      • Contre les regards condescendants : Le CESE souhaite lutter contre les perceptions négatives et stigmatisantes des quartiers populaires, souvent réduits à leurs défis (pauvreté, enclavement, discrimination). Thierry Baudet, président du CESE, affirme que ces quartiers "méritent mieux que les regards trop souvent condescendants ou anxiogène qu'on leur porte".
      • Lieux de résilience et de créativité : Au-delà des difficultés, ces quartiers sont décrits comme des "lieux de résilience, d'engagement, de créativité, de solidarité" avec un "vivier de talent, une densité associative, une capacité d'initiative que peu de territoires peuvent revendiquer avec autant de vitalité".
      • Vision positive : Swad Bellad souligne l'importance de voir "le verre à moitié plein et même souvent plein et non pas comme peuvent le faire beaucoup effectivement de de médias de fixés sur les vides". Il s'agit de "braquer les projecteurs sur ceux et celles qui font et qui souvent comblent les manques voire déficit des pouvoirs publics".
      • Innovation sociale : Nora Amadi insiste sur la nécessité de parler de ces quartiers pour leur "dimension d'innovation sociale", plutôt que pour les seules "exceptions" (violences, colère). Ismaël Cousin utilise les termes "innovation et développement" pour décrire l'approche nécessaire.
      • Changer la narration : L'objectif est de "tordre le bras à cette loupe politique et médiatique" et de "démontrer que des solutions existent". Ismaël Cousin et Wael Wael soulignent l'importance de former les jeunes à l'écriture de scénarios et à la réalisation de documentaires pour qu'ils puissent "raconter eux-mêmes leur récit" et changer la "narration" dominante. Sana Sanouli de Banlieue Climat met en avant l'importance des "fissures d'espoir" et de changer le regard sur ces quartiers : "les quartiers populaires c'est l'avenir c'est la richesse de la France".

      2. Le Désenclavement : Au-delà de l'Infrastructure, un Enjeu Humain et Social :

      • Briser les barrières visibles et invisibles : Le désenclavement ne se limite pas à "poser une ligne de tramoué ou ouvrir une nouvelle médiathèque". Il s'agit de "briser les barrières visibles et invisibles celles qui enferme qui stigmatise qui fracture".
      • Mobilité et accès à l'emploi : Imen Swed Cadir Mbarc insiste sur le rôle crucial des transports (T9, ligne 14 du métro) pour "rapprocher nos habitants des secteurs d'emploi" et connecter les villes de banlieue entre elles. Le permis de conduire pour les mères, évoqué par Bartha chez Mamam, est également un levier d'autonomisation et de désenclavement.
      • Accès à la culture : La culture est un vecteur essentiel. Faudel Kepier (Micro-folie) et Valérie Suner (Théâtre de la Poudrerie) travaillent à rendre la culture accessible au plus près des habitants, souvent victimes d'"autocensure" et se sentant "pas légitimes" à fréquenter les grands musées ou théâtres. L'objectif est de créer une "curiosité culturelle" et de faciliter le passage vers les institutions culturelles classiques.
      • "Aller vers" et "Faire avec" : C'est une démarche clé. Le Théâtre de la Poudrerie va "rencontrer les gens chez eux à domicile" et inclut les habitants dans le "processus de création artistique". Ismaël Cousin (Action Baumayiller) amène le cinéma "en bas d'immeuble". Cette approche participative est essentielle pour que les habitants "s'approprient" les projets. Valérie Suner le résume : "quand on embarque tout le monde c'est pas une question de lieu en fait c'est une question de dynamique".
      • L'ingénierie locale : Maryline Picherie et Cadir Mbarc soulignent le rôle fondamental des élus et des équipes locales pour impulser des politiques de proximité et recréer du lien social. Le Conservatoire de musique et de danse de Melun, transféré dans les quartiers nord, en est un exemple de succès en termes de mixité.

      3. Le Rôle Central de la Culture et de l'Éducation :

      • Démocratisation de l'art : Le projet Micro-folie vise à apporter les œuvres des grands établissements culturels "au plus près des habitants", en utilisant le numérique pour démocratiser l'accès à l'art. Valérie Suner met en avant le "théâtre de la social", où "le cœur de la rencontre de l'autre de celui qui est différent de moi est au centre de nos préoccupations".
      • La culture comme vecteur de lien social : À Melun, la médiathèque "la boussole" est un "outil hybride" où "la culture et le vecteur de lien social dans le quartier". Brahim Timrich (Le Grand Bleu) utilise l'apprentissage de la natation comme un moyen de "réapproprier la mer" pour les habitants de Marseille, au-delà de la simple compétence technique.
      • L'école de la République : Plusieurs intervenants insistent sur le rôle crucial de l'école. Maryline Picherie regrette que l'école "n'est pas assez ambitieuse" et ne permette pas toujours aux enfants des quartiers d'avoir les "mêmes chances". Le financement des Cités éducatives est salué par Imen Swed, mais questionné par Maryline Picherie sur son financement. La difficulté pour les jeunes à trouver des stages est également évoquée comme un frein à leur parcours.
      • Changer les imaginaires : La culture et les initiatives comme celles de Wael Wael (documentaires "Mon incroyable 93", "Banlieue Tour d'Europe") visent à "détourner ces récits" négatifs et à montrer la "réalité" et le "vécu" des territoires.

      4. Les Défis et la Nécessité d'une Action Collective et Durable :

      • Baisse des financements publics : Saïd Ramani et Maryline Picherie expriment leur inquiétude face à la baisse des budgets de la politique de la ville ("moins 3% pour chaque contrat de ville et 5% qui sont gelés"), mettant en péril les actions locales et le maintien des services essentiels pour les populations. La question des "quartiers d'été" est particulièrement préoccupante.
      • Lutte contre les rixes : Awa Diablé, mère de victime, témoigne de la douleur des familles et de la nécessité de "parler aux jeunes" dans leurs mots ("embrouille" plutôt que "rixe") pour leur faire prendre conscience de la gravité des conséquences. Mohamed Magassa et Awa Diablé dénoncent un "abandon de l'État" face à ce phénomène, soulignant que les associations "pâient les lacunes". Le fait que les jeunes transportent des armes blanches par peur est un constat alarmant.
      • Rôle des familles et des habitants : Awa Diablé insiste sur la "responsabilisation des parents" et l'importance de la "parentalité". Mohamed Magassa met en avant la formation des mères pour qu'elles deviennent des actrices clés dans la prévention des rixes, valorisant leur "émancipation".
      • Écologie Populaire : Camera Vit (Picpic Environnement) et Sana Sanouli (Banlieue Climat) promeuvent une "écologie populaire" qui redonne le "pouvoir d'agir aux citoyens", en particulier aux mères. Elles dénoncent l'exclusion des habitants des quartiers des débats sur le climat, alors qu'ils sont les premiers touchés par la pollution et les impacts environnementaux. L'École Populaire du Climat et le Collectif des Mamans pour le Climat sont des initiatives concrètes qui "arment" les habitants pour faire valoir leurs droits.
      • Importance des réseaux et de la collaboration : Leila Breton (Social Hackers Lab) souligne la complexité des financements européens et l'importance d'accompagner les associations à les obtenir. Elle encourage la "collaboration entre les différentes structures pour créer des modèles de collaboration" face à la raréfaction des moyens. L'appel à "se coaliser" et à "sortir des silos" est récurrent.
      • Reprendre le pouvoir et la narration : La phrase de Nelson Mandela "Tout ce qui est fait pour moi sans moi est contre moi" est citée comme un principe fondamental. L'idée est que les personnes concernées doivent "porter [leurs] propres revendications" et non plus laisser d'autres "s'exprimer à [leur] place". La mobilisation des jeunes, des femmes et des habitants des quartiers est perçue comme une "prise de pouvoir".

      Conclusion : Cette conférence met en lumière la richesse et la vitalité des quartiers populaires, tout en soulignant les défis structurels auxquels ils sont confrontés, notamment le manque de moyens et la stigmatisation.

      Les solutions présentées reposent sur une approche participative, une valorisation des initiatives locales, un réinvestissement dans l'accès à la culture et à l'éducation, et une volonté de "désenclaver" au sens large : briser les barrières physiques et mentales, recréer du lien social et donner le pouvoir d'agir aux habitants pour qu'ils soient les acteurs de leur propre développement et du "vivre ensemble".

      Le message final est clair : "il n'y a pas de fatalité" et l'action collective est la clé pour un avenir apaisé.

    1. Note de Synthèse : Réflexion sur les Politiques de l'Enfance en France

      Date : 27 Octobre 2023 Sujet : Bilan et perspectives des politiques publiques de l'enfance en France, rôle du Haut Commissariat à l'Enfance, défis et pistes d'action.

      Source : Extraits de "CCTE - Session#1 : Échanges avec Sarah EL HAÏRY - En direct"

      1. Création et Mission du Haut Commissariat à l'Enfance (HCE)

      Le Haut Commissariat à l'Enfance est une institution nouvellement créée, ayant moins de trois mois d'existence au moment de l'intervention.

      Sa création répond à un besoin jugé "criant" de repenser la place de l'enfant dans la société française de manière globale.

      • Motivation : Sarah El Haïry, Haute Commissaire à l'Enfance, souligne que la réflexion sur l'enfant était auparavant fragmentée : "on pense les enfants vous savez par avec une casquette à chaque fois soit on le pense comme un élève soit on pense l'enfant comme finalement bah c'est notre enfant... soit on le pense finalement comme parfois un patient... soit on le pense comme un adhérent d'une voilà d'une aventure associative culturelle ou sportive mais on n'avait pas de lieu de moment pour dire bah enfin c'est le même c'est c'est le même".

      L'objectif est de créer un environnement qui pense l'ensemble des temps et spécificités de l'enfant.

      • Rôle transversal : La mission principale du HCE est de "coordonner toute l'action sur les politiques de l'enfance".

      Sarah El Haïry se décrit comme celle qui va "pousser la place de l'enfant ou la voie de l'enfant quel que soit le ministère et donc quelle que soit la politique publique pensée".

      Son rôle n'est pas opérationnel mais garantit la prise en compte des besoins et des droits de l'enfant dans toutes les instances, même celles éloignées de l'univers de l'enfance (ex: secteur du tourisme avec la question du "No Kids").

      • Pouvoir et marge de manœuvre : Ancien ministre, Sarah El Haïry explique que son poste actuel lui confère une "force" et lui permet d'être une "coordinatrice", un "garant" des politiques de l'enfance, dépassant les silos ministériels.

      Elle travaille en étroite collaboration avec Matignon pour assurer l'interministérialité et peut mobiliser toutes les administrations.

      Elle peut demander des expertises mais surtout comprendre "Qu'est-ce qui a bloqué ? Pourquoi lui tout seul il l'a pas fait ?".

      2. Défis Majeurs des Politiques de l'Enfance

      Plusieurs défis sont soulevés, illustrant la complexité et les lacunes actuelles du système :

      • Fragmentation des approches (les "silos") : Malgré les efforts passés (école ouverte, Devoir Fait, lutte contre le harcèlement, SNU, etc.), un citoyen souligne que "si on est là c'est que ça ne marche pas tellement".

      Sarah El Haïry confirme ce point : "rien ça a été fait par silo". La prise en charge des enfants en situation de handicap, par exemple, implique de multiples acteurs (département pour le transport, État pour l'éducation, ministère de la santé pour les soins) sans coordination globale, menant à des "inégalités territoriales" et une situation de "petit bonheur la chance".

      • Place de l'enfant dans la société : La question des "No Kids" (établissements interdisant l'accès aux enfants) est soulevée comme une illustration du manque de prise en compte de la place de l'enfant, qui est pourtant un "premier des impératifs".

      • Protection et bien-être matériel : La situation des "enfants à la rue" est un "engagement" du Président de la République mais reste une réalité criante.

      La Haute Commissaire insiste sur la "faiblesse ou la fragilité parfois de notre système" où la responsabilité est renvoyée entre l'État (pour les familles) et les départements (pour les enfants seuls), menant à "3000" enfants à la rue.

      Elle souligne que "quelle que soit sa nationalité quelle que soit son identité c'est pas aujourd'hui un élément qui doit être différenciant".

      • Éducation et adaptation des systèmes : Un citoyen s'interroge sur le fait que l'identité de genre ait été une "problématique principale" des débats récents sur l'enfance, tandis que des problèmes plus fondamentaux (agressions, disparitions d'enfants) persistent.

      Une citoyenne soulève la question des enfants jugés "dysfonctionnants" à l'école, qui sont trop souvent médicalisés au lieu d'être accompagnés pour transformer leurs particularités en "chance et une force".

      • Moyens et budgets : Un citoyen dénonce la "discrimination de base" en matière de matériel scolaire et le fait que les décisions concernant les rythmes scolaires soient souvent guidées par le "budget" plutôt que par le bien-être de l'enfant.

      La Haute Commissaire mentionne l'absence de "jaune budgétaire" pour l'enfance, rendant difficile une vision d'ensemble des investissements.

      3. Soutien à la Parentalité et Rôle des Parents

      Le rôle des parents et le besoin de soutien sont des thèmes centraux des échanges :

      • Évolution du contexte parental : Sarah El Haïry constate des "nouveaux défis" pour les parents : la fragilisation des solidarités familiales, l'éloignement des grands-parents, des temps de trajet domicile-travail plus longs, l'augmentation des familles monoparentales, et la place du "deuxième parent".
      • Responsabilités et devoirs : Un citoyen (Christian) insiste sur le "devoir des adultes", notamment des parents biologiques, qui ne doivent pas s'effacer derrière l'État. Il suggère également de mentionner le "devoir entre guillemets des enfants", en leur montrant leur rôle au sein de la famille et de la société.
      • Besoin d'accompagnement : Les parents sont confrontés à des "injonctions très contradictoires" et ont besoin d'aide. Le soutien à la parentalité est encore perçu comme "réservé à ceux qui vont pas bien", alors qu'il devrait être accessible à tous, sans jugement. Il faut "déculpabiliser".
      • Congé de naissance et parentalité : La question du "réarmement démographique" est liée au soutien à la parentalité. Le congé de naissance est en discussion pour être rallongé et mieux rémunéré, afin de permettre aux deux parents de s'investir davantage, reflétant "un combat de l'égalité plus fort".
      • Éducation affective : Une mère s'inquiète du contenu du programme "affectif" dans les écoles, estimant que l'éducation affective relève de la famille et questionnant la "neutralité" de l'éducation nationale sur des sujets sensibles comme l'identité de genre.

      Sarah El Haïry répond que l'objectif est de "donner à nos enfants les apprentissages essentiels" et de les "accompagner dans cette éducation au consentement", en complémentarité avec les parents.

      4. Valorisation des Métiers de l'Enfance

      La crise des vocations et le manque de reconnaissance des professionnels travaillant auprès des enfants sont un sujet de préoccupation :

      • Pénurie de personnel : Le manque de personnel dans les crèches (10 000 postes non pourvus) et la médecine scolaire, ainsi que le manque de psychomotriciens et ergothérapeutes dans les IME, sont soulignés.
      • Manque de reconnaissance : Au-delà de la rémunération, la "place dans la société" de ces professionnels est moins reconnue. "L'éducation populaire a connu le grand âge [mais] aujourd'hui cette place d'expertise d'expérience de faire grandir elle elle s'atténue".
      • Nécessité de parcours et de formation : Il est suggéré de créer "plus de parcours" pour permettre aux professionnels d'évoluer et de changer de milieu, afin de bâtir une "communauté éducative" plus large.

      5. Engagement et Perspectives

      Sarah El Haïry affirme son engagement personnel et la singularité de sa mission :

      • Engagement personnel : Elle a accepté ce poste "pour la cause", car elle "croit que aujourd'hui on a très envie d'aller d'aller bous [bouger] ça".
      • Durabilité de la mission : Sa position de Haute Commissaire lui confère une "force" car elle n'est pas soumise à l'instabilité politique d'un ministre. Sa mission est de suivre la cause de l'enfance "dans la durée", "quels que soient les ministres en place, quel que soit le sujet".
      • Optimisme : Elle exprime un optimisme mesuré, voyant des ouvertures et une volonté collective : "je vois toute la force des équipes de l'Élysée toute la force des équipes de Matignon la force des ministères avec qui je travaille en se disant 'Bah OK mais toi tu vas suivre dans la durée.' Bah oui moi je vais suivre dans la durée".

      • En conclusion, cette séance d'échanges met en lumière la volonté de la France de dépasser les approches fragmentées des politiques de l'enfance par la création d'un Haut Commissariat dédié.

      Les défis sont immenses, allant de la protection des enfants vulnérables et de l'accès à un environnement décent, au soutien d'une parentalité en mutation et à la valorisation des métiers de l'enfance.

      L'accent est mis sur la transversalité, la coordination et la nécessité d'une vision globale et durable pour assurer le bien-être de tous les enfants.

    1. Author response:

      The following is the authors’ response to the original reviews.

      Public Reviews:

      Reviewer #1 (Public review):

      Summary:

      The authors aimed to elucidate the molecular mechanisms underlying HIV-1 persistence and host immune dysfunction in CD4+ T cells during early infection (<6 months). Using single-cell multi-omics technologies-including scRNA-seq, scATAC-seq, and single-cell multiome analyses-they characterized the transcriptional and epigenomic landscapes of HIV-1-infected CD4+ T cells. They identified key transcription factors (TFs), signaling pathways, and T cell subtypes involved in HIV-1 persistence, particularly highlighting KLF2 and Th17 cells as critical regulators of immune suppression. The study provides new insights into immune dysregulation during early HIV-1 infection and reveals potential epigenetic regulatory mechanisms in HIV-1-infected T cells.

      Strengths:

      The study excels through its innovative integration of single-cell multi-omics technologies, enabling detailed analysis of gene regulatory networks in HIV-1-infected cells. Focusing on early infection stages, it fills a crucial knowledge gap in understanding initial immune responses and viral reservoir establishment. The identification of KLF2 as a key transcription factor and Th17 cells as major viral reservoirs, supported by comprehensive bioinformatics analyses, provides robust evidence for the study's conclusions. These findings have immediate clinical relevance by identifying potential therapeutic targets for HIV-1 reservoir eradication.

      We sincerely appreciate the reviewer’s positive evaluation of our work.

      Weaknesses:

      Despite its strengths, the study has several limitations. By focusing exclusively on CD4+ T cells, the study overlooks other relevant immune cells such as CD14+ monocytes, NK cells, and B cells. Additionally, while the authors generated their own single-cell datasets, they need to validate their findings using other publicly available single-cell data from HIV-1-infected PBMCs.

      Thank you to Reviewer #1 for your feedback on our work. In response to this feedback, we have examined cell-cell interactions between HIV-1-infected CD4+ T cells and other innate immune cells, including monocytes and NK cells. We identified altered interaction signaling patterns (e.g., MIF, ICAM2, CCL5, CLEC2B) that contribute to immune dysfunction and viral persistence (page 9, Supplementary Fig. 5) In addition, we validated the expression of KLF2 and its target genes using a publicly available scRNA-seq dataset from HIV-1-infected PBMCs [1], which includes both healthy donors and individuals with chronic HIV-1 infection. The upregulation of key KLF2 targets in HIV-1-infected CD4+ T cells from this dataset supports the reproducibility of our findings. We have incorporated into the revised Results, Discussion, and Supplementary Materials (page 8, page 12 and Supplementary Fig. 4A).

      Reviewer #2 (Public review):

      Summary:

      The authors observed gene ontologies associated with upregulated KLF2 target genes in HIV-1 RNA+ CD4 T Cells using scRNA-seq and scATAC-seq datasets from the PBMCs of early HIV-1-infected patients, showing immune responses contributing to HIV pathogenesis and novel targets for viral elimination.

      Strengths:

      The authors carried out detailed transcriptomics profiling with scRNA-seq and scATAC-seq datasets to conclude upregulated KLF2 target genes in HIV-1 RNA+ CD4 T Cells.

      We thank the reviewer for highlighting the strengths of our work.

      Weaknesses:

      This key observation of up-regulation KLF2 associated genes family might be important in the HIV field for early diagnosis and viral clearance. However, with the limited sample size and in-vivo study model, it will be hard to conclude. I highly recommend increasing the sample size of early HIV-1-infected patients.

      Thank you to Reviewer #2 for this important comment. We acknowledge the limitations of our modest sample size, which reflects the challenges of recruiting well-characterized individuals in early HIV-1 infection (<6 months) and obtaining high-quality PBMCs for single-cell multi-omic profiling. To strengthen our findings, we validated the upregulation of KLF2 target genes using a publicly available scRNA-seq dataset from HIV-1-infected PBMCs [1], which showed similar expression patterns in HIV-1 RNA+ CD4+ T cells (page 8 and Supplementary Fig. 4A).

      Reviewer #3 (Public review):

      Summary:

      This manuscript studies intracellular changes and immune processes during early HIV-1 infection with an additional focus on the small CD4+ T cell subsets. The authors used single-cell omics to achieve high resolution of transcriptomic and epigenomic data on the infected cells which were verified by viral RNA expression. The results add to understanding of transcriptional regulation which may allow progression or HIV latency later in infected cells. The biosamples were derived from early HIV infection cases, providing particularly valuable data for the HIV research field.

      Strengths:

      The authors examined the heterogeneity of infected cells within CD4 T cell populations, identified a significant and unexpected difference between naive and effector CD4 T cells, and highlighted the differences in Th2 and Th17 cells. Multiple methods were used to show the role of the increased KLF2 factor in infected cells. This is a valuable finding of a new role for the major transcription factor in further disease progression and/or persistence.

      The methods employed by the authors are robust. Single-cell RNA-Seq from PBMC samples was followed by a comprehensive annotation of immune cell subsets, 16 in total. This manuscript presents to the scientific community a valuable multi-omics dataset of good quality, which could be further analyzed in the context of larger studies.

      We sincerely thank the reviewer for the insightful and concise summary of our work.

      Weaknesses:

      Methods and Supplementary materials

      Some technical aspects could be described in more detail. For example, it is unclear how the authors filtered out cells that did not pass quality control, such as doublets and cells with low transcript/UMI content. Next, in cell annotation, what is the variability in cell types between donors? This information is important to include in the supplementary materials, especially with such a small sample size. Without this, it is difficult to determine, whether the differences between subsets on transcriptomic level, viral RNA expression level, and chromatin assessment are observed due to cell type variations or individual patient-specific variations. For the DEG analysis, did the authors exclude the most variable genes?

      Thank you to Reviewer #3 for these detailed comments and observations. In the revised Methods section (page 16), we have added information on our quality control filtering process. Specifically, we excluded cells with fewer than 200 detected genes, high mitochondrial content (>30%), or low UMI counts. Doublets were identified and removed using DoubletFinder.

      To address inter-donor variability, we included a new supplementary figure (Supplementary Fig. 1B) showing the distribution of major immune cell types across individual donors. While we observed some variation in cell-type composition between individuals, this likely reflects natural biological heterogeneity in early HIV-1 infection. Additionally, we applied fastMNN batch correction to mitigate donor-specific technical variation. After correction, the overall patterns of gene expression within each major CD4+ T cell subset were consistent across individuals (Supplementary Fig. 1C).

      Regarding the DEG analysis, we used ‘FindMarkers’ function in Seurat (v.3.2.1), which does not exclude highly variable genes. These details have been clarified in the updated Methods section (page 18).

      The annotation of 16 cell types from PBMC samples is impressive and of good quality, however, not all cell types get attention for further analysis. It’s natural to focus primarily on the CD4 T cells according to the research objectives. The authors also study potential interactions between CD4 and CD8 T cells by cell communication inference. It would be interesting to ask additional questions for other underexplored immune cell subsets, such as: 1) Could viral RNA be detected in monocytes or macrophages during early infection? 2) What are the inferred interactions between NK cells and infected CD4 T cells, are interactions similar to CD4-CD8 results? 3) What are the inferred interactions between monocytes or macrophages and infected CD4 T cells?

      In line with our study objectives, we initially focused on CD4+ T cells as primary HIV-1 targets. However, in response to the reviewer’s comment, we examined the inferred communications between HIV-1-infected CD4+ T cells and other immune cells.

      (1) With regard to the presence of viral RNA in monocytes or macrophages, we observed negligible HIV-1 RNA signal in these cell types in our dataset, consistent with their low permissiveness in early-stage infection [2]. However, we acknowledge the limitations of detecting rare infected cells at the single-cell level.

      (2) We identified increased MIF and ICAM2 signaling between NK cells and HIV-1-infected CD4+ T cells, which are associated with KLF2-mediated immune modulation. These patterns are consistent with the CD4–CD8 interaction results observed in our dataset. (Supplementary Fig. 5A)

      (3) Through the cell-cell interaction analysis with differential expression analysis, we inferred reduced CCL5 and CD55 signaling between monocytes and HIV-1-infected CD4+ T cells (Supplementary Fig. 5B). These reductions may potentially impair immune responses and antiviral defense.

      We appreciate the reviewer’s suggestions and believe that the analysis of underexplored immune subsets strengthens the relevance of our findings. These results have been incorporated into the revised Results (page 9).

      Discussion

      It would be interesting to see more discussion of the observation of how naïve T cells produce more viral RNA compared to effector T cells. It seems counterintuitive according to general levels of transcriptional and translational activity in subsets.

      Another discussion block could be added regarding the results and conclusion comparison with Ashokkumar et al. paper published earlier in 2024 (10.1093/gpbjnl/qzae003). This earlier publication used both a cell line-based HIV infection model and primary infected CD4 T cells and identified certain transcription factors correlated with viral RNA expression.

      Thank you to Reviewer #3 for the insightful suggestions. We observed that the proportion of HIV-1-infected naïve CD4 T cells is higher compared to effector T cells. Although effector CD4 T cells are generally more active, previous studies have suggested that naïve CD4 T cells are susceptible to HIV-1 infection during early infection that may associate with initial expansion and rapid progression [3, 4]. This may be due to less restriction by antiviral signaling or more accessible chromatin states in resting cells. We have added this context and cited relevant papers to address this observation (page 11)

      In addition, we have incorporated a comparative discussion with the recent study [5], which identified FOXP1 and GATA3 as transcriptional regulators associated with HIV-1 RNA expression. While these TFs were not significantly differentially expressed in our dataset, we discuss potential reasons for this discrepancy—including differences in infection model (in vitro vs. ex vivo), infection stage (latency vs. acute), and T cell subset composition—and emphasize that both studies highlight the importance of transcriptional regulation in HIV-1 persistence (page 12 and Supplementary Fig. 4B).

      Recommendations for the authors:

      Reviewer #1 (Recommendations for the authors):

      The study has several notable limitations.

      First, it was restricted to early-stage HIV-1 infection (<6 months) without longitudinal data, preventing the authors from capturing temporal changes in immune cell populations, gene expression profiles, and epigenetic landscapes throughout disease progression.

      Thank you to Reviewer #1 for this important limitation. As noted, our study focused exclusively on early-stage HIV-1 infection (<6 months) to capture the initial immune dysregulation and epigenetic alterations. We agree that longitudinal analysis would provide valuable insights into disease progression. However, due to the limited availability of early-infection patient samples suitable for performing multi-omics profiling, we prioritized capturing a detailed snapshot at this early stage. To address this limitation, future studies incorporating longitudinal sampling—including chronic infection and long-term non-progressors—will be essential to fully elucidate the temporal dynamics of HIV-1 pathogenesis.

      Second, while the bioinformatic analysis compared "Uninfected" and "HIV-1-infected" cells from patients, the authors could have strengthened their findings by incorporating publicly available single-cell data from healthy donors and chronically infected HIV-1 patients to validate their arguments across all figures.

      To support the robustness of our findings, we incorporated a publicly available single-cell RNA-seq dataset [1], which includes both healthy donors and individuals with chronic HIV-1 infection. In this dataset, we validated the upregulation of KLF2 and its target genes in HIV-1-infected CD4+ T cells and observed generally consistent expression patterns with those in our early-infection cohort (page 8; page 12 and Supplementary Fig. S4). While not all gene-level trends were identically reflecting differences in infection stage and immune activation status, this external comparison reinforces the reproducibility of key observations and highlights the unique transcriptional features associated with early HIV-1 infection.

      Third, although the study focused on CD4+ T cells as primary HIV-1 targets, it overlooked other important immune cells such as CD8+ T cells, monocytes, and NK cells, which may contribute to viral persistence and immune dysfunction through cell-cell interactions.

      In the revised manuscript, we expanded our analysis to include predicted ligand–receptor interactions between HIV-1-infected and uninfected CD4+ T cells with innate and cytotoxic immune cells using CellChat v.2.1.1. Specifically, we evaluated interactions with NK cells and monocytes and identified altered signaling pathways such as MIF, ICAM2, CCL5, and CLEC2B, which are associated with immune modulation (Supplementary Fig. 5A). We have added these results to the revised Results (page 9).

      Lastly, comparing these findings with other chronic viral infections (e.g., HBV, HCV) would have positioned this work more effectively within the broader field of viral immunology and enhanced its impact.

      We agree that broader comparisons with other chronic viral infections could enhance the impact of our findings. In the current discussion, we noted similarities in interferon signaling disruption with viruses such as HCV and HSV. (page 11). Our observation that HIV-1-infected CD4+ T cells exhibit impaired interferon responses is consistent with immune evasion mechanisms reported in HCV and HSV infections. These results underscore both the shared and specific features of immune modulation and persistence during HIV-1 early infection.

      Reviewer #3 (Recommendations for the authors):

      Supplementary Table S1 should indicate which technique was used for sequencing. However, the current version of the table marks no protocol applied to the majority of the samples, which is confusing and needs to be corrected.

      Thank you to Reviewer #3 for pointing out this important oversight. We have revised Supplementary Table S1 to clearly indicate the sequencing method used for each sample. Separate columns for scRNA-seq, scATAC-seq, and sc-Multiome now specify whether each technique was applied (“Yes” or “No”) to improve clarity and transparency.

      (1) Wang, S., et al., An atlas of immune cell exhaustion in HIV-infected individuals revealed by single-cell transcriptomics. Emerg Microbes Infect, 2020. 9(1): p. 2333-2347.

      (2) Arfi, V., et al., Characterization of the early steps of infection of primary blood monocytes by human immunodeficiency virus type 1. J Virol, 2008. 82(13): p. 6557-65.

      (3) Douek, D.C., et al., HIV preferentially infects HIV-specific CD4+ T cells. Nature, 2002. 417(6884): p. 95-8.

      (4) Jiao, Y., et al., Higher HIV DNA in CD4+ naive T-cells during acute HIV-1 infection in rapid progressors. Viral Immunol, 2014. 27(6): p. 316-8.

      (5) Ashokkumar, M., et al., Integrated Single-cell Multiomic Analysis of HIV Latency Reversal Reveals Novel Regulators of Viral Reactivation. Genomics Proteomics Bioinformatics, 2024. 22(1).

    1. Author response:

      The following is the authors’ response to the original reviews.

      Joint Public Review:

      Summary:

      The authors sought to elucidate the mechanism by which infections increase sleep in Drosophila. Their work is important because it further supports the idea that the blood-brain barrier is involved in brain-body communication, and because it advances the field of sleep research. Using knock-down and knock-out of cytokines and cytokine receptors specifically in the endocrine cells of the gut (cytokines) as well as in the glia forming the blood-brain barrier (BBB) (cytokines receptors), the authors show that cytokines, upd2 and upd3, secreted by entero-endocrine cells in response to infections increase sleep through the Dome receptor in the BBB. They also show that gut-derived Allatostatin (Alst) A promotes wakefulness by inhibiting Alst A signaling that is mediated by Alst receptors expressed in BBB glia. Their results suggest there may be additional mechanisms that promote elevated sleep during gut inflammation.

      The authors suggest that upd3 is more critical than upd2, which is not sufficiently addressed or explained. In addition, the study uses the gut's response to reactive oxygen molecules as a proxy for infection, which is not sufficiently justified. Finally, further verification of some fundamental tools used in this paper would further solidify these findings making them more convincing.

      Strengths:

      (1) The work addresses an important topic and proposes an intriguing mechanism that involves several interconnected tissues. The authors place their research in the appropriate context and reference related work, such as literature about sickness-induced sleep, ROS, the effect of nutritional deprivation on sleep, sleep deprivation and sleep rebound, upregulated receptor expression as a compensatory mechanism in response to low levels of a ligand, and information about Alst A.

      (2) The work is, in general, supported by well-performed experiments that use a variety of different tools, including multiple RNAi lines, CRISPR, and mutants, to dissect both signal-sending and receiving sides of the signaling pathway.

      (3) The authors provide compelling evidence that shows that endocrine cells from the gut are the source of the upd cytokines that increase daytime sleep, that the glial cells of the BBB are the targets of these upds, and that upd action causes the downregulation of Alst receptors in the BBB via the Jak/Stat pathways.

      We are pleased that the reviewers recognized the strength and significance of our findings describing a gut-to-brain cytokine signaling mechanism involving the blood-brain barrier (BBB) and its role in regulating sleep, and we thank them for their comments.

      Weaknesses:

      (1) There is a limited characterization of cell types in the midgut which are classically associated with upd cytokine production.

      We thank the reviewer for raising this point. Although several midgut cell types (including the absorptive enterocytes) may indeed produce Unpaired (Upd) cytokines, our study specifically focused on enteroendocrine cells (EECs), which are well-characterized as secretory endocrine cells capable of exerting systemic effects. As detailed in our response to Results point #2 (please see below), we show that EEC-specific manipulation of Upd signaling is both necessary and sufficient to regulate sleep in response to intestinal oxidative stress. These findings support the role of EECs as a primary source of gut-derived cytokine signaling to the brain. To acknowledge the possible involvement of other source, we have also added a statement to the Discussion in the revised manuscript noting that other, non-endocrine gut cell types may contribute to systemic Unpaired signaling that modulates sleep.

      (2) Some of the main tools used in this manuscript to manipulate the gut while not influencing the brain (e.g., Voilà and Voilà + R57C10-GAL80), are not directly shown to not affect gene expression in the brain. This is critical for a manuscript delving into intra-organ communication, as even limited expression in the brain may lead to wrong conclusions.

      We agree with the reviewer that this is an important point. To address it, we performed additional validation experiments to assess whether the voilà-GAL4 driver in combination with R57C10-GAL80 (EEC>) influences upd2 or upd3 expression in the brain. Our results show that manipulation using EEC> alters upd2 and upd3 expression in the gut (Fig. 1a,b), with new data showing that this does not affect their expression levels in neuronal tissues (Fig. S1a), supporting the specificity of our approach. These new data are now included in the revised manuscript and described in the Results section. This additional validation strengthens our conclusion that the observed sleep phenotypes result from gut-specific cytokine signaling, rather than from effects on Unpaired cytokines produced in the brain.

      (1) >(3) The model of gut inflammation used by the authors is based on the increase in reactive oxygen species (ROS) obtained by feeding flies food containing 1% H2O2. The use of this model is supported by the authors rather weakly in two papers (refs. 26 and 27 ): The paper by Jiang et al. (ref. 26) shows that the infection by Pseudomonas entomophila induces cytokine responses upd2 and 3, which are also induced by the Jnk pathway. In addition, no mention of ROS could be found in Buchon et al. (ref 27); this is a review that refers to results showing that ROS are produced by the NADPH oxidase DUOX as part of the immune response to pathogens in the gut. Thus, there is no strong support for the use of this model.

      We thank the reviewer for raising this point. We agree that the references originally cited did not sufficiently justify the use of H<sub>2</sub>O<sub>2</sub> feeding as a model of gut inflammation. To address this, we have revised the Results section to clarify that we use H<sub>2</sub>O<sub>2</sub> feeding as a controlled method to elevate intestinal ROS levels, rather than as a general model of inflammation. This approach allows us to investigate the specific effects of ROS-induced cytokine signaling in the gut. We have also added additional citations to support the physiological relevance of this model. For instance, Tamamouna et al. (2021) demonstrated that H<sub>2</sub>O<sub>2</sub> feeding induces intestinal stem-cell proliferation – a response also observed during bacterial infection – and Jiang et al. (2009) showed that enteric infections increase upd2 and upd3 expression, which we similarly observe following H<sub>2</sub>O<sub>2</sub> feeding (Fig. 3a). These findings support the use of H<sub>2</sub>O<sub>2</sub> as a tool to mimic specific ROS-linked responses in the gut. We believe this targeted and tractable model is a strength of our study, enabling us to dissect how intestinal ROS modulates systemic physiology through cytokine signaling

      Additionally, we have included a statement in the Discussion acknowledging that ROS generated during infection may activate signaling mechanisms distinct from those triggered by chemically induced oxidative stress, and that exploring these differences in future studies may yield important insights into gut–brain communication. These revisions provide a stronger justification for our model while more accurately conveying both its relevance and its limitations.

      (2) >(4) Likewise, there is no support for the use of ROS in the food instead a direct infection by pathogenic bacteria. Furthermore, it is known that ROS damages the gut epithelium, which in turn induces the expression of the cytokines studied. Thus the effects observed may not reflect the response to infection. In addition, Majcin Dorcikova et al. (2023). Circadian clock disruption promotes the degeneration of dopaminergic neurons in male Drosophila. Nat Commun. 2023 14(1):5908. doi: 10.1038/s41467-02341540-y report that the feeding of adult flies with H2O2 results in neurodegeneration if associated with circadian clock defects. Thus, it would be important to discuss or present controls that show that the feeding of H2O2 does not cause neuronal damage.

      We thank the reviewer for this thoughtful follow-up point. We would like to clarify that we do not claim that the effects observed in our study directly reflect the full response to enteric infection. As outlined in our revised response to comment 3, we have updated the manuscript to more precisely describe the H<sub>2</sub>O<sub>2</sub>-feeding paradigm as a model that induces local intestinal ROS responses comparable to, but not equivalent to, those observed during pathogenic challenges. This revised framing highlights both the potential similarities and differences between chemically induced oxidative stress and infection-induced responses. Indeed, in the revised Discussion, we now explicitly acknowledge that ROS generated during infection may engage distinct signaling mechanisms compared to exogenous H<sub>2</sub>O<sub>2</sub> and emphasize the value of future studies in delineating these pathways. We are currently pursuing this direction in an independent ongoing study investigating the effects of enteric infections. However, for the present work, we chose to focus on the effects of ROS-induced responses in isolation, as this provides a clean and well-controlled context to dissect the specific contribution of oxidative stress to cytokine signaling and sleep regulation.

      To further address the reviewer’s concern, we have also included new data (a TUNEL stain for apoptotic DNA fragmentation) in the revised manuscript showing that H<sub>2</sub>O<sub>2</sub> feeding does not damage neuronal tissues under our experimental conditions (Fig. S3f,g). This addresses the point raised regarding the potential neurotoxicity of H<sub>2</sub>O<sub>2</sub>, as described by Majcin Dorcikova et al. (2023), and supports the specificity of the sleep phenotypes observed in our study. We believe these revisions and clarifications strengthen the manuscript and make our interpretation more precise.

      (3) >(5) The novelty of the work is difficult to evaluate because of the numerous publications on sleep in Drosophila. Thus, it would be very helpful to read from the authors how this work is different and novel from other closely related works such as: Li et al. (2023) Gut AstA mediates sleep deprivation-induced energy wasting in Drosophila. Cell Discov. 23;9(1):49. doi: 10.1038/s41421-023-00541-3.

      Our work highlights a distinct role for gut-derived AstA in sleep regulation compared to findings by Lin et al. (Cell Discovery, 2023)[1], who showed that gut AstA mediates energy wasting during sleep deprivation. Their study focused on the metabolic consequences of sleep loss, proposing that sleep deprivation increases ROS in the gut, which then promotes the release of the glucagon-like hormone adipokinetic hormone (AKH) through gut AstA signaling, thereby triggering energy expenditure.

      In contrast, our study addresses the inverse question – how ROS in the gut influences sleep. In our model, intestinal ROS promotes sleep, raising the intriguing possibility – cleverly pointed out by the reviewers – that ROS generated during sleep deprivation might promote sleep by inducing Unpaired cytokine signaling in the gut. According to our findings, this suppresses wake-promoting AstA signaling in the BBB, providing a mechanism to promote sleep as a restorative response to gut-derived oxidative stress and potentially limiting further ROS accumulation. Importantly, our findings support a wakepromoting role for EEC-derived AstA, demonstrated by several lines of evidence. First, EEC-specific knockdown of AstA increases sleep. Second, activation of AstA<sup>+</sup> EECs using the heat-sensitive cation channel Transient Receptor Potential A1 (TrpA1) reduces sleep, and this effect is abolished by simultaneous knockdown of AstA, indicating that the sleep-suppressing effect is mediated by AstA and not by other peptides or secreted factors released by these cells. Third, downregulation of AstA receptor expression in BBB glial cells increases sleep, further supporting the existence of a functional gut AstA– glia arousal pathway. We have now included new data in the revised manuscript showing that AstA release from EECs is downregulated during intestinal oxidative stress (Fig. 7k,l,m). This suggests that this wake-promoting signal is suppressed both at its source (the gut endocrine cells), by unknown means, and at its target, the BBB, via Unpaired cytokine signaling that downregulates AstA receptor expression. This coordinated downregulation may serve to efficiently silence this arousal-promoting pathway and facilitate sleep during intestinal stress. These new data, along with an expanded discussion, provide further mechanistic insight into gut-derived AstA signaling and strengthen our proposed model.

      This contrasts with the interpretation by Lin et al., who observed increased AstA peptide levels in EECs after antioxidant treatment and interpreted this as peptide retention. However, peptide accumulation may result from either increased production or decreased release, and peptide levels alone are insufficient to distinguish between these possibilities. To resolve this, we examined AstA transcript levels, which can serve as a proxy for production. Following oxidative stress (24 h of 1% H<sub>2</sub>O<sub>2</sub> feeding and the following day), when animals show increased sleep (Fig. 7e), we observed a decrease in AstA transcript levels followed by an increase in peptide levels (Fig. 7k,l,m), suggesting that oxidative stress leads to reduced gut AstA production and release. Furthermore, we recently found that a class of EECs that produce the hormone Tachykinin (Tk) and are distinct from the AstA<sup>+</sup> EECs express the ROSsensitive cation channel TrpA1 (Ahrentløv et al., 2025, Nature Metabolism2). In these Tk<sup>+</sup> EECs, TrpA1 mediates ROS-induced Tk hormone release. In contrast, single-cell RNA-seq data[3] do not support TrpA1 expression in AstA<sup>+</sup> EECs, consistent with our findings that ROS does not promote AstA release – an effect that would be expected if TrpA1 were functionally expressed in AstA<sup>+</sup> EECs. This contradicts the findings of Lin et al., who reported TrpA1 expression in AstA<sup>+</sup> EECs. We have now included relevant single-cell data in the revised manuscript (Fig. S6f) showing that TrpA1 is specifically expressed in Tk<sup>+</sup> EECs, but not in AstA<sup>+</sup> EECs, and we have expanded the discussion to address discrepancies in TrpA1 expression and AstA regulation.

      Taken together, our results reveal a dual-site regulatory mechanism in which Unpaired cytokines released from the gut act at the BBB to downregulate AstA receptor expression, while AstA release from EECs is simultaneously suppressed. We thank the reviewers for raising this important point. We have also included a discussion the other point raised by the reviewers – the possibility that ROS generated during sleep deprivation may engage the same signaling pathways described here, providing a mechanistic link between sleep deprivation, intestinal stress, and sleep regulation.

      Recommendations for the authors:

      A- Material and Methods:

      (1) Feeding Assay: The cited publication (doi.org:10.1371/journal.pone.0006063) states: "For the amount of label in the fly to reflect feeding, measurements must therefore be confined to the time period before label egestion commences, about 40 minutes in Drosophila, a time period during which disturbance of the flies affects their feeding behavior. There is thus a requirement for a method of measuring feeding in undisturbed conditions." Was blue fecal matter already present on the tube when flies were homogenized at 1 hour? If so, the assay may reflect gut capacity rather than food passage (as a proxy for food intake). In addition, was the variability of food intake among flies in the same tube tested (to make sure that 1-2 flies are a good proxy for the whole population)?

      We agree that this is an important point for feeding experiments. We are aware of the methodological considerations highlighted in the cited study and have extensive experience using a range of feeding assays in Drosophila, including both short- and long-term consumption assays (e.g., dye-based and CAFE assays), as well as automated platforms such as FLIC and FlyPAD (Nature Communications, 2022; Nature Metabolism, 2022; and Nature Metabolism, 2025)[2,4,5].

      For the dye-based assay, we carefully selected a 1-hour feeding window based on prior optimization. Since animals were not starved prior to the assay, shorter time points (e.g., 30 minutes) typically result in insufficient ingestion for reliable quantification. A 1-hour period provides a robust readout while remaining within the timeframe before significant label excretion occurs under our experimental conditions. To support the robustness of our findings, we complemented the dye-based assay with data from FLIC, which enables automated, high-resolution monitoring of feeding behavior in undisturbed animals over extended periods. The FLIC results were consistent with the dye-based data, strengthening our confidence in the conclusions. To minimize variability and ensure consistency across experiments, all feeding assays were performed at the same circadian time – Zeitgeber Time 0 (ZT0), corresponding to 10:00 AM when lights are turned on in our incubators. This time point coincides with the animals' natural morning feeding peak, allowing for reproducible comparisons across conditions. Regarding variability among flies within tubes, each biological replicate in the dye assay consisted of 1–2 flies, and results were averaged across multiple replicates. We observed good consistency across samples, suggesting that these small groups reliably reflect group-level feeding behavior under our conditions.

      (2) Biological replicates: whereas the number of samples is clearly reported in each figure, the number of biological replicates is not indicated. Please include this information either in Material and methods or in the relevant figure legends. Please also include a description of what was considered a biological replicate.

      We have now clarified in the Materials and Methods section under Statistics that all replicates represent independent biological samples, as suggested by the reviewers.

      (3) Control Lines: please indicate which control lines were used instead of citing another publication. If preferred, this information could be supplied as a supplementary table.

      We now provide a clear description of the control lines used in the Materials and Methods section. Specifically, all GAL4 and GAL80 lines used in this study were backcrossed for several generations into a shared w<sup>1118</sup> background and then crossed to the same w<sup>1118</sup> strain used as the genetic background for the UAS-RNAi, <i.CRISPR, or overexpression lines. This approach ensures, to a strong approximation, that the only difference between control and experimental animals is the presence or absence of the UAS transgene.

      (4) Statistical analyses: for some results (e.g., those shown in Figure 3d), it could be useful to test the interaction between genotype and treatment.

      We thank the reviewer for this helpful suggestion. In response, we have now performed two-way ANOVA analyses to assess genotype × treatment (diet) interaction effects for the relevant data, including those shown in Figure 3d as well as additional panels where animals were exposed to oxidative stress and sleep phenotypes were measured. We have added the corresponding interaction p-values in the updated figure legends for Figures 3d, 3k, 5a–c, 5f, 5h, 5i, 6c, 6e, and 7e. All of these tests revealed significant interaction effects, supporting the conclusion that the observed differences in sleep phenotypes are specifically dependent on the interaction between genetic manipulation (e.g., cytokine or receptor knockdown) and oxidative stress. These additions reinforce the interpretation that Unpaired cytokine signaling, glial JAK-STAT pathway activity, and AstA receptor regulation functionally interact with intestinal ROS exposure to modulate sleep. We thank the reviewer for suggesting this improvement.

      (5) Reporting of p values. Some are reported as specific values whereas others are reported as less than a specific value. Please make this reporting consistent across different figures.

      All p-values reported in the manuscript are exact, except in cases where values fall below p < 0.0001. In those instances, we use the inequality because the Prism software package (GraphPad, version 10), which was used for all statistical analyses, does not report more precise values. We believe this reporting approach reflects standard practice in the field.

      (6) Please include the color code used in each figure, either in the figure itself or in the legend.

      We have now clarified the color coding in all relevant figures. In particular, we acknowledge that the meaning of the half-colored circles used to indicate H<sub>2</sub>O<sub>2</sub> treatment was not previously explained. These have now been clearly labeled in each figure to indicate treatment conditions.

      (7) The scheme describing the experimental conditions and the associated chart is confusing. Please improve.

      We have improved the schematic by replacing “ROS” with “H<sub>2</sub>O<sub>2</sub>” to more clearly indicate the experimental condition used. Additionally, we have added the corresponding circle annotations so that they now also appear consistently above the relevant charts. This revised layout enhances clarity and helps readers more easily interpret the experimental conditions. We believe these changes address the reviewer’s concern and make the figure significantly more intuitive.

      8) Please indicate which line was used for upd-Gal4 and the evidence that it faithfully reflects upd3 expression.

      We have now clarified in the Materials and Methods section that the upd3-GAL4 line used in our study is Bloomington stock #98420, which drives GAL4 expression under the control of approximately 2 kb of sequence upstream of the upd3 start codon. This line has previously been used as a transcriptional reporter for upd3 activity. The only use of this line was to illustrate reporter expression in the EECs. To support this aspect of Upd3 expression, we now include new data in the revised manuscript using fluorescent in situ hybridization (FISH) against upd3, which confirms the presence of upd3 transcripts in prospero-positive EECs of the adult midgut (Fig. S1b). Additionally, we show that upd3 transcript levels are significantly reduced in dissected midguts following EEC-specific knockdown using multiple independent RNAi lines driven by voilà-GAL4, both alone and in combination with R57C10-GAL80, consistent with endogenous expression in these cells (Fig. 1a,b).

      To further address the reviewer’s concern and provide additional support for the endogenous expression of upd3 in EECs, we performed targeted knockdown experiments focusing on molecularly defined EEC subpopulations. The adult Drosophila midgut contains two major EEC subtypes characterized by their expression of Allatostatin C (AstC) or Tachykinin (Tk), which together encompass the vast majority of EECs. To selectively manipulate these populations, we used AstC-GAL4 and Tk-GAL4 drivers – both knock-in lines in which GAL4 is inserted at the respective endogenous hormone loci. This design enables precise GAL4 expression in AstC- or Tk-expressing EECs based on their native transcriptional profile. To eliminate confounding neuronal expression, we combined these drivers with R57C10GAL80, restricting GAL4 activity to the gut and generating AstC<sup>Gut</sup>> and Tk<sup>Gut</sup>> drivers. Using these tools, we knocked down upd2 and upd3 selectively in the AstC- or Tk-positive EECs. Knockdown of either cytokine in AstC-positive EECs significantly increased sleep under homeostatic conditions, recapitulating the phenotype observed with knockdown in all EECs (Fig. 1m-o). In contrast, knockdown of upd2 or upd3 in Tk-positive EECs had no effect on sleep (Fig. 1p-r). Furthermore, we show in the revised manuscript that selective knockdown of upd2 or upd3 in AstC-positive EECs abolishes the H<sub>2</sub>O<sub>2</sub>-induced increase in sleep (Fig. 3f–h). These findings demonstrate that Unpaired cytokine signaling from AstC-positive EECs is essential for mediating the sleep response to intestinal oxidative stress, highlighting this specific EEC subtype as a key source of cytokine-driven regulation in this context. These new results indicate that AstC-positive EECs are a primary source of the Unpaired cytokines that regulate sleep, while Tk-positive EECs do not appear to contribute to this function. Importantly, upd3 transcript levels were significantly reduced in dissected midguts following AstC<sup>Gut</sup> driven knockdown (Fig. S1r), further confirming that upd3 is endogenously expressed in AstC-positive EECs. Thus we have bolstered our confidence that upd3 is indeed expressed in EECs, as illustrated by the reporter line, through several means.

      (9) Please indicate which GFP line was used with upd-Gal4 (CD8, NLS, un-tagged, etc). The Material and Methods section states that it was "UAS-mCD8::GFP (#5137);", however, the stain does not seem to match a cell membrane pattern but rather a nuclear or cytoplasmic pattern. This information would help the interpretation of Figure 1C.

      We confirm that the GFP reporter line used with upd3-GAL4 was obtained from Bloomington stock #98420. As noted by the Bloomington Drosophila Stock Center, “the identity of the UAS-GFP transgene is a guess,” and the subcellular localization of the GFP fusion is therefore uncertain. We agree with the reviewer that the signal observed in Figure 1c does not display clear membrane localization and instead appears diffuse, consistent with cytoplasmic or partially nuclear localization. In any case, what we find most salient is the reporter’s labeling of Prospero-positive EECs in the adult midgut, consistent with upd3 expression in these cells. This conclusion is further supported by multiple lines of evidence presented in the revised manuscript, as mentioned above in response to question #8: (1) fluorescent in situ hybridization (FISH) for upd3 confirms expression in EECs (Fig. S1b), (2) EEC-specific RNAi knockdown of upd3 reduces transcript levels in dissected midguts, and (3) publicly available single-cell RNA sequencing datasets[3] also indicate that upd3 is expressed at low levels in a subset of adult midgut EECs under normal conditions. We have also clarified in the revised Materials and Methods section that GFP localization is undefined in the upd3-GAL4 line, to guide interpretation of the reporter signal.

      B- Results

      (1) Figure 1: According to previous work (10.1016/j.celrep.2015.06.009, http://flygutseq.buchonlab.com/data?gene=upd3%0D%0A), in basal conditions upd3 is expressed as following: ISC (35 RPKM), EB (98 RPKM), EC (57 RPKM), and EEC (8 RPKM). Accordingly, even complete KO in EECs should eliminate only a small fraction of upd3 from whole guts, even less considering the greater abundance of other cell types such as ECs compared to EECs. It would be useful to understand where this discrepancy comes from, in case it is affecting the conclusion of the manuscript. While this point per se does not affect the main conclusions of the manuscript, it makes the interpretation of the results more difficult.

      We acknowledge the previously reported low expression of upd3 in EECs. However, the FlyGut-seq site appears to be no longer available, so we could not directly compare other related genes. Nonetheless, our data – based on in situ hybridization, reporter expression, and multiple RNAi knockdowns – consistently support upd3 expression in EECs. These complementary approaches strengthen the conclusion that EECs are an important source of systemic upd3 under the conditions tested.

      (2) Figure 1: The upd2-3 mutants show sleep defects very similar to those of EEC>RNAi and >Cas9. It would thus be helpful to try to KO upd3 with other midgut drivers (An EC driver like Myo1A or 5966GS and a progenitor driver like Esg or 5961GS) to validate these results. Such experiments might identify precisely which cells are involved in the gut-brain signaling reported here.

      We appreciate the reviewer’s suggestion and agree that exploring other potential sources of Upd3 in the gut is an interesting direction. In this study, we have focused on EECs, which are the primary hormone-secreting cells in the intestine and thus the most likely candidates for mediating systemic effects such as gut-to-brain signaling. While it is possible that other gut cell types – such as enterocytes (e.g., Myo1A<sup>+</sup>) or intestinal progenitors (e.g., Esg<sup>+</sup>) – also contribute to Upd3 production, these cells are not typically endocrine in nature. Demonstrating their involvement in gutto-brain communication would therefore require additional, extensive validation beyond the scope of the current study. Importantly, our data show that manipulating Upd3 specifically in EECs is both necessary and sufficient to modulate sleep in response to intestinal ROS, strongly supporting the conclusion that EEC-derived cytokine signaling underlies the observed phenotype. In contrast, manipulating cytokines in other gut cells could produce indirect effects – such as altered proliferation, epithelial integrity, or immune responses – that complicate the interpretation of behavioral outcomes like sleep. For these reasons, we chose to focus on EECs as the source of endocrine signals mediating gut-to-brain communication. However, to address this point raised by the reviewer, we have now included a statement in the Discussion acknowledging that other non-endocrine gut cell types may also contribute to the systemic Unpaired signaling that modulates sleep in response to intestinal oxidative stress.

      (3) Figure 3: "This effect mirrored the upregulation observed with EEC-specific overexpression of upd3, indicating that it reflects physiologically relevant production of upd3 by the gut in response to oxidative stress." Please add (Figure 3a) at the end of this sentence.

      We have now added “(Figure 3a)” at the end of the sentence to clearly reference the relevant data.

      (4) For Figure 3b, do you have data showing that the increased amount of sleep was due to the addition of H2O2 per se, rather than the procedure of adding it?

      We have added new data to address this point. To ensure that the observed sleep increase was specifically due to the presence of H<sub>2</sub>O<sub>2</sub> and not an effect of the food replacement procedure, we performed a control experiment in which animals were fed standard food prepared using the same protocol and replaced daily, but without H<sub>2</sub>O<sub>2</sub>. These animals did not exhibit increased sleep, confirming that the sleep effect is attributable to intestinal ROS rather than the supplementation procedure itself (Fig. S3a). Thanks for the suggestion.

      (5) In the text it is stated that "Since 1% H2O2 feeding induced robust responses both in upd3 expression and in sleep behavior, we asked whether gut-derived Unpaired signaling might be essential for the observed ROS-induced sleep modulation. Indeed, EEC-specific RNAi targeting upd2 or upd3 abolished the sleep response to 1% H2O2 feeding." While it is indeed true that there is no additional increase in sleep time due to EEC>upd3 RNAi, it is also true that EEC>upd3 RNAi flies, without any treatment, have already increased their sleep in the first place. It is then possible that rather than unpaired signaling being essential, an upper threshold for maximum sleep allowed by manipulation of these processes was reached. It would be useful to discuss this point.

      Several findings argue against a ceiling effect and instead support a requirement for Unpaired signaling in mediating ROS-induced sleep. Animals with EEC-specific upd2 or upd3 knockdown or null mutation not only fail to increase sleep following H<sub>2</sub>O<sub>2</sub> treatment but actually exhibit reduced sleep during oxidative stress (Fig. 3e, k, l; Fig. 5e, f), suggesting that Unpaired signaling is required to sustain sleep under these conditions. Similarly, animals with glial dome knockdown also show reduced sleep under oxidative stress, closely mirroring the phenotype of EEC-specific upd3 RNAi animals (Fig. 5a–c, g–i). These results support the conclusion that gut-to-glia Unpaired cytokine signaling is necessary for maintaining elevated sleep during oxidative stress. In the absence of this signaling, animals exhibit increased wakefulness. We identify AstA as one such wake-promoting signal that is suppressed during intestinal stress. We present new data showing that this pathway is downregulated not only via Unpaired-JAK/STAT signaling in glial cells but also through reduced AstA release from the gut in the revised manuscript. This model, in which Unpaired cytokines promote sleep during intestinal stress by suppressing arousal pathways, is discussed throughout the manuscript to address the reviewer’s point.

      (6) In Figure 3k, the dots highlighting the experiment show an empty profile, a full one, and a half one. Please define what the half dots represent.

      We have now clarified the color coding in all relevant figures. Specifically, we acknowledge that the meaning of the half-colored circles indicating H<sub>2</sub>O<sub>2</sub> treatment was not previously defined – it indicates washout or recovery time. In the revised version, these symbols are now clearly labeled in each figure to indicate the treatment condition, ensuring consistent and intuitive interpretation across all panels.

      (7) The authors used appropriate GAL4 and RNAi lines to the knockdown dome, a upd2/3 JAK-STATlinked receptor, specifically in neurons and glia, respectively, in order to identify the CNS targets of upd2/3 cytokines produced by enteroendocrine cells (EECs). Pan-neuronal dome knockdown did not alter daytime sleep in adult females, yet pan-glial dome knockdown phenocopied effects of upd2/3 knockdown in EECs. They also observed that EEC-specific knockdown of upd2 and upd3 led to a decrease in JAK-STAT reporter activity in repo-positive glial cells. This supports the authors' conclusion that glial cells, not neurons, are the targets by which unpaired cytokines regulate sleep via JAK-STAT signaling. However, they do not show nighttime sleep data of pan-neuronal and pan-glial dome knockdowns. It would strengthen their conclusion if the nighttime sleep of pan-glial dome knockdown phenocopied the upd2/3 knockdowns as well, provided the pan-neuronal dome knockdown did not alter nighttime sleep.

      We have now added nighttime sleep data for both pan-glial and pan-neuronal domeless knockdowns in the revised manuscript (Fig. 2a). Glial knockdown increased nighttime sleep, similar to EEC-specific upd2/3 knockdown, while neuronal knockdown had no effect. These results further support the glial cells’ being the relevant target of gut-derived Unpaired signaling.

      (8) The authors only used one method to induce oxidative stress (hydrogen peroxide feeding). It would strengthen their argument to test multiple methods of inducing oxidative stress, such as lipopolysaccharide (LPS) feeding. In addition, it would be useful to use a direct bacterial infection to confirm that in flies, the infection promotes sleep. Additionally, flies deficient in Dome in the BBB and infected should not be affected in their sleep by the infection. These experiments would provide direct support for the mechanism proposed. Finally, the authors should add a primary reference for using ROS as a model of bacterial infection and justify their choice better.

      We agree that directly comparing different models of intestinal stress, such as bacterial infection or LPS feeding, would provide valuable insight into how gut-derived signals influence sleep in response to infection. As noted in our detailed responses above, we now include an expanded rationale for our use of H<sub>2</sub>O<sub>2</sub> feeding as a controlled and well-established method for inducing intestinal ROS – one of the key physiological responses to enteric infection and inflammation. In the revised Discussion, we explicitly acknowledge that pathogenic infections – which trigger both intestinal ROS and additional immune pathways – may engage distinct or complementary mechanisms compared to chemically induced oxidative stress. We emphasize the importance of future studies aimed at dissecting these differences. In fact, we are actively pursuing this direction in ongoing work examining sleep responses to enteric infection. For the purposes of the present study, however, we chose to focus on a tractable and specific model of ROS-induced stress to define the contribution of Unpaired cytokine signaling to gut-brain communication and sleep regulation. This approach allowed us to isolate the effect of oxidative stress from other confounding immune stimuli and identify a glia-mediated signaling mechanism linking gut epithelial stress to changes in sleep behavior.

      (9) To confirm that animals lacking EEC Unpaired signaling are not more susceptible to ROS-induced damage, the authors assessed the survival of upd2 and upd3 knockdowns on 1% H2O2 and concluded they display no additional sensitivity to oxidative stress compared to controls. It may be useful to include other tests of sensitivity to oxidative stress, in addition to survival.

      We appreciate the reviewer’s suggestion. In our view, survival is a highly informative and stringent readout, as it reflects the overall physiological capacity of the animal to withstand oxidative stress. Importantly, our data show that animals lacking EEC-derived Unpaired signaling do not exhibit reduced survival following H<sub>2</sub>O<sub>2</sub> exposure, indicating that their oxidative stress resistance is not compromised. Furthermore, we previously confirmed that feeding behavior is unaffected in these animals, suggesting that their ability to ingest food (and thus the stressor) is not impaired. As a molecular complement to these assays in response to this point and others, we have also performed an assessment of neuronal apoptosis (a TUNEL assay, Fig. S3f,g). This assay did not identify an increase in cell death in the brains of animals fed peroxide-containing medium. Thus, gross neurological health, behavior, and overall survival appear to be resilient to the environmental treatment regime we apply here, suggesting that the outcomes we observe arise from signaling per se.

      (10) The authors confirmed that animals lacking EEC-derived upd3 displayed sleep suppression similar to controls in response to starvation. These results led the authors to conclude that there is a specific requirement for EEC-derived Unpaired signaling in responding to intestinal oxidative stress. However, they previously showed that EEC-specific knockdown of upd3 and upd2 led to increased daytime sleep under normal feeding conditions. Their interpretations of their data are inconsistent.

      We appreciate the reviewer’s comment. While animals lacking EEC-derived Unpaired signaling show increased baseline sleep under normal feeding conditions, they still exhibit a robust reduction in sleep when subjected to starvation – comparable to that of control animals (Fig. S3h–j). This demonstrates that they retain the capacity to appropriately modulate sleep in response to metabolic stress. Thus, the sleep-promoting phenotype under normal conditions does not reflect a generalized inability to adjust sleep behavior. Rather, it highlights a specific role for Unpaired signaling in mediating sleep responses to intestinal oxidative stress, not in broadly regulating all sleep-modulating stimuli.

      (11) The authors report a significant increase in JAK-STAT activity in surface glial cells at ZT0 in animals fed 1% H2O2-containing food for 20 hours. This response was abolished in animals with EECspecific knockdown of upd2 or upd3. The authors confirmed there were no unintended neuronal effects on upd2 or upd3 expression in the heads. They also observed an upregulation of dome transcript levels in the heads of animals with EEC-specific knockdown of upd3 fed 1% H2O2-containing food for 15 hours, which they interpret to be a compensatory mechanism in response to low levels of the ligand. This assay is inconsistent with previous experiments in which animals were fed hydrogen peroxide for 20 hours.

      We thank the reviewer for identifying this discrepancy. The inconsistency arose from a labeling error in the manuscript. Both the JAK-STAT reporter assays in glial cells and the dome expression measurements were performed following 15 hours of H<sub>2</sub>O<sub>2</sub> feeding, not 20 hours as previously stated. We have now corrected this in the revised manuscript.

      (12) The authors show that animals with glia-specific dome knockdown did not have decreased survival on H2O2-containing food, and displayed normal rebound sleep in the morning following sleep deprivation. These results potentially undermine the significance of the paper. If the normal sleep response to oxidative stress is an important protective mechanism, why would oxidative stress not decrease survival in dome knockdown flies (that don't have the normal sleep response to oxidative stress)? This suggests that the proposed mechanism is not important for survival. The authors conclude that Dome-mediated JAK-STAT signaling in the glial cells specifically regulates ROS-induced sleep responses, which their results support.

      We agree that our survival data show that glial dome knockdown does not reduce survival under continuous oxidative stress. However, we believe this does not undermine the importance of the sleep response as an adaptive mechanism. In our survival assay, animals were continuously exposed to 1% H<sub>2</sub>O<sub>2</sub> without the opportunity to recover. In contrast, under natural conditions, oxidative stress is likely to be intermittent, and the ability to mount a sleep response may be particularly important for promoting recovery and maintaining homeostasis during or after transient stress episodes. Thus, while the JAK-STAT-mediated sleep response may not directly enhance survival under constant oxidative challenge, it likely plays a critical role in adaptive recovery under natural conditions.

      (13) Altogether, the authors conclude that enteric oxidative stress induces the release of Unpaired cytokines which activate the JAK-STAT pathway in subperineurial glia of the BBB, which leads to the glial downregulation of receptors for AstA, which is a wake-promoting factor also released by EECs. This mechanism is supported by their results, however, this research raises some intriguing questions, such as the role of upd2 versus upd3, the role of AstA-R1 versus AstA-R2, the importance of this mechanism in terms of survival, the sex-specific nature of this mechanism, and the role that nutritional availability plays in the dual functionality of Unpaired cytokine signaling in regards to sleep.

      We thank the reviewer for highlighting these important questions. Our data suggest that Upd2 and Upd3, while often considered partially redundant, both contribute to sleep regulation, with stronger effects observed for Upd3. This is consistent with prior studies indicating overlapping but non-identical roles for these cytokines. Similarly, although AstA-R1 and AstA-R2 can both be activated by AstA, knockdown of AstA-R2 consistently produces more robust sleep phenotypes, suggesting a predominant role in mediating this effect. The possibility of sex-specific regulation is indeed compelling. While our study focused on females, many gut hormones show sex-dependent activity, and we recognize this as an important avenue for future research. Finally, we have included new data in the revised manuscript showing that gut-derived AstA is downregulated under oxidative stress, further supporting our model in which Unpaired signaling suppresses arousal pathways during intestinal stress

      (14)Data Availability: It is indicated that: "Reasonable data requests will be fulfilled by the lead author". However, eLife's guidelines for data sharing require that all data associated with an article to be made freely and widely available.

      We thank the reviewer for pointing this out. We have revised the Data Availability section of the manuscript to clarify that all data will be made freely available from the lead contact without restriction, in accordance with eLife’s open data policy.

      References

      (1) Li, Y., Zhou, X., Cheng, C., Ding, G., Zhao, P., Tan, K., Chen, L., Perrimon, N., Veenstra, J.A., Zhang, L., and Song, W. (2023). Gut AstA mediates sleep deprivaPon-induced energy wasPng in Drosophila. Cell Discov 9, 49. 10.1038/s41421-023-00541-3. (2) Ahrentlov, N., Kubrak, O., Lassen, M., Malita, A., Koyama, T., Frederiksen, A.S., Sigvardsen, C.M., John, A., Madsen, P., Halberg, K.A., et al. (2025). Protein-responsive gut hormone Tachykinin directs food choice and impacts lifespan. Nature Metabolism. 10.1038/s42255-025-01267-0.

      (3) Li, H., Janssens, J., De Waegeneer, M., Kolluru, S.S., Davie, K., Gardeux, V., Saelens, W., David, F.P.A., Brbic, M., Spanier, K., et al. (2022). Fly Cell Atlas: A single-nucleus transcriptomic atlas of the adult fruit fly. Science 375, eabk2432. 10.1126/science.abk2432.

      (4) Kubrak, O., Koyama, T., Ahrentlov, N., Jensen, L., Malita, A., Naseem, M.T., Lassen, M., Nagy, S., Texada, M.J., Halberg, K.V., and Rewitz, K. (2022). The gut hormone AllatostaPn C/SomatostaPn regulates food intake and metabolic homeostasis under nutrient stress. Nature communicaPons 13, 692. 10.1038/s41467-022-28268-x.

      (5) Malita, A., Kubrak, O., Koyama, T., Ahrentlov, N., Texada, M.J., Nagy, S., Halberg, K.V., and Rewitz, K. (2022). A gut-derived hormone suppresses sugar appePte and regulates food choice in Drosophila. Nature Metabolism 4, 1532-1550. 10.1038/s42255-022-00672-z.

    1. Synthèse Détaillée : Adaptation de l'Aménagement des Territoires au Changement Climatique en France

      • Ce document de briefing s'appuie sur les conclusions du rapport de la mission d'information parlementaire sur l'adaptation de l'aménagement des territoires au changement climatique.

      Il met en lumière les retards accumulés par la France en matière d'adaptation, l'insuffisance des politiques actuelles et la nécessité urgente d'une stratégie plus ambitieuse, coordonnée et financée pour faire face aux impacts croissants du dérèglement climatique.

      1. Le Contexte et l'Urgence de l'Adaptation

      Le rapport s'inscrit dans un contexte marqué par la publication du PNACC 3 (3e Plan National d'Adaptation au Changement Climatique) en mars dernier.

      Si les politiques d'atténuation (réduction des émissions de gaz à effet de serre) restent "indispensables pour limiter l'ampleur du changement climatique", elles doivent désormais être "complétées par une politique d'adaptation ambitieuse" face aux impacts déjà visibles et futurs.

      Constat alarmant : La France a pris un "important retard" en matière d'adaptation.

      Les réponses actuelles sont "insuffisantes", les "coûts de l'inaction s'alourdissent", et les politiques publiques peinent à traduire "l'urgence climatique en action concrète".

      Prévisions climatiques : "La trajectoire actuelle de réchauffement climatique pourrait conduire les températures à augmenter d'ici 2100 en France de 3 à 4°C supplémentaire par rapport à l'ère pré-industrielle".

      L'ampleur et la vitesse de ces évolutions sont "inédites", affectant les sols, la disponibilité de l'eau, les rendements agricoles, et augmentant la récurrence d'événements extrêmes (inondations, sécheresses).

      Impacts sur le quotidien des Français : "Disparition d'habitations et d'infrastructures littorales ou de montagne, baisse de la productivité économique lors des fortes chaleurs, dommages considérables du retrait gonflement des argiles sur les maisons individuelles, coupure récurrente de route, impossibilité d'assurer certains biens."

      2. Atténuation vs. Adaptation : Deux Piliers

      Complémentaires et Complexes La lutte contre le changement climatique repose sur deux piliers :

      Atténuation : Agit sur les "sources du réchauffement climatique".

      Adaptation : Agit sur les "conséquences de ce dernier".

      Ces deux démarches sont "complémentaires" (ex: végétalisation des villes atténue et adapte).

      Cependant, elles peuvent aussi s'opposer si l'adaptation conduit à des "maladaptations" (ex: "répondre aux vagues de chaleur en installant des millions de climatiseurs").

      L'adaptation est "plus complexe que celle de l'atténuation" car elle nécessite de "réduire les vulnérabilités physiques et de trouver des moyens d'adaptation fonctionnels selon des méthodes qui diffèrent en fonction des territoires des secteurs d'activité et des choix opérés par les élus et la population". Il n'existe pas de "politique d'adaptation unique".

      Contrairement à l'atténuation, qui dépend d'un effort mondial, "les politiques d'adaptation ne dépendent que de nous".

      L'action est urgente car "l'adaptation doit être pensée et mise en œuvre dès maintenant pour éviter la maladaptation et des coûts futurs importants".

      3. Le Coût de l'Inaction et les Bénéfices de l'Adaptation

      Bien qu'il n'existe pas d'"évaluation globale du coût de l'inadaptation", ce coût est "important" et "exponentiel".

      • Le changement climatique est responsable de près de la moitié de l'augmentation des coûts d'assurance, passés de "1,5 à 3,5 milliards d'euros par an" entre les décennies 1980 et 2010.
      • Les vagues de chaleur ont provoqué entre "22 et 37 milliards d'euros de surcoût entre 2014 et 2022", sans compter les milliers de morts.
      • Exemple frappant de maladaptation : le déploiement de la fibre optique sans enfouissement des câbles, nécessitant un investissement supplémentaire de "7 à 17 milliards d'euros" pour correction.
      • À l'inverse, "les bénéfices de l'adaptation dépassent largement ses coûts". Selon la Banque Mondiale, "chaque euro investi dans l'adaptation rapporte entre 2 et 10 €". Agir dès maintenant présente des "bénéfices économiques" et permet d'éviter des "investissements déjà très lourds" à refaire.

      4. Recommandations Clés pour une Politique d'Adaptation Efficace

      Le rapport formule une centaine de propositions. Les plus importantes incluent :

      4.1. Renforcement du Cadre Juridique et Stratégique

      • Reconnaître l'adaptation comme une "véritable priorité nationale" en lui dédiant un chapitre au sein du Code de l'Environnement, sur le modèle de la stratégie nationale bas-carbone.
      • Donner une "valeur législative" à la trajectoire de réchauffement de référence pour l'adaptation (TRACC), fixée à 4°C de réchauffement en France à l'horizon 2100 par le PNACC 3. Cela imposerait aux documents stratégiques locaux (PLU, SCoT) de prendre en compte le climat futur.

      4.2. Financement et Ressources

      • Lutter contre l'impensé du financement de l'adaptation. Le PNACC 3 n'est pas assorti d'un plan de financement chiffré.
      • Développer une "méthodologie de chiffrage" pour les collectivités territoriales.
      • Publier en annexe du projet de loi de finances un "orange budgétaire" récapitulant les actions de financement de l'adaptation au niveau de l'État.
      • Rétablir un "lien d'évolution automatique" entre l'augmentation de la surprime d'assurance catastrophe naturelle (passée de 12 à 20% en 2025) et l'augmentation des recettes du Fonds Barnier, en le tournant davantage vers la prévention.
      • Rehausser le Fonds Vert à son niveau de 2024, augmenter la part consacrée à l'adaptation et les exigences de verdissement des projets financés.
      • Renforcer "majeurement les moyens humains et financiers des opérateurs de l'État" (ex: ADEME, CEREMA) impliqués dans l'adaptation, qui ont vu leurs effectifs réduits malgré une charge de travail croissante. Le CEREMA, par exemple, a perdu "20% de ses effectifs en 10 ans" tout en étant impliqué dans près de "2/3 des actions du PNACC 3".
      • Libérer les ressources des Agences de l'Eau en supprimant complètement leur plafond de recettes et en rehaussant leur plafond de dépenses.
      • Instaurer un "test de conformité à la TRACC" pour chaque investissement d'ampleur et intégrer impérativement la prise en compte du climat futur dans les marchés publics.

      4.3. Ingénierie Territoriale et Culture du Risque

      • Le "déficit d'ingénierie territoriale" est un frein majeur. Les petites collectivités manquent de moyens et d'expertise.
      • Mettre en place une "formation obligatoire des élus" à la culture du risque et aux enjeux climatiques en début de mandat.
      • Labelliser les bureaux d'études réalisant des diagnostics de vulnérabilité.
      • Renforcer le CEREMA pour structurer l'accompagnement des collectivités et réduire les inégalités territoriales.
      • Renforcer le volet adaptation des SRADDET et envisager la fusion des ALEC avec les agences d'urbanisme pour créer des agences locales de l'urbanisme et du climat.
      • Fusionner les COPES régionales et les CESER pour élargir la concertation citoyenne sur les choix d'adaptation.

      4.4. Adaptation de l'Aménagement et du Droit

      • Repenser l'ensemble du droit de l'urbanisme pour éviter la maladaptation dans les zones à risque.
      • Mieux articuler les lois Montagne et Littoral ainsi que l'objectif ZAN (Zéro Artificialisation Nette) avec les impératifs d'adaptation, notamment le "recul stratégique d'habitation ou d'infrastructure".
      • Après les catastrophes naturelles, la "reconstruction à l'identique ne soit plus la norme". Le droit de l'urbanisme et de l'assurance doit évoluer pour y mettre fin.
      • Responsabiliser les assureurs (qui restent dans les zones à risque) et les assurés (qui n'effectuent pas les travaux de prévention).

      4.5. Enjeux Spécifiques et Cas Particuliers

      • Prévention des inondations : Évolution de la compétence GEMAPI pour inclure le ruissellement et favoriser une "plus grande solidarité territoriale" (entre amont et aval).
      • Risques littoraux (érosion côtière, submersion marine) : Création d'un "fond dédié au financement des actions face à l'érosion côtière", alimenté par les taxes sur les éoliennes en mer et les locations touristiques de courte durée dans les zones concernées. Nécessité d'accepter parfois de "se retirer" plutôt que de lutter inutilement.
      • Chaleurs extrêmes en ville et logement : Les villes sont en "première ligne". Le nombre de nuits tropicales à Paris "quadruplera d'ici 2050".
      • Intégrer les enjeux d'habitabilité d'été dans les travaux éligibles à Ma Prime Rénov' et à l'éco-prêt à taux zéro.
      • Lutter contre les îlots de chaleur urbains : renforcer la présence de l'eau, végétaliser, développer les surfaces à fort albédo, repenser l'organisation spatiale.
      • Territoires ultramarins : Malgré une influence océanique atténuant le réchauffement moyen, ils sont confrontés à l'érosion/submersion marine, l'affaiblissement de la ressource en eau douce, l'intensification des cyclones, l'acidification de l'océan, et les sargasses (dont le classement en catastrophe naturelle est envisagé).
      • Manque de territoires de repli pour l'urbanisme, car l'habitat côtier est très vulnérable (en Polynésie, "près de 8 habitants sur 10 vivent ainsi à moins d'1 km de la mer").
      • Augmenter "significativement les aides allouées à l'amélioration de l'habitat" du ministère des Outre-mer pour la réhabilitation et la relocalisation des logements menacés.

      5. L'Adaptation comme Levier de Résilience et de Développement

      • Le rapport souligne que l'adaptation n'est pas seulement une "contrainte et un coût", mais aussi un "levier de résilience, d'innovation et d'attractivité pour les territoires". Les sommes investies peuvent "servir à faire levier pour redynamiser l'activité" tout en "protégeant d'inévitables coûts futurs". Pour cela, il est impératif de "nous mettre en ordre de bataille pour intégrer cet enjeu dans l'ensemble de nos politiques publiques et ainsi éviter la maladaptation et la gabegie des deniers publics."

      6. Débats et Points de Tension Plusieurs points de discussion ont émergé :

      • Loi ZAN : Des divergences persistent sur l'application rigide de la loi et la nécessité de l'adapter aux spécificités territoriales (érosion côtière, montagne). Certains critiquent une "artificialisation dogmatique" qui serait "contre-productive" face à la protection humaine. D'autres insistent sur la nécessité de maintenir le cap du ZAN, le qualifiant de "chance de repenser nos manières d'habiter et de vivre ensemble", face à la vacance de logements et l'impact sur l'écosystème.
      • Rôle de l'État : Appel à une réaffirmation claire du rôle de l'État comme "garant de la cohésion nationale de l'égalité et de la sécurité de tous", notamment pour la solidarité financière (Fonds Barnier, érosion côtière) et l'accompagnement des collectivités.
      • Simplification normative : Demande d'un "vrai chantier de simplification de cohérence et surtout d'arbitrage entre protection environnementale sans concession et sécurité humaine".
      • Stations de montagne : La "fin possible de certaines activités économiques" (comme le ski) est une réalité difficile à accepter pour les territoires qui ont investi massivement. La diversification économique viable est un défi majeur nécessitant un accompagnement national fort.
      • Sentiers littoraux : Questionnement sur la pertinence de continuer à construire des sentiers littoraux coûteux et souvent détruits par les tempêtes, face à l'érosion inévitable, suggérant une gestion plus agile et locale des investissements.
      • Délai d'instruction des dossiers : Nécessité d'accélérer les procédures administratives pour les aides après catastrophes naturelles, en s'inspirant des procédures d'urgence utilisées dans le Pas-de-Calais.
    1. Compte rendu détaillé : La formation des professionnels de santé et son impact sur l'accès aux soins

      Ce document synthétise les points clés soulevés lors de l'audition concernant l'organisation du système de santé et l'accès aux soins, avec un accent particulier sur la formation des professionnels de santé.

      Les discussions ont mis en lumière les défis actuels, les réformes en cours et les pistes de réflexion pour l'avenir.

      1. Le constat des difficultés d'accès aux soins

      • Le rapporteur souligne d'emblée la gravité de la situation : « 6 millions de nos concitoyens n'ont pas de médecin traitant et des territoires entiers peuvent être considérés comme des déserts médicaux ». Ce problème n'est pas propre à la France, mais une difficulté mondiale, particulièrement dans les zones éloignées des grands centres urbains. Au-delà du nombre, la question de la répartition territoriale et de la couverture du spectre des besoins de santé est cruciale.

      2. Le rôle central de la formation

      La formation des professionnels de santé, relevant en grande partie du ministère de l'enseignement supérieur, est identifiée comme un levier majeur pour améliorer la situation sanitaire. Les enjeux liés à la formation sont de trois ordres :

      • Quantitatif : Définir le nombre de professionnels à former. Bien que le ministère de la Santé soit prioritairement en charge de cette définition des besoins, c'est une question fondamentale et complexe. Il est noté que le numerus clausus est passé d'un point bas de 3500 par an dans les années 90 à près de 11000 aujourd'hui, mais un « effet retard » d'environ 10 ans existe entre le début de la formation et l'arrivée effective des médecins sur le terrain.
      • Qualitatif : Former des médecins capables de couvrir toutes les disciplines et champs de la santé, assurant une bonne répartition entre les spécialités et l'adéquation des compétences aux missions.
      • Territorial : Assurer une répartition équitable des médecins sur le territoire pour répondre aux besoins locaux, ce qui n'est « évidemment criant que ce n'est pas le cas aujourd'hui ».

      3. Les leviers d'action et réformes en cours

      Plusieurs mesures sont mises en œuvre ou envisagées pour améliorer la situation :

      • Diversification du recrutement : L'objectif est de recruter des jeunes issus de territoires d'origine et de milieux sociaux diversifiés. Cela passe par l'extension des « options santé dans les lycées », notamment pour les élèves les plus éloignés des carrières de santé. Ces options sont en phase d'expérimentation et les premiers retours sont très positifs, les lycéens ayant suivi ces options gérant mieux leur première année d'études de santé.
      • Décentralisation de la première année d'études de santé (PASS/LASS) : Une proposition phare est la possibilité d'avoir « une première année d'accès aux études de santé par département », y compris via des campus connectés. Cette mesure vise à rapprocher la formation des territoires et à envoyer un signal sur la répartition des professionnels. L'expérimentation débutera dès l'année prochaine.
      • Simplification des parcours d'accès : La réforme de la première année d'études, initiée en 2019, vise à rendre les parcours plus lisibles et moins socialement déterminants. Le système de la PACES présentait de nombreux inconvénients, notamment un taux d'échec élevé (2/3 des étudiants) et une mauvaise réponse aux besoins territoriaux. L'objectif est de réduire les redoublements et de diversifier les profils.
      • Adaptation aux réalités locales et modes d'exercice : Il est jugé essentiel que les étudiants découvrent les territoires et les différents modes d'exercice, ainsi que les disciplines sous-couvertes (personnes âgées, soins palliatifs, santé mentale, santé scolaire, santé au travail).
      • Généralisation des stages hors CHU : Actuellement, moins de 40 % des stages ont lieu en dehors des Centres Hospitaliers Universitaires. L'objectif est de changer cet état de fait pour que les stages se déroulent sur tout le territoire, avec la « généralisation d'un stage en dehors des CHU et en territoire soudance au cours de la formation en 2e ou 3e cycle ». Dès novembre 2026, la 4e année d'internat en médecine générale incitera les docteurs en formation à réaliser des stages en zone fortement sous-dense.
      • Développement professionnel continu et passerelles : Pour retenir les professionnels, il est nécessaire d'assurer un développement professionnel continu. Il faut aussi « faciliter les passerelles entre les formations pour permettre des évolutions de carrière ».

      4. Débats et pistes de réflexion complémentaires

      Plusieurs points ont fait l'objet de discussions approfondies :

      • L'alternance : Le concept d'une formation en alternance plus poussée, dès la première année, est évoqué par le rapporteur, citant l'exemple de médecins ruraux souhaitant former des jeunes en vue d'une reprise de patientèle. Le ministre tempère en soulignant les défis logistiques et la nature très théorique de la première année. Cependant, il reconnaît que la formation actuelle est déjà fortement basée sur la pratique en cycles supérieurs (« en 2e cycle aujourd'hui ils passent 50 % de leur temps en stage et en 3e cycle 80 % »). La 4e année d'internat est d'ailleurs une réponse à ce besoin de professionnalisation.
      • Les compétences non-médicales : La nécessité d'inclure des cours sur les « relations humaines » (management, communication) et l'« entrepreneuriat » (pour la médecine libérale) dès les premières années est soulignée par le rapporteur. Le ministre indique que ces sujets sont déjà abordés, notamment l'éthique dès le premier cycle et la gestion de cabinet en fin de troisième cycle, mais que les maquettes peuvent être améliorées.
      • La durée des études : Le rapporteur s'interroge sur la possibilité de raccourcir les études, citant l'Allemagne et la Suède où les durées sont différentes. Le ministre précise que les diplômes belges et allemands de 6 ans ne confèrent pas un exercice complet de la médecine, et que le premier cycle français est jugé incompressible en raison de disciplines fondamentales. L'allongement d'un an de la formation en médecine générale est justifié par la complexité croissante de l'exercice et la contribution des docteurs juniors à la force de travail dès la 4e année.
      • La territorialisation de l'internat : La question du fléchage des internes, majoritairement vers les CHU, est un enjeu majeur pour les hôpitaux de province. L'obligation de stages en zones sous-denses est une première réponse, mais la réflexion se poursuit sur des mécanismes plus justes.
      • La suppression du concours de première année : Le rapporteur propose de supprimer le concours de première année, jugé trop sélectif, socialement discriminant (coût des prépas privées) et inadapté pour évaluer une carrière de 10 ans. Le ministre partage cette vision d'une plus grande ouverture et de donner « plusieurs chances à des étudiants », permettant de rebondir après un premier échec en licence non-médicale. Il reconnaît toutefois la difficulté de cette transition en France en raison du « culte dans les dans mais y compris des parents paradoxalement de du concours de la note ».
      • L'orientation vers les spécialités : Le système actuel laisse aux étudiants le choix de leur spécialité, ce qui entraîne des déséquilibres (ex: difficulté à attirer les étudiants vers la psychiatrie). Deux approches sont envisagées : réduire les marges de flexibilité ou revaloriser l'attractivité des spécialités moins choisies.
      • Le retour des certificats d'études spécialisées (CES) : La possibilité de réintroduire des spécialisations intermédiaires entre la médecine générale et l'hyperspécialisation CHU est évoquée comme une piste pour améliorer la prise en charge des patients et éviter des consultations inutiles chez des hyperspécialistes.

      5. Coût de la formation

      Le ministre n'est pas en mesure de donner le coût précis de la formation d'un médecin. Le coût moyen d'un étudiant toutes filières confondues est d'environ 12 000 euros par an, mais il précise que les étudiants en santé contribuent aussi directement au système de soins via leurs stages.

      En conclusion, la France est engagée dans une série de réformes visant à résoudre la crise de l'accès aux soins par une refonte profonde de la formation des professionnels de santé, axée sur la décentralisation, la diversification des parcours, l'intégration de la pratique et une meilleure anticipation des besoins territoriaux et des compétences futures.

    1. Author response:

      The following is the authors’ response to the original reviews.

      Reviewer #1 (Public Review)>

      Summary:

      This research group has consistently performed cutting-edge research aiming to understand the role of hormones in the control of social behaviors, specifically by utilizing the genetically tractable teleost fish, medaka, and the current work is no exception. The overall claim they make, that estrogens modulate social behaviors in males and females is supported, with important caveats. For one, there is no evidence these estrogens are generated by "neurons" as would be assumed by their main claim that it is NEUROestrogens that drive this effect. While indeed the aromatase they have investigated is expressed solely in the brain, in most teleosts, brain aromatase is only present in glial cells (astrocytes, radial glia). The authors should change this description so as not to mislead the reader. Below I detail more specific strengths and weaknesses of this manuscript.

      We thank the reviewer for this very positive evaluation of our work and greatly appreciate their helpful comments and suggestions for improving the manuscript. We agree with the comment that the term “neuroestrogens” is misleading. Therefore, we have replaced “neuroestrogens” with “brain-derived estrogens” or “brain estrogens” throughout the manuscript, including the title.

      In the following sections, “neuroestrogens” has been revised to align with the surrounding context.

      Line 21: “in the brain, also known as neuroestrogens,” → “in the brain.”

      Line 28: “neuroestrogens” → “these estrogens.”

      Line 30: “mechanism of action of neuroestrogens” → “mode of action of brain-derived estrogens.”

      Line 43: “brain-derived estrogens, also called neuroestrogens,” → “estrogens.”

      Line 74: “neuroestrogen synthesis is selectively impaired while gonadal estrogen synthesis remains intact” → “estrogen synthesis in the brain is selectively impaired while that in the gonads remains intact.”

      Line 77: “neuroestrogens” → “these estrogens.”

      Line 335: “levels of neuroestrogens” → “brain estrogen levels.”

      Line 338: “neuroestrogens” → “these estrogens.”

      Line 351: “neuroestrogens” → “these estrogens.”

      Line 357: “neuroestrogen action” → “the action of brain-derived estrogens.”

      Line 359: “neuroestrogens” → “estrogen synthesis in the brain.”

      Line 390: “active synthesis of neuroestrogens” → “active estrogen synthesis in the brain.”

      Line 431: “neuroestrogens” → “estrogens in the brain.”

      Line 431: “neuroestrogen action” → “the action of brain-derived estrogens.”

      Line 433: “neuroestrogen action” → “their action.”

      Strengths:

      Excellent use of the medaka model to disentangle the control of social behavior by sex steroid hormones.

      The findings are strong for the most part because deficits in the mutants are restored by the molecule (estrogens) that was no longer present due to the mutation.

      Presentation of the approach and findings are clear, allowing the reader to make their own inferences and compare them with the authors'.

      Includes multiple follow-up experiments, which lead to tests of internal replication and an impactful mechanistic proposal.

      Findings are provocative not just for teleost researchers, but for other species since, as the authors point out, the data suggest mechanisms of estrogenic control of social behaviors may be evolutionarily ancient.

      We again thank the reviewer for their positive evaluation of our work.

      Weaknesses:

      (1) As stated in the summary, the authors attribute the estrogen source to neurons and there isn't evidence this is the case. The impact of the findings doesn't rest on this either.

      As noted in Response to reviewer #1’s summary comment, we have replaced “neuroestrogens” with “brain-derived estrogens” or “brain estrogens” throughout the manuscript.

      Line 63: We have also added the text “In teleost brains, including those of medaka, aromatase is exclusively localized in radial glial cells, in contrast to its neuronal localization in rodent brains (18– 20).” Following this addition, “This observation suggests” in the subsequent sentence has been replaced with “These observations suggest.”

      The following references (#18–20), cited in the newly added text above, have been included in the reference list, with other references renumbered accordingly:

      P. M. Forlano, D. L. Deitcher, D. A. Myers, A. H. Bass, Anatomical distribution and cellular basis for high levels of aromatase activity in the brain of teleost fish: aromatase enzyme and mRNA expression identify glia as source. J. Neurosci. 21, 8943–8955 (2001).

      N. Diotel, Y. Le Page, K. Mouriec, S. K. Tong, E. Pellegrini, C. Vaillant, I. Anglade, F. Brion, F. Pakdel, B. C. Chung, O. Kah, Aromatase in the brain of teleost fish: expression, regulation and putative functions. Front. Neuroendocrinol. 31, 172–192 (2010).

      A. Takeuchi, K. Okubo, Post-proliferative immature radial glial cells female-specifically express aromatase in the medaka optic tectum. PLoS One 8, e73663 (2013).

      (2) The d4 versus d8 esr2a mutants showed different results for aggression. The meaning and implications of this finding are not discussed, leaving the reader wondering.

      Line 282: As the reviewer correctly noted, circles were significantly reduced in mutant males of the Δ8 line, whereas no significant reduction was observed in those of the Δ4 line. However, a tendency toward reduction was evident in the Δ4 line (P = 0.1512), and both lines showed significant differences in fin displays. Based on these findings, we believe our conclusion that esr2a<sup>−/−</sup> males exhibit reduced aggression remains valid. To clarify this point and address potential reader concerns, we have revised the text as follows: “esr2a<sup>−/−</sup> males from both the Δ8 and Δ4 lines exhibited significantly fewer fin displays than their wildtype siblings (P = 0.0461 and 0.0293, respectively). Circles followed a similar pattern, with a significant reduction in the Δ8 line (P = 0.0446) and a comparable but non-significant decrease in the Δ4 line (P = 0.1512) (Fig. 5L; Fig. S8E), showing less aggression.”

      (3) Lack of attribution of previously published work from other research groups that would provide the proper context of the present study.

      In response to this and other comments from this reviewer, we have revised the Introduction and Discussion sections as follows.

      Line 56: “solely responsible” in the Introduction has been modified to “largely responsible”.

      Line 57: “This is consistent with the recent finding in medaka fish (Oryzias latipes) that estrogens act through the ESR subtype Esr2b to prevent females from engaging in male-typical courtship (10)” has been revised to “This is consistent with recent observations in a few teleost species that genetic ablation of AR severely impairs male-typical behaviors (13–16) and with findings in medaka fish (Oryzias latipes) that estrogens act through the ESR subtype Esr2b to prevent females from engaging in maletypical courtship (12)” to include previous studies on the behavior of AR mutant fish (Yong et al., 2017; Alward et al., 2020; Ogino et al., 2023; Nishiike and Okubo, 2024) in the Introduction.

      Line 65: “It is worth mentioning that systemic administration of estrogens and an aromatase inhibitor increased and decreased male aggression, respectively, in several teleost species, potentially reflecting the behavioral effects of brain-derived estrogens (21–24)” has been added to the Introduction. This addition provides an overview of previous studies on the effects of estrogens and aromatase on male fish aggression (Hallgren et al., 2006; O’Connell and Hofmann, 2012; Huffman et al., 2013; Jalabert et al., 2015).

      Line 367: “treatment of males with an aromatase inhibitor reduces their male-typical behaviors (31– 33)” has been edited to read “treatment of males with an aromatase inhibitor reduces their male-typical behaviors, while estrogens exert the opposite effect (21–24).”

      After the revisions described above, the following references (#13, 14, and 22) have been added to the reference list, with other references renumbered accordingly:

      L. Yong, Z. Thet, Y. Zhu, Genetic editing of the androgen receptor contributes to impaired male courtship behavior in zebrafish. J. Exp. Biol. 220, 3017–3021 (2017).

      B. A. Alward, V. A. Laud, C. J. Skalnik, R. A. York, S. A. Juntti, R. D. Fernald, Modular genetic control of social status in a cichlid fish. Proc. Natl. Acad. Sci. U.S.A. 117, 28167–28174 (2020).

      L. A. O’Connell, H. A. Hofmann, Social status predicts how sex steroid receptors regulate complex behavior across levels of biological organization. Endocrinology 153, 1341–1351 (2012).

      (4) There are a surprising number of citations not included; some of the ones not included argue against the authors' claims that their findings were "contrary to expectation".

      Line 68: As detailed in Response to reviewer #1’s comment 3 on weaknesses, we have cited previous studies on the effects of estrogens and aromatase on male fish aggression (Hallgren et al., 2006; O’Connell and Hofmann, 2012; Huffman et al., 2013; Jalabert et al., 2015) in the Introduction.

      The following revisions have also been made to avoid phrases such as “contrary to expectation” and “unexpected.”

      Line 76: “Contrary to our expectations” → “Remarkably.”

      Line 109: “Contrary to this expectation, however” → “Nevertheless.”

      Line 135: “Again, contrary to our expectation, cyp19a1b<sup>−/−</sup> males” → “cyp19a1b<sup>−/−</sup> males.”

      Line 333: “unexpected” → “noteworthy.”

      Line 337: “unexpected” → “notable.”

      (5) The experimental design for studying aggression in males has flaws. A standard test like a resident intruder test should be used.

      We agree that the resident-intruder test is the most commonly used method for assessing aggression. However, medaka form shoals and lack strong territoriality, and even slight dominance differences between the resident and the intruder can increase variability in the results, compromising data consistency. Therefore, in this study, we adopted an alternative approach: placing four unfamiliar males together in a tank and quantifying aggressive interactions in total. This method allows for the assessment of aggression regardless of territorial tendencies, making it more appropriate for our investigation.

      (6) While they investigate males and females, there are fewer experiments and explanations for the female results, making it feel like a small addition or an aside.

      We agree that the data and discussion for females are less extensive than for males. However, we have previously elucidated the mechanism by which estrogen/Esr2b signaling promotes female mating behavior (Nishiike et al., 2021, Curr Biol, 1699–1710). Accordingly, it follows that the new insights into female behavior gained from the cyp19a1b knockout model are more limited than those for males. Nevertheless, when combined with our prior findings, the female data in this study offer valuable insights, and the overall mechanism through which estrogens promote female mating behavior is becoming clearer. Therefore, we do not consider the female data in this study to be incomplete or merely supplementary.

      (7) The statistics comparing "experimental to experimental" and "control to experimental" aren't appropriate.

      The reviewer raises concerns about the statistical analysis used for Figures 4C and 4E, suggesting that Bonferroni’s test should be used instead of Dunnett’s test. However, Dunnett’s test is commonly used to compare treatment groups to a reference group that receives no treatment, as in our study. Since we do not compare the treated groups with each other, we believe Dunnett’s test is the most appropriate choice.

      Line 619: The reviewer’s concern may have arisen from the phrase “comparisons between control and experimental groups” in the Materials and Methods. We have revised it to “comparisons between untreated and E2-treated groups in Fig. 4, C and D” for clarity.

      Reviewer #2 (Public Review):

      Summary:

      The novelty of this study stems from the observations that neuro-estrogens appear to interact with brain androgen receptors to support male-typical behaviors. The study provides a step forward in clarifying the somewhat contradictory findings that, in teleosts and unlike other vertebrates, androgens regulate male-typical behaviors without requiring aromatization, but at the same time estrogens appear to also be involved in regulating male-typical behaviors. They manipulate the expression of one aromatase isoform, cyp19a1b, that is purported to be brain-specific in teleosts. Their findings are important in that brain estrogen content is sensitive to the brain-specific cyp19a1b deficiency, leading to alterations in both sexual behavior and aggressive behavior. Interestingly, these males have relatively intact fertility rates, despite the effects on the brain.

      We thank this reviewer for their positive evaluation of our work and constructive comments, which we found very helpful in improving the manuscript.

      That said, the framing of the study, the relevant context, and several aspects of the methods and results raise concerns. Two interpretations need to be addressed/tempered:

      (1) that the rescue of cyp19a1b deficiency by tank-applied estradiol is not necessarily a brain/neuroestrogen mode of action, and

      Line 155: cyp19a1b-deficient males exhibited a severe reduction in brain E2 levels, yet their peripheral E2 levels remained comparable to those in wild-type males. Given this hormonal milieu and the lack of behavioral change in wild-type males following E2 treatment, the observed recovery of mating behavior in cyp19a1b-deficient males following E2 treatment can be best explained by the restoration of brain E2 levels. However, as the reviewer pointed out, we cannot rule out the possibility that bath-immersed E2 influenced behavior through an indirect peripheral mechanism. To address this concern, we have modified the text as follows: “These results suggest that reduced E2 in the brain is the primary cause of the mating defects, highlighting a pivotal role of brain-derived estrogens in male mating behavior. However, caution is warranted, as an indirect peripheral effect of bath-immersed E2 on behavior cannot be ruled out, although this is unlikely given the comparable peripheral E2 levels in cyp19a1b-deficient and wild-type males. In contrast to mating.”

      (2) the large increases in peripheral and brain androgen levels in the cyp19a1b deficient animals imply some indirect/compensatory effects of lifelong cyp19a1b deficiency.

      As stated in line 151, androgen/AR signaling has a strong facilitative effect on male-typical behaviors in teleosts. If increased androgen levels in the periphery and brain affected behavior, the expected effect would be facilitative. However, cyp19a1b-deficient males exhibited impaired male-typical behaviors, suggesting that elevated androgen levels were unlikely to be responsible. Although chronic androgen elevation could cause androgen receptor desensitization, which could lead to behavioral suppression, our long-term androgen treatments have consistently promoted, rather than inhibited, male-typical behaviors (e.g., Nishiike et al., Proc Natl Acad Sci USA 121:e2316459121). Hence, this possibility is also highly unlikely.

      Reviewer #3 (Public Review):

      Summary:

      Taking advantage of the existence in fish of two genes coding for estrogen synthase, the enzyme aromatase, one mostly expressed in the brain (Cyp19a1b) and the other mostly found in the gonads (Cyp19a1a), this study investigates the role of neuro-estrogens in the control of sexual and aggressive behavior in teleost fish. The constitutive deletion of Cyp19a1b reduced brain estrogen content by 87% in males and about 50% in females. It led to reduced sexual and aggressive behavior in males and reduced sexual behavior in females. These effects are reversed by adult treatment with estradiol thus indicating that they are activational in nature. The deletion of Cyp19a1b is associated with a reduced expression of the genes coding for the two androgen receptors, ara, and arb, in brain regions involved in the regulation of social behavior. The analysis of the gene expression and behavior of mutants of estrogen receptors indicates that these effects are likely mediated by the activation of the esr1 and esr2a isoforms. These results provide valuable insight into the role of neuro-estrogens in social behavior in the most abundant vertebrate taxa. While estrogens are involved in the organization of the brain and behavior of some birds and rodents, neuro-estrogens appear to play an activational role in fish through a facilitatory action of androgen signaling.

      We thank this reviewer for their positive evaluation of our work and comments that have improved the manuscript.

      Strengths:

      Evaluation of the role of brain "specific" Cyp19a1 in male teleost fish, which as a taxa are more abundant and yet proportionally less studied than the most common birds and rodents. Therefore, evaluating the generalizability of results from higher vertebrates is important. This approach also offers great potential to study the role of brain estrogen production in females, an understudied question in all taxa.

      Results obtained from multiple mutant lines converge to show that estrogen signaling drives aspects of male sexual behavior.

      The comparative discussion of the age-dependent abundance of brain aromatase in fish vs mammals and its role in organization vs activation is important beyond the study of the targeted species.

      We again thank the reviewer for their positive evaluation of our work.

      Weaknesses:

      (1) The new transgenic lines are under-characterized. There is no evaluation of the mRNA and protein products of Cyp19a1b and ESR2a.

      We did not directly assess the function of cyp19a1b and esr2a in our mutant fish. However, the observed reduction in brain E2 levels, with no change in peripheral E2 levels, in cyp19a1b-deficient fish strongly supports the loss of cyp19a1b function. This is stated in the Results section (line 97) as follows: “These results show that cyp19a1b-deficient fish have reduced estrogen levels coupled with increased androgen levels in the brain, confirming the loss of cyp19a1b function.”

      Line 473: A previous study reported that female medaka lacking esr2a fail to release eggs due to oviduct atresia (Kayo et al., 2019, Sci Rep 9:8868). Similarly, in this study, some esr2a-deficient females exhibited spawning behavior but were unable to release eggs, although the sample size was limited (Δ8 line: 2/3; Δ4 line: 1/1). In contrast, this was not observed in wild-type females (Δ8 line: 0/12; Δ4 line: 0/11). These results support the effective loss of esr2a function. To incorporate this information into the manuscript, the following text has been added to the Materials and Methods: “A previous study reported that esr2a-deficient female medaka cannot release eggs due to oviduct atresia (59). Likewise, some esr2a-deficient females generated in this study, despite the limited sample size, exhibited spawning behavior but were unable to release eggs (Δ8 line: 2/3; Δ4 line: 1/1), while such failure was not observed in wild-type females (Δ8 line: 0/12; Δ4 line: 0/11). These results support the effective loss of esr2a function.”

      The following reference (#59), cited in the newly added text above, have been included in the reference list:

      D. Kayo, B. Zempo, S. Tomihara, Y. Oka, S. Kanda, Gene knockout analysis reveals essentiality of estrogen receptor β1 (Esr2a) for female reproduction in medaka. Sci. Rep. 9, 8868 (2019).

      (2) The stereotypic sequence of sexual behavior is poorly described, in particular, the part played by the two sexual partners, such that the conclusions are not easily understandable, notably with regards to the distinction between motivation and performance.

      Line 103: To provide a more detailed description of medaka mating behavior, we have revised the text from “The mating behavior of medaka follows a stereotypical pattern, wherein a series of followings, courtship displays, and wrappings by the male leads to spawning” to “The mating behavior of medaka follows a stereotypical sequence. It begins with the male approaching and closely following the female (following). The male then performs a courtship display, rapidly swimming in a circular pattern in front of the female. If the female is receptive, the male grasps her with his fins (wrapping), culminating in the simultaneous release of eggs and sperm (spawning).”

      (3) The behavior of females is only assessed from the perspective of the male, which raises questions about the interpretation of the reduced behavior of the males.

      In medaka, female mating behavior is largely passive, except for rejecting courtship attempts and releasing eggs. Therefore, its analysis relies on measuring the latency to receive following, courtship displays, or wrappings from the male and the frequency of courtship rejection or wrapping refusal. We understand the reviewer’s perspective that cyp19a1b-deficient females might not be less receptive but instead less attractive to males, potentially leading to reduced male mating efforts. However, since these females are approached and followed by males at levels comparable to wild-type females, this possibility appears unlikely. Moreover, cyp19a1b-deficient females tend to avoid males and exhibit a slightly female-oriented sexual preference. While these traits are closely associated with reduced sexual receptivity, they do not readily align with reduced sexual attractiveness. Therefore, it is more plausible to conclude that these females have decreased receptivity rather than being less attractive to males.

      (4) At no point do the authors seem to consider that a reduced behavior of one sex could result from a reduced sensory perception from this sex or a reduced attractivity or sensory communication from the other sex.

      Line 112: As noted above, the impaired mating behavior of cyp19a1b-deficient females is unlikely to be due to reduced attractiveness to males. Similarly, mating behavior tests using esr2b-deficient females as stimulus females suggest that the impaired mating behavior of cyp19a1b-deficient males cannot be attributed to reduced attractiveness to females. However, the possibility that their impaired mating behavior could be attributed to altered cognition or sexual preference cannot be ruled out. To reflect this in the manuscript, we have revised the text “, suggesting that they are less motivated to mate” to “. These results suggest that they are less motivated to mate, though an alternative interpretation that their cognition or sexual preference may be altered cannot be dismissed.”

      (5) Aspects of the methods are not detailed enough to allow proper evaluation of their quality or replication of the data.

      In response to this and other specific comments from this reviewer, we have revised the Materials and Methods section to include more detailed descriptions of the methods.

      Line 469: The following text has been added to describe the method for domain identification in medaka Esr2a: “The DNA- and ligand-binding domains of medaka Esr2a were identified by sequence alignment with yellow perch (Perca flavescens) Esr2a, for which these domain locations have been reported (58).”

      The following reference (#58), cited in the newly added text above, have been included in the reference list:

      S. G. Lynn, W. J. Birge, B. S. Shepherd, Molecular characterization and sex-specific tissue expression of estrogen receptor α (esr1), estrogen receptor βa (esr2a) and ovarian aromatase (cyp19a1a) in yellow perch (Perca flavescens). Comp. Biochem. Physiol. B Biochem. Mol. Biol. 149, 126–147 (2008).

      Line 540: The text “, and the total area of signal in each brain nucleus was calculated using Olyvia software (Olympus)” has been revised to include additional details on the single ISH method as follows: “. The total area of signal across all relevant sections, including both hemispheres, was calculated for each brain nucleus using Olyvia software (Olympus). Images were converted to a 256-level intensity scale, and pixels with intensities from 161 to 256 were considered signals. All sections used for comparison were processed in the same batch, without corrections between samples.”

      Line 596: The following text has been added to include additional details on the double ISH method: “Cells were identified as coexpressing the two genes when Alexa Fluor 555 and fluorescein signals were clearly observed in the cytoplasm surrounding DAPI-stained nuclei, with intensities markedly stronger than the background noise.”

      (6) It seems very dangerous to use the response to a mutant abnormal behavior (ESR2-KO females) as a test, given that it is not clear what is the cause of the disrupted behavior.

      esr2b-deficient females have fully developed ovaries, a normal sex steroid milieu, and sexual attractiveness to males comparable to wild-type females, yet they are completely unreceptive to male courtship (Nishiike et al., 2021, Curr Biol, 1699–1710). Although, as the reviewer noted, the detailed mechanisms underlying this phenotype remain unclear, it is evident that the loss of estrogen/Esr2b signaling in the brain severely impairs sexual receptivity. Therefore, using esr2b-deficient females as stimulus females in the mating behavior test eliminates the influence of female sexual receptivity and male attractiveness to females, enabling the exclusive assessment of male mating motivation. This rationale is already presented in the Results section (lines 116–120), and we believe this experimental design offers a robust framework for assessing male mating motivation.

      Additionally, the mating behavior test with esr2b-deficient females complemented the test with wildtype females, and its results were not the sole basis for our discussion of the male mating behavior phenotype. The results of both tests were largely concordant, and we believe that the conclusions drawn from them are highly reliable.

      Meanwhile, in the test with esr2b-deficient females, cyp19a1b-deficient males were courted more frequently by these females than wild-type males. As the reviewer noted, this may suggest an anomaly in the test. Accordingly, we have confined our discussion to the possibility that “Perhaps cyp19a1b<sup>−/−</sup> males are misidentified as females by esr2b-deficient females because they are reluctant to court or they exhibit some female-like behavior” (line 131).

      (7) Most experiments are weakly powered (low sample size) and analyzed by multiple T-tests while 2 way ANOVA could have been used in several instances. No mention of T or F values, or degrees of freedom.

      Histological analysis was conducted with a relatively small sample size, as our previous experience suggested that interindividual variability in the results would not be substantial. As significant differences were detected in many analyses, further increasing the sample size is unnecessary.

      Although two-way ANOVA could be used instead of multiple T-tests for analyzing the data in Figures 4D, 4F, 6D, S4A, and S4B, we applied the Bonferroni–Dunn correction to control for multiple pairwise comparisons in multiple T-tests. As this comparison method is equivalent to the post hoc test following two-way ANOVA, the statistical results are identical regardless of whether T-tests or two-way ANOVA are used.

      For the data in Figures 4D, 4F, S4A, and S4B, the primary focus is on whether relative luciferase activity differs between E2-treated and untreated conditions for each mutant construct. Therefore, two-way ANOVA is not particularly relevant, as assessing the main effect of construct type or its interaction with E2 treatment does not provide meaningful insights. Similarly, in Figure 6D, the focus is solely on whether wild-type and mutant females differ in time spent at each distance. Given this, two-way ANOVA is unnecessary, as analyzing the main effect of distance is not meaningful.

      Accordingly, two-way ANOVA was not employed in this study, and therefore, its corresponding F values were not included. As the figure legends specify the sample sizes for all analyses, specifying degrees of freedom separately was deemed unnecessary.

      (8) The variability of the mRNA content for the same target gene between experiments (genotype comparison vs E2 treatment comparison) raises questions about the reproducibility of the data (apparent disappearance of genotype effect).

      As the reviewer pointed out, the overall area of ara expression is larger in Figure 2J than in Figure 2F. However, the relative area ratios of ara expression among brain nuclei are consistent between the two figures, indicating the reproducibility of the results. Thus, this difference is unlikely to affect the conclusions of this study.

      Additionally, the differences in ara expression in pPPp and arb expression in aPPp between wild-type and cyp19a1b-deficient males appear less pronounced in Figures 2J and 2K than in Figures 2F and 2H. This is likely attributable to the smaller sample size used in the experiments for Figures 2J and 2K, resulting in less distinct differences. However, as the same genotype-dependent trends are observed in both sets of figures, the conclusion that ara and arb expression is reduced in cyp19a1b-deficient male brains remains valid.

      (9) The discussion confuses the effects of estrogens on sexual differentiation (developmental programming = permanent) and activation (= reversible activation of brain circuits in adulthood) of the brain and behavior. Whether sex differences in the circuits underlying social behaviors exist is not clear.

      We recognize that the effects of adult steroids are sometimes not considered to be sexual differentiation, as they do not differentiate the neural substrate, but rather transiently activate the already masculinized or feminized substrate. Arnold (2017, J Neurosci Res 95:291–300) contends that all factors that cause sex differences, including the transient effects of adult steroids, should be incorporated into a theory of sexual differentiation, and indeed, these effects may be the most potent proximate factors that make males and females different. We concur with this perspective and have adopted it as a foundation for our manuscript.

      In teleosts, early developmental exposure to steroids has minimal impact, and sexual differentiation relies primarily on steroid action in adulthood (Okubo et al., 2022, Spectrum of Sex, pp. 111–133). This is evidenced by the effective reversal of sex-typical behaviors through experimental hormonal manipulation in adult teleosts and the absence of transient early-life steroid surges observed in mammals and birds. Accordingly, our discussion on brain sexual differentiation, including the statement in line 347, “This variation among species may represent the activation of neuroestrogen synthesis at life stages critical for sexual differentiation of behavior that are unique to each species”, remains well-supported. Additionally, given these considerations, while sex differences in neural circuit activation are evident in teleosts, substantial structural differences in these circuits are unlikely.

      (10) Overall, the claims regarding the activational role of neuro-estrogens on male sexual behavior are supported by converging evidence from multiple mutant lines. The role of neuroestrogens on gene expression in the brain is mostly solid too. The data for females are comparatively weaker. Conclusions regarding sexual differentiation should be considered carefully.

      We agree that the data for females are less extensive than for males. However, we have previously elucidated the mechanism by which estrogen/Esr2b signaling promotes female mating behavior (Nishiike et al., 2021). Accordingly, it follows that the new insights into female behavior gained from the cyp19a1b knockout model are more limited than those for males. Nevertheless, when integrated with our prior findings, the data on females in this study provide significant insights, and the overall mechanism through which estrogens promote female mating behavior is becoming clearer. Therefore, we do not consider the female data in this study to be incomplete or merely supplementary.

      Recommendations For The Authors:

      Reviewer #1 (Recommendations For The Authors):

      The authors set out to answer an intriguing question regarding the hormonal control of innate social behaviors in medaka. Specifically, they wanted to test the effects of cyp19a1b mutation on mating and aggression in males. They also test these effects in females. Their approach takes them down several distinct experimental pathways, including one investigating how cyp19a1a function is related to androgen receptor expression and how estrogens themselves may act on the androgen receptor to modulate its expression, as well as how different esr genes may be involved. The study and its results are valuable and a clear, general conclusion of a pathway from brain aromatase>estrogens>esr genes> androgen receptor can be made. This is important, novel, and impactful. However, there are issues with how the study logic is set up, the approach for assessing certain behaviors, the statistics used, the interpretation of findings, and placing the findings in the proper context based on previous work, which manifests as a general issue where previous work is not properly attributed to.

      Thank you for your thoughtful review. We have carefully addressed each specific comment, as detailed below.

      Major comments:

      (1) The background for the rationale of the current study is misleading and lacks proper context. The authors root the logic of their experiment in determining whether estrogens regulate male-typical behaviors because the current assumption is androgens are "solely responsible" for male-typical behaviors in teleosts. This is not the case. Previous studies have shown aromatase/estrogens are involved in male-typical aggression in teleosts. For example, to name a couple:

      Huffman, L. S., O'Connell, L. A., & Hofmann, H. A. (2013). Aromatase regulates aggression in the African cichlid fish Astatotilapia burtoni. Physiology & behavior, 112, 77-83.

      O'Connell, L. A., & Hofmann, H. A. (2012). Social status predicts how sex steroid receptors regulate complex behavior across levels of biological organization. Endocrinology, 153(3), 1341-1351.

      And even a recent paper sheds light on a possible AR>aromatase.estradiol hypothesis of male typical behaviors:

      Lopez, M. S., & Alward, B. A. (2024). Androgen receptor deficiency is associated with reduced aromatase expression in the ventromedial hypothalamus of male cichlids. Annals of the New York Academy of Sciences.

      Interestingly, the authors cite Hufmann et al in the discussion, so I don't understand why they make the claims they do about estrogens and male-typical behavior.

      Related to this, is an issue of proper attribution to published work. Indeed, missing are key references from lab groups using AR mutant teleosts. Here are a couple:

      Yong, L., Thet, Z., & Zhu, Y. (2017). Genetic editing of the androgen receptor contributes to impaired male courtship behavior in zebrafish. Journal of Experimental Biology, 220(17), 3017-3021.

      Alward, B. A., Laud, V. A., Skalnik, C. J., York, R. A., Juntti, S. A., & Fernald, R. D. (2020). Modular genetic control of social status in a cichlid fish. Proceedings of the National Academy of Sciences, 117(45), 28167-28174.

      Ogino, Y., Ansai, S., Watanabe, E., Yasugi, M., Katayama, Y., Sakamoto, H., ... & Iguchi, T. (2023). Evolutionary differentiation of androgen receptor is responsible for sexual characteristic development in a teleost fish. Nature communications, 14(1), 1428.

      As noted in Response to reviewer #1’s comment 3 on weaknesses, we have revised the Introduction and Discussion sections as follows.

      Line 56: “solely responsible” in the Introduction has been modified to “largely responsible”.

      Line 57: The text “This is consistent with the recent finding in medaka fish (Oryzias latipes) that estrogens act through the ESR subtype Esr2b to prevent females from engaging in male-typical courtship (10)” has been revised to “This is consistent with recent observations in a few teleost species that genetic ablation of AR severely impairs male-typical behaviors (13–16) and with findings in medaka fish (Oryzias latipes) that estrogens act through the ESR subtype Esr2b to prevent females from engaging in male-typical courtship (12)” to include previous studies on the behavior of AR mutant fish (Yong et al., 2017; Alward et al., 2020; Ogino et al., 2023; Nishiike and Okubo, 2024) in the Introduction.

      Line 65: “It is worth mentioning that systemic administration of estrogens and an aromatase inhibitor increased and decreased male aggression, respectively, in several teleost species, potentially reflecting the behavioral effects of brain-derived estrogens (21–24)” has been added to the Introduction, providing an overview of previous studies on the effects of estrogens and aromatase on male fish aggression (Hallgren et al., 2006; O’Connell and Hofmann, 2012; Huffman et al., 2013; Jalabert et al., 2015).

      Line 367: “treatment of males with an aromatase inhibitor reduces their male-typical behaviors (31– 33)” has been edited to read “treatment of males with an aromatase inhibitor reduces their male-typical behaviors, while estrogens exert the opposite effect (21–24).”

      After the revisions described above, the following references (#13, 14, and 22) have been added to the reference list:

      L. Yong, Z. Thet, Y. Zhu, Genetic editing of the androgen receptor contributes to impaired male courtship behavior in zebrafish. J. Exp. Biol. 220, 3017–3021 (2017).

      B. A. Alward, V. A. Laud, C. J. Skalnik, R. A. York, S. A. Juntti, R. D. Fernald, Modular genetic control of social status in a cichlid fish. Proc. Natl. Acad. Sci. U.S.A. 117, 28167–28174 (2020).

      L. A. O’Connell, H. A. Hofmann, Social status predicts how sex steroid receptors regulate complex behavior across levels of biological organization. Endocrinology 153, 1341–1351 (2012).

      While Lopez and Alward (2024) provide valuable insights into the regulation of cyp19a1b expression by androgens, our study focuses specifically on the functional aspects of cyp19a1b. Expanding the discussion to include expression regulation would divert from the primary focus of our manuscript. For this reason, we have opted not to cite this reference.

      (2) As it is now, the authors are only citing a book chapter/review from their own group. This is a serious issue as it does not provide the proper context for the work. The authors need to fix their issues of attribution to previously published work and the proper interpretation of the work that they are aware of as it pertains to ideas proposed on the roles of androgens and estrogens in the control of male-typical behaviors. This is also important to get the citations right because the common use of "contrary to expectations" when describing their results is actually not correct. Many of the observations are expected to a degree. However, this doesn't take away from a generally stellar experimental design and mostly clear results. The authors do not need to rely on enhancing the impact of their paper by making false claims of unexpected findings. The depth and clarity of your findings are where the impact of your work is.

      As detailed in Response to reviewer #1’s comment 3 on weaknesses, we have cited previous studies on the effects of estrogens and aromatase on male fish aggression (Hallgren et al., 2006; O’Connell and Hofmann, 2012; Huffman et al., 2013; Jalabert et al., 2015) in the Introduction.

      Additionally, as noted in Response to reviewer #1’s comment 4 on weaknesses, we have made the following revisions to avoid phrases such as “contrary to expectation” and “unexpected.”

      Line 76: “Contrary to our expectations” → “Remarkably.”

      Line 109: “Contrary to this expectation, however” → “Nevertheless.”

      Line 135: “Again, contrary to our expectation, cyp19a1b<sup>−/−</sup> males” → “cyp19a1b<sup>−/−</sup> males.”

      Line 333: “unexpected” → “noteworthy.”

      Line 337: “unexpected” → “notable.”

      (3) The experimental design for studying aggression in males has flaws. A standard test like a residentintruder test should be used. An assay in which only male mutants are housed together? I do not understand the logic there and the logic for the approach isn't even explained. Too many confounds that are not controlled for. It makes it seem like an aspect of the study that was thrown in as an aside.

      As noted in Response to reviewer #1’s comment 5 on weaknesses, medaka form shoals and lack strong territoriality. As a result, even slight differences in dominance between the resident and intruder can substantially impact the outcomes of the resident-intruder test. Therefore, we adopted an alternative approach in this study.

      (4) Hormonal differences in the mutants seem to vary based on sex, and the meaning of these differences, or how they affect interpreting the findings, wasn't discussed. There was no acknowledegment of the fact that female central E2 was still at 50%, meaning the "rescue" experiments using peripheral injections are not given the proper context. For example, this is different than giving a fish with only 16% of their normal central E2 an E2 injection. Missing as well is a clear hypothesis for why E2 injections did not rescue aggression deficits in cyp19a1b mutant males.

      Line 385: As the reviewer pointed out, the degree of brain estrogen reduction in cyp19a1b-deficient fish differs greatly between males and females. This is likely because females receive a large supply of estrogens from the ovaries. Given that estrogen levels in cyp19a1b-deficient females were 50% of those in wild-type females, it can be inferred that half of their brain estrogens are synthesized locally, while the other half originates from the ovaries. This is an important finding, and we have already noted in the Discussion that “females have higher brain levels of estrogens, half of which are synthesized locally in the brain (i.e., neuroestrogens)” However, as this explanation was not sufficiently clear, we have revised it to “females have higher brain levels of estrogens, with half being synthesized locally and the other half supplied by the ovaries.”

      The reviewer raised a concern that conducting the estrogen rescue experiment in females, where 50% of brain estrogens remain, might be inappropriate. However, as this experiment was conducted exclusively in males, this concern is not applicable.

      Line 377: As noted in the reviewer’s subsequent comment, the failure of aggression recovery in E2treated cyp19a1b-deficient males could be due to insufficient induction of ara/arb expression in aggression-relevant brain regions. To address this concern, we have inserted the following statement into the Discussion after “the development of male behaviors may require moderate neuroestrogen levels that are sufficient to induce the expression of ara and arb, but not esr2b, in the underlying neural circuitry”: “This may account for the lack of aggression recovery in E2-treated cyp19a1b-deficient males in this study.”

      (5) In relation to that, the "null" results may have some of the most interesting implications, but they are barely discussed. For example, what does it mean that E2 didn't restore aggression in male cyp19 mutants? Is this a brain region factor? Could this relate to findings from Lopez et al NYAS, where male and female Ara mutants show different effects on brain-region-specific aromatase expression? And maybe this relates to the different impact of estrogens on ar expression. Were the different effects impacted in aggression areas? Maybe this is why E2 injection didn't retore aggression in males. You could make the argument that: (1) E2 doesn't restore ar expression in aggression regions and that's why there was no rescue. Or (2) that the circuits in adulthood that regulate aggression are NOT dependent on aggression but in early development they are. Another null finding not expanded on is why the two esr2a mutant lines showed differences. There is no reason to trust one line over the other, meaning we still don't know whether esr2a is required for latency to follow.

      As stated in our response to the previous comment, we have added the following text to the Discussion (line 377): “This may account for the lack of aggression recovery in E2-treated cyp19a1b-deficient males in this study.” Meanwhile, as discussed in lines 341–342, it is highly unlikely that the neural circuits regulating aggression are primarily influenced by early-life estrogen exposure, because androgen administration in adulthood alone is sufficient to induce high levels of aggression in both sexes. This notion is further supported by previous observations that cyp19a1b expression in the brain is minimal during embryonic development (Okubo et al., 2011, J Neuroendocrinol, 23:412–423).

      The findings of Lopez and Alward (2024) pertain to the regulation of cyp19a1b expression by androgen receptors. While this represents an important aspect of neuroendocrine regulation, it does not appear to be directly relevant to our discussion on cyp19a1b-mediated regulation of androgen receptor expression.

      To ensure the reliability of behavioral analyses in mutant fish, we consider a phenotype valid only when it is consistently observed in two independent mutant lines. In the mating behavior test examining esr2adeficient males using esr2b-deficient females as stimulus females, Δ8 line males exhibited a shorter latency to initiate following than wild-type males, whereas Δ4 line males did not. This discrepancy led us to refrain from drawing conclusions about the role of esr2a in mating behavior, even though the mating behavior test using wild-type females as stimulus females yielded consistent results in the Δ8 and Δ4 lines. Therefore, we do not consider the reviewer’s concern to be a significant issue.

      (6) Not sure what's going on with the statistics, but it is not appropriate here to treat a "control" group as special. All groups are "experimental" groups. There is nothing special about the control group in this context. all should be Bonferroni post-hoc tests.

      Line 619: As detailed in Response to reviewer #1’s comment 7 on weaknesses, we consider Dunnett’s test the most appropriate choice for the experiments presented in Figures 4C and 4E. We acknowledge that the reviewer’s concern may stem from the phrase “comparisons between control and experimental groups” in the Materials and Methods section. To clarify this point, we have revised it to “comparisons between untreated and E2-treated groups in Fig. 4, C and D” for clarity.

      Minor comments:

      Line 47: then how can you say the aromatization hypothesis is "correct"? it only applies to a few species so far. Need to change the framing, not state so strongly such a vague thing as a hypothesis being "correct".

      Line 45: To address this concern, we have modified “widely accepted as correct” to “widely acknowledged”, ensuring a more precise characterization.

      Figure 1: looks like a dosage effect in males but not females. this should be discussed at some point, even if just to mention a dosage effect exists and put it in context.

      Line 91: We have revised the sentence “In males, brain E2 in heterozygotes (cyp19a1b+/−) was also reduced to 45% of the level in wild-type siblings (P = 0.0284) (Fig. 1A)” by adding “, indicating a dosage effect of cyp19a1b mutation” to make this point explicit.

      Were male cyp19 KO aggressive towards females?

      We have not observed cyp19a1b-deficient males exhibiting aggressive behavior towards females in our experiments. Therefore, we do not consider them aggressive toward females.

      Please explain how infertility would lead to reduced mating.

      Line 142: As the reviewer has questioned, even if cyp19a1b-deficient males exhibit infertility due to efferent duct obstruction, it is difficult to imagine that this directly leads to reduced mating. However, the inability to release sperm could indirectly affect behavior. To address this, we have added “, possibly due to the perception of impaired sperm release” after “If this is also the case in medaka, the observed behavioral defects might be secondary to infertility.”

      Describe something about the timing of the treatment here. How can peripheral E2 injections restore it when peripheral levels are normal? Did these injections restore central levels? This needs to be shown experimentally.

      Line 517: As described in the Materials and Methods, E2 treatment was conducted by immersing fish in E2-containing water for 4 days. However, we had not explicitly stated that the water was changed daily to maintain the nominal concentration. To clarify this and address reviewer #2’s comment 9, we have revised “males were treated with 1 ng/ml of E2 (Fujifilm Wako Pure Chemical, Osaka, Japan) or vehicle (ethanol) alone by immersion in water for 4 days” to “males were treated with 1 ng/ml of E2 (Fujifilm Wako Pure Chemical, Osaka, Japan), which was first dissolved in 100% ethanol (vehicle), or with the vehicle alone by immersion in water for 4 days, with daily water changes to maintain the nominal concentration.”

      Line 522: The treatment effectively restored mating activity and ara/arb expression in the brain, suggesting a sufficient increase in brain E2 levels. However, we did not measure the actual increase, and its extent remains uncertain. To reflect this in the manuscript, we have now added the following sentence: “Although the exact increase in brain E2 levels following E2 treatment was not quantified, the observed positive effects on behavior and gene expression suggest that it was sufficient.”

      I know the nomenclature differs among those who study teleosts, but it's ARa and then gene is ar1 (as an example; arb would be ar2). You're recommended the following citation to remain consistent:

      Munley, K. M., Hoadley, A. P., & Alward, B. A. (2023). A phylogenetics-based nomenclature system for steroid receptors in teleost fishes. General and Comparative Endocrinology, 114436.

      Paralogous genes resulting from the third round of whole-genome duplication in teleosts are typically designated by adding the suffixes “a” and “b” to their gene symbols. This convention also applies to the two androgen receptor genes, commonly referred to as ara and arb. While the alternative names ar1 and ar2 may gain broader acceptance in the future, ara and arb remain more widely used at present. Therefore, we have chosen to retain ara and arb in this manuscript.

      Line 268: how is this "suggesting" less aggression? They literally showed fewer aggressive displays, so it doesn't suggest it - it literally shows it.

      Line 285: Following this thoughtful suggestion, we have changed “suggesting less aggression” to “showing less aggression.”

      Line 317: how can you still call it the primary driver?

      The stimulatory effects of aromatase/estrogens on male-typical behaviors are exerted through the potentiation of androgen/AR signaling. Thus, we still believe that androgens—specifically 11KT in teleosts—serve as the primary drivers of these behaviors.

      Line 318: not all deficits, like aggression, were rescued.

      Line 334: To address this comment, “These behavioral deficits were rescued by estrogen administration, indicating that reduced levels of neuroestrogens are the primary cause of the observed phenotypes: in other words, neuroestrogens are pivotal for male-typical behaviors in teleosts” has been modified and now reads “Deficits in mating were rescued by estrogen administration, indicating that reduced brain estrogen levels are the primary cause of the observed mating impairment; in other words, brain-derived estrogens are pivotal at least for male-typical mating behaviors in teleosts.”

      Line 324: what do you mean by "sufficient"? To show that, you'd have to castrate the male and only give estrogen back. the authors continue to overstate virtually every aspect of their study, seemingly in an unnecessary manner.

      Line 341: Our intention was to convey that brain-derived estrogens early in life are not essential for the expression of male-typical behaviors in teleosts. However, we recognize that the term “sufficient” could be misinterpreted as implying that estrogens alone are adequate, without contributions from other factors such as androgens. To clarify this, we have revised the text from “neuroestrogen activity in adulthood is sufficient for the execution of male-typical behaviors, while that in early in life is not requisite. Thus, while” to “brain-derived estrogens early in life is not essential for the execution of male-typical behaviors. While.”

      Line 329: so? in adult mice, amygdala aromatase neurons still regulate aggression. The amount in adulthood seems less important compared to site-specific functions.

      Line 346: We do not intend to suggest that brain aromatase activity in adulthood plays a negligible role in male behaviors in rodents, as we have already acknowledged its necessity in the Introduction (lines 42–43). To enhance clarity and prevent misinterpretation, we have added “, although it remains important for male behavior in adulthood” to the end of the sentence: “brain aromatase activity in rodents reaches its peak during the perinatal period and thereafter declines with age.”

      Line 351: This contradicts what you all have been saying.

      Line 65: As mentioned in Response to reviewer #1’s comment 3 on weaknesses, the following text has been added to the Introduction: “It is worth mentioning that systemic administration of estrogens and an aromatase inhibitor increased and decreased male aggression, respectively, in several teleost species, potentially reflecting the behavioral effects of brain-derived estrogens (21–24)”, providing an overview of previous studies on the effects of estrogens and aromatase on male fish aggression (Hallgren et al., 2006; O’Connell and Hofmann, 2012; Huffman et al., 2013; Jalabert et al., 2015). With this revision, we believe the inconsistency has been addressed.

      Line 367: Additionally, we have revised the sentence from “treatment of males with an aromatase inhibitor reduces their male-typical behaviors (31–33)” to “treatment of males with an aromatase inhibitor reduces their male-typical behaviors, while estrogens exert the opposite effect (21–24).”

      Line 360: change to "...possibility that is not mutually exclusive,"

      Line 378: We have revised the phrase as suggested from “Another possibility, not mutually exclusive,” to “Another possibility that is not mutually exclusive.”

      Line 363: but it didn't rescue aggression

      Line 381: In response, we have revised the sentence from “This possibility is supported by the present observation that estrogen treatment facilitated mating behavior in cyp19a1b-deficient males but not in their wild-type siblings” to “This possibility is at least likely for mating behavior, as estrogen treatment facilitated mating behavior in cyp19a1b-deficient males but not in their wild-type siblings.”

      Line 367: on average

      To explain the sex differences in the role of aromatase, what about the downstream molecular or neural targets? In mammals, hodology is related to sex differences. there could be convergent sex differences in regulating the same type of behaviors as well.

      Our findings demonstrate that brain-derived estrogens promote the expression of ara, arb, and their downstream target genes vt and gal in males, while enhancing the expression of npba, a downstream target of Esr2b signaling, in females. The identity of additional target genes and their roles in specific neural circuits remain to be elucidated, and we aim to address these in future research.

      Lines 378-382: this doesn't logically follow. pgf2a could be the target of estrogens which in the intact animal do regulate female sexual receptivity. And how can you say this given that your lab has shown in esr2b mutants females don't mate?

      We agree that PGF2α signaling may be activated by estrogen signaling, as stated in lines 404–407: “the present finding provides a likely explanation for this apparent contradiction, namely, that neuroestrogens, rather than or in addition to ovarian-derived circulating estrogens, may function upstream of PGF2α signaling to mediate female receptivity.” The observation that esr2b-deficient females do not accept male courtship is also stated in lines 401–403: “we recently challenged it by showing that female medaka deficient for esr2b are completely unreceptive to males, and thus estrogens play a critical role in female receptivity.”

      Line 396-397: or the remaining estrogens are enough to activate esr2b-dependent female-typical mating behaviors.

      We agree that cyp19a1b deficiency did not completely preclude female mating behavior, most likely because residual estrogens in the brains of cyp19a1b-deficient females enable weak activation of Esr2b signaling. However, the relevant section in the Discussion is not focused on examining why mating behavior persisted, but rather on considering the implications of this finding for the neural circuits regulating mating behavior. Therefore, incorporating the suggested explanation here would shift the focus and would not be appropriate.

      Line 420-421: this is a lot of variation. Was age controlled for?

      The time required for medaka to reach sexual maturity varies with rearing density and food availability. Due to space constraints, we adjust these parameters as needed, which led to variation in the ages of the experimental fish. However, since all experiments were conducted using sibling fish of the same age that had just reached sexual maturity, we believe this does not affect our conclusions.

      Line 457: have these kits been validated in medaka?

      Although we have not directly validated its applicability in medaka, its extensive use in this species suggests that it us unlikely to pose any issues (e.g., Ussery et al., 2018, Aquat Toxicol, 205:58–65; Lee et al., 2019, Ecotoxicol Environ Saf, 173:174–181; Kayo et al., 2020, Gen Comp Endocrinol, 285:113272; Fischer et al., 2021, Aquat Toxicol, 236:105873; Royan et al., 2023, Endocrinology, 164:bqad030).

      Line 589, re fish that spawned: how many times did this happen? Please note it is based on genotype and experiment. This could be important.

      Line 627: In response to this comment, we have added the following details: “Specifically, 7/18 cyp19a1b<sup>+/+</sup>, 11/18 cyp19a1b<sup>+/−</sup>, and 6/18 cyp19a1b<sup>−/−</sup> males were excluded in Fig. 1D; 6/10 cyp19a1b<sup>+/+</sup>, 3/10 cyp19a1b<sup>+/−</sup>, and 6/10 cyp19a1b<sup>−/−</sup> females were excluded in Fig. 6B; 2/23 esr1+/+ and 5/24 esr1−/− males were excluded in Fig. S7; 2/24 esr2a+/+ and 3/23 esr2a<sup>−/−</sup> males were excluded in Fig. S8A; 0/23 esr2a+/+ and 0/23 esr2a<sup>−/−</sup> males were excluded in Fig. S8B.”

      Reviewer #2 (Recommendations For The Authors):

      Abstract:

      (A1) The framing of neuroestrogens being important for male-typical rodents, and not for other vertebrate lineages, does not account for other groups (birds) in which this is true (the authors can consult their cited work by Balthazart (Reference 6) for extensive accounting of this). This makes the novelty clause in the abstract "indicating that neuro-estrogens are pivotal for male-typical behaviors even in nonrodents" less surprising and should be acknowledged by the authors by amending or omitting this novelty clause. The findings regarding androgen receptor transcription (next sentence) are more important and pertinent.

      Line 27: We recognize that the aromatization hypothesis applies to some birds, including zebra finches, as stated in the Introduction (lines 48–49) and Discussion (lines 432–433). However, this was not reflected in the Abstract. Following the reviewer’s suggestion, we have changed “in non-rodents” to “in teleosts.”

      (A2) The medaka line that has been engineered to have aromatase absent in the brain is presented briefly in the abstract, but can be misinterpreted as naturally occurring. This should be amended, by including something like "engineered" or "directed mutant" before 'male medaka fish'.

      Line 24: We have added “mutagenesis-derived” before “male medaka fish” in response to this comment.

      Introduction:

      (I1) The paragraph on teleost brain aromatase should acknowledge that while the capacity for estrogen synthesis in the brain is 100-1000 fold higher in teleosts as compared to rodents and other vertebrates, the majority of this derives from glial and not neural sources. This can be confusing for readers since the term 'neuroestrogens' often refers to the neuronal origin and signalling. And this observation includes the exclusive radial glial expression of cyp19a1b in medaka (Diotel et al., 2010), and first discovered in midshipman (Forlano et al., 2001), each of which should also be cited here. In addition, the authors expend much text comparing teleosts and rodents, but it is worth expanding these kinds of comparisons, especially by pointing out that parts of the primate brain are found to densely express aromatase (see work by Ei Terasawa and others).

      In response to this comment and a similar comment from reviewer #1, we have replaced “neuroestrogens” with “brain-derived estrogens” or “brain estrogens” throughout the manuscript.

      Line 63: We have also added the text “In teleost brains, including those of medaka, aromatase is exclusively localized in radial glial cells, in contrast to its neuronal localization in rodent brains (18– 20).” As a result of this addition, we have changed “This observation suggests” to “These observations suggest” in the subsequent sentence.

      Line 51: Additionally, to include information on aromatase in the primate brain, we have added the following text: “In primates, the hypothalamic aromatization of androgens to estrogens plays a central role in female gametogenesis (10) but is not essential for male behaviors (7, 8).”

      The following references (#10 and 18–20), cited in the newly added text above, have been included in the reference list, with other references renumbered accordingly:

      E. Terasawa, Neuroestradiol in regulation of GnRH release. Horm. Behav. 104, 138–145 (2018).

      P. M. Forlano, D. L. Deitcher, D. A. Myers, A. H. Bass, Anatomical distribution and cellular basis for high levels of aromatase activity in the brain of teleost fish: aromatase enzyme and mRNA expression identify glia as source. J. Neurosci. 21, 8943–8955 (2001).

      N. Diotel, Y. Le Page, K. Mouriec, S. K. Tong, E. Pellegrini, C. Vaillant, I. Anglade, F. Brion, F. Pakdel, B. C. Chung, O. Kah, Aromatase in the brain of teleost fish: expression, regulation and putative functions. Front. Neuroendocrinol. 31, 172–192 (2010).

      A. Takeuchi, K. Okubo, Post-proliferative immature radial glial cells female-specifically express aromatase in the medaka optic tectum. PLoS One 8, e73663 (2013).

      (I2) It is difficult to resolve from the introduction and work cited how restricted cyp19a1b is to the medaka brain. Important for the results of this study, it is not clear whether it is more of a bias in the brain vs other tissues, or if the cyp19a1b deficiency is restricted to the brain, and gonadal/peripheral cyp19 expression persists. The authors need to improve their consideration of the alternatives, i.e., that this manipulation is not somehow affecting: 1) peripheral aromatase expression (either cyp19a1a or cyp19a1b) in the gonad or elsewhere, 2) compensatory processes, such as other steroidogenic genes (are androgen synthesizing enzymes increasing?).

      Our previous study demonstrated that cyp19a1b is expressed in the gonads, but at levels tens to hundreds of times lower than those in the brain (Okubo et al., 2011, J Neuroendocrinol 23:412–423). Additionally, a separate study in medaka reported that cyp19a1b expression in the ovary is considerably lower than that of cyp19a1a (Nakamoto et al., 2018, Mol Cell Endocrinol 460:104–122). Given these observations, any potential effect of cyp19a1b knockout on peripheral estrogen synthesis is likely negligible. Indeed, Figures S1C and S1D confirm that cyp19a1b knockout does not alter peripheral E2 levels.

      Line 72: To incorporate this information into the Introduction and address the following comment, we have added the following text: “In medaka, cyp19a1b is also expressed in the gonads, but only at a level tens to hundreds of times lower than in the brain and substantially lower than that of cyp19a1a (26, 27).”

      The following references (#26 and 27), cited in the newly added text above, have been included in the reference list, with other references renumbered accordingly:

      K. Okubo, A. Takeuchi, R. Chaube, B. Paul-Prasanth, S. Kanda, Y. Oka, Y. Nagahama, Sex differences in aromatase gene expression in the medaka brain. J. Neuroendocrinol. 23, 412–423 (2011).

      M. Nakamoto, Y. Shibata, K. Ohno, T. Usami, Y. Kamei, Y. Taniguchi, T. Todo, T. Sakamoto, G. Young, P. Swanson, K. Naruse, Y. Nagahama, Ovarian aromatase loss-of-function mutant medaka undergo ovary degeneration and partial female-to-male sex reversal after puberty. Mol. Cell. Endocrinol. 460, 104–122 (2018).

      We have not assessed whether the expression of other steroidogenic enzymes is altered in cyp19a1bdeficient fish, and this may be investigated in future studies.

      (I3) Related, there are documented sex differences in the brain expression of cyp19a1b especially in adulthood (Okubo et al 2011) and this study should be cited here for context.

      Line 72: As stated in our previous response, we have cited Okubo et al. (2011) by adding the following sentence: “In medaka, cyp19a1b is also expressed in the gonads, but only at a level tens to hundreds of times lower than in the brain and substantially lower than that of cyp19a1a (26, 27).”

      Methods

      (M1) The rationale is unclear as presented for using mutagen screening for cype19a1b while using CRISPR for esr2a. Are there methodological/biochemical reasons why the authors chose to not use the same method for both?

      At the time we generated the cyp19a1b knockouts, genome editing was not yet available, and the TILLING-based screening was the only method for obtaining mutants in medaka. In contrast, by the time we generated the esr2a knockouts, CRISPR/Cas9 had become available, enabling a more efficient and convenient generation of knockout lines. This is why the two knockout lines were generated using different methods.

      (M2) Measurement of steroids in biological matrices is not straightforward, and it is good that the authors use multiple extraction steps (organic followed by C18 columns) before loading samples on the ELISA plates, which are notoriously sensitive. Even though these methods have been published before by this group of authors previously, the quality control and ELISA performance values (recovery, parallelism, etc.) should be presented for readers to evaluate.

      Thank you for appreciating our sample purification method. Unfortunately, we have not evaluated the recovery rate or parallelism, but we recognize this a subject for future studies.

      (M3) Mating behavior - E2 treated males were not co-housed with social partners for the full 24 hr before testing, but instead a few hours (?) prior to testing. The rationale for this should be spelled out explicitly.

      Line 494: In response to this comment, we have added “to ensure the efficacy of E2 treatment” to the end of the sentence “The set-up was modified for E2-treated males, which were kept on E2 treatment and not introduced to the test tanks until the day of testing.”

      (M4) The E2 treatment is listed as 1ng/ml vs. vehicle (ethanol). Is the E2 dissolved in 100% ethanol for administration to the tank water? Clarification is needed.

      Line 517: As the reviewer correctly assumed, E2 was first dissolved in 100% ethanol before being added to the tank water. To provide this information and address reviewer #1’s minor comment 5, we have revised “males were treated with 1 ng/ml of E2 (Fujifilm Wako Pure Chemical, Osaka, Japan) or vehicle (ethanol) alone by immersion in water for 4 days” to “males were treated with 1 ng/ml of E2 (Fujifilm Wako Pure Chemical, Osaka, Japan), which was first dissolved in 100% ethanol (vehicle), or with the vehicle alone by immersion in water for 4 days, with daily water changes to maintain the nominal concentration.”

      (M5) The authors exclude fish from the analysis of courtship display behavior for those individuals that spawned immediately at the start of the testing (and therefore it was impossible to register courtship display behaviors). How often did fish in the various treatment groups exhibit this "fast spawning" behavior? Was the occurrence rate different by treatment group? It is unlikely that these omissions from the data set drove large-scale patterns, but an indication of how often this occurred would be reassuring.

      Line 627: In response to this comment, we have included the following details: “Specifically, 7/18 cyp19a1b<sup>+/+</sup>, 11/18 cyp19a1b<sup+/−</sup>, and 6/18 cyp19a1b<sup>−/−</sup> males were excluded in Fig. 1D; 6/10 cyp19a1b+/+, 3/10 cyp19a1b+/−, and 6/10 cyp19a1b<sup>−/−</sup> females were excluded in Fig. 6B; 2/23 esr1+/+ and 5/24 esr1−/− males were excluded in Fig. S7; 2/24 esr2a+/+ and 3/23 esr2a<sup>−/−</sup> males were excluded in Fig. S8A; 0/23 esr2a+/+ and 0/23 esr2a<sup>−/−</sup> males were excluded in Fig. S8B.” These data indicate that the proportion of excluded males is nearly constant within each trial and is independent of the genotype of the focal fish.

      Results

      (R1) It is striking to see the genetic-'dose' dependent suppression of brain E2 content by heterozygous and homozygous cyp19a1b deficiency, indicating that, as the authors point out, the majority of E2 in the male medaka brain (and 1/2 in the female brain) have a brain-derived origin. It is important also for the interpretation that there are large compensatory increases in brain levels of androgens, when E2 levels drop in the cyp19a1b mutant homozygotes. This latter point should receive more attention.

      Also, there are large increases in peripheral androgen levels in the homozygote mutants for cyp19a1b in both males and females. This indicates a peripheral effect in addition to the clear brain knockdown of E2 synthesis. These nuances need to be addressed.

      In response to this comment, we have revised the Results section as follows:

      Line 91: “, indicating a dosage effect of cyp19a1b mutation” has been added to the end of the sentence “In males, brain E2 in heterozygotes (cyp19a1b<sup>+/−</sup>) was also reduced to 45% of the level in wild-type siblings (P = 0.0284) (Fig. 1A).”

      Line 94: To draw more attention to the increase in brain androgen levels caused by cyp19a1b deficiency, “Brain levels of testosterone” has been modified to “Strikingly, brain levels of testosterone.”

      Line 100: “Their peripheral 11KT levels also increased 3.7- and 1.8-fold, respectively (P = 0.0789, males; P = 0.0118, females) (Fig. S1, C and D)” has been modified and now reads “In addition, peripheral 11KT levels in cyp19a1b<sup>−/−</sup> males and females increased 3.7- and 1.8-fold, respectively (P = 0.0789, males; P = 0.0118, females) (Fig. S1, C and D), indicating peripheral influence in addition to central effects.”

      (R2) The interpretation on page 4 that cyp19a1b deficient males are 'less motivated' to mate is premature, given the behavioral measures used in this study. There are several competing explanations for these findings (e.g., alterations in motivation, sensory discrimination, preference, etc.) that could be followed up in future work, but the current results are not able to distinguish among these possibilities.

      Line 112: We agree that the possibility of altered cognition or sexual preference cannot be dismissed. To incorporate this perspective, we have revised the text “, suggesting that they are less motivated to mate” to “These results suggest that they are less motivated to mate, though an alternative interpretation that their cognition or sexual preference may be altered cannot be dismissed.”

      (R3) On page 5, the authors present that peripheral E2 manipulation (delivery to the fish tank) restores courtship behavior in males, and then go on to erroneously conclude that this demonstrates "that reduced E2 in the brain was the primary cause of the mating defects, indicating a pivotal role of neuroestrogens in male mating behavior." Because this is a peripheral E2 treatment, there can be manifold effects on gonadal physiology or other endocrine events that can have indirect effects on the brain and behavior. Without manipulation of E2 directly to the brain to 'rescue' the cyp19a1b deficiency, the authors cannot conclude that these effects are directly on the central nervous system. Tellingly, the tank E2 treatment did not rescue aggressive behavior, suggestive of the potential for indirect effects.

      Line 155: As detailed in Response to reviewer #2’s specific comment 1, we have revised the text from “These results demonstrated that reduced E2 in the brain was the primary cause of the mating defects, indicating a pivotal role of neuroestrogens in male mating behavior. In contrast” to “These results suggest that reduced E2 in the brain is the primary cause of the mating defects, highlighting a pivotal role of brain-derived estrogens in male mating behavior. However, caution is warranted, as an indirect peripheral effect of bath-immersed E2 on behavior cannot be ruled out, although this is unlikely given the comparable peripheral E2 levels in cyp19a1b-deficient and wild-type males. In contrast to mating.”

      (R4) The downregulation of androgen-dependent gene expression (vasotocin in pNVT and galanin in pPMp) in the cyp19a1b deficient males (Figure 3) could be due to exceedingly high levels of brain androgens in the cyp19a1b deficient males. The best way to test the idea that estrogens can restore the expression to be more wild-type directly (like what is happening for ara and arb) is to look at these same markers (vasotocin and galanin) in these same brain areas in the brains of E2-treated males. The authors should have these brains from Figure 2. Unless I missed something, those experiments were not performed/reported here. It is clear that the ara and arb receptors have EREs and are 'rescued' by E2 treatment, but in principle, there could be indirect actions for reasons stated above for the behavior due to the peripheral E2 tank application.

      Thank you for your insightful comment. We agree that the current results cannot exclude the possibility that excessive androgen levels caused the downregulation of vt and gal. However, our previous studies showed that excessive 11KT administration to gonadectomized males and females increased the expression of these genes to levels comparable to wild-type males (Yamashita et al., 2020, eLife, 9:e59470; Kawabata-Sakata et al., 2024, Mol Cell Endocrinol 580:112101), making this scenario unlikely. That said, testing whether estrogen treatment restores vt and gal expression in cyp19a1bdeficient males would be informative, and we see this as an important direction for future research.

      Discussion

      (D1) The authors need to clarify whether EREs are found in other vertebrate AR introns, or is this unique to the teleost genome duplication?

      We have identified multiple ERE-like sequences within intron 1 of the mouse AR gene. However, sequence data alone do not provide sufficient evidence of their functionality, rendering this information of limited relevance. Therefore, we have chosen not to include this discussion in the current paper.

      Reviewer #3 (Recommendations For The Authors):

      (1) The authors are strongly encouraged to report information regarding the effect of Cyp19a1b deletion on the brain content of aromatase protein (ideally both isoforms investigated separately) as the two isoforms are mostly but not completely brain vs gonad specific. The analysis of other tissues would also strengthen the characterization of this model.

      We agree that measuring aromatase protein levels in the brain of our fish would be valuable for confirming the loss of cyp19a1b function. However, as no suitable method is currently available, this issue will need to be addressed in future studies. While this constitutes indirect evidence, the observed reduction in brain E2 levels, with no change in peripheral E2 levels, in cyp19a1b-deficient fish strongly suggests the loss of cyp19a1b function, as noted in Response to reviewer #3’s comment 1 on weaknesses.

      (2) As presented, this study reads as niche work. A better description of the behavior and reproductive significance of the different aspects of the behavioral sequence would allow a better understanding of the results and would thus allow the non-specialist to appreciate the significance of the observations.

      Line 103: In response to this comment and Reviewer #3’s comment 2 on weaknesses, we have revised the sentence from “The mating behavior of medaka follows a stereotypical pattern, wherein a series of followings, courtship displays, and wrappings by the male leads to spawning” to “The mating behavior of medaka follows a stereotypical sequence. It begins with the male approaching and closely following the female (following). The male then performs a courtship display, rapidly swimming in a circular pattern in front of the female. If the female is receptive, the male grasps her with his fins (wrapping), culminating in the simultaneous release of eggs and sperm (spawning)” in order to provide a more detailed description of medaka mating behavior.

      (3) The data regarding female behavior are limited and incomplete. It is suggested to keep this for another manuscript unless data on the behavior of the female herself is added. Indeed, analyzing female's behavior from the male's perspective complicates the interpretation of the results while a description of what the females do would provide valuable and interpretable information.

      We thank the reviewer for this thoughtful suggestion and agree that the data and discussion for females are less extensive than for males. However, we have previously elucidated the mechanism by which estrogen/Esr2b signaling promotes female mating behavior (Nishiike et al., 2021). Accordingly, it follows that the new insights into female behavior gained from the cyp19a1b knockout model are more limited than those for males. Nevertheless, when combined with our prior findings, the female data in this study offer valuable insights, and the overall mechanism through which estrogens promote female mating behavior is becoming clearer. Therefore, we do not consider the female data in this study to be incomplete or merely supplementary.

      (4) In Figure 2, the validity to run multiple T-tests rather than a two-way ANOVA comparing TRT and genotype is questionable. Moreover, why are the absolute values in CTL higher than in the initial experiment comparing genotypes for ara in PPa, pPPp, and NVT as well as for arb in aPPp. More importantly, these graphs do not seem to reproduce the genotype effects for ara in pPPp and NVT and for arb in aPPp.

      The data in Figures 2J and 2K were analyzed with an exclusive focus on the difference between vehicletreated and E2-treated males, without considering genotype differences. Therefore, the use of T-tests for significance testing is appropriate.

      As the reviewer noted, the overall ara expression area is larger in Figure 2J than in Figure 2F. However, as detailed in Response to reviewer #3’s comment 8 on weaknesses, the relative area ratios of ara expression among brain nuclei are consistent between the two figures, indicating the reproducibility of the results. Thus, we consider this difference unlikely to affect the conclusions of this study.

      Additionally, the differences in ara expression in pPPp and arb expression in aPPp between wild-type and cyp19a1b-deficient males appear smaller in Figures 2J and 2K compared to Figures 2F and 2H. This is likely due to the smaller sample size used in the experiments for Figures 2J and 2K, which makes the differences less distinct. However, since the same genotype-dependent trends are observed in both sets of figures, the conclusion that ara and arb expression is reduced in cyp19a1b-deficient male brains remains valid.

      (5) More information is required regarding the analysis of single ISH - How was the positive signal selected from the background in the single ISH analyses? How was this measure standardized across animals? How many sections were imaged per region? Do the values represent unilateral or bilateral analysis?

      Line 540: Following this comment, we have provided additional details on the single ISH method in the manuscript. Specifically, “, and the total area of signal in each brain nucleus was calculated using Olyvia software (Olympus)” has been revised to “The total area of signal across all relevant sections, including both hemispheres, was calculated for each brain nucleus using Olyvia software (Olympus). Images were converted to a 256-level intensity scale, and pixels with intensities from 161 to 256 were considered signals. All sections used for comparison were processed in the same batch, without corrections between samples.”

      (6) More information should be provided in the methods regarding the image analysis of double ISH. In particular, what were the criteria to consider a cell as labeled are not clear. This is not clear either from the representative images.

      Line 596: To provide additional details on the single ISH method in the manuscript, we have added the following sentence: “Cells were identified as coexpressing the two genes when Alexa Fluor 555 and fluorescein signals were clearly observed in the cytoplasm surrounding DAPI-stained nuclei, with intensities markedly stronger than the background noise.”

      (7) There is no description of the in silico analyses run on ESR2a in the methods.

      The method for identifying estrogen-responsive element-like sequences in the esr2a locus is described in line 549: “Each nucleotide sequence of the 5′-flanking region of ara and arb was retrieved from the Ensembl medaka genome assembly and analyzed for potential canonical ERE-like sequences using Jaspar (version 5.0_alpha) and Match (public version 1.0) with default settings.”

      However, the method for domain identification in Esr2a was not described. Therefore, we have added the following text in line 469: “The DNA- and ligand-binding domains of medaka Esr2a were identified by sequence alignment with yellow perch (Perca flavescens) Esr2a, for which these domain locations have been reported (58).”

      The following reference (#58), cited in the newly added text above, have been included in the reference: S. G. Lynn, W. J. Birge, B. S. Shepherd, Molecular characterization and sex-specific tissue expression of estrogen receptor α (esr1), estrogen receptor βa (esr2a) and ovarian aromatase (cyp19a1a) in yellow perch (Perca flavescens). Comp. Biochem. Physiol. B Biochem. Mol. Biol. 149, 126–147 (2008).

      (8) Information about the validation steps of the EIA that were carried out as well as the specificity of the antibody the steroids and the extraction efficacy should be provided.

      We have not directly validated the applicability of the EIA kit, but its extensive use in medaka suggests that it us unlikely to pose any issues (e.g., Ussery et al., 2018, Aquat Toxicol, 205:58–65; Lee et al., 2019, Ecotoxicol Environ Saf, 173:174–181; Kayo et al., 2020, Gen Comp Endocrinol, 285:113272; Fischer et al., 2021, Aquat Toxicol, 236:105873; Royan et al., 2023, Endocrinology, 164:bqad030).

      The specificity (cross-reactivity) of the antibodies is detailed as follows.

      (1) Estradiol ELISA kits: estradiol, 100%; estrone, 1.38%; estriol, 1.0%; 5α-dihydrotestosterone, 0.04%; androstenediol, 0.03%; testosterone, 0.03%; aldosterone, <0.01%; cortisol, <0.01%; progesterone, <0.01%.

      (2) Testosterone ELISA kits: testosterone, 100%; 5α-dihydrotestosterone, 27.4%; androstenedione, 3.7%; 11-ketotestosterone, 2.2%; androstenediol, 0.51%; progesterone, 0.14%; androsterone, 0.05%; estradiol, <0.01%.

      (3) 11-Keto Testosterone ELISA kits: 11-ketotestosterone, 100%; adrenosterone, 2.9%; testosterone, <0.01%.

      As this information is publicly available on the manufacturer’s website, we deemed it unnecessary to include it in the manuscript.

      Unfortunately, we have not evaluated the extraction efficacy of the samples, but we recognize this a subject for future studies.

      (9) I wonder whether the evaluation of the impact of the mutation by comparing the behavior of a group of wild-type males to a group of mutated males is the most appropriate. Justifying this approach against testing the behavior of one mutated male facing one or several wild-type males would be appreciated.

      We agree that the resident-intruder test, in which a single focal resident is confronted with one or more stimulus intruders, is the most commonly used method for assessing aggression. However, medaka form shoals and lack strong territoriality, and even slight dominance differences between the resident and the intruder can increase variability in the results, compromising data consistency. Therefore, in this study, we adopted an alternative approach: placing four unfamiliar males together in a tank and quantifying aggressive interactions in total. This method allows for the assessment of aggression regardless of territorial tendencies, making it more appropriate for our investigation.

      (10) Lines 329-331: this sentence should be rephrased as it contributes to the confusion between sexual differentiation and activation of circuits. The restoration of sexual behavior by adult estrogen treatment pleads in favor of an activational role of neuro-estrogens on behavior rather than an organizational role. Therefore, referring to sexual differentiation is misleading, even more so that the study never compares sexes.

      As detailed in Response to reviewer #3’s comment 9 on weaknesses, we consider that all factors that cause sex differences, including the transient effects of adult steroids, need to be incorporated into a theory of sexual differentiation. In teleosts, since steroids during early development have little effect and sexual differentiation primarily relies on steroid action in adulthood, our discussion on brain sexual differentiation remains valid, including the statement in line 347: “This variation among species may represent the activation of neuroestrogen synthesis at life stages critical for sexual differentiation of behavior that are unique to each species.”

      (11) Lines 384-386: I may have missed something but I do not see data supporting the notion that neuroestrogens may function upstream of PGF2a signaling to mediate female receptivity.

      Line 403: We acknowledge that our explanation was insufficient and apologize for any confusion. To clarify this point, “Given that estrogen/Esr2b signaling feminizes the neural substrates that mediate mating behavior, while PGF2α signaling triggers female sexual receptivity,” has been added before the sentence “The present finding provides a likely explanation for this apparent contradiction, namely, that neuroestrogens, rather than or in addition to ovarian-derived circulating estrogens, may function upstream of PGF2α signaling to mediate female receptivity.”

      Additional alteration

      Reference list (line 682): a preprint article has now been published in a peer-reviewed journal, and the information has been updated accordingly as follows: “bioRxiv doi: 10.1101/2024.01.10.574747 (2024)” to “Proc. Natl. Acad. Sci. U.S.A. 121, e2316459121 (2024).”

    1. Note de synthèse de l'audition de Isac Mayembo (Alex Hitchens) par la commission d'enquête sur TikTok

      Date de l'audition : [Non spécifiée, mais contexte indique "aujourd'hui" et "cet après-midi"]

      Personne auditionnée : Isac Mayembo, créateur de contenu sous le pseudonyme Alex Hitchens.

      1. Contexte de l'audition et déclaration d'intérêts

      • Isac Mayembo a été convoqué par la commission d'enquête sur l'impact de TikTok sur la santé mentale des jeunes.
      • Il est invité à déclarer tout intérêt public ou privé susceptible d'influencer ses déclarations, notamment ses sources de rémunération liées aux plateformes.
      • Avant de commencer, il prête serment de "dire la vérité, toute la vérité et rien que la vérité" conformément à l'article 6 de l'ordonnance du 17 novembre 1958.
      • Déclaration d'intérêts :
      • Rémunération TikTok : Isac Mayembo déclare ne pas être directement rémunéré par la monétisation des vidéos sur TikTok.
      • Modèle économique : Ses revenus proviennent principalement de la vente de ses formations. Il a mis en place un programme d'affiliation où d'autres personnes promeuvent ses formations sur TikTok et touchent des commissions (en moyenne 50%, voire 60-70% pour les meilleurs affiliés).
      • Intérêts : Il reconnaît avoir des intérêts financiers avec TikTok, affirmant : "Oui je gagne de l'argent avec TikTok et oui j'ai des intérêts avec cette plateforme bien entendu."
      • Honnêteté face à la plateforme : Malgré ses intérêts, il affirme vouloir être "100% honnête" et estime que TikTok est une plateforme "néfaste" et qui "déprime". Il ajoute : "Je pense que cette plateforme de manière générale est néfaste déprime à bord lorsque TikTok est sorti c'était quelque chose d'intéressant."

      2. Évolution et impact perçu de TikTok

      • TikTok initialement : À son lancement, il trouvait TikTok "intéressant", permettant de "condenser un peu les informations, regarder une vidéo de 1 minute 2 minutes pour pouvoir ainsi apprendre tout un tas de choses".
      • Problèmes actuels : Le format court (1 à 2 minutes) rend difficile l'obtention d'informations complètes, ce qui a créé "énormément de problèmes notamment énormément de désinformations". Il peut lui-même être victime de désinformation par l'isolement de propos hors de leur contexte (ex: "on va prendre une vidéo de 10 minutes on va isoler 30 secondes ou une minute bien choisie pour manipuler l'information").
      • Recommandation : Il conclut son propos liminaire en affirmant que "TikTok est à ban bien entendu selon moi et je pense que cette plateforme est néfaste pour les jeunes si elle est mal entradé encadrer bien entendu ça à préciser quand même et c'est le cas je pense."

      3. Parcours sur TikTok et stratégies de contenu

      • Débuts : Il a commencé sur TikTok fin 2021/début 2022.
      • Contenu performant : Il a rapidement constaté que ce qui fonctionnait le mieux est le "contenu qui choque".
      • Importance des premières secondes : Sur TikTok, les "premières secondes sont primordiales", contrairement à YouTube où les miniatures attirent davantage. Le contenu doit être "tranchant", "cash", et "clair" dès le début.
      • Contenu initial à succès : Ses premières vidéos à succès étaient sur le thème de la "séduction", notamment la "drague de rue" et les "caméras cachées" où il abordait des gens dans la rue. Ce type de contenu "fonctionnait extrêmement bien et ça fonctionne d'ailleurs encore maintenant".
      • Monétisation des vidéos à succès : Bien que ses vidéos aient pu générer des millions de vues et de la monétisation, il affirme n'avoir "jamais touché à cette monétisation".

      Il n'avait même pas connecté sa carte bancaire car la vente de formations était beaucoup plus rentable.

      La monétisation TikTok était "bien moins avantageuse" en 2021/début 2022. Actuellement, il laisse même la monétisation à ses collaborateurs qui créent du contenu pour lui.

      4. La communauté et l'interaction

      • Taille de la communauté : Il estime avoir entre 3 et 5 millions de "personnes" qui le suivent via tous les comptes liés à lui sur TikTok.
      • Difficulté à définir la communauté : Il trouve "extrêmement dur" de cibler les tranches d'âge spécifiques de sa communauté. Il rencontre aussi bien des hommes de 40 ans que des jeunes de 18 ans ou des personnes de 50 ans.
      • Interaction : Il n'a pas beaucoup l'occasion d'interagir directement avec sa communauté, sauf lors de rares lives TikTok (une fois tous les deux-trois mois). Dans ces lives, les participants sont généralement des "jeunes", mais il précise que TikTok est aussi très présent chez les adultes (30-40 ans).
      • Présence de mineurs : Il reconnaît qu'il y a "forcément des mineurs" parmi les 4000 personnes qui peuvent regarder ses lives, même s'il demande l'âge. Il estime que c'est à la plateforme de modérer.

      5. Gestion des comptes et responsabilité

      • Comptes multiples : Il y a une "cinquantaine de comptes" le concernant. Sept comptes sont gérés personnellement par lui et son équipe.
      • Comptes "non-affiliés" : Les 43+ autres comptes sont gérés par des personnes qui "postent de leur plein gré pour toucher la monétisation". Ces personnes ne sont pas affiliées à lui et il ne touche pas directement d'argent de leur monétisation, bien qu'elles puissent vendre ses formations.
      • Responsabilité et propriété intellectuelle : La rapporteur souligne qu'il a une responsabilité sur ces contenus si son nom et son image sont utilisés. Il tolère ces comptes mais a du mal à les stopper malgré des tentatives.
      • Loi "influenceur" (Loi du 9 juin 2023) : Interrogé sur le respect de cette loi concernant la mention des partenariats commerciaux, Isac Mayembo n'est pas certain de son application à son modèle.

      Il pense qu'il n'est pas obligé de le notifier si la promotion n'est pas faite "dans la vidéo même" mais par un lien en description.

      Il reconnaît qu'il le ferait si la promotion était directe dans la vidéo. La rapporteur indique que la question sera examinée.

      6. Contenus controversés, modération et désinformation

      • Critiques sur les contenus : La rapporteur soulève les critiques concernant ses contenus, notamment leur impact sur la santé mentale des jeunes et leur vision des femmes, mentionnant que son nom est connu par des enfants dès 9-10 ans.
      • Perception de ses contenus : Isac Mayembo rejette l'idée que ses contenus soient "contestables" ou "problématiques", les considérant comme "une question de point de vue". Il affirme : "Je ne trouve pas que mes propos soient problématiques même si bon voilà problématique ça ça veut rien dire Et je pense qu'un jeune homme de 13 14 ans 15 ans devrait suivre mes conseils Je pense que je donne de bons conseils pour la jeunesse."
      • Bannissement de TikTok : Il a été banni de TikTok. Il explique que cela est dû à un grand nombre de "signalements" (100, 200, 300, 400) de la part d'utilisateurs qui ne sont pas d'accord avec ses vidéos, et non à une décision initiale de TikTok autorisant la publication. Il précise qu'une même vidéo peut ne pas être bannie sur un autre compte.
      • Techniques d'évitement de la modération : Il admet "adoucir" ses propos pour TikTok. Par exemple, utiliser le mot "poutrer" au lieu de termes plus vulgaires pour éviter la censure.
      • Propos controversés cités par la commission : La commission cite des propos qu'il aurait tenus :
      • "Vous prenez son téléphone si elle refuse c'est une pute fin de relation."
      • "la majorité des femmes énormément de P u T S peu de filles bien." (il utilise "P U T S" pour échapper à la modération).
      • "une femme après 22h qu'est-ce qu'elle fout dehors ?"
      • Défense contre l'accusation de désinformation : Isac Mayembo affirme que les propos cités par la commission ont été prononcés lors de lives YouTube et non TikTok.

      Il accuse la commission de "désinformation" en isolant ses propos : "Vous êtes en train d'isoler mon propos Donc vous avez pris 10 secondes d'un propos de 8 10 minutes où j'expliquais justement parce queon va rentrer en détail parce qu'apparemment on est en train d'en parler donc pourquoi pas J'expliquais que le gouvernement était responsable de la sécurité J'ai n'était pas normal qu'une femme en 2025 ne puisse pas sortir dehors euh le soir très tard sur Paris Et justement après je parlais du fait que dans ce monde dans ce monde qui est dur que fait une femme dehors après 22h et je poursuivais ensuite il est préférable de sortir avec une amie ou avec deux amis ou avec un homme Vous vous avez pris 10 secondes de vos propos vous l'avez isolé et vous venez de me le balancer à la gueule."

      7. Incident et suspension de l'audition

      • Un échange tendu a lieu entre Isac Mayembo et le président de la commission, ce dernier lui reprochant de "balancer la gueule" et de ne pas le laisser finir.
      • Isac Mayembo refuse de se soumettre aux règles de l'audition ("Vous changer de sujet Je vous demande de me laisser finir C'est moi qui mène l'audition Je suis président de la commission d'enquête Je vous demande de me laisser finir Non je vous lis Je suis président Excusez-moi excusez-moi On va couper le son de monsieur Ichen s'il vous plaît si vous continuez Voilà Donc je finis ma je finis mon propos s'il vous plaît Je vous disais au revoir monsieur Bonne journée").
      • Le son de Isac Mayembo est coupé.
      • L'audition est suspendue pour le recontacter et l'informer qu'il ne peut quitter une audition sans autorisation.
    1. Reviewer #2 (Public review):

      Summary:

      Malboubi et al. present a novel experimental framework to investigate the rheological properties of the cell cytoplasm. Their findings support a model where the cytoplasm behaves as a poroelastic material governed by Darcy's law - a property overlooked in previous literature. They demonstrate that this poroelastic behavior delays the equilibration of hydrostatic pressure gradients within the cytoplasm over timescales of 1 to 10 seconds following a perturbation, likely due to fluid-solid friction within the cytoplasmic matrix. Furthermore, under sustained perturbations such as depressurization, they reveal that pressure gradients can persist for minutes, which they propose might potentially influence physiological processes like mechanotransduction or cell migration typically happening on these timescales.

      Strengths:

      This article holds significant value within the ongoing efforts of the cell biology and biophysics communities to quantitatively characterize the mechanical properties of cells. The experiments are innovative and thoughtfully contextualized with quantitative estimates and a finite element model that supports the authors' hypotheses.

      Comments & Questions:

      While the hypothesis of a poroelastic cytoplasm is insightful and supported by the results, certain parts of the paper (detailed below) rely on qualitative arguments. Given the experimental approaches and accompanying modeling, the study has the potential for more in-depth discussions and stronger quantitative evidence. Placing greater emphasis on quantifications and direct comparisons between the model and experimental data would enhance the work. Additionally, exploring the limitations of the proposed model would add valuable depth to the paper.

      The authors state, "Next, we sought to quantitatively understand how the global cellular response to local indentation might arise from cellular poroelasticity." However, the evidence presented in the following paragraph appears more qualitative than strictly quantitative. For instance, the length scale estimate of ~7 μm is only qualitatively consistent with the observed ~10 μm, and the timescale 𝜏𝑧 ≈ 500 ms is similarly described as "qualitatively consistent" with experimental observations. Strengthening this point would benefit from more direct evidence linking the short timescale to cell surface tension. Have you tried perturbing surface tension and examining its impact on this short-timescale relaxation by modulating acto-myosin contractility with Y-27632, depolymerizing actin with Latrunculin, or applying hypo/hyperosmotic shocks?

      The authors demonstrate that the second relaxation timescale increases (Figure 1, Panel D) following a hyperosmotic shock, consistent with cytoplasmic matrix shrinkage, increased friction, and consequently a longer relaxation timescale. While this result aligns with expectations, is a seven-fold increase in the relaxation timescale realistic based on quantitative estimates given the extent of volume loss?

      If the authors' hypothesis is correct, an essential physiological parameter for the cytoplasm could be the permeability k and how it is modulated by perturbations, such as volume loss or gain. Have you explored whether the data supports the expected square dependency of permeability on hydraulic pore size, as predicted by simple homogeneity assumptions? Additionally, do you think that the observed decrease in k in mitotic cells compared to interphase cells is significant? I would have expected the opposite naively as mitotic cells tend to swell by 10-20 percent due to the mitotic overshoot at mitotic entry (see Son Journal of Cell Biology 2015 or Zlotek Journal of Cell Biology 2015).

      Based on your results, can you estimate the pore size of the poroelastic cytoplasmic matrix? Is this estimate realistic? I wonder whether this pore size might define a threshold above which the diffusion of freely diffusing species is significantly reduced. Is your estimate consistent with nanobead diffusion experiments reported in the literature?

      Do you have any insights into the polymer structures that define this pore size? For example, have you investigated whether depolymerizing actin or other cytoskeletal components significantly alters the relaxation timescale?

      There are no quantifications in Figure 6, nor is there a direct comparison with the model. Based on your model, would you expect the velocity of bleb growth to vary depending on the distance of the bleb from the pipette due to the local depressurization? Specifically, do blebs closer to the pipette grow more slowly?

      I find it interesting that during depressurization of the interphase cells, there is no observed volume change, whereas in pressurization of metaphase cells, there is a volume increase. I assume this might be a matter of timescale, as the microinjection experiments occur on short timescales, not allowing sufficient time for water to escape the cell. Do you observe the radius of the metaphase cells decreasing later on? This relaxation could potentially be used to characterize the permeability of the cell surface.

      I am curious about the saturation of the time lag at 30 microns from the pipette in Figure 4, Panel E for the model's prediction. A saturation which is not clearly observed in the experimental data. Could you comment on the origin of this saturation and the observed discrepancy with the experiments (Figure E panel 2)? Naively, I would have expected the time lag to scale quadratically with the distance from the pipette, as predicted by a poroelastic model and the diffusion of displacement. It seems weird to me that the beads start to move together at some distance from the pipette or else I would expect that they just stop moving. What model parameters influence this saturation? Does membrane permeability contribute to this saturation?

  4. notebooksharing.space notebooksharing.space
    1. 1%

      given absolute numbers for temperature deviations is easier to understand, as a 1% deviation of 2.7°C is a different absolute number than 1% deviation of 4°C. (and how do you express a deviation from 0°C in %?)

    1. 4°C and 2.7°C. The slight positive deviation for the 1.5°C target is minor but notable

      Here it would be good to also add some numbers you have found (e.g. for 4°C the selection has an mean temperature of 4.06°C and a median tempreture of ...)

    1. Reviewer #2 (Public review):

      Summary:

      In this paper, Selberg et al present an extension of their widely used BUSTED family of codon models for the detection of episodic ("site-branch") positive selection from coding gene sequences. The extension adds an "error component" to ω (dN/dS) to capture misaligned codons. This ω component is set to an arbitrarily high value to distinguish it from positive selection, which is characterised by ω > 1 but assumed not to be so high.

      The new method is tested on several datasets of comparative genomes, characterised by their size and the fact that the authors scanned for positive selection and/or provided filtering of alignment quality. It is also tested on simple simulations.

      Overall, the new method appears to capture relatively little of the ω variability in the alignments, although it is often significant. Given the complexity of codon evolution, adding a new parameter is more or less significant, and the question is whether it captures the signal that is intended, preferably in an unbiased manner.

      Strengths:

      This is an important issue, and I am enthusiastic to see it explicitly modeled within the codon modeling framework, rather than externalised to ad hoc filtering methods. The promise of quantifying the divergence signal from alignment error vs selection is exciting.

      The BUSTED family of models is widely used and very powerful for capturing many aspects of codon evolution, and it is thus an excellent choice for this extension.

      Weaknesses:

      (1) The definition of alignment error by a very large ω is not justified anywhere in the paper. There are known cases of bona fide positive selection with many non-synonymous and 0 synonymous substitutions over branches. How would they be classified here? E.g., lysosyme evolution, bacterial experimental evolution.

      Using the power of the model family that the authors develop, I would suggest characterising a more specific error model. E.g., radical amino-acid "changes" clustered close together in the sequence, proximity to gaps in the alignment, correlation of apparent ω with genome quality.

      Also concerning this high ω, how sensitive is its detection to computational convergence issues?

      (2) The authors should clarify the relation between the "primary filter for gross or large-scale errors" and the "secondary filter" (this method). Which sources of error are expected to be captured by the two scales of filters? What is their respective contribution to false positives of positive selection?

      Sources of error in the alignment of coding genes include:

      a) Errors in gene models, which may differ between species but also propagate among close species (i.e., when one species is used as a reference to annotate others).

      b) Inconsistent choice of alternative transcripts/isoforms.

      Both of these lead to asking an alignment algorithm to align non-homologous sequences, which violates the assumptions of the algorithms, yet both are common issues in phylogenomics.

      c) Sequencing errors, but I doubt they affect results much here.

      d) Low complexity regions of proteins.

      e) Aproximations by alignment heuristics, sometimes non-deterministic or dependent on input order.

      f) Failure to capture aspects of protein or gene evolution in the optimality criteria used.

      For example, Figure 1 seems to correspond to a wrong or inconsistent definition of the final exon of the gene in one species, which I would expect to be classified as "gross or large-scale error".

      (3) The benchmarking of the method could be improved both for real and simulated data.

      For real data, the authors only analysed sequences from land vertebrates with relatively low Ne and thus relatively low true positive selection. I suggest comparing results with e.g. Drosophila genomes, where it has been reported that 50% of all substitutions are fixed by positive selection, or with viral evolution.

      For simulations, the authors should present simulations with or without alignment errors (e.g., introduce non-homologous sequences, or just disturb the alignments) and with or without positive selection, to measure how much the new method correctly captures alignment errors and incorrect positive selection.

      I also recommend simulating under more complex models, such as multinucleotide mutations or strong GC bias, and investigating whether these other features are captured by the alignment error component.

      Finally, I suggest taking true alignments and perturbing them (e.g., add non-homologous segments or random gaps which shift the alignment locally), to verify how the method catches this. It would be interesting to apply such perturbations to genes which have been reported as strong examples of positive selection, as well as to genes with no such evidence.

      (4) It would be interesting to compare to results from the widely used filtering tool GUIDANCE, as well as to the Selectome database pipeline (https://doi.org/10.1093/nar/gkt1065). Moreover, the inconsistency between BUSTED-E and HMMCleaner, and BMGE is worrying and should be better explained.

      (5) For a new method such as this, I would like to see p-value distributions and q-q plots, to verify how unbiased the method is, and how well the chi-2 distribution captures the statistical value.

      (6) I disagree with the motivation expressed at the beginning of the Discussion: "The imprimatur of "positive selection" has lost its luster. Researchers must further refine prolific candidate lists of selected genes to confirm that the findings are robust and meaningful." Our goal should not be to find a few impressive results, but to measure accurately natural selection, whether it is frequent or rare.

    2. Author response:

      eLife Assessment

      Alignment and sequencing errors are a major concern in molecular evolution, and this valuable study represents a welcome improvement for genome-wide scans of positive selection. This new method seems to perform well and is generally convincing, although the evidence could be made more direct and more complete through additional simulations to determine the extent to which alignment errors are being properly captured.

      We thank the editors for their positive assessment and for highlighting the core strength and a key area for improvement. The main request (also echoed by both reviewers) is for us to conduct additional simulation studies where true alignment errors are known and assess the performance of BUSTED-E. We plan to conduct several simulations (on the order of 100,000 individual alignments in total) in response to that request, with the caveat that we are not aware of any tools that simulate realistic alignment errors, so these simulations are likely only a pale reflection of biological reality.

      (1) Ad hoc small local edits of alignments similar to what was implemented in the HMMCleaner paper. These local edits would include operations like replacement of codons or small stretches of sequences with random data, local transposition, inversion.

      (a) Using parametrically simulated alignments (under BUSTED models).

      (b) Using empirical alignments.

      (2) Simulations under model misspecification, specifically to address the point of reviewer 2. For example, we would simulate under models that allow for multi-nucleotide substitutions, and then apply error filtering under models which do not.

      We will also run several new large-scale screens of existing alignments, to directly and indirectly address the reviewers comments. These will include

      (a) A drosophila dataset (from https://academic.oup.com/mbe/article/42/4/msaf068/8092905)

      (b) Current Selectome data (https://selectome.org/), both filtered and unfiltered. Here the filtering procedure refers to what Selectome does to obtain what its authors think are high quality alignments.

      (c) Current OrthoMam data, both (https://orthomam.mbb.cnrs.fr/) filtered and unfiltered. Here the filtering procedure refers to what OrthoMam does to obtain what its authors think are high quality alignments.

      Reviewer #1:

      We are grateful to Reviewer #1 for their positive and encouraging review. We are pleased they found our analyses convincing and recognized BUSTED-E as a "simple, efficient, and computationally fast" improvement for evolutionary scans.

      Strengths:

      As a side note, I found it particularly interesting how the authors tested the statistical support for the new method compared to the simpler version without the error class. In many cases, the simpler model could not be statistically rejected in favor of the more complex model, despite producing biologically incorrect results in terms of parameter inference. This highlights a broader issue in molecular evolution and phylogenomics, where model selection often relies too heavily on statistical tests, potentially at the expense of biological realism.

      We agree that this observation touches upon a critical issue in phylogenomics. A statistically "good" fit does not always equate to a biologically accurate model. We believe our work serves as a useful case study in this regard. We will add discussion of the importance of considering biological realism alongside statistical adequacy in model selection.

      Weaknesses:

      Regarding the structure of the manuscript, the text could be clearer and more precise.

      We appreciate this feedback. We will perform a thorough revision of the entire manuscript to improve its clarity, flow, and precision. We will focus on streamlining the language and ensuring that our methodological descriptions and results are as unambiguous as possible.

      Clear, practical recommendations for users could also be provided in the Results section.

      To make our method more accessible and its application more straightforward, we will add a new section that provides clear, practical recommendations for users. This includes guidance on when to apply BUSTED-E, how to interpret its output, and best practices for distinguishing potential errors from strong selection.

      Additionally, the simulation analyses could be further developed to include scenarios with both alignment errors and positive selection, in order to better assess the method's performance.

      Additional simulations will be conducted (see above)

      Finally, the model is evaluated only in the context of site models, whereas the widely used branch-site model is mentioned as possible but not assessed.

      BUSTED class models support branch-site variation in dN/dS, so technically all of our analyses are already branch-site. However, we interpret the reviewer’s comment as describing use cases when a method is used to test for selection on a subset of tree branches (as opposed to the entire tree). BUSTED-E already supports this ability, and we will add a section in the manuscript describing how this type of testing can be done, including examples. However, we do not plan to conduct additional extensive data analyses or simulations, as this would probably bloat the manuscript too much.

      Reviewer #2:

      We thank Reviewer #2 for their detailed and thought-provoking comments, and for their enthusiasm for modeling alignment issues directly within the codon modeling framework. The criticisms raised are challenging and we will work on improving the justification, testing, and contextualization of our method.

      Weaknesses:

      The definition of alignment error by a very large ω is not justified anywhere in the paper... I would suggest characterising a more specific error model. E.g., radical amino-acid "changes" clustered close together in the sequence, proximity to gaps in the alignment, correlation of apparent ω with genome quality... Also concerning this high ω, how sensitive is its detection to computational convergence issues?

      This is a fundamental point that we are grateful to have the opportunity to clarify. Our intention with the high ω category is not to provide a mechanistic or biological definition of an alignment error. Rather, its purpose is to serve as a statistical "sink" for codons exhibiting patterns of divergence so extreme that they are unlikely to have resulted from a typical selective process. It is phenomenological and ad hoc. The reviewer makes sensible suggestions for other ad hoc/empirical approaches to alignment quality filtering, but most of those have already been implemented in existing (excellent) alignment filtering tools. BUSTED-E is never meant to replace them, but rather to catch what is left over. Importantly, error detection is not even the primary goal of BUSTED-E; errors are treated as a statistical nuisance. With all due respect, all of the reviewers suggestions are similarly ad hoc -- there is no rigorous quantitative justification for any of them, but they are all sensible and plausible, and usually work in practice.

      Computational convergence issues can never be fully dismissed, but we do not consider this to be a major issue. Our approach already pays careful attention to proper initialization, does convergence checks, considers multiple initial starting points. We also don’t need to estimate large ω with any degree of precision, it just needs to be “large”.

      The authors should clarify the relation between the "primary filter for gross or large-scale errors" and the "secondary filter" (this method). Which sources of error are expected to be captured by the two scales of filters?

      We will add discussion and examples to explicitly define the distinct and complementary roles of these filtering stages.

      The benchmarking of the method could be improved both for real and simulated data... I suggest comparing results with e.g. Drosophila genomes... For simulations, the authors should present simulations with or without alignment errors... and with or without positive selection... I also recommend simulating under more complex models, such as multinucleotide mutations or strong GC bias...

      We will add more simulations as suggested (see above). We will also analyze a drosophila gene alignment from previously published papers.

      It would be interesting to compare to results from the widely used filtering tool GUIDANCE, as well as to the Selectome database pipeline... Moreover, the inconsistency between BUSTED-E and HMMCleaner, and BMGE is worrying and should be better explained.

      Some of the alignments we have analyzed had already been filtered by GUIDANCE. We’ll also run the Selectome data through BUSTED-E: both filtered and unfiltered. We consider it beyond the scope of this manuscript to conduct detailed filtering pipeline instrumentation and side-by-side comparison.

      For a new method such as this, I would like to see p-value distributions and q-q plots, to verify how unbiased the method is, and how well the chi-2 distribution captures the statistical value.

      We will report these values for new null simulations.

      I disagree with the motivation expressed at the beginning of the Discussion... Our goal should not be to find a few impressive results, but to measure accurately natural selection, whether it is frequent or rare.

      That’s a philosophical point; at some level, given enough time, every single gene likely experiences some positive selection at some point in the evolutionary past. The practically important question is how to improve the sensitivity of the methods while controlling for ubiquitous noise. We do agree with the sentiment that the ultimate goal is to “measure accurately natural selection, whether it is frequent or rare”. However, we also must be pragmatic about what is possible with dN/dS methods on available genomic data.

    1. Document de Synthèse : Audition d'Adrien Laurent par la Commission d'Enquête sur TikTok

      Date de l'audition : Non spécifiée, mais fait suite à plus d'une centaine d'auditions. Intervenants principaux :

      • Président de la Commission : M. de la Porte
      • Rapporteure : Mme. Marie B. (députée)
      • Auditionné : Adrien Laurent (AD Laurent), créateur de contenu.
      • Autres députés : M. Vermel, M. Vogeta

      1. Contexte et Objectifs de l'Audition

      • La commission d'enquête parlementaire a été mise en place pour comprendre le fonctionnement et les usages des réseaux sociaux, en particulier TikTok, et leurs mécanismes qui peuvent aboutir à des interpellations sur divers sujets.

      L'objectif est de faire la lumière sur la production de contenus et la régulation. L'audition d'Adrien Laurent fait suite à une consultation citoyenne ayant recueilli plus de 30 000 réponses et à des témoignages, son nom étant "revenu très souvent" parmi les influenceurs ou créateurs de contenu jugés "problématiques" par les jeunes.

      Le Président de la commission a rappelé qu'il ne s'agit pas d'un tribunal mais d'un travail de compréhension, avec des pouvoirs étendus, sans se substituer à la justice. L'audition est médiatisée, mais l'objectif premier reste la prise en compte des victimes.

      Adrien Laurent a été invité à déclarer tout intérêt public ou privé pouvant influencer ses déclarations et à détailler la nature de ses revenus liés aux plateformes. Il a prêté serment de "dire la vérité, toute la vérité, rien que la vérité".

      2. Présentation et Défense d'Adrien Laurent

      • Adrien Laurent, ancien sportif de haut niveau en basket, s'est fait connaître à 22 ans dans la téléréalité avant de devenir "créateur de contenu" plutôt qu'influenceur, terme qu'il juge réducteur.

      Il se présente comme son "propre producteur". Parallèlement, il est depuis deux ans créateur de contenu pour adultes, vidéos commercialisées exclusivement sur des plateformes réservées aux majeurs et "ne sont pas présentes sur TikTok". Il travaille avec des "actrices professionnelles majeures qui ont elles-mêmes leur compte sur ces plateformes".

      • Il réfute "avec force" les accusations du Président de la Porte le décrivant comme "un influenceur extrêmement violent qui véhicule un imaginaire sexiste" et dont le contenu serait "problématique" en raison de vidéos pour adultes sur son compte X (anciennement Twitter).

      Ses arguments principaux :

      • Contenu TikTok : Reprenait les codes de la téléréalité, montrant son quotidien, voyages, proches, et activité professionnelle, tout en respectant les règles de la plateforme (pas de nudité, accessibles aux plus de 13 ans). Il estime son bannissement de TikTok "infondé et motivé par des raisons politiques".
      • Contenu sexuel et législation : Fait une distinction claire entre contenu évocateur de sexualité adulte (classé -12 ans par l'ARCOM) et contenu érotique (classé -16 ans).

      Il affirme n'avoir "aucun contenu érotique sur TikTok". * Twitter/X : Reconnaît que Twitter autorise les contenus pour adultes mais en restreint l'accès aux majeurs via des réglages. * Accusations de sexisme/violence : Affirme que son contenu n'est "ni sexiste ni misogyne ni masculiniste" et qu'il n'a "jamais été violent". Il évoque sa vie d'acteur de contenu pour adultes "de manière assumée mais transparente et respectueuse", sans "dénigrer leurs envies ni leurs pratiques ni les rabaisser". * Public mineur et responsabilité : "Je n'ai jamais encouragé un public mineur à consommer du contenu inadapté." Il insiste sur le fait que "la sexualité ne s'apprend pas à travers le contenu pour adultes". Avec près de 2 millions d'abonnés sur TikTok, il a diffusé des messages de prévention sur le dépistage et le port du préservatif. * Accès des CM2 à TikTok : "Les CM2 ne peuvent pas avoir accès à TikTok. La plateforme est interdite au moins de 13 ans." Si des enfants de cet âge y accèdent, il s'agit d'un "problème de contrôle parental et de responsabilité de TikTok, pas de la mienne." Il refuse "d'endosser une responsabilité qui ne [lui] appartient pas".

      3. Relations avec TikTok et Revenus

      • Liens avec TikTok : Il n'a "pas de lien particulier avec la plateforme", n'est pas "son ambassadeur", et n'a "jamais été rémunéré" ni eu de partenariat direct avec TikTok.
      • Revenus TikTok : En 3 ans, il estime avoir gagné entre 15 000 et 20 000 €, soit une moyenne haute de 555 € par mois, "loin d'un business". Ses revenus provenaient majoritairement de la monétisation de contenu (0,50 € à 1 € pour 1000 vues de plus d'une minute) et des "cadeaux" (emojis monétisés) lors des lives.
      • Live Match : Il était "réticent à cette pratique et [en] n'a fait que très peu" (environ une dizaine en 3 ans), bien que cela puisse "rapporter énormément d'argent".
      • Lives classiques : Ses lives, réalisés tous les soirs de 22h à minuit, lui permettaient d'échanger "directement et légèrement" avec sa communauté.
      • Règles d'accès aux lives TikTok : Selon lui, TikTok confirme l'âge des utilisateurs pour l'accès aux lives : "Si nous confirmons que tu as 18 ans ou plus, tu pourras passer en live.

      Si nous ne pouvons pas confirmer ton âge, tu ne pourras passer en live et enfin si nous confirmons que tu as moins de 18 ans tu ne pourras pas accéder au live."

      Il réfute les accusations de la ministre Aurore Berger concernant des "lives sexuels avec des jeunes femmes masquées" douteuses quant à leur majorité et consentement, affirmant qu'aucun contenu sexuel n'était diffusé et que les participants étaient "majeurs et consentants".

      4. Modération et Algorithme

      • Algorithme : Juge l'algorithme "flou", mais comprend qu'il faut être "percutant et accrocheur dans les premières secondes de la vidéo".
      • Rôle de la commission : Trouve la commission "essentielle" et la réflexion "extrêmement utile". Il ne comprend pas la décision "hâtive" du bannissement de son compte par l'exécutif sans attendre les conclusions parlementaires.
      • Propositions : Si les conclusions montrent des effets négatifs sur la santé mentale des mineurs, il serait "le premier à demander qu'il n'ait pas accès à ce contenu", par exemple en "restreignant l'accès de certains réseaux ou certains contenus aux mineurs de 15 ans". Il faudrait un "contrôle efficace mais sans faire peser toute la responsabilité sur les créateurs qui ne sont ni éducateurs ni parents mais qui doivent seulement respecter les règles fixées par la plateforme."

      5. Échanges avec les Députés

      • Notoriété auprès des jeunes : La rapporteure confirme que son nom est "bien connu" des jeunes, y compris des collégiens, lycéens, et parfois primaires. "Un jeune sur deux de 11 ans est sur la plateforme TikTok aujourd'hui".

      La commission cherche à comprendre "pourquoi vous êtes allé sur TikTok", "comment vous gérez vos contenus" face à cette communauté jeune, et la modération.

      • Bannissements d'autres plateformes : Adrien Laurent confirme avoir été banni de Snapchat et Instagram en raison de signalements massifs, sans toujours avoir d'explication claire.

      • Choix de TikTok : S'est mis sur TikTok "très tard" sur conseil de son frère, y voyant une opportunité de visibilité grâce à l'application "la plus téléchargée en France et même dans le monde". Il appréciait les vidéos "très rapides avec beaucoup d'engagement".

      • Diversité de sa communauté : Sur ses 2 millions d'abonnés, "il n'y a pas 2 millions de personnes qui me suivent par rapport au contenu pour adultes". Beaucoup le suivent pour la téléréalité ou l'aspect "positif" et "bienveillant" de ses lives.

      • Responsabilité vis-à-vis des mineurs : Il ne peut pas "être responsable de tout" si des CM2 contournent les règles d'âge.

      Il met en parallèle la vente d'alcool en magasin, où la responsabilité n'incombe pas au vendeur si un mineur contourne l'interdiction d'achat.

      Il se considère comme un "simple usager de la plateforme qui respecte les règles". * Comparaison avec Alex Chen : Il se dit "totalement mais sur tous les points opposés à ce monsieur", affirmant ne pas être "ni sexiste ni misogyne ni masculiniste". Il défend la "liberté sexuelle à égalité" et met la femme "sur un piédestal tout le temps". * Promotion croisée et contenu pour adultes : Il confirme rediriger sa communauté TikTok vers d'autres plateformes (Snap, Insta, Twitch, YouTube) pour "alimenter [ses] autres plateformes", mais insiste sur le fait que son contenu est "totalement différent" et adapté à chaque plateforme. Pour ses contenus privés (Mim, OnlyFans), il affirme une "double authentification" qui empêche l'accès aux mineurs, qualifiant son porno d'"éthique". * Lives avec des mineurs : Confronté à une vidéo de live avec un mineur très jeune, Adrien Laurent explique qu'il prend "énormément de gens tous les soirs" et que si une personne de moins de 18 ans réussit à contourner les règles, ce n'est pas son problème. Il affirme cependant avoir une "responsabilité" en énonçant un "propos responsable" même dans ces cas-là (ex: "il est tard faut que tu ailles te coucher"). * "Pranks" et provocation : Décrit ses "pranks" comme de l'"autodérision" et du "fun", citant l'exemple de la "trompe d'éléphant" ou "viser le trou" au basket. Sa mère, professeur, le soutient. * Accusation de transphobie/humiliation : Réfute l'accusation d'avoir humilié une personne transgenre en live. Il pose des questions par "intérêt", et "n'humilie jamais personne". * Outils de restriction d'audience : Questionné par M. Vogeta sur l'utilisation d'outils de restriction d'audience pour exclure les mineurs sur ses contenus "classiques" (non pornographiques), Adrien Laurent répond que sur Twitter/X, il faut modifier les réglages pour voir du contenu sensible, ce qui protège le compte vierge. * Agents OnlyFans/MIM : Il n'a pas d'agent mais une "équipe qui bosse avec [lui] justement pour sécuriser un petit peu [son] travail". Il insiste sur le fait que c'est un "boulot" qui demande "beaucoup de travail". Il se considère comme un "artiste" et demande le respect de sa "liberté de création artistique". * Recrutement pour la pornographie via TikTok : Il indique que certaines abonnées peuvent exprimer leur intérêt pour des collaborations dans le milieu du contenu pour adultes, mais il les redirige alors vers un "email professionnel" et "coupe le lien" sur TikTok, ne souhaitant pas en parler sur la plateforme. * Impact sur les enfants : Questionné en tant que députée et mère sur l'impact de ses contenus sur un enfant de 13 ans, il répond qu'il ne "choisit pas sa communauté". En tant que futur père, il ferait une éducation basée sur la "communication" et laisserait à sa fille, une fois majeure, le choix de son chemin professionnel. * Contenus sexualisants en live : La rapporteure constate, après un test avec un compte mineur, que les lives sont accessibles aux mineurs, malgré les affirmations d'Adrien Laurent. Elle cite des propos "sexualisants" (ex: "Ça va ma puce il y a du monde au balcon") et "hypersexualisants" (taille des poitrines) tenus en live. * Comparaison avec des artistes musicaux : Adrien Laurent compare ses propos à des paroles de chansons d'artistes comme Michel Sardou, Bruno Mars ou Orelsan (citant des extraits explicites), se plaignant d'une "indignation à géométrie" variable, ce que la rapporteure qualifie d'"œuvres à caractère artistique" et non de lives soumis à des conditions d'utilisation différentes. * Restriction des lives : La rapporteure précise que TikTok permet aux hôtes de "restreindre" leurs lives, option qu'Adrien Laurent n'active pas car il considère ses lives comme "bon enfant". Il reconnaît qu'il n'est pas un "technicien TikTok" mais s'efforce de "se conformer au maximum aux règles communautaires". * Modération interne : Il a une équipe de "modérateurs modératrices" qui "bannissent tous les commentaires à caractère négatif les insultes". Il note l'opacité de l'algorithme et la nécessité de contourner certains mots pour éviter le "shadow ban" (ex: "viol" par "ool", "pute" par "pu pute").

      6. Conclusions de l'Audition

      • L'audition met en lumière la tension entre la liberté de création et d'expression d'un créateur de contenu et la nécessité de protéger un public jeune et potentiellement vulnérable.

      Adrien Laurent insiste sur sa professionnalisation dans le contenu pour adultes éthique et son respect des règles (en théorie) de TikTok, tout en reconnaissant les défis de la modération et de l'accès des mineurs aux plateformes.

      La commission insiste sur la réalité de la présence de jeunes mineurs sur TikTok et la nécessité de trouver des solutions législatives pour protéger les enfants.

      La question de l'accessibilité réelle des lives aux mineurs et la responsabilité des créateurs et de la plateforme reste un point de divergence majeur.

    1. Reviewer #2 (Public review):

      The authors of the present study are responsible for a previous study, which also showed that in response to DNA damage, Werner syndrome protein WRN, WRN interacting protein WRNIP1, and Rev1 assemble together with Y-family Pols (Polη, Polι, or Polκ), and that they are indispensable for Trans-Lesion-Synthesis (TLS) (Genes Dev 2024). They also identified a role of WRN's 3'→5' exonuclease activity in the high in vivo fidelity of TLS by Y-family, through UV-induced CPDs by Polη, through N6 ethenodeoxyadenosine (εdA) by Polι, through thymine glycol by Polκ, and through UV-induced (6-4) photoproducts by Polη and Polι. Thus, by removing nucleotides misinserted opposite DNA lesions by the Y-family Pols, WRN's 3'→5' exonuclease activity improves the fidelity of TLS by these Pols. The present work, which follows up on this previous work, reports the crucial role also of the ATPase activities of WRN and WRNIP1 in raising the fidelity of TLS by Y family Pols, in addition to the exonuclease activity, with an entirely different mechanism, which normally consists in unwinding of DNA containing secondary structures.

      By using adequate cell line models and methodologies, notably DNA fiber, TLS, and mutation analyses assays, as well as specific ATPase point mutations, they found that progression of the replication forks through UV lesions was not affected in cells lacking the WRN exonuclease activity as well as the WRN and WRNIP1 ATPase activities, but occurs with a vast increase in error-prone TLS, notably through CPDs by Polη, with differential impacts on the nature of mutations between WRN ATPase and WRNIP1 ATPase. The relative contributions of these activities (exonuclease and ATPase) to the fidelity of TLS Pols, however, vary, depending upon the DNA lesion and the TLS Pol involved. Additionally, defects in these ATPase activities cause mutational hot spot formation in different sequence contexts. The authors provide evidence that the combined action of WRN and WRNIP1 ATPases, along with WRN 3' to 5' exonuclease, confers an enormous rise in the fidelity of TLS by Y-family Pols. They identify the means by which these otherwise highly error-prone TLS Pols have been adapted to function in an error-free manner. They suggest that WRNIP1 ATPases prevent misincorporations while WRN exonuclease removes misinserted nucleotides. This combination confers a vast increase in the fidelity of Y-family Pols, essential for genome stability.

      Overall, this is a comprehensive and thoughtful manuscript, and all the findings reported are convincing and well supported. The data cannot be considered as entirely novel, as they follow-up on the recent 2024 publication by the same authors who unveiled that the exonuclease activity of WRN and WRNIP1 confers accuracy of TLS. The experimental methods are multiple and rigorous.

    1. Compte-rendu de l'Audition de Manon et Julien Tanti par la Commission d'Enquête sur TikTok

      • Date de l'audition : Non spécifiée, mais mention de "cet après-midi". Contexte : La commission d'enquête a pour objectif de "préparer les lois à venir, de réfléchir sur la bonne application des différentes normes, des différents cadres juridiques (...) nationaux ou européens et donc en fait l'enjeu c'est de nous éclairer sur la meilleure protection des enfants à l'air numérique et en particulier sur les effets psychologiques de TikTok sur les mineurs." (Président de la commission). Les personnes auditionnées doivent prêter serment de dire la vérité.

      I. Préambule et Positionnement des Influenceurs

      Manon et Julien Tanti ont été convoqués en tant qu'influenceurs pour s'exprimer sur leur modèle économique, leurs revenus via TikTok et d'autres plateformes, ainsi que sur l'impact de TikTok sur les mineurs.

      • Réaction de Manon Tanti face aux accusations : Manon Tanti exprime un profond regret concernant la préparation publique de l'audition et les déclarations du président l'accusant d'être une "influenceuse à contenu problématique" et d'humilier ou dégrader l'image de ses propres enfants. Elle déclare : "Je ne suis pas venue ici pour fuir mes responsabilités. J'ai conscience que lorsque l'on s'expose publiquement, surtout sur des plateformes comme TikTok, on a un devoir d'exemplarité, d'autant plus quand on est suivi par des jeunes. Mais je veux poser les choses clairement dès le départ : je regrette profondément deux choses dans la manière dont cette audition a été préparée publiquement. Je regrette vos déclarations Monsieur le Président, je ne suis pas une influenceuse à contenu problématique, du moins je ne pense pas, et du coup quelle décision de justice vous fondez-vous pour affirmer cela ? Ce genre de jugement lancé dans les médias avant toute audition ne révèle pas d'un travail d'enquête objectif, mais d'une condamnation sans débat. La seconde, plus grave à mes yeux, ce sont ces propos affirmant que j'humilierai et que je dégraderai l'image de mes propres enfants. Ces accusations sont violentes, injustes et totalement déplacées. Je suis mère avant tout et jamais je ne tolérerais qu'on prête des intentions aussi graves sans preuve ni dialogue." Elle précise avoir été "profondément attristée" par la diffusion de ces accusations sur des chaînes comme TF1 et BFM, alors qu'elle était initialement "flattée d'avoir été convoquée" pour aider à comprendre le fonctionnement de TikTok.

      • Positionnement professionnel : Julien Tanti se définit principalement comme une "personne qui fait de la téléréalité" depuis 14 ans, et non comme un influenceur. Il affirme : "Moi travail principal les tournages, je fais de la télé ça fait 14 ans que je fais de la télé et le reste c'est des hobis parce que ben je suis à Dubaï (...)." Il ajoute : "je n'influence personne je suis sur les réseaux parce que j'aime ça parce que c'est pour moi c'est un divertissement c'est quelque chose que je kiffe et je n'influence personne à faire quoi que ce soit je ne suis pas un influenceur." Manon Tanti soutient cette idée, expliquant qu'ils sont des "personnes qui font de la téléréalité" et que les réseaux sociaux sont une continuité de cette exposition de leur vie.

      II. Modèle Économique et Sources de Revenus

      Les deux influenceurs détaillent leurs différentes sources de revenus, insistant sur le fait que TikTok n'est pas leur source principale.

      Revenus de Julien Tanti :

      • Télévision : Principal revenu. Il effectue "3 à 4 tournages par an", ce qui équivaut à "pratiquement 7 mois dans l'année 6 à 7 mois" de travail.
      • TikTok Live (dons) : Une source de revenus secondaire, perçue comme un "kiff" et un "plaisir" plutôt qu'une activité principale. Il explique que TikTok prend 50% des gains. Le président de la commission estime ses revenus liés aux lives à environ "40000 dollars par mois", ce que Julien qualifie d' "énorme". Il explique reverser cet argent en organisant des événements pour sa "team" de joueurs, comme un yacht loué à Dubaï pour plus de 30 personnes. Il passe "à peu près 2-3 heures par jour" sur TikTok et se classe "souvent dans le top 20, dans le top 30, top 20, top 30, top 10". Manon souligne que son mari est un "showman" et que cette activité est sa "passion", allant au-delà de la simple rémunération.

      Revenus de Manon Tanti :

      • TikTok (vidéos de plus d'une minute) : Très peu de revenus. Elle explique être éligible à la rémunération pour les vidéos de plus d'une minute depuis peu et en poste très rarement (une ou deux par mois). Elle estime que TikTok représente "très très honnêtement 1% de la question" de ses revenus. Elle mentionne un RPM (ratio par minute) très bas (0,10 centimes) car elle ne poste pas assez fréquemment (il faudrait "minimum deux à trois vidéos par jour" pour optimiser l'algorithme). Sa vidéo la plus lucrative lui aurait rapporté "800 € il y a des années en arrière", la moyenne étant plutôt de "30-40 €".
      • Autres plateformes et partenariats : Principale source de revenus. Manon perçoit des revenus via d'autres plateformes.
      • Placements de produits : Ils sont toujours sous contrat avec des agences comme Shona Events et Wi Events. Julien Tanti affirme faire "toujours une pub ou deux, voir même trois ou quatre par semaine" et Manon "deux ou trois". Ils expliquent que "les personnes qui veulent contacter ils contactent directement les agences" et qu'ils n'ont plus besoin de faire la promotion de ces collaborations.
      • III. Exposition des Enfants et Cadre Légal
      • Un point central de l'audition concerne l'exposition des enfants sur les réseaux sociaux et le respect de la législation.

      Motivation de l'exposition des enfants : Manon Tanti explique que l'exposition de ses enfants est une "continuité de ce qu'on fait en télé" car ils sont des "personnages publics".

      Elle insiste sur le caractère "naturel" de cette exposition dans leur quotidien : "nous sommes des personnages publics, nos enfants aussi".

      Elle affirme ne pas les "surexposer" et qu'ils sont "consentants" et même demandeurs d'apparaître dans les vidéos.

      Elle cite l'exemple de son fils qui "aimerait avoir une chaîne par exemple", comme des "enfants youtubeurs" célèbres.

      • Accusations d'humiliation et dégradation : Manon conteste fermement les accusations d'humiliation, citant l'exemple d'une vidéo où les enfants jouent avec des ballons d'eau lors d'un barbecue : "ce que je veux vous dire c'est que le terme humiliant dégradant en tout cas moi en tant que maman je pense savoir ce qui est bon pour mes enfants ce qui est humiliant dégradant ou pas mes enfants jamais je ferai des vidéos ou des jeux s'ils en ont pas envie."

      Elle défend une vidéo où les enfants ont la "tête dans une espèce de bassine d'eau", expliquant que c'était une "trend" (tendance) et que les enfants étaient "morts de rire".

      Elle reconnaît cependant que "peut-être que d'autres parents le le reproduirait de d'une mauvaise manière" mais insiste : "sur cette vidéo je ne trouve absolument pas la vidéo humiliante puisque mes enfants sont ils sont morts de rire parce que c'est vraiment dans une bonne c'est bon enfant encore une fois je je je suis pas du tout en train de noyer mes enfants".

      Non-rémunération directe des enfants : Manon affirme ne pas utiliser ses enfants pour la rémunération : "je me sers pas de mes enfants pour la rémunération parce que dans tous les cas moi avec ou mes ou mes sans mes enfants je gagne ma vie".

      • Contrats de mannequins et placement de produits : La commission interroge Manon sur un placement de produit Instagram avec sa fille pour la marque "Ora Bora" (des brumes).

      La députée mentionne l'absence de "contrat de manquina" et de versement des revenus sur un "compte sous séquestre" comme l'exige la loi sur l'influence commerciale.

      Manon Tanti reconnaît : "premièrement déjà ça je ne savais pas deuxièmement encore une fois que cette marque là et cette vidéo là en l'occurrence que vous pouvez me citer et troisièmement au rabora en fait j'ai dû le faire une cinquantaine de je je n'ai pas besoin de ma fille pour vendre en fait".

      Un autre exemple est soulevé : une collaboration commerciale récente avec la marque "Shane" (vêtements) où les enfants apparaissent, sans mention de "collaboration commerciale" et sans respect du cadre légal.

      Manon se défend en disant : "j'ai appris avec vous il y a donc 10 minutes qu'à partir du moment où il y avait écrit collaboration mes enfants ne pouvaient pas apparaître je l'ai appris ben c'est vous qui me l'avez appris".

      Elle ajoute avoir déjà été contrôlée par la DGCCRF et avoir payé une amende, mais que "lorsque que Julien a eu son amende par exemple ça n'a pas été mentionné dans les choses qu'on avait mal faites donc si on l'avait su bah forcément on aurait arrêté".

      IV. Impact de TikTok sur les Mineurs et Propositions

      Les influenceurs sont interrogés sur leur perception de l'âge de leur communauté et leur avis sur la protection des mineurs.

      • Âge de la communauté et restriction d'accès : Manon Tanti estime que sa communauté est très diverse, allant des "préadolescents" aux "grand-mères". Elle est d'accord sur la nécessité de restrictions d'âge pour les réseaux sociaux : "TikTok est-ce que je sens il me semble que c'est interdit au moins de 15 ans c'est ça ça c'est quel est l'âge de TikTok ? 13 ans".

      Elle est catégorique : "mes enfants n'auront pas de compte TikTok et n'auront pas accès à TikTok".

      De même, pour Instagram, leurs enfants ont un compte géré par elle en tant que mère, mais "n'auront pas accès à ces réseaux sociaux là on en parlera quand ils seront plus grands mais je pense au moins avant leur 14 voir 16 ans".

      • Proposition de pièce d'identité : Manon Tanti propose une solution pour mieux encadrer l'accès des mineurs : "pour moi la seule solution qu'il aurait à tout ça ce serait de demander une pièce, je sais que ce serait ce serait pas possible mais pour moi si les réseaux sociaux dès le début comme certains réseaux de de contenu comme MIME ou tout ça demandait une pièce d'identité à chaque inscription ça éviterait plusieurs choses ça éviterait déjà bah que il y ait trop de mineurs qui qui qui tombent sur des choses qu'ils n'ont pas à voir et en plus de ça ça éviterait nous en tant qu'influenceur d'avoir du harcèlement des haters".

      Conclusion

      • L'audition met en lumière la complexité de réguler l'activité des influenceurs, notamment en ce qui concerne l'exposition des enfants et la distinction entre contenu personnel et commercial.

      Les Tanti se positionnent comme des personnalités de téléréalité avant d'être des influenceurs, gérant leurs réseaux sociaux comme un prolongement de leur vie médiatisée. Ils reconnaissent certaines lacunes dans leur connaissance de la loi (notamment sur les contrats de mannequins enfants) mais affirment leur volonté de se conformer aux réglementations une fois informés.

      L'échange souligne également le fossé entre la perception de l'influenceur sur son propre contenu ("bon enfant") et la réception par le public ou l'interprétation par la loi ("humiliant", "illégal").

    1. Compte rendu détaillé de l'audition de Nasser Sari (Nasdas) par la commission d'enquête sur TikTok

      • Date de l'audition : Non précisée (référence à "aujourd'hui")

      Personne auditionnée : Nasser Sari, alias Nasdas, influenceur avec 3,7 millions de followers sur TikTok et plus de 9 millions sur Snapchat.

      Contexte : La commission d'enquête de l'Assemblée nationale vise à comprendre les mécanismes de TikTok et des réseaux sociaux en général, ainsi qu'à élaborer une meilleure régulation pour protéger les mineurs des contenus choquants.

      L'audition fait suite à une consultation citoyenne et des signalements.

      Thèmes principaux et idées/faits importants :

      1. Rôle et rémunération sur TikTok vs. Snapchat :

      • Nasdas se définit avant tout comme un "Snapchatter", sa principale source de revenus étant Snapchat.
      • Il déclare que TikTok représente une part "quasi rien", estimée à "0,1 %" de ses rémunérations globales. Il affirme avoir gagné moins de 5000 € sur TikTok en 5 ans.
      • Sur TikTok, seuls les vidéos de plus d'une minute et les lives (via dons) sont rémunérés. Nasdas n'a posté qu'une soixantaine de vidéos en 4 ans, dont seulement deux de plus d'une minute, et environ 10 lives.
      • "Moi principalement ma source de revenu elle vient de Snapchat c'est un autre réseau [...] majoritairement ça vient de Snapchat."
      • "Sur TikTok comme je vous ai dit j'en gagne très peu."
      • Sur Snapchat, la rémunération se fait "à la vue" et via des placements de produits. Il déclare que 80% de ses placements de produits sont gratuits, dédiés au soutien des commerces de proximité.

      2. Utilisation de TikTok comme "tremplin" et viralité :

      • Malgré une faible monétisation directe, Nasdas utilise TikTok comme un "tremplin pour booster [ses] vidéos", gagner en visibilité et en autorité.
      • Il reconnaît que "le réseau principal aujourd'hui pour avoir plus d'aud [audience] c'est c'est c'est TikTok."
      • Ses vidéos Snapchat sont souvent relayées sur TikTok via des "comptes redif" (rediffusion), qui republient son contenu sans sa permission, obtenant parfois plus d'ampleur que sur Snapchat. Il qualifie cela de "normal" mais le reconnaît comme un "pillage de contenu".
      • Ces comptes rediffusent des vidéos virales ou de petits créateurs, en faisant des captures d'écran et en les repostant, sans identité claire. Il existe des milliers de ces comptes.

      3. Audience et présence de mineurs :

      • Nasdas est suivi par 3,7 millions de personnes sur TikTok et 9 millions sur Snapchat.
      • Il admet voir "énormément de jeunes" dans sa communauté, reconnaissable à leur écriture et leurs commentaires ("on voit bien que c'est un gamin de 14 ans ou 15 ans").
      • Cependant, il affirme que sur Snapchat, son réseau principal, plus de 87% de son audience est majeure, sa plus grande communauté étant les 25-36 ans. Il ne dispose pas de chiffres précis pour TikTok.
      • "Je vais vous dire que je n'ai pas réussi à regarder le nombre de mineurs qui me regardent."

      4. Les jeunes fugueurs et la responsabilité :

      • Nasdas est conscient que sa notoriété a entraîné des "jeunes mineurs qui fugent de leur ville pour venir à Perpignan", y compris des enfants de 10-11 ans attendus à 2h du matin.
      • Son adresse a fuité, entraînant 200 à 300 personnes par jour devant sa maison.
      • Il reconnaît avoir "une part de responsabilité" mais souligne aussi celle des parents. "Vous pensez pas que les parents ont une part de responsabilité ?" Il cite des cas de parents lui demandant de garder leurs enfants fugueurs.
      • Il affirme avoir toujours inclus une "morale" dans ses vidéos, disant "arrêtez ne venez pas arrêtez de croire au rêve Nasdas."
      • Il aide les jeunes en difficulté (hébergement, achat de vêtements, aide financière pour des opérations médicales), mais a "ralenti énormément" ces actions filmées, surtout l'année dernière, et s'est "isolé dans une villa" face à l'ampleur du phénomène.
      • Il mentionne que beaucoup de jeunes qui viennent sont des jeunes de foyers (aide sociale à l'enfance), se sentant "plus en sécurité des fois que dans certains foyers".
      • Il nie "rajouter de la misère à la misère" et souligne qu'il n'a jamais demandé aux jeunes de venir. Il a même collaboré avec la police pour gérer la situation.
      • Le maire de Perpignan (RN) n'aurait mis aucune aide en place, et même au contraire, des policiers seraient intervenus lors de ses actions sociales non autorisées. Il se sent "vraiment seul".

      5. La santé mentale des créateurs de contenu et la pression :

      • Nasdas a annoncé suspendre ses réseaux sociaux, une décision prise 3 mois avant l'audition, non liée à cette dernière.
      • Il évoque la difficulté mentale du métier : "notre santé mentale elle est impactée."
      • La "course au vues", à l'"image", au "buzz" met une pression sur les créateurs, les poussant "à poster des choses sans même en être conscient".
      • Il se reconnaît responsable de ses erreurs mais estime n'avoir pas été préparé à une telle notoriété.
      • Il envisage une pause d'un à trois ans : "je ne sais pas si j'arrête totalement définitivement mais c'est une décision sage." Il perdra "énormément d'argent" en s'arrêtant.
      • Il estime qu'il faudrait "plus d'encadrement, pas sévère, pas des punitions" pour les créateurs de contenu.

      6. Évolution de la ligne éditoriale et accusation de contenus choquants :

      • Des parlementaires accusent Nasdas d'une évolution de sa ligne éditoriale vers une "mise en scène assez violente qu'elle soit physique, psychologique ou symbolique", montrant des personnes "vulnérables filmées dans des situations de mise en concurrence assez dégradante", avec des encouragements à des comportements "discriminatoires et misogynes".
      • Il est spécifiquement interrogé sur la mise en scène de relations amoureuses dans sa villa, impliquant parfois des mineurs, et sur la frontière entre réalité et fiction.
      • Le cas d'une jeune fille "Leina" accusée d'être tombée enceinte d'un homme de la villa alors qu'elle était mineure est cité. Nasdas affirme qu'elle a menti sur sa grossesse et son âge (16-17 ans). Il mentionne qu'elle est majeure et qu'elle a le droit à l'image.
      • Le cas de "Dibril" jetant un téléphone sur sa compagne est évoqué comme un acte de violence conjugale filmé. Nasdas affirme que la scène était "surjouée" et que le couple est toujours ensemble.
      • Il admet que "il y a des choses qui sont mises en scène oui et d'autres choses réelles".
      • Un incident sur Twitch où une jeune fille a montré sa poitrine a été "pas volontaire" et le live a été coupé immédiatement. Il affirme qu'elle est majeure et qu'il l'a conseillée de s'éloigner des commentaires haineux.
      • Il réfute l'accusation d'avoir incité au racisme suite à l'expression "ramenez un banania" concernant un jeune garçon. Il explique qu'il s'agissait d'une référence à une boisson chocolatée et que l'auteur s'est excusé.
      • Il nie contribuer à la "banalisation de la violence" ou de l'harcèlement. Il se dit lui-même victime de harcèlement via ses vidéos. Il affirme que ses amis et lui se protègent mutuellement.

      7. Recommandations et auto-critique :

      • Nasdas reconnaît ne pas avoir de "baguette magique" ou de "solution miracle" pour réguler TikTok. Il se demande si "ce n'est pas un peu trop tard".
      • Il suggère qu'un "âge minimum" pour utiliser TikTok pourrait être de 14 ou 15 ans.
      • Il pense qu'il faudrait "plus une question d'algorithme pour les jeunes, plus les ramener vers un contenu on va dire éducatif".
      • Il souligne la difficulté de vérifier l'âge des utilisateurs et la facilité de mentir sur l'âge à l'inscription.
      • Il déclare que les "dramas" (contenus violents, misogynes, etc.) font "largement plus de vues qu'une vidéo qui explique [...] comment fonctionne une commission d'enquête". "Donc ça rapporte plus d'argent de faire des dramas que de faire de la pédagogie ah ben mais mais mais totalement."
      • Il avoue avoir partagé du "Paris sportif" et du "trading" par le passé, avant la loi influenceur, sous l'influence d'agences peu scrupuleuses, et reconnaît avoir causé des pertes à des familles. Il salue la nouvelle loi qui responsabilise les agences.
      • Il regrette d'avoir indirectement poussé les jeunes à croire en lui plutôt qu'en leurs études ou leur éducation. "Je représente un symbole de renaissance pour eux de d'une meilleure vie et surtout d'un meilleur avenir et c'est là où j'ai C'est là ou c'est là où je le regrette."

      En conclusion, il conseille à ceux qui veulent se lancer sur les réseaux : "vous lancez pas sur les réseaux."

      Questions en suspens / Points d'attention :

      • L'écart entre le discours de Nasdas sur la faible rémunération de TikTok et la reconnaissance de la plateforme comme "tremplin" pour la visibilité.
      • La difficulté pour Nasdas de fournir des chiffres précis sur la part des mineurs dans son audience TikTok, malgré son impact reconnu sur cette tranche d'âge.
      • La ligne floue entre "réalité" et "mise en scène" dans ses contenus, et les implications légales potentielles.
      • Le rôle des agences d'influenceurs et leur responsabilité dans les contenus problématiques (bien que la loi influenceur soit censée y remédier).
      • L'absence d'aide des services publics locaux face à l'afflux de jeunes chez Nasdas à Perpignan.
      • La perception de Nasdas que l'audition était trop axée sur des attaques personnelles plutôt que sur l'algorithme de TikTok.
    1. Voici un compte-rendu détaillé des principaux thèmes et idées importants des sources fournies, incluant des citations pertinentes :

      Synthèse du Rapport de la Commission d’Experts sur l’Impact de l’Exposition des Jeunes aux Écrans

      Ce document de briefing synthétise les points clés soulevés lors de l'audition de deux experts, * Madame Mouton (neurologue) et * Monsieur Benjamina (neurophysiologiste), co-présidents d'une commission antérieure sur l'impact des écrans.

      L'audition se concentre sur l'impact des réseaux sociaux, en particulier TikTok, sur la santé mentale et physique des jeunes.

      1. La Détérioration de la Santé Mentale des Jeunes et le Rôle des Réseaux Sociaux

      Les experts soulignent une chute de la santé mentale des moins de 25 ans depuis les années 2010, antérieure à la pandémie de COVID-19, qui a cependant accentué cette tendance.

      Parallèlement, l'usage des réseaux sociaux s'est massivement répandu, soulevant des questions sur leur implication dans cette détérioration.

      • Problème global des réseaux sociaux : Bien que la commission se concentre sur TikTok, les experts insistent sur le fait que "les réseaux sociaux posent globalement aujourd'hui tous les mêmes problèmes de design non éthique". TikTok est "peut-être particulièrement efficace pour capter et retenir l'attention des usagers", mais d'autres réseaux ne sont pas exempts de ces problèmes.

      • Modèle économique et captation de l'attention : Le problème fondamental réside dans le "design de TikTok et des réseaux sociaux qui étant basé sur l'économie de l'attention, la captation des données qui vont ensuite être monnayées à des fins de publicité ciblées". L'objectif est de "maintenir les usagers en ligne le plus longtemps possible de les faire venir en ligne le plus souvent possible et également de leur faire des achats en ligne".

      2. Conséquences Négatives sur la Santé Physique et Mentale

      L'usage excessif des écrans et des réseaux sociaux entraîne de multiples effets délétères, même indépendamment des contenus.

      • Santé physique :Sédentarité : Les activités sur écran sont sources d'inactivité sédentaire, un facteur de risque cardiovasculaire (infarctus, AVC, maladies artérielles, surpoids, obésité, diabète de type 2).
      • Sommeil : L'empiètement sur les heures de sommeil ou l'interruption de celui-ci (réveils pour des défis en ligne) compromet la qualité et la quantité du sommeil, favorisant les maladies cardiovasculaires, le surpoids, l'obésité et les infections. "La dette chronique de sommeil pouvant favoriser à nouveau les maladies cardiovasculaire mais aussi le surpoids l'obésité les infections".
      • Vision : L'activité en intérieur, le manque d'exposition à la lumière naturelle, la surexposition à la lumière bleue et la sursollicitation de la vision de près favorisent la myopie.
      • Santé mentale (par l'intermédiaire du sommeil) : La dette chronique de sommeil favorise également "l'anxiété et la dépression".

      3. La Question de l'Addiction aux Écrans et Réseaux Sociaux

      La discussion autour de l'addiction est nuancée, soulignant une réalité clinique distincte des classifications académiques.

      • Réalité clinique : Le Professeur Benjamina affirme traiter de nombreux jeunes "qui consomment et qui sont dépendants aux réseaux sociaux et TikTok en particulier".

      Ces problématiques sont prises en charge "à l'instar des produits comme le cannabis la cocaïne les extasiies ou l'alcool".

      Les dommages incluent des "effets métaboliques ou bien somatiques", ainsi que des "problématiques associées de type psychiatrique ou psychologique anxiété insomnie dépression difficulté l'adaptation relationnelle environnementale".

      • Classification académique : Sur le plan académique, l'addiction aux écrans ou aux réseaux sociaux n'est pas encore classée comme telle dans les classifications internationales (OMS, Association Américaine de Psychiatrie), à l'exception du jeu pathologique. Cependant, il est probable que cela évoluera à l'avenir.

      • TikTok, un produit "dépendogène" : TikTok est considéré comme "extrêmement accrocheur addictogène" en raison de son algorithme "extrêmement développé" et de la "fugacité du contenu" (vidéos courtes et répétitives), qui stimulent de manière intense le système de récompense. "Ces deux éléments ne sont pas là par le fait du hasard".

      4. Responsabilité des Plateformes et Nécessité de Régulation

      Les experts estiment que la responsabilité première du "mésusage" ou "surutilisation" des plateformes incombe aux industriels.

      • Design non éthique : Le modèle économique de TikTok et autres réseaux sociaux est délibérément conçu pour maximiser le temps passé en ligne, sans considération éthique pour la santé des utilisateurs. "Aucune éthique évidemment n'est convoquée puisque on a des contenus absolument scandaleux".

      • Manque de bonne foi des plateformes : Les plateformes sont réticentes à mettre en place des contraintes sans obligation légale. Elles mettent en avant "responsabilité liberté" et renvoient la "minorité" vers la "responsabilité de ses parents".

      Le Professeur Benjamina déclare : "Il faut pas s'attendre que les plateformes s'exécutent s'il n'y a pas de contrainte parce qu'elles ont les capacités à évidemment mettre en place des choses éthiques".

      5. Prise de Conscience Sociétale et Mesures Recommandées

      Il y a une prise de conscience sociétale croissante, mais des efforts significatifs sont encore nécessaires.

      • Écart de connaissance : Il existe un "gouffre entre peut-être des parents ou des professionnels de santé qui sont sensibles au sujet et qui sont bien informés et qui peuvent déjà avoir cette connaissance de l'impact des réseaux sociaux sur la santé des jeunes mais qu'il y a aussi toute une frange de la population aujourd'hui qui ignore totalement ses effets".

      • Communication massive et ciblée : Une "communication qui soit extrêmement massive sur ce sujet" est nécessaire, ainsi qu'une "communication plus ciblée aussi sur les professionnels de santé" qui n'ont pas toujours le réflexe d'interroger les jeunes sur leur usage des réseaux sociaux.

      • Formation des soignants : La formation des soignants sur l'usage des écrans est "très hétérogène aujourd'hui" et nécessite une formation "massive" des professions en lien avec la petite enfance et les adolescents.

      • Alternatives et réinvestissement des espaces physiques : La question "si on nous retire les réseaux sociaux qu'est-ce que vous nous mettez à la place" est comprise.

      Les jeunes trouvent dans ces plateformes un "refuge de divertissement". Il est essentiel de "proposer des alternatives aujourd'hui suffisamment puissantes pour les extraire de cette attraction très très forte de l'univers numérique".

      L'exemple des terrains vagues aménagés en espaces d'activités physiques montre l'efficacité de "choses qui n'ont pas demandé beaucoup de ni de temps ni d'énergie ni surtout d'argent et qui les ont finalement motivés à faire autre chose".

      • Réseaux sociaux "éthiques" et progressivité : La recommandation de limiter l'accès aux réseaux sociaux à 15 ans pour les plateformes dont la "conception serait éthique" est évoquée.

      Le concept de "réseau social éthique" implique un design qui ne vise pas la captation à tout prix, mais le bien-être de l'utilisateur. Cependant, la définition et l'application d'un tel âge limite se heurtent à la complexité de la vérification de l'âge et à la mauvaise foi des plateformes.

      L'idée de 15 ans se cale sur la "majorité numérique" et la "majorité sexuelle". La question est posée si cet âge ne devrait pas être plus élevé (18 ans), étant donné la vulnérabilité des adolescents et le fait que le cerveau continue de mûrir jusqu'à 25 ans.

      6. La Résistance des Jeunes et le Conflit de Génération

      Les jeunes rejettent souvent l'idée de la dangerosité des plateformes, considérant les adultes comme des "boomers" qui "n'ont rien compris".

      • Discours immobilisant : Le discours selon lequel "on peut pas revenir en arrière c'est le progrès et puis on peut pas faire autrement ils sont partout" est critiqué car il "désarme toute volonté de changer".

      Les experts insistent sur le fait que "oui on a le choix" de développer des modèles différents et de réguler.

      • Information insuffisante : "L'information qu'un produit est néfaste pour la santé suffisait à changer les comportements depuis le temps qu'on fait la prévention en santé publique on le saurait". L'information seule ne suffit pas ; une "régulation extrêmement" forte est nécessaire pour les produits addictifs ou "addictif-like".

      • Temps de la science vs. Évolution technologique : La reconnaissance scientifique des addictions prend du temps (90-100 ans pour le tabac), mais la technologie évolue "toutes les semaines" avec de nouveaux produits, plaçant la science "des années de retard".

      7. Approche Clinique et Traitement des Addictions aux Écrans

      La prise en charge clinique ne dépend pas d'une classification officielle mais des dommages constatés.

      • Prise en charge globale : Le traitement est "biopsychosocial", incluant "des mesures évidemment sociales", des "thérapies systémiques parents enfants", et la limitation de la consommation pour "éviter les le clash".
      • Bilan psychiatrique : Un bilan est crucial car de "grandes maladies psychiatriques commencent à l'adolescence" (schizophrénie, troubles bipolaires, anxiétés).
      • Thérapies : Des thérapies cognitivocomportementales, la psychanalyse ou psychodynamie de groupe sont utilisées. La recréation d'une "communauté" de jeunes en milieu de soin est efficace.
      • Transfert de dépendance : Le fait d'arrêter une consommation d'écrans n'est pas "à l'origine d'un transfert" vers d'autres substances. La réalité est plutôt celle de "polyconsommateur" et "polyxpérimentateur" où l'offre de drogues est variée.

      • En conclusion, l'audition met en lumière l'urgence d'une prise de conscience collective et d'une action politique ferme face à l'impact délétère des réseaux sociaux, dont le modèle économique est intrinsèquement problématique pour la santé des jeunes.

      La régulation des plateformes, la formation des professionnels de santé et le développement d'alternatives concrètes sont des pistes essentielles pour inverser la tendance.

    1. Document d'information détaillé : "Le pavillon des irresponsables"

      Ce document d'information analyse les thèmes principaux, les idées essentielles et les faits marquants des extraits du documentaire "Le pavillon des irresponsables".

      Il se concentre sur la vie des patients déclarés pénalement irresponsables et internés en Unités pour Malades Difficiles (UMD), en France.

      1. La Catégorie des "Irresponsables Pénaux" : Définition et Contexte

      Le documentaire s'ouvre sur la présentation des "irresponsables pénaux", des individus ayant commis des crimes (meurtre, agressions graves) mais échappant à la prison en raison de leur état mental au moment des faits. Ils sont internés dans des UMD.

      • Définition légale et clinique : Ces patients sont "des criminels qui échappent à la prison en raison de leur état mental et sont internés dans des unités pour malades difficiles". Leur statut d'"irresponsable" est caractérisé par un "caractère psychotique indéniable" et une "absence de conscience de ce qu'il pouvait faire".
      • Historique et Évolution : Historiquement, la psychiatrie, au milieu du 19e siècle, était une "mesure d'ordre public" participant à la "sécurité de la société". L'avènement des neuroleptiques dans les années 50-60 a permis une "ouverture". Cependant, ces dernières années, il y a un "repli vers une crainte et une volonté de plus de sécurité", mais les professionnels avertissent qu'un maintien coûte que coûte en milieu hospitalier risque d'être "liberticide" pour ceux qui pourraient évoluer favorablement.
      • Proportion et Durée de Séjour : Les patients irresponsables ne représentent qu'une "infime partie" des patients en UMD (environ 10 à 20 à Sarreguemines), mais ce sont "ceux qui restent de loin le plus longtemps en UMD".

      2. Le Quotidien et les Défis de la Vie en UMD

      Le documentaire offre un aperçu du quotidien des patients internés, soulignant les contraintes de l'environnement, mais aussi les efforts pour créer un espace de vie et de soin.

      • Soins Contraints et Environnement : Les UMD sont des "lieux de soins qu'on pourrait qualifier de soins de recours" pour des patients venant d'hôpitaux psychiatriques de secteur, souvent "les plus déstructurés, les plus délirants". Le terme "difficile" est approprié car ils "usent les équipes", nécessitant des séjours en UMD pour une "rupture".
      • Adaptation à la Contrainte : Malgré la privation de liberté, les patients développent des habitudes et cherchent à créer leur "petit espace", comme l'entretien méticuleux de leur chambre pour Christian Dornier : "C'est la chambre la plus ordonnée de tout le CHS... les affaires comme ça ça coûte cher alors il faut quand même un minimum de de soin à apporter au aux objets que j'ai acheté". La participation à des activités comme l'ergothérapie (Sylvain, Giselin) ou le travail du bois (Sylvain) est valorisée, car elle permet de "ne rien penser du tout" et de ne plus entendre de voix.
      • Souffrance et Délire Persistant : Malgré des traitements lourds, la souffrance des patients reste palpable. Giselin Anès, qui a tué sa mère, "reste un patient qui reçoit un traitement extrêmement lourd malgré ce traitement on devine chez lui plus que d'autres la souffrance qui est la sienne et qui est générée par ce qu'il ressent encore et ce qui constitue le noyau persécutif". Certains patients, comme Sylvain, continuent d'exprimer des délires de grandeur ("je suis Dieu, je suis Shiva, je suis tous les dieux") ou des missions salvatrices.
      • Gestion de la Dangerosité : Le personnel soignant est constamment attentif à la dangerosité potentielle. Pour le patient ayant tué sa grand-mère, "on devine parfaitement quand on quand on regarde l'évolution de ce patient qui reste malgré tout un des patients au potentiel de dangerosité le plus important dans ce qui reste de son délire il y a une dimension de mission qu'il aurait à accomplir en dehors d'un lieu comme l'UMD plus rien ne le retiendrait".

      3. Les Histoires Individuelles et la Complexité des Cas

      Le documentaire met en lumière des cas spécifiques qui illustrent la nature des maladies mentales et les défis de leur prise en charge à long terme.

      • Christian Dornier : Atteint de "schizophrénie paranoïde" avec des "éléments délirants extrêmement importants", il a commis un "meurtre de masse au sein de sa famille et du village" à la fin des années 80. Malgré plus de 30 ans de prise en charge, il n'a "jamais pu... avoir conscience qu'il était malade" et demeure convaincu d'"éléments persécutifs" qui ont nourri son délire. À 66 ans, la question de son avenir et d'un possible transfert vers un hôpital psychiatrique classique se pose, bien qu'un juge ait refusé sa sortie en 2023. Il exprime des regrets ("j'ai des regrets") mais explique ses actes par la "folie".
      • Giselin Anès : A tué sa mère lors d'une "séquence de décompensation psychotique". Il est arrivé en UMD après avoir été "retranché dans sa chambre, extrêmement hostile, menaçant". Sa dangerosité était "importante à ce moment-là". Il a toujours une "souffrance qui est la sienne et qui est générée par ce qu'il ressent encore et ce qui constitue le noyau persécutif".
      • Le Patient Incendiaire/Homicide : Un patient raconte avoir "brûlé une chambre" et "tué un mec". Il attribue ses actes à "Dieu ou voix" et à la "faute du psychiatre" précédent, refusant la responsabilité de ses actes et affirmant qu'il ne récidivera pas grâce au "bon traitement du psychiatre" actuel. Il nie être dangereux ("vous êtes trompé moi je suis pas du tout dangereux").
      • Sylvain Laurent : Se prend pour "Dieu", "Shiva", "tous les dieux", et se croit "la dernière personne sur qui on peut compter avant que la fat". Il décrit une mission de "massacrer sur la roche" pour revenir avec une "baguette magique en or" et faire disparaître les pédophiles et terroristes. Il ne perçoit pas ses idées comme un délire, affirmant: "mon délire à moi il dit non c'est pas vrai si j'ai fait ça c'est choquant mais j'avais des bonnes raisons de le faire".
      • Monsieur Tourchef : Exprime la difficulté de vivre "tout le temps avec les mêmes personnes" et la frustration de ne pas pouvoir sortir. Il a été maintenu en UMD en raison de son "comportement", notamment un "passage à l'acte agressif" récent.

      4. Les Commissions de Suivi Médical et la Question de la Sortie

      Les commissions sont un élément central de la vie en UMD, déterminant le maintien ou le transfert des patients.

      • Fonctionnement de la Commission : Tous les six mois, un collège de trois médecins examine chaque dossier et s'entretient avec le patient pendant 20 à 30 minutes. Ils ont à leur disposition le dossier médical et une synthèse des séjours. La commission rend un avis de maintien en UMD ou de transfert vers un hôpital d'origine si l'évolution est favorable et les critères de dangerosité "fortement atténués".
      • Critères d'Évaluation : Les critères incluent "l'état clinique de la personne", la persistance du délire, des hallucinations, de la froideur affective, la capacité à formuler des regrets ou de l'empathie, et les antécédents d'actes violents.

      Dilemmes de la Sortie :

      • Volonté du Patient : Certains patients souhaitent ardemment quitter l'UMD, même s'ils n'en ont pas les moyens cliniques, comme le patient incendiaire qui veut "retourner à mon hôpital d'origine au plus vite" pour "être comme un roi". D'autres, paradoxalement, "font tout ce qu'il faut pour rester", car ils ont "presque trouvé une sorte de petite famille", se sentant en "sécurité" et obtenant des "bénéfices secondaires" de l'hospitalisation.
      • Sécurité versus Liberté : Le "risque zéro n'existe pas en psychiatrie", et il n'y a "pas de garde fou ultime pour éviter le passage à l'acte d'un grand psychotique". La décision est complexe car elle doit concilier la sécurité de la société et du patient avec le droit à une évolution possible.
      • Pression Sociétale : La France a "de plus en plus de mal à répondre à l'inquiétude de la société face à la maladie mentale", conduisant parfois à des lois et décisions qui peuvent privilégier la sécurité au détriment de l'évolution individuelle des patients. Le maintien en UMD, pour certains, signifie une "qualité de vie" inégalée ailleurs (sorties accompagnées), mais aussi une absence de "perspective" d'une vie autonome.

      Conclusion : Une Réflexion sur l'Équilibre

      Le documentaire met en lumière la complexité de la prise en charge des patients pénalement irresponsables. Entre la nécessité de protéger la société, de soigner des individus atteints de pathologies lourdes et de préserver leurs droits, les UMD représentent un équilibre délicat.

      La question de la durée d'internement, de la conscience de la maladie par les patients, et de leur potentiel de réinsertion, même minime, reste au cœur des débats et des préoccupations des professionnels.

    1. Chào mọi người,Gia đình nhỏ của mình gồm hai vợ chồng và một bé trai 4 tuổi vừa kết thúc chuyến đi Nha Trang. Vấn đề nan giải nhất khi đi du lịch cùng con nhỏ chính là tìm được một hoạt động vừa vui cho con, vừa "nhàn" cho bố mẹ. Sau khi cân nhắc, nhà mình đã quyết định đặt tour Bình Hưng 1 ngày của Nha Trang Travel, và thật sự đây là một quyết định vô cùng đúng đắn.Mình xin chia sẻ lại trải nghiệm chân thực nhất để các gia đình có con nhỏ khác tham khảo nhé!Những Nỗi Lo Của Bố Mẹ Và Lời Giải Đáp Từ Tour1. Vấn đề di chuyển có an toàn và tiện lợi không?Đây là điều mình lo lắng nhất. Nhưng tour đã giải quyết rất tốt: Xe đưa đón tận nơi: Cả nhà không phải vất vả tự lái xe hay tìm đường. Đúng giờ là xe đến đón, bé nhà mình có thể ngủ thêm một giấc trên xe. Cano cao tốc: Mình đã lo con sẽ sợ, nhưng không ngờ bé lại rất phấn khích! Cano chạy êm, an toàn và quan trọng là có đầy đủ áo phao cho cả người lớn và trẻ em. Anh hướng dẫn viên cũng rất tâm lý, luôn để mắt và dặn dò các gia đình có con nhỏ. Xe điện trên đảo: Đây chính là "cứu tinh"! Thay vì phải bế con đi bộ dưới trời nắng, cả nhà được ngồi xe điện tham quan rất thảnh thơi. Bé nhà mình rất thích thú khi được ngồi xe điện vi vu ngắm cảnh. 2. Lịch trình có quá sức với trẻ nhỏ không?Lịch trình được sắp xếp rất hợp lý, không hề dồn dập. Thời gian di chuyển và tham quan xen kẽ, có đủ thời gian nghỉ ngơi nên bé nhà mình không hề bị mệt hay quấy khóc.

      Chào mọi người, Gia đình nhỏ của mình gồm hai vợ chồng và một bé trai 4 tuổi vừa kết thúc chuyến đi Nha Trang. Vấn đề nan giải nhất khi đi du lịch cùng con nhỏ chính là tìm được một hoạt động vừa vui cho con, vừa "nhàn" cho bố mẹ. Sau khi cân nhắc, nhà mình đã quyết định đặt tour Bình Hưng 1 ngày của Nha Trang Travel, và thật sự đây là một quyết định vô cùng đúng đắn. Mình xin chia sẻ lại trải nghiệm chân thực nhất để các gia đình có con nhỏ khác tham khảo nhé!

    1. Document d'information détaillé : Stratégies contre la violence scolaire : Prévention et Gestion Source : Extraits de "Stratégies Contre la Violence Scolaire : Prévention et Gestion" (Circulaire n° 2019-122 du 3-9-2019, NOR : MENE1925181C)

      Ce document officiel du Ministère de l'Éducation Nationale et de la Jeunesse (MENJ) et de la Direction Générale de l'Enseignement Scolaire (DGESCO) détaille un plan d'action exhaustif visant à prévenir et gérer la violence en milieu scolaire. Il s'adresse aux recteurs d'académie, inspecteurs, directeurs académiques, chefs d'établissement et professeurs.

      Thèmes principaux et idées clés :

        1. Le Respect d'Autrui comme Savoir Fondamental : Le document pose le respect d'autrui comme une "condition du bonheur collectif et de l'épanouissement de chacun". Il est présenté comme un savoir essentiel qui s'acquiert à travers l'enseignement et une "éducation quotidienne qui passe par le respect des règles élémentaires de civilité et du règlement intérieur."
      • 2. Tolérance Zéro pour les Incivilités et Agressions : Un principe non négociable est établi : "Chaque agression, chaque insulte, chaque incivilité doit être signalée et sanctionnée." Cette exigence est d'autant plus forte si les actes sont dirigés contre un représentant de l'autorité publique. L'institution scolaire doit à la fois prévenir et apporter des réponses concrètes.

        1. Renforcement des Procédures Disciplinaires : Les décrets n° 2019-906 et 2019-908 du 30 août 2019 visent à assurer une "réponse rapide, juste et efficace" aux manquements graves.
      • Signalement systématique et suivi : Chaque incident doit être signalé, faire l'objet d'un suivi, et être recensé avec la sanction appliquée. Un bilan annuel est présenté au conseil d'administration.

      • Simplification et rapidité : Les procédures de convocation des conseils de discipline sont simplifiées et les délais réduits (par exemple, passage de 8 à 5 jours pour la convocation initiale).
      • Diversité des sanctions : "Tout le panel des sanctions doit être mobilisé, et notamment les mesures de responsabilisation." Les sanctions doivent être adaptées à la gravité des faits.
      • Dimension pédagogique : La commission éducative est soulignée pour sa capacité à faire prendre conscience aux élèves de la gravité de leurs actes.
      • Suivi des élèves sanctionnés : Une "période probatoire est instaurée" après une exclusion, avec un suivi particulier pour faire le point sur la situation de l'élève.
      • Articulation avec la justice : En cas de faits graves, l'autorité judiciaire peut être saisie, selon des critères définis dans des conventions Justice-Éducation nationale qui seront actualisées.
      • 4. Renforcement de la Protection des Personnels : Les personnels scolaires bénéficient du statut juridique de "personne chargée d'une mission de service public", ce qui aggrave la qualification pénale des violences commises à leur encontre.

      • Réponse institutionnelle systématique : "Toute incivilité, atteinte ou autre fait grave commis à l'encontre d'un personnel de l'éducation nationale doit systématiquement faire l'objet d'une réponse de la part de l'institution."

      • Information et accompagnement : Les personnels doivent être "mieux informés des moyens à leur disposition" et accompagnés en cas d'agression ou de mise en cause abusive. Des guides d'accompagnement ont été créés à cet effet.
      • 5. Prise en Charge des Élèves Hautement Perturbateurs et Poly-exclus : Des dispositifs gradués sont envisagés pour les élèves dont les actes de violence sont récurrents.

      • Équipe mobile mixte d'intervention scolaire : Intervient en "troisième niveau", après l'échec des approches pédagogiques et éducatives et l'intervention d'autres professionnels. Cette équipe associe les familles dans le cadre d'un contrat limité dans le temps.

      • Classes relais : Le décret n° 2019-909 permet l'inscription d'un élève définitivement exclu dans une classe relais "sans le consentement préalable de ses représentants légaux", afin qu'il puisse poursuivre sa scolarité dans un cadre adapté. L'élève est également inscrit dans un établissement qu'il réintégrera.
      • Protocole d'accompagnement et de responsabilisation des parents (Par) : En cas de deux exclusions définitives au cours de la même année scolaire, le chef d'établissement peut saisir le DASEN pour mettre en œuvre ce protocole.

      Le Par vise à "poursuivre un dialogue avec les personnes responsables de l'élève et de les guider, en cas de besoin, vers le service ou le dispositif de soutien le plus approprié."

      Il repose sur l'alliance avec les parents, qui s'engagent à faire respecter par l'élève les obligations scolaires et à participer aux mesures d'accompagnement (aide pédagogique, activités éducatives, suivi médico-social).

      • 6. Organisations Adaptées aux Enjeux : Le plan prévoit des structures et des rôles spécifiques pour une mise en œuvre efficace.

      • Cellule de lutte contre les violences scolaires et référent départemental : Chaque DASEN doit créer un comité de pilotage avec un référent dédié au suivi des questions de violence. Ce comité a pour missions le suivi des faits, l'analyse des décisions disciplinaires, le traitement des affectations après exclusion, l'élaboration de conventions Justice/Éducation nationale, la régulation des saisines pour le PAR, la promotion des initiatives innovantes, l'impulsion de formations, et le renforcement des liens avec les acteurs locaux.

      • Identification des classes relais : Le DASEN doit spécifiquement identifier les classes relais aptes à accueillir les élèves hautement perturbateurs et/ou poly-exclus.
      • Transformation des internats relais en internats tremplins : L'objectif est d'avoir au moins un internat tremplin par académie d'ici 2022. Ces internats sont destinés aux élèves "en rupture profonde avec les exigences de la vie des établissements scolaires (élèves poly-exclus) et/ou est incapable d'améliorer son comportement au sein de l'établissement sans accompagnement spécifique."

      Ils reposent sur les principes d'inclusion, de personnalisation et de responsabilisation, avec un encadrement éducatif renforcé et un projet pédagogique global. Le placement peut être décidé si la classe relais est insuffisante, si l'élève relève d'une mesure de protection de l'enfance et ne peut rester en famille, ou sur décision judiciaire. * Nouveaux partenariats interministériels : Une circulaire interministérielle réactivera les conventions Éducation nationale/Justice et organisera les contrats intercommunaux/locaux de sécurité (CI/LSPD) pour impulser de nouveaux partenariats avec la justice, l'intérieur, l'éducation nationale et l'agriculture. * Annexe 1 : Modifications du Régime Disciplinaire (D. 2019-906 et 2019-908) * * Simplification des procédures : Réduction des délais pour le prononcé des sanctions (3 à 2 jours) et la convocation des conseils de discipline (8 à 5 jours). * Renforcement des réponses : Allongement de la durée de conservation de certaines sanctions dans le dossier administratif de l'élève (blâme et mesure de responsabilisation : fin de l'année scolaire suivante ; exclusions temporaires : fin de la deuxième année scolaire ; exclusion définitive : fin de la scolarité au second degré). Révocation systématique du sursis en cas de nouveau manquement grave. * Mesures d'accompagnement spécifiques : Pour les élèves réintégrés après une exclusion temporaire pour des faits de violence. * Information annuelle du conseil d'administration : Bilan des décisions disciplinaires et des suites données aux demandes de saisine du conseil de discipline. * Renforcement du droit des victimes : Les témoins mineurs sont entendus en présence de leur représentant légal. * Annexe 2 : Modèle type de Protocole d'accompagnement et de responsabilisation des parents (Par)

      • Cette annexe fournit un modèle détaillé du PAR, incluant :

      • Objet du protocole : Rappel des obligations parentales et proposition de mesures d'accompagnement.

      • Obligations des parents : Engagement à faire respecter l'assiduité, la ponctualité, le travail scolaire, le respect des biens et des personnes, et le règlement intérieur.

      Des volets spécifiques peuvent être ajoutés (ex: accompagner l'enfant, vérifier le matériel, consulter le carnet de correspondance, participer aux réunions). * Mesures d'accompagnement : Actions pédagogiques (aide, remédiation, tutorat), éducatives (Devoirs faits, stages, activités UNSS), et médico-sociales (rencontres avec l'assistante sociale, l'infirmière, le médecin scolaire). * Suivi du dispositif : Points réguliers avec les parents, suivi par le chef d'établissement qui rend compte au DASEN de l'exécution du protocole. * Durée et modification : Le protocole a une durée déterminée, renouvelable, et peut être modifié par avenant ou résilié en cas de non-respect des engagements.

      • En somme, la circulaire met en place une politique ferme mais accompagnatrice, axée sur la prévention, une réponse rapide et proportionnée à la violence, la protection des personnels, et une prise en charge différenciée des élèves en difficulté, impliquant fortement les parents et une collaboration inter-institutions.
    1. Synthèse des auditions des responsables de la modération TikTok par la commission d’enquête

      1. Structure de la modération de contenu chez TikTok

      TikTok emploie une approche hybride pour la modération des contenus, combinant des systèmes automatisés (algorithmes et IA) avec l'intervention humaine.

      Nikessou, responsable de la sécurité juridique, a précisé que "98 % des contenus qui violent les conditions" sont supprimés de manière proactive grâce à ces systèmes automatisés.

      La modération humaine, qui implique 509 modérateurs francophones, se concentre sur les contenus les plus sensibles ou contextuels. Les contenus signalés ou devenus populaires font l'objet d'examens supplémentaires.

      Cependant, il y a une diminution du nombre de modérateurs humains, passant de 634 au premier semestre à 509 au deuxième semestre.

      TikTok justifie cette baisse par l'amélioration de ses outils d'IA, permettant une suppression plus rapide et cohérente des contenus problématiques, et minimisant l'exposition des utilisateurs et des employés à ces contenus.

      Les modérateurs reçoivent une formation initiale et des vérifications hebdomadaires et mensuelles de leur interprétation des règles. Un soutien psychologique est également mis en place pour les modérateurs exposés à des contenus difficiles.

      2. Efficacité de la modération et défis liés aux contenus problématiques

      TikTok affirme que "moins de 1 % du contenu ne respecte pas les lignes directrices", mais la commission a remis en question la pertinence de ce pourcentage en raison de l'algorithme de recommandation qui peut amplifier même un faible volume de contenu problématique.

      Un exemple majeur de ce défi est la tendance "Skinny Talk", qui a incité à l'anorexie et aux troubles alimentaires. TikTok a expliqué avoir initialement détecté un volume faible et un faible taux de non-conformité.

      Ce n'est qu'après l'augmentation du volume et l'émergence d'une communauté centrée sur de mauvaises habitudes alimentaires que des mesures, y compris le blocage du hashtag, ont été prises.

      Malgré ces efforts, des contenus problématiques liés à ce thème, comme le hashtag "fearfood", persistent, soulevant des questions sur l'efficacité de la modération et la capacité de TikTok à honorer son "obligation de résultat".

      La représentante de TikTok a admis que "bien sûr, nous faisons des erreurs, c'est inévitable".

      La commission a également soulevé le problème des "moyens de contournement" utilisés par les jeunes, tels que l'utilisation de symboles (ex: petit zèbre pour la scarification) pour aborder des sujets sensibles sans être détectés.

      Les responsables de TikTok reconnaissent cette problématique et affirment travailler à anticiper ces contournements.

      3. Gestion des signalements et relations avec les organisations externes

      TikTok collabore avec des organisations comme Stop Fisha, e-Enfance, Génération Numérique et Point de Contact, qui agissent comme "signaleurs de confiance". Ces organisations bénéficient d'un canal de signalement prioritaire, assurant une réponse rapide.

      Cependant, la commission a fait état de divergences entre les signalements effectués par des particuliers et ceux des organisations, ces dernières entraînant des suppressions de contenu plus fréquentes. TikTok justifie cette différence par l'expertise des signaleurs de confiance, qui aident à identifier plus précisément les violations des règles communautaires.

      4. Sanction des comptes et politiques de tolérance

      TikTok applique une politique de tolérance variable selon la gravité des infractions.

      Les violations mineures peuvent entraîner des avertissements et des opportunités de correction, tandis que les infractions graves comme les discours de haine ou la pédopornographie entraînent une "tolérance zéro" et une interdiction immédiate.

      Un document public détaillant cette gradation des sanctions existe et peut être partagé.

      La commission a exprimé sa préoccupation quant à la lenteur de réaction face à des comptes d'influenceurs connus, suivis par des millions de personnes, qui diffusent des contenus problématiques (ex: propos sexistes, incitation à la violence). TikTok a souligné la difficulté d'examiner l'intégralité du contenu d'un utilisateur et le caractère contextuel des violations.

      5. Modération et fonctionnalités de TikTok Live

      TikTok Live est un produit de diffusion en direct où les créateurs interagissent avec leur communauté. L'équipe de modération (TNS) est la même que pour les contenus préenregistrés et agit en toute indépendance.

      Des modèles dédiés sont utilisés pour détecter des signaux de violation pendant les diffusions en direct, permettant d'interrompre la vidéo ou de donner des retours aux créateurs. Les menaces à la vie sont signalées aux autorités locales.

      Une fonctionnalité notable est le "Live Match", où deux ou quatre créateurs s'affrontent pendant 5 minutes, accumulant des points via des cadeaux virtuels et des "J'aime" du public.

      Le vainqueur est celui qui a le plus de points. Les cadeaux virtuels vont d'une "rose virtuelle" valant environ 5 centimes à plusieurs centaines d'euros. TikTok prélève 50 % de la valeur des cadeaux.

      Les agences externes spécialisées dans le live streaming sont rémunérées par TikTok et peuvent recevoir des pénalités financières si leurs créateurs enfreignent les règles. Un "score de santé" est attribué aux agences, démarrant à 100 points et diminuant en cas de violation.

        1. Préoccupations liées à l'addiction et à la protection des mineurs sur TikTok Live

      La commission a exprimé de vives inquiétudes quant au caractère addictif de TikTok, en particulier des Lives. Les responsables de TikTok ont souligné plusieurs mesures de protection:

      • Interdiction des Lives pour les moins de 18 ans: Les créateurs doivent vérifier leur identité (pièce d'identité et selfie) pour lancer un Live.
      • Interdiction de l'envoi de cadeaux virtuels pour les mineurs: Seuls les majeurs peuvent acheter et envoyer des cadeaux.
      • Limitation du temps d'écran: Les utilisateurs de 13 à 17 ans ont une limite de 60 minutes par jour, activée par défaut, avec des rappels réguliers.
      • Contenu non personnalisé: Dans le cadre du DSA, TikTok propose des flux non personnalisés pour permettre aux utilisateurs de découvrir une diversité de contenus.
      • Cependant, la commission a confronté TikTok à des témoignages directs de mineurs participant à des Lives et dépensant de l'argent via le compte Apple Pay de leurs parents, ou étant incités à changer leur date de naissance pour accéder à certaines fonctionnalités. La vérification de l'âge reste un défi majeur. TikTok a reconnu la persistance du problème, indiquant que "642 000 comptes" de moins de 13 ans ont été supprimés en France l'année dernière, et 6 millions par mois dans le monde.

      • La commission a également interrogé le modèle de rémunération des Live, où les "top créateurs" peuvent gagner "plusieurs dizaines de milliers d'euros par mois", et la nature des "Live Match" qui, selon certains membres, s'apparentent à des "mécanismes similaires à ceux des jeux d'argent". TikTok a réfuté cette assimilation, arguant qu'il n'y a pas d'espérance de gain pour les donateurs et que les jeux d'argent sont strictement interdits.

      Le remerciement des donateurs par les streamers, même s'il est considéré par TikTok comme de la "politesse", est perçu par la commission comme une "forme de gratification" et d' "encouragement au don".

      7. Transparence et obligations légales

      TikTok publie des rapports de transparence trimestriels et des rapports dédiés sur les demandes de retrait gouvernementales, les demandes d'information, les suppressions pour propriété intellectuelle, la lutte contre les opérations d'influence et les abus sexuels sur mineurs.

      La plateforme est également soumise aux obligations du DSA (Digital Services Act) et du code de pratique de lutte contre la désinformation de l'Union européenne.

      Conclusion

      • L'audition a mis en lumière la complexité de la modération de contenu sur une plateforme de l'ampleur de TikTok, confrontée à la fois à des défis technologiques (détection de contournements, vérification de l'âge) et humains (volume de contenu, contexte culturel).

      Si TikTok a détaillé ses efforts en matière de sécurité et de conformité réglementaire, la commission a exprimé de fortes réserves quant à l'efficacité réelle de ces mesures, en particulier concernant la protection des mineurs et la persistance de contenus problématiques.

      Des informations complémentaires ont été demandées à TikTok par écrit, avec la possibilité d'une reconvocation en cas de non-fourniture ou de divergence des réponses.

    1. Compte-Rendu d'Audition des Responsables de TikTok France

      Contexte de l'Audition et Objectifs * L'audition vise à examiner le modèle économique, les stratégies de contenu, les mesures de sécurité et de modération de TikTok en France, ainsi que son impact sur les mineurs. Les représentantes de TikTok, * Marlène Masure (Responsable du contenu, Europe, Moyen-Orient, Afrique) et * Marie Hugon (Responsable des enquêtes réglementaires européennes), ont prêté serment de dire la vérité.

      L'objectif de la commission est d'obtenir des informations précises et d'éviter les redites avec les auditions précédentes.

      I. Activités et Positionnement de TikTok en France et en Europe

      1. Portée et Mission de TikTok :

      • TikTok compte 25 millions d'utilisateurs actifs chaque mois en France et plus de 175 millions en Europe.
      • La plateforme se positionne comme un "tremplin pour des milliers de créateurs et professionnels" et une "véritable vitrine sur le monde".
      • L'objectif est d'encourager la création de contenus "créatifs, éducatifs, divertissants, de qualité au service d'une communauté très engagée".
      • TikTok affirme soutenir les contenus "utiles et positifs" et veiller à la "sécurité et au bien-être de notre communauté", agissant "en responsabilité".

      2. Partenariats et Contenus Promus :

      • TikTok collabore avec plus de 250 médias (Le Monde, France Info, AFP, etc.) pour les aider à "développer leur audience en favorisant l'interaction avec de nouveaux publics".
      • Des partenariats sont établis avec des acteurs de la culture, du sport (ex: Tour de France, JO Paris 2024, INA).
      • L'entreprise soutient activement les créateurs de contenu, notamment à travers des initiatives éducatives :
      • Fil STEM (Sciences, Technologies, Ingénierie, Mathématiques) lancé en avril 2024, consulté par 27% des utilisateurs de moins de 18 ans au moins une fois par semaine en France. Les moins de 18 ans le voient par défaut.
      • Programme "Apprendre sur TikTok" : valorise "toutes les formes de savoir", a généré plus de 5 milliards de vues depuis son lancement en 2023 grâce à 250 000 vidéos éducatives.
      • Marlène Masure mentionne travailler avec une sélection de 1000 créateurs et 400 partenaires pour créer du contenu jugé "intéressant" et "utile".

      II. Engagement Réglementaire et Mesures de Sécurité

      1. Conformité au DSA (Digital Services Act) et Transparence :

      • TikTok a été désignée "très grande plateforme" (VLOP) par la Commission européenne en avril 2023.
      • L'entreprise soutient le DSA, le considérant comme une "avancée majeure" pour le secteur.
      • TikTok réalise des "évaluations détaillées des risques systémiques", notamment liés à la protection des mineurs, et met en œuvre des "mesures d'atténuation raisonnable, proportionnée et efficace".
      • Cela inclut l'ajustement des conditions d'utilisation, le renforcement des politiques de modération, la modification des systèmes de recommandation et la promotion de l'éducation aux médias.
      • Des audits externes et indépendants et des rapports de transparence (nombre d'utilisateurs actifs, suppressions proactives de contenus illégaux) sont publiés annuellement.
      • En France, 91% des contenus problématiques sont supprimés avant même d'être vus. TikTok emploie 509 modérateurs en langue française et des milliers en Europe.

      2. Mesures Spécifiques pour la Protection des Mineurs :

      • TikTok applique une "approche ferme et globale" avec des "politiques de tolérance zéro", des "technologies innovantes", des "fonctionnalités de contrôles intégrées" et des "ressources pédagogiques".
      • Contenus sensibles : les contenus classifiés "matures" ne sont pas proposés aux mineurs et peuvent ne pas apparaître dans le "Pour Toi".
      • Contenu créé par des mineurs : le contenu créé par des moins de 16 ans n'est pas éligible aux recommandations (pas dans le "Pour Toi").
      • Publicité personnalisée : n'existe plus pour les 13-17 ans depuis août 2023.
      • Gestion du temps d'écran :
      • TikTok a été "la première plateforme à proposer cette limite de 60 minutes de temps d'écran pour les mineurs". Si le contrôle parental est activé, l'enfant est bloqué après 60 minutes, seul le parent peut prolonger. Sans contrôle parental, l'enfant peut choisir de prolonger.
      • Notifications push désactivées automatiquement entre 21h et 8h pour les 13-15 ans, et entre 22h et 8h pour les 16-17 ans.
      • Outils de contrôle parental ("Mode Connexion Famille") : permettent de filtrer des mots-clés, gérer le temps d'écran, le type de personnes pouvant interagir, et bloquer des heures d'accès.
      • Marlène Masure insiste sur la "culture du feedback" et l'écoute des retours des partenaires, associations et experts pour améliorer la sécurité.

      3. Gestion des Données (Projet Clover) :

      • TikTok a investi 1,2 milliard de dollars dans le "projet Clover" pour la souveraineté numérique, visant à localiser les données personnelles des utilisateurs européens en Europe (data centers à Dublin, en Finlande, en Norvège).
      • Ce projet est validé par un tiers de confiance, NCC. Actuellement, certaines données sont encore hébergées dans des pays ayant des accords avec l'UE (États-Unis, Singapour) en attendant le transfert complet.

      III. Défis et Points de Tension

      1. Contradiction entre Propos et Témoignages :

      • Les rapporteuses confrontent les représentantes de TikTok avec de nombreux témoignages de jeunes et d'enseignants décrivant des expériences négatives : addiction, spirale de contenu toxique (liés à la dépression, l'hypersexualisation, le racisme, le sexisme, les violences), développement de complexes, idées noires, troubles du sommeil, désintérêt scolaire, perte d'esprit critique, isolement social.
      • "L'algorithme a amplifié mon état en m'inondant de contenu en lien avec ma détresse il savait exactement ce que je ressentais et il me le servait en boucle ce qui était un divertissement est devenu un piège et j'ai mis des mois à m'en sortir" (Thibault, 20 ans).
      • "Aujourd'hui TikTok est saturé de contenus violents dégradants sexualisés ou tout simplement toxique" (Manon, 20 ans).
      • Une enseignante : "il est urgent de protéger nos enfants de cette addiction Leurs parents n'étant pas toujours au courant ou conscient de l'emprise de TikTok sur leur façon de penser ou de ne plus penser par eux-mêmes".
      • Les représentantes reconnaissent l'importance de ces témoignages mais nuancent, soulignant l'existence de témoignages positifs de créateurs ayant trouvé soutien, créé des entreprises ou bénéficié des programmes éducatifs. Elles affirment que le problème dépasse TikTok et concerne l'usage du numérique en général.

      2. Fonctionnement de l'Algorithme et "Bulles de Contenu" :

      • L'algorithme de TikTok est basé sur les "centres d'intérêt" et non les connexions sociales, recommandant du contenu en fonction des consommations passées de l'utilisateur et d'utilisateurs similaires.
      • Les rapporteuses expriment leur préoccupation face à l'enfermement dans des "bulles de contenu" et la promotion de contenus "provocateurs" ou "choc" par l'algorithme qui privilégie l'"attention" plutôt que les "intentions profondes" ou la "raison".
      • Elles évoquent l'infinit scrolling comme une spécificité addictive de TikTok.
      • TikTok affirme avoir des "principes de dispersion des contenus" pour éviter la répétition excessive de contenus sensibles.
      • Concernant la recommandation de contenus éducatifs, TikTok encourage l'utilisation de hashtags comme #apprendresurTikTok et soutient des médias et créateurs qualitatifs. Elles citent l'exemple de BookTok, une "très belle histoire" de communauté littéraire, bien que les rapporteuses mentionnent des articles de presse faisant état de la présence de "Dark Romance" hypersexualisée et violente sur cette tendance.

      3. Efficacité de la Modération et Contournement des Règles :

      • TikTok se dit en "permanence en train de rééduquer nos algorithmes" pour détecter les mots-clés détournés (ex: "algospeak", substitution de lettres par des chiffres ou émoticônes).
      • Cependant, des tests effectués par la commission montrent que des recherches avec des mots-clés détournés (ex: "scarification" avec un "c", "zèbre" pour scarification, "Suisse" pour suicide) donnent toujours accès à des contenus problématiques, même après signalement.
      • Les rapporteuses dénoncent le manque de réactivité de TikTok et l'insuffisance des messages de prévention pour des recherches telles que "je veux mourir" ou "comment se pendre".
      • Elles soulignent que l'obligation de TikTok est une "obligation de résultat" pour la protection des enfants, pas seulement une "obligation de moyens".

      4. Vérification de l'Âge et Comptes de Mineurs :

      • TikTok reconnaît avoir supprimé 642 000 comptes en France (sur la période 2024-2024) de moins de 13 ans n'ayant pas pu prouver leur âge, ce qui atteste que "beaucoup de jeunes mentent sur leur âge".
      • Cependant, TikTok ne dispose pas de statistiques précises sur le pourcentage de mineurs réels sur la plateforme ni sur l'activation des outils de contrôle parental par les comptes de mineurs identifiés.
      • Elles déclarent que la vérification de l'âge à l'inscription est déclarative et qu'il n'y a pas d'obligation réglementaire européenne pour une vérification plus stricte.
      • Les rapporteuses critiquent cette passivité, suggérant que TikTok pourrait être "plus responsable que les autres" en mettant en place une vérification d'âge a priori, même imparfaite (comme la solution "Connet" proposée par l'Éducation Nationale et refusée par TikTok).
      • Elles estiment que la réalité des mineurs sur la plateforme est que "deux tiers d'entre eux sont inscrits comme des majeurs" et ont accès à des contenus inappropriés.

      5. Différences avec Douyin (version chinoise) :

      • Les représentantes de TikTok affirment que Douyin est une application "complètement différente" gérée par des équipes chinoises, et qu'elles n'ont pas de lien ni de connaissance approfondie de ce produit, ce qui limite leur capacité à commenter ses mécanismes de protection des mineurs.

      6. Influenceurs Problématiques et Signalement :

      • La commission s'interroge sur la lenteur de la réaction de TikTok face à des influenceurs problématiques très suivis (ex: Ad Laurent, Alexis Chens) qui ont été signalés par des associations (Stop Fisha) ou des personnalités politiques (Aurore Berger).
      • TikTok affirme avoir été "les premiers" à retirer certains comptes, mais reconnaît des systèmes de "graduation" avant le bannissement. Elles estiment que l'intervention médiatique met "un coup de pression" mais que des processus réglementaires existent.
      • Les rapporteuses regrettent que les signalements d'individus soient moins bien traités que ceux d'organisations.

      IV. Conclusion et Perspectives

      • Les représentantes de TikTok réitèrent leur engagement continu pour la sécurité, l'amélioration des outils et la collaboration avec les régulateurs, associations et chercheurs. Elles soulignent les investissements massifs dans la sécurité et les efforts de modération (plus de 6 millions de vidéos supprimées en France en 2024).
      • Elles reconnaissent que "cette marge d'erreur on l'accepte pas" et "on travaille pour lutter contre effectivement des contenus qui peuvent créer des drames".
      • Elles rappellent la "fierté de ce que la plateforme offre comme opportunité" et son rôle dans la "création de valeur", "d'engagement" et de "carrières".
      • La commission exprime une "frustration" face aux réponses, estimant que les mesures de TikTok ne sont pas à la hauteur de la "dépendance très très forte des mineurs" et des "drames évitables" (suicides, scarifications).
      • La commission avertit qu'en l'absence d'"amélioration effective", l'interdiction de la plateforme pourrait devenir une option si des vies d'enfants continuent d'être affectées.
      • Des questions importantes sur le modèle économique (revenus des lives, part des revenus publicitaires) restent sans réponse et pourraient mener à une nouvelle audition.
    1. Author response:

      The following is the authors’ response to the original reviews.

      We thank all reviewers for the highly detailed review and the time and effort which has been invested in this review. It is clear from the reviews that we’ve had the privilege to have our work extensively and thoroughly checked by knowledgeable experts, for which we are very grateful. We have read their perspectives, questions and suggested improvements with great interest. We have reflected on the public review in detail and have included detailed responses below. First, we would like to respond to four main issues pointed out by the editor and reviewers:

      (1) Lack of yield data in the manuscript: Yield data has been collected in most of the sites and years of our study, and these have already been published and cited in our manuscript. In the appendix of our manuscript, we included a table with yield data for the sites and years in which the beetle diversity was studied. These data show that strip cropping does not cause a systematic yield reduction.

      (2) Sampling design clarification: Our paper combines data from trials conducted at different locations and years. On the one hand this allows an analysis of a comprehensive dataset, but on the other hand in some cases this resulted in variations in how data were collected or processed (e.g. taxonomic level of species identification). We have added more details to the sections on sampling design and data analysis to increase clarity and transparency.

      (3) Additional data analysis: In the revised manuscript we present an analysis on the responses of abundances of the 12 most common ground beetle genera to strip cropping. This gives better insight in the variation of responses among ground beetle taxa.

      (4) Restrict findings to our system: We nuanced our findings further and focused more on the implications of our data on ground beetle communities, rather than on agrobiodiversity in a broader sense.

      Below we also respond to the editor and reviewers in more detail.

      Reviewing Editor Comments:

      (1) You only have analyzed ground beetle diversity, it would be important to add data on crop yields, which certainly must be available (note that in normal intercropping these would likely be enhanced as well).

      Most yield data have been published in three previous papers, which we already cited or cite now (one was not yet published at the time of submission). Our argumentation is based on these studies. We had also already included a table in the appendix that showed the yield data that relates specifically to our locations and years of measurement. The finding that strip cropping does not majorly affect yield is based on these findings. We revised the title of our manuscript to remove the explicit focus on yield.

      (2) Considering the heterogeneous data involving different experiments it is particularly important to describe the sampling design in detail and explain how various hierarchical levels were accounted for in the analysis.

      We agree that some important details to our analysis were not described in sufficient detail. Especially reviewer 2 pointed out several relevant points that we did account for in our analyses, but which were not clear from the text in the methods section. We are convinced that our data analyses are robust and that our conclusions are supported by the data. We revised the methods section to make our approach clearer and more transparent.

      (3) In addition to relative changes in richness and density of ground beetles you should also present the data from which these have been derived. Furthermore, you could also analyze and interpret the response of the different individual taxa to strip cropping.

      With our heterogeneous dataset it was quite complicated to show overall patterns of absolute changes in ground beetle abundance and richness, especially for the field-level analyses. As the sampling design was not always the same and occasionally samples were missing, the number of year series that made up a datapoint were different among locations and years. However, we always made sure that for the comparison of a paired monoculture and strip cropping field, the number of year series was always made equal through rarefaction. That is, the number of ground beetle(s) (species) are always expressed as the number per 2 to 6 samples. Therefore, we prefer to stick to relative changes as we are convinced that this gives a fairer representation of our complex dataset.

      We agree with the second point that both the editor and several reviewers pointed out. The indicator species analyses that we used were biased by rare species, and we now omit this analysis. Instead, we included a GLM analysis on the responses of abundances of the 12 most common ground beetle genera to strip cropping. We chose for genera here (and not species) as we could then include all locations and years within the analyses, and in most cases a genus was dominated by a single species (but notable exceptions were Amara and Harpalus, which were often made up of several species). We illustrate these analyses still in a similar fashion as we did for the indicator species analysis.

      (4) Keep to your findings and don't overstate them but try to better connect them to basic ecological hypotheses potentially explaining them.

      After careful consideration of the important points that reviewers point out, we decided to nuance our reasoning about biodiversity conservation along two key lines: (1) the extent to which ground beetles can be indicators of wider biodiversity changes; and (2) our findings that are not as straightforward positive as our narrative suggests. We still believe that strip cropping contributes positively to carabid communities, and have carefully checked the text to avoid overstatements.

      Reviewer #1 (Public review):

      Summary:

      This study demonstrates that strip cropping enhances the taxonomic diversity of ground beetles across organically-managed crop systems in the Netherlands. In particular, strip cropping supported 15% more ground beetle species and 30% more individuals compared to monocultures.

      Strengths:

      A well-written study with well-analyzed data of a complex design. The data could have been analyzed differently e.g. by not pooling samples, but there are pros and cons for each type of analysis and I am convinced this will not affect the main findings. A strong point is that data were collected for 4 years. This is especially strong as most data on biodiversity in cropping systems are only collected for one or two seasons. Another strong point is that several crops were included.

      We thank reviewer 1 for their kind words and agree with this strength of the paper. The paper combines data from trials conducted at different locations and years. On the one hand this allows an analysis of a comprehensive dataset, but on the other hand in some cases there were slight variations in how data were collected or processed (e.g. taxonomic level of species identification).

      Weaknesses:

      This study focused on the biodiversity of ground beetles and did not examine crop productivity. Therefore, I disagree with the claim that this study demonstrates biodiversity enhancement without compromising yield. The authors should present results on yield or, at the very least, provide a stronger justification for this statement.

      We acknowledge that we indeed did not formally analyze yield in our study, but we have good reason for this. The claim that strip cropping does not compromise yield comes from several extensive studies (Juventia & van Apeldoorn, 2024; Ditzler et al., 2023; Carillo-Reche et al., 2023) that were conducted in nearly all the sites and years that we included in our study. We chose not to include formal analyses of productivity for two key reasons: (1) a yield analysis would duplicate already published analyses, and (2) we prefer to focus more on the ecology of ground beetles and the effect of strip cropping on biodiversity, rather than diverging our focus also towards crop productivity. Nevertheless, we have shown the results on yield in Table S6 and refer extensively to the studies that have previously analyzed this data (line 203-207, 217-221).

      Reviwer #1 (Recommendations for the authors):

      This is a well-written study on the effects of strip cropping on ground-beetle diversity. As stated above the study is well analyzed, presented, and written but you should not pretend that you analyzed yield e.g. lines 25-27 "We show that strip cropping...enhance ground beetle biodiversity without incurring major yield loss.

      We understand the confusion caused by this sentence, and it was never our intention to give the impression that we analyzed yield losses. These findings were based on previous research by ourselves and colleagues, and we have now changed the sentence to reflect this (line 25-27).

      I think you assume that yield does not differ between strip cropping and monoculture. I am not sure this is correct as one crop might attract pests or predators spilling over to the other crop. I am also not sure if the sowing and harvest of the crop will come with the same costs. So if you assume this, you should only do it in the main manuscript and not the abstract, to justify this better.

      With three peer-reviewed papers on the same fields as we studied, we can convincingly state that strip cropping in organic agriculture generally does not result in major yield loss, although exceptions exist, which we refer to in the discussion.

      In the introduction lines 28-43, you refer to insect biomass decline. I wonder if you would like to add the study of Loboda et al. 2017 in Ecography. It seems not fitting as it is from the Artic but also the other studies you cite are not only coming from agricultural landscapes and this study is from the same time as the Hallmann et al. 2017 study and shows a decline in flies of 80%

      We have removed the sentence that this comment refers to, to streamline the introduction more.

      Lines 50-51. You only have one citation for biodiversity strategies in agricultural systems. I suggest citing Mupepele et al. 2021 in TREE. This study refers to management but also the policies and societal pressures behind it.

      We have added this citation and a recent paper by Cozim-Melges et al. (2024) here (line 49-52).

      In the methods, I am missing a section on species identifications. This would help to understand why you used "taxonomic richness".

      Thanks for pointing this out. We have now included a new section on ground beetle identification (line 304-309 in methods).

      Figure 1 is great and I like that you separated the field and crop-level data, although there is no statistical power for the crop-specific data. I personally would move k to the supplements. It is very detailed and small and therefore hard to read

      We chose to keep figure 1k, as in our view it gives a good impression of the scale of the experiment, the number of crops included and the absolute numbers of caught species.

      Reviewer #2 (Public review):

      Summary:

      The authors aimed to investigate the effects of organic strip cropping on carabid richness and density as well as on crop yields. They find on average higher carabid richness and density in strip cropping and organic farming, but not in all cases.

      We did not intend to investigate the effect of strip cropping on crop yields, but rather place our work in the framework of earlier studies that already studied yield. All the monocultures and strip cropping fields were organic farms. Our findings thus compare crop diversity effects within the context of organic farming.

      Strengths:

      Based on highly resolved species-level carabid data, the authors present estimates for many different crop types, some of them rarely studied, at the same time. The authors did a great job investigating different aspects of the assemblages (although some questions remain concerning the analyses) and they present their results in a visually pleasing and intuitive way.

      We appreciate the kind words of reviewer 2 and their acknowledgement of the extensiveness of our dataset. In our opinion, the inclusion of many different crops is indeed a strength, rarely seen in similar studies; and we are happy that the figures are appreciated.

      Weaknesses:

      The authors used data from four different strip cropping experiments and there is no real replication in space as all of these differed in many aspects (different crops, different areas between years, different combinations, design of the strip cropping (orientation and width), sampling effort and sample sizes of beetles (differing more than 35 fold between sites; L 100f); for more differences see L 237ff). The reader gets the impression that the authors stitched data from various places together that were not made to fit together. This may not be a problem per se but it surely limits the strength of the data as results for various crops may only be based on small samples from one or two sites (it is generally unclear how many samples were used for each crop/crop combination).

      The paper indeed combines data from trials conducted at different locations and years. On the one hand this allows an analysis of a comprehensive dataset, but on the other hand in some cases there were slight differences in the experimental design. At the time that we did our research, there were only a handful of farmers that were employing strip cropping within the Netherlands, which greatly reduced the number of fields for our study. Therefore, we worked in the sites that were available and studied as many crops on these sites. Since there was variation in the crops grown in the sites, for some crops we have limited replication. In the revision we have explained this more clearly (line 297-300).

      One of my major concerns is that it is completely unclear where carabids were collected. As some strips were 3m wide, some others were 6m and the monoculture plots large, it can be expected that carabids were collected at different distances from the plot edge. This alone, however, was conclusively shown to affect carabid assemblages dramatically and could easily outweigh the differences shown here if not accounted for in the models (see e.g. Boetzl et al. (2024) or Knapp et al. (2019) among many other studies on within field-distributions of carabids).

      Point well taken. Samples were always taken at least 10 meters into the field, and always in the middle of the strip. This would indeed mean that there is a small difference between the 3- and 6m wide strips regarding distance from another strip, but this was then only a difference of 1.5 to 3 meters from the edge. A difference that, based on our own extensive experience with ground beetle communities, will not have a large impact on the findings of ground beetles. The distance from field/plot edges was similar between monocultures and strip cropped fields. We present a more detailed description of the sampling design in the methods of the revised manuscript (line 294-297).

      The authors hint at a related but somewhat different problem in L 137ff - carabid assemblages sampled in strips were sampled in closer proximity to each other than assemblages in monoculture fields which is very likely a problem. The authors did not check whether their results are spatially autocorrelated and this shortcoming is hard to account for as it would have required a much bigger, spatially replicated design in which distances are maintained from the beginning. This limitation needs to be stated more clearly in the manuscript.

      To be clear, this limitation relates to the comparison that we did for the community compositions of ground beetles in two crops either in strip cropping or monocultures. In this case, it was impossible to avoid potential autocorrelation due to our field design. We also acknowledge this limitation in the results section (line 130-133). However, for our other analyses we corrected for spatial autocorrelation by including variables per location, year and crop. This grouped samples that were spatially autocorrelated. Therefore, we don’t see this as a discrepancy of our other analyses.

      Similarly, we know that carabid richness and density depend strongly on crop type (see e.g. Toivonen et al. (2022)) which could have biased results if the design is not balanced (this information is missing but it seems to be the case, see e.g. Celeriac in Almere in 2022).

      We agree and acknowledge that crop type can influence carabid richness and density, which is why we have included variables to account for differences caused by crops. However, we did not observe consistent differences between crops in how strip cropping affected ground beetle richness and density. Therefore, we don’t think that crop types would have influenced our conclusions on the overall effect of strip cropping.

      A more basic problem is that the reader neither learns where traps were located, how missing traps were treated for analyses how many samples there were per crop or crop combination (in a simple way, not through Table S7 - there has to have been a logic in each of these field trials) or why there are differences in the number of samples from the same location and year (see Table S7). This information needs to be added to the methods section.

      Point well taken. We have clarified this further in the revised manuscript (line 294-301, 318-322). As we combined data from several experimental designs that originally had slightly different research questions, this in part caused differences between numbers of rounds or samples per crop, location or year.

      As carabid assemblages undergo rapid phenological changes across the year, assemblages that are collected at different phenological points within and across years cannot easily be compared. The authors would need to standardize for this and make sure that the assemblages they analyze are comparable prior to analyses. Otherwise, I see the possibility that the reported differences might simply be biased by phenology.

      We agree and we dealt with this issue by using year series instead of using individual samples of different rounds. This approach allowed us to get a good impression of the entire ground beetle community across seasons. For our analyses we had the choice to only include data from sampling rounds that were conducted at the same time, or to include all available data. We chose to analyze all data, and made sure that the number of samples between strip cropping and monoculture fields per location, year and crop was always the same by pooling and rarefaction.

      Surrounding landscape structure is known to affect carabid richness and density and could thus also bias observed differences between treatments at the same locations (lower overall richness => lower differences between treatments). Landscape structure has not been taken into account in any way.

      We did not include landscape structure as there are only 4 sites, which does not allow a meaningful analysis of potential effects landscape structure. Studying how landscape interacts with strip cropping to influence insect biodiversity would require at least, say 15 to 20 sites, which was not feasible for this study. However, such an analysis may be possible in an ongoing project (CropMix) which includes many farms that work with strip cropping.

      In the statistical analyses, it is unclear whether the authors used estimated marginal means (as they should) - this needs to be clarified.

      In the revised manuscript we further clarified this point (line 365-366, 373-374).

      In addition, and as mentioned by Dr. Rasmann in the previous round (comment 1), the manuscript, in its current form, still suffers from simplified generalizations that 'oversell' the impact of the study and should be avoided. The authors restricted their analyses to ground beetles and based their conclusions on a design with many 'heterogeneities' - they should not draw conclusions for farmland biodiversity but stick to their system and report what they found. Although I understand the authors have previously stated that this is 'not practically feasible', the reason for this comment is simply to say that the authors should not oversell their findings.

      In the revised manuscript, we nuanced our findings by explaining that strip cropping is a potentially useful tool to support ground beetle biodiversity in agricultural fields (line 33-35).

      Reviewer #2 (Recommendations for the authors):

      In addition to the points stated under 'Weaknesses' above, I provide smaller comments and recommendations:

      Overall comments:

      (i) The carabid images used in the figures were created by Ortwin Bleich and are copyrighted. I could not find him accredited in the acknowledgements; the figure legends simply state that the images were taken from his webpage. Was his permission obtained? This should be stated.

      We have received written permission from Ortwin Bleich for using his pictures in our figures, and have accredited him for this in the acknowledgements (line 455-456).

      (ii) There is a great confusion in the field concerning terminology. The authors here use intercropping and strip cropping, a specific form of intercropping, interchangeably. I advise the authors to stick to strip cropping as it is more precise and avoids confusion with other forms of intercropping.

      We agree with the definitions given by reviewer 2 and had already used them as such in the text. We defined strip cropping in the first paragraph of the introduction and do not use the term “intercropping” after this definition to avoid confusion.

      Comments to specific lines:

      Line 19: While this is likely true, there is so far not enough compelling evidence for such a strong statement blaming agriculture. Please rephrase.

      Changed the sentence to indicate more clearly that it is one of the major drivers, but that the “blame” is not solely on agriculture (line 18-19).

      Line 22: Is this the case? I am aware of strip cropping being used in other countries, many of them in Europe. Why the focus on 'Dutch'?

      Indeed, strip cropping is now being pioneered by farmers throughout Europe. However in the Netherlands, some farmers have been pioneering strip cropping already since 2014. We have added this information to indicate that our setting is in the Netherlands, and as in our opinion it gives a bit more context to our manuscript.

      Line 24: I would argue that carabids are actually not good indicators for overall biodiversity in crop fields as they respond in a very specific way, contrasting with other taxa. It is commonly observed that carabids prefer more disturbed habitats and richness often increases with management intensity and in more agriculturally dominated landscapes - in stark contrast to other taxa like wild bees or butterflies.

      We have reworded this sentence to reflect that they are not necessarily indicators of wide agricultural biodiversity, but that they do hold keystone positions within food webs in agricultural systems (line 23-25).

      Line 31: This statement here is also too strong - carabids are not overall biodiversity and patterns found for carabids likely differ strongly from patterns that would be observed in other taxa. This study is on carabids and the conclusion should thus also refer to these in order to avoid such over-simplified generalizations.

      We agree and have nuanced this sentence to indicate that our findings are only on ground beetles (line 33-35). However, we would like to point out that the statement that “patterns found for carabids likely differ strongly from patterns that would be observed in other taxa” assumes a disassociation between carabids and other taxa.

      Line 41: I am sure the authors are aware of the various methodological shortcomings of the dataset used in Hallmann et al. (2017) which likely led to an overestimation of the actual decline. Analysing the same data, Müller et al. (2023) found that weather can explain fluctuations in biomass just as well as time. I thus advise not putting too much focus on these results here as they seem questionable.

      We have removed this sentence to streamline the introduction, thus no longer mentioning the percentages given by Hallmann et al. (2017).

      Line 46: Surely likely but to my knowledge this is actually remarkably hard to prove. Instead of using the IPBES report here that simply states this as a fact, it would be better to see some actual evidence referenced.

      We removed IPBES as a source and changed this for Dirzo et al. (2014), a review that shows the consequences of biodiversity decline on a range of different ecosystem services and ecological functions (line 45-47).

      Line 52ff: I am not sure whether this old land-sparing vs. land-sharing debate is necessary here. The authors could simply skip it and directly refer to the need of agricultural areas, the dominating land-use in many regions, to become more biodiversity-friendly. It can be linked directly to Line 61 in my opinion which would result in a more concise and arguably stronger introduction.

      After reconsidering, we agree with reviewer 2 that this section was redundant and we have removed the lines on land-sparing vs land-sharing.

      Line 59: Just a note here: this argument is not meaningful when talking about strip cropping in the Netherlands as there is virtually no land left that could be converted (if anything, agricultural land is lost to construction). The debate on land-use change towards agriculture is nowadays mostly focused on the tropics and the Global South.

      We argue that strip cropping could play an important role as a measure that does not necessarily follow the trade-off between biodiversity and agriculture for a context beyond the Netherlands (line 52-58).

      Line 69: Does this statement really need 8 references?

      Line 71: ... and this one 5 additional ones?

      We have removed excess references in these two lines (line 62-66).

      Line 74: But also likely provides the necessary crop continuity for many crop pests - the authors should keep in mind that when practitioners read agricultural biodiversity, they predominantly think of weeds and insect pests.

      We agree with reviewer 2 that agricultural biodiversity is still a controversial topic. However, as the focus in this manuscript is more on biodiversity conservation, rather than pest management, we prefer to keep this sentence as is. In other published papers and future work we focus more on the role of strip cropping for pest management.

      Line 83: Consider replacing 'moments' maybe - phenological stages or development stages?

      Although we understand the point of reviewer 2, we prefer to keep it at moments, as we did not focus on phenological stages and we only wanted to say that we set pitfall traps at several moments throughout the year. However, by placing the pitfall traps at several moments throughout the year, we did capture several phenological stages.

      Line 86: Not only farming practices - there are also massive fluctuations between years in the same crop with the same management due to effects of the weather in the previous reproductive season. Interpreting carabid assemblage changes is therefore not straightforward.

      We absolutely agree that interpreting carabid assemblage is not straightforward, but as we did not study year or crop legacy effects we chose to keep this sentence to maintain focus on our research goals.

      Line 88: 'ecolocal'?

      Typo, should have been ecological. Changed (line 81).

      Line 90: 'As such, they are often used as indicator group for wider insect diversity in agroecosystems' - this is the third repetition of this statement and the second one in this paragraph - please remove. Having worked on carabids extensively myself, I also think that this is not the true reason - they are simply easy to collect passively.

      We agree with the reviewer and have removed this sentence.

      Line 141: I have doubts about the value of the ISA looking at the results. Anchomenus dorsalis is a species extremely common in cereal monoculture fields in large parts of Europe, especially in warmer and drier conditions (H. griseus was likely only returned as it is generally rare and likely only occurred in few plots that, by chance, were strip-cropped). It can hardly be considered an indicator for diverse cropping systems but it was returned as one here (which I do not doubt). This often happens with ISA in my experience as they are very sensitive to the specific context of the data they are run on. The returned species are, however, often not really useable as indicators in other contexts. I thus believe they actually have very limited value. Apart from this, we see here that both monocultures and strip cropping have their indicators, as would likely all crop types. I wonder what message we would draw from this ...

      On close reconsideration, we agree with the reviewer that the ISAs might have been too sensitive to rare species that by chance occur in one of two crop configurations. To still get an idea on what happens with specific ground beetle groups, we chose to replace the ISAs with analyses on the 12 most common ground beetle genera. For this purpose we have added new sections to the methods (line 368-374) and results (line 135-143), replaced figure 2 and table S5, and updated the discussion (line 182-200).

      Line 165: Carabid activity is high when carabids are more active. Carabids can be more active either when (i) there are simply more carabid individuals or /and (ii) when they are starved and need to search more for prey. More carabid activity does thus not necessarily indicate more individuals, it can indicate that there is less prey. This aspect is missing here and should be discussed. It is also not true that crop diversification always increases prey biomass - especially strip cropping has previously been shown to decrease pest densities (Alarcón-Segura et al., 2022). Of course, this is a chicken-egg problem (less pests => less carabids or more carabids => less pests ?) ... this should at least be discussed.

      We have rewritten this paragraph to further discuss activity density in relation to food availability (line 175-185).

      Line 178: These species are not exclusively granivorous - this speculation may be too strong here.

      Line 185: true for all but C. melanocephalus - this species is usually more associated with hedgerows, forests etc.

      After removing the ISA’s, we also chose to remove this paragraph and replace it with a paragraph that is linked to the analyses on the 12 most common genera (line 182-200).

      Line 202: These statements are too strong for my taste - the authors should add an 'on average' here. The data show that they likely do not always enhance richness by 15 % and as the authors state, some monocultures still had higher richness and densities.

      “on average” added (line 211)

      Line 203: 'can lead' - the authors cannot tell based on their results if this is always true for all taxa.

      Changed to “can lead” (line 213)

      Line 205: What is 'diversification' here?

      This concerns measures like hedgerows or flower strips. We altered the sentence to make this clearer (line 215-216).

      Line 208: Does this statement need 5 references? (as in the introduction, the reader gets the impression the authors aimed to increase the citation count of other articles here).

      We have removed excess references (line 219-221).

      Line 222: How many are 'a few'? Maybe state a proportion.

      We only found two species, we’ve changed the sentence accordingly (line 232-233).

      Line 224: As stated above, I would not overstress the results of the ISAs - the authors stated themselves that the result for A. dorsalis is likely only based on one site ...

      We removed this sentence after removing the ISAs.

      Line 305: I think there is an additional nested random level missing - the transect or individual plot the traps were located in (or was there only one replicate for each crop/strip in each experiment)? Hard to tell as the authors provide no information on the actual sample sizes.

      Indeed, there was one field or plot per cropping system per crop per location per year from which all the samples were taken. Therefore the analysis does not miss a nested random level. We provided information on sample sizes in Table S7.

      Line 314ff: The authors describe that they basically followed a (slightly extended) Chao-Hill approach (species richness, Shannon entropy & inverse Simpson) without the sampling effort / sample completeness standardization implemented in this approach and as a reader I wonder why they did not simply just use the customary Chao-Hill approach.

      We were not aware of the Chao-Hill approach, and we see it as a compliment that we independently came up with an approach similar to a now accepted approach.

      Line 329: Unclear what was nested in what here - location / year / crop or year / location / crop ?

      For the crop-level analyses, the nested structure was location > year > crop. This nested structure was chosen as every location was sampled across different years and (for some locations) the crops differed among years. However, as we pooled the samples from the same field in the field-level analyses, using the same random structure would have resulted in each individual sampling unit being distinguished as a group. Therefore, the random structure here was only location > year. We explain this now more clearly in lines 329 and 355-357.

      Line 334: I can see why the authors used these distributions but it is presented here without any justification. As a side note: Gamma (with log link) would likely be better for the Shannon model as well (I guess it cannot be 0 or negative ...).

      We explain this now better in lines 360-364.

      Line 341: Why Hellinger and not simply proportions?

      We used Hellinger transformation to give more weight to rarer species. Our pitfall traps were often dominated by large numbers of a few very abundant / active species. If we had used proportions, these species would have dominated the community analyses. We clarified this in the text (line 379-381).

      Line 348: An RDA is constrained by the assumptions / model the authors proposed and "forces" the data into a spatial ordination that resembles this model best. As the authors previously used an unconstrained PERMANOVA, it would be better to also use an NMDS that goes along with the PERMANOVA.

      The initial goal of the RDA was not to directly visualize the results of the PERMANOVA, but to show whether an overall crop configuration effect occurred, both for the whole dataset and per location. We have now added NMDS figures to link them to the PERMANOVA and added these to the supplementary figures (fig S6-S8). We also mention this approach in the methods section (line 387-390).

      Line 355f: This is also a clear indication of the strong annual fluctuations in carabid assemblages as mentioned above.

      Indeed.

      Line 361: 'pairwise'.

      Typo, we changed this.

      Line 362: reference missing.

      Reference added (line 405)

      References

      Alarcón-Segura, V., Grass, I., Breustedt, G., Rohlfs, M., Tscharntke, T., 2022. Strip intercropping of wheat and oilseed rape enhances biodiversity and biological pest control in a conventionally managed farm scenario. J. Appl. Ecol. 59, 1513-1523.

      Boetzl, F.A., Sponsler, D., Albrecht, M., Batáry, P., Birkhofer, K., Knapp, M., Krauss, J., Maas, B., Martin, E.A., Sirami, C., Sutter, L., Bertrand, C., Baillod, A.B., Bota, G., Bretagnolle, V., Brotons, L., Frank, T., Fusser, M., Giralt, D., González, E., Hof, A.R., Luka, H., Marrec, R., Nash, M.A., Ng, K., Plantegenest, M., Poulin, B., Siriwardena, G.M., Tscharntke, T., Tschumi, M., Vialatte, A., Van Vooren, L., Zubair-Anjum, M., Entling, M.H., Steffan-Dewenter, I., Schirmel, J., 2024. Distance functions of carabids in crop fields depend on functional traits, crop type and adjacent habitat: a synthesis. Proceedings of the Royal Society B: Biological Sciences 291, 20232383.

      Hallmann, C.A., Sorg, M., Jongejans, E., Siepel, H., Hofland, N., Schwan, H., Stenmans, W., Müller, A., Sumser, H., Hörren, T., Goulson, D., de Kroon, H., 2017. More than 75 percent decline over 27 years in total flying insect biomass in protected areas. PLoS One 12, e0185809.

      Knapp, M., Seidl, M., Knappová, J., Macek, M., Saska, P., 2019. Temporal changes in the spatial distribution of carabid beetles around arable field-woodlot boundaries. Scientific Reports 9, 8967.

      Müller, J., Hothorn, T., Yuan, Y., Seibold, S., Mitesser, O., Rothacher, J., Freund, J., Wild, C., Wolz, M., Menzel, A., 2023. Weather explains the decline and rise of insect biomass over 34 years. Nature.

      Toivonen, M., Huusela, E., Hyvönen, T., Marjamäki, P., Järvinen, A., Kuussaari, M., 2022. Effects of crop type and production method on arable biodiversity in boreal farmland. Agriculture, Ecosystems & Environment 337, 108061.

      Reviewer #3 (Public review):

      Summary:

      In this paper, the authors made a sincere effort to show the effects of strip cropping, a technique of alternating crops in small strips of several meters wide, on ground beetle diversity. They state that strip cropping can be a useful tool for bending the curve of biodiversity loss in agricultural systems as strip cropping shows a relative increase in species diversity (i.e. abundance and species richness) of the ground beetle communities compared to monocultures. Moreover, strip cropping has the added advantage of not having to compromise on agricultural yields.

      Strengths:

      The article is well written; it has an easily readable tone of voice without too much jargon or overly complicated sentence structure. Moreover, as far as reviewing the models in depth without raw data and R scripts allows, the statistical work done by the authors looks good. They have well thought out how to handle heterogenous, yet spatially and temporarily correlated field data. The models applied and the model checks performed are appropriate for the data at hand. Combining RDA and PCA axes together is a nice touch.

      We thank reviewer 3 for their kind words and appreciation for the simple language and analysis that we used.

      Weaknesses:

      The evidence for strip cropping bringing added value for biodiversity is mixed at best. Yes, there is an increase in relative abundance and species richness at the field level, but it is not convincingly shown this difference is robust or can be linked to clear structural and hypothesised advantages of the strip cropping system. The same results could have been used to conclude that there are only very limited signs of real added value of strip cropping compared to monocultures.

      Point well taken. We agree that the effect of strip cropping on carabid beetle communities are subtle and we nuanced the text in the revised version to reflect this. See below for more details on how we revised the manuscript to reflect this point.

      There are a number of reasons for this:

      (1) Significant differences disappear at crop level, as the authors themselves clearly acknowledge, meaning that there are no differences between pairs of similar crops in the strip cropping fields and their respective monoculture. This would mean the strips effectively function as "mini-monocultures".

      This is indeed in line with our conclusions. Based on our data and results, the advantages of strip cropping seem mostly to occur because crops with different communities are now on the same field, rather than that within the strips you get mixtures of communities related to different crops. We discussed this in the first paragraph of the discussion in the original submission (line 161-164).

      The significant relative differences at the field level could be an artifact of aggregation instead of structural differences between strip cropping and monocultures; with enough data points things tend to get significant despite large variance. This should have been elaborated further upon by the authors with additional analyses, designed to find out where differences originate and what it tells about the functioning of the system. Or it should have provided ample reason for cautioning in drawing conclusions about the supposed effectiveness of strip cropping based on these findings.

      We believe that this is a misunderstanding of our approach. In the field-level analyses we pooled samples from the same field (i.e. pseudo-replicates were pooled), resulting in a relatively small sample size of 50 samples. We revised the methods section to better explain this (line 318-322). Therefore, the statement “with enough data points things tend to get significant” is not applicable here.

      (2) The authors report percentages calculated as relative change of species richness and abundance in strip cropping compared to monocultures after rarefaction. This is in itself correct, however, it can be rather tricky to interpret because the perspective on actual species richness and abundance in the fields and treatments is completely lost; the reported percentages are dimensionless. The authors could have provided the average cumulative number of species and abundance after rarefaction. Also, range and/or standard error would have been useful to provide information as to the scale of differences between treatments. This could provide a new perspective on the magnitude of differences between the two treatments which a dimensionless percentage cannot.

      We agree that this would be the preferred approach if we would have had a perfectly balanced dataset. However, this approach is not feasible with our unbalanced design and differences in sampling effort. While we acknowledge the limitation of the interpretation of percentages, it does allow reporting relative changes for each combination of location, year and crop. The number of samples on which the percentages were based were always kept equal (through rarefaction) between the cropping systems (for each combination of location, year and crop), but not among crops, years and location. This approach allowed us to make a better estimation whenever more samples were available, as we did not always have an equal number of samples available between both cropping systems. For example, sometimes we had 2 samples from a strip cropped field and 6 from the monoculture, here we would use rarefaction up to 2 samples (where we would just have a better estimation from the monoculture). In other cases, we had 4 samples in both strip cropped and monoculture fields, and we chose to use rarefaction to 4 samples to get a better estimation altogether. Adding a value for actual richness or abundance to the figures would have distorted these findings, as the variation would be huge (as it would represent the number of ground beetle(s) species per 2 to 6 pitfall samples). Furthermore, the dimension that reviewer 3 describes would thus be “The number of ground beetle species / individuals per 2 to 6 samples”, not a very informative unit either.

      (3) The authors appear to not have modelled the abundance of any of the dominant ground beetle species themselves. Therefore it becomes impossible to assess which important species are responsible (if any) for the differences found in activity density between strip cropping and monocultures and the possible life history traits related reasons for the differences, or lack thereof, that are found. A big advantage of using ground beetles is that many life history traits are well studied and these should be used whenever there is reason, as there clearly is in this case. Moreover, it is unclear which species are responsible for the difference in species richness found at the field level. Are these dominant species or singletons? Do the strip cropping fields contain species that are absent in the monoculture fields and are not the cause of random variation or sampling? Unfortunately, the authors do not report on any of these details of the communities that were found, which makes the results much less robust.

      Thank you for raising this point. We have reconsidered our indicator species analysis and found that it is rather sensitive for rare species and insensitive to changes in common species. Therefore, we have replaced the indicator species analyses with a GLM analysis for the 12 most common genera of ground beetles in the revised manuscript. This will allow us to go more in depth on specific traits of the genera which abundances change depending on the cropping system. In the revised manuscript, we will also discuss these common genera more in depth, rather than focusing on rarer species (line 135-143, 182-200 in discussion). Furthermore, we have added information on rarity and habitat preference to the table that shows species abundances per location (Table S2), and mention these aspects briefly in the results (line 145-153).

      (4) In the discussion they conclude that there is only a limited amount of interstrip movement by ground beetles. Otherwise, the results of the crop-level statistical tests would have shown significant deviation from corresponding monocultures. This is a clear indication that the strips function more like mini-monocultures instead of being more than the sum of its parts.

      This is in line with our point in the first paragraph of the discussion and an important message of our manuscript.

      (5) The RDA results show a modelled variable of differences in community composition between strip cropping and monoculture. Percentages of explained variation of the first RDA axis are extremely low, and even then, the effect of location and/or year appear to peak through (Figure S3), even though these are not part of the modelling. Moreover, there is no indication of clustering of strip cropping on the RDA axis, or in fact on the first principal component axis in the larger RDA models. This means the explanatory power of different treatments is also extremely low. The crop level RDA's show some clustering, but hardly any consistent pattern in either communities of crops or species correlations, indicating that differences between strip cropping and monocultures are very small.

      We agree and we make a similar point in the first paragraph of the discussion (line 160-162).

      Furthermore, there are a number of additional weaknesses in the paper that should be addressed:

      The introduction lacks focus on the issues at hand. Too much space is taken up by facts on insect decline and land sharing vs. land sparing and not enough attention is spent on the scientific discussion underlying the statements made about crop diversification as a restoration strategy. They are simply stated as facts or as hypotheses with many references that are not mentioned or linked to in the text. An explicit link to the results found in the large number of references should be provided.

      We revised the introduction by omitting the land sharing vs. land sparing topic and better linking references to our research findings.

      The mechanistic understanding of strip cropping is what is at stake here. Does strip cropping behave similarly to intercropping, a technique that has been proven to be beneficial to biodiversity because of added effects due to increased resource efficiency and greater plant species richness? This should be the main testing point and agenda of strip cropping. Do the biodiversity benefits that have been shown for intercropping also work in strip cropping fields? The ground beetles are one way to test this. Hypotheses should originate from this and should be stated clearly and mechanistically.

      We agree with the reviewer and clarified this research direction clearer in the introduction of the revised manuscript (line 66-72).

      One could question how useful indicator species analysis (ISA) is for a study in which predominantly highly eurytopic species are found. These are by definition uncritical of their habitat. Is there any mechanistic hypothesis underlying a suspected difference to be found in preferences for either strip cropping or monocultures of the species that were expected to be caught? In other words, did the authors have any a priori reasons to suspect differences, or has this been an exploratory exercise from which unexplained significant results should be used with great caution?

      Point well taken. We agree that the indicator species analysis has limitations and therefore now replaced this with GLM analysis for the 12 most common ground beetle genera.

      However, setting these objections aside there are in fact significant results with strong species associations both with monocultures and strip cropping. Unfortunately, the authors do not dig deeper into the patterns found a posteriori either. Why would some species associate so strongly with strip cropping? Do these species show a pattern of pitfall catches that deviate from other species, in that they are found in a wide range of strips with different crops in one strip cropping field and therefore may benefit from an increased abundance of food or shelter? Also, why would so many species associate with monocultures? Is this in any way logical? Could it be an artifact of the data instead of a meaningful pattern? Unfortunately, the authors do not progress along these lines in the methods and discussion at all.

      We thank reviewer 3 for these valuable perspectives. In the revised manuscript, we further explored the species/genera that respond to cropping systems and discuss these findings in more detail in the revised manuscript (line 182-200 in discussion).

      A second question raised in the introduction is whether the arable fields that form part of this study contain rare species. Unfortunately, the authors do not elaborate further on this. Do they expect rare species to be more prevalent in the strip cropping fields? Why? Has it been shown elsewhere that intercropping provides room for additional rare species?

      The answer is simply no, we did not find more rare species in strip cropping. In the revised manuscript, we added a column for rarity (according to waarneming.nl) in the table showing abundances of species per location (table S2). We only found two rare species, one of which we only found a single individual and one that was more related to the open habitat created by a failed wheat field. We discuss this more in depth in the revised results (line 145-153).

      Considering the implications the results of this research can have on the wider discussion of bending the curve and the effects of agroecological measures, bold claims should be made with extreme restraint and be based on extensive proof and robust findings. I am not convinced by the evidence provided in this article that the claim made by the authors that strip cropping is a useful tool for bending the curve of biodiversity loss is warranted.

      We believe that strip cropping can be a useful tool because farmers readily adopt it and it can result in modest biodiversity gains without yield loss. However, strip cropping is indeed not a silver bullet (which we also don’t claim). We nuanced the implications of our study in the revised manuscript (line 30-35, 232-237).

      Reviewer #3 (Recommendations for the authors):

      General comments:

      (1) I am missing the R script and data files in the manuscript. This is a serious drawback in assessing the quality of the work.

      Datasets and R scripts will be made available upon completion of the manuscript.

      (2) I have doubts about the clarity of the title. It more or less states that strip cropping is designed in order to maintain productivity. However, the main objective of strip cropping is to achieve ecological goals without losing productivity. I suggest a rethink of the title and what it is the authors want to convey.

      As the title lead to false expectations for multiple reviewers regarding analyses on yield, we chose to alter the title and removed any mention of yield in the title.

      (3) Line 22: I would add something along the lines of: "As an alternative to intercropping, strip cropping is pioneerd by Dutch farmers... " This makes the distinction and the connection between the two more clear.

      In our opinion, strip cropping is a form of intercropping. We have changed this sentence to reflect this point better. (line 21-22)

      (4) Line 24: "these" should read "they"

      After changing this sentence, this typo is no longer there (line 24).

      (5) Line 34-48. I think this introduction is too long. The paper is not directly about insect decline, so the authors could consider starting with line 43 and summarising 34-42 in one or two sentences.

      Removed a sentence on insect declines here to make the introduction more streamlined.

      (6) Line 51-59. I am not convinced the land sparing - land sharing idea adds anything to the paper. It is not used in the discussion and solicits much discussion in and of itself unnecessary in this paper. The point the authors want to make is not arable fields compared to natural biodiversity, but with increases in biodiversity in an already heavily degraded ecosystem; intensive agriculture. I think the introduction should focus on that narrative, instead of the land sparing-sharing dichotomy, especially because too little attention is spent on this narrative.

      We removed the section on land-sparing vs land-sharing as it was indeed off-topic.

      (7) Line 85. Dynamics is not correctly used here. It should read Ground beetle communities are sensitive.

      Changed accordingly (line 78-79).

      (8) Line 90-91. Here, it should be added that ground beetles are used as indicators for ground-dwelling insect diversity, not wider insect diversity in agricultural systems. In fact, Gerlach et al., the reference included, clearly warn against using indicator groups in a context that is too wide for a single indicator group to cover and Van Klink (2022) has recently shown in a meta-analysis that the correlation between trends in insect groups is often rather poor.

      We removed the sentence that claimed ground beetles to be indicators of general biodiversity, and have focused the text in general more on ground beetle biodiversity, rather than general biodiversity.

      (9) Line 178: was there a high weed abundance measured in the stripcropping fields? Or has there been reports on higher weed abundance in general? The references provided do not appear to support this claim.

      To our knowledge, there is only one paper on the effect of strip cropping on weeds (Ditzler et al., 2023). This paper shows strip cropping (and more diverse cropping systems) reduce weed cover, but increase weed richness and diversity. We mistakenly mentioned that crop diversification increases weed seed biomass, but have changed this accordingly to weed seed richness. The paper from Carbonne et al. (2022) indeed doesn’t show an effect of crop diversification on weeds. However, it does show a positive relation between weed seed richness and ground beetle activity density. We have moved this citation to the right place in the sentence (line 172-175).

      (10) Line 279-288. The description of sampling with pitfalls is inadequate. Please follow the guidelines for properly incorporating sufficient detail on pitfall sampling protocols as described in Brown & Matthews 2016,

      We were sadly not aware of this paper prior to the experiments, but have at least added information on all characteristics of the pitfall traps as mentioned in the paper (line 290-294).

      (11) Lines 307-310. What reasoning lies behind the choice to focus on the most beetle-rich monocultures? Do the authors have references for this way of comparing treatments? Is there much variation in the monocultures that solicits this approach? It would be preferable if the authors could elaborate on why this method is used, provide references that it is a generally accepted statistical technique and provide additional assesments of the variation in the data so it can be properly related to more familiar exploratory data analysis techniques.

      We ran two analyses for the field-level richness and abundance. First we used all combinations of monocultures and strip cropping. However, as strip cropping is made up of (at least) 2 crops, we had 2 constituent monocultures. As we would count a comparison with the same strip cropped field twice when we included both monocultures, we also chose to run the analyses again with only those monocultures that had the highest richness and abundance. This choice was done to get a conservative estimate of ground beetle richness increases through strip cropping. We explained this methodology further in the statistical analysis section (line 329-335).

      In Figure S6 the order of crop combinations is altered between 2021 on the left and 2022 on the right. This is not helpful to discover any possible patterns.

      We originally chose this order as it represented also the crop rotations, but it is indeed not helpful without that context. Therefore, we chose to change the order to have the same crop combinations within the rows.

    1. Author response:

      The following is the authors’ response to the previous reviews.

      Public Reviews:

      Reviewer #1 (Public review):

      Summary:

      Recent work has demonstrated that the hummingbird hawkmoth, Macroglossum stellatarum, like many other flying insects, use ventrolateral optic flow cues for flight control. However, unlike other flying insects, the same stimulus presented in the dorsal visual field, elicits a directional response. Bigge et al., use behavioral flight experiments to set these two pathways in conflict in order to understand whether these two pathways (ventrolateral and dorsal) work together to direct flight and if so, how. The authors characterize the visual environment (the amount of contrast and translational optic flow) of the hawkmoth and find that different regions of the visual field are matched to relevant visual cues in their natural environment and that the integration of the two pathways reflects a prioritization for generating behavior that supports hawkmoth safety rather than the prevalence for a particular visual cue that is more prevalent in the environment.

      Strengths:

      This study creatively utilizes previous findings that the hawkmoth partitions their visual field as a way to examine parallel processing. The behavioral assay is well-established and the authors take the extra steps to characterize the visual ecology of the hawkmoth habitat to draw exciting conclusions about the hierarchy of each pathway as it contributes to flight control.

      Reviewer #2 (Public review):

      Summary

      Bigge and colleagues use a sophisticated free-flight setup to study visuo-motor responses elicited in different parts of the visual field in the hummingbird hawkmoth. Hawkmoths have been previously shown to rely on translational optic flow information for flight control exclusively in the ventral and lateral parts of their visual field. Dorsally presented patterns, elicit a formerly completely unknown response - instead of using dorsal patterns to maintain straight flight paths, hawkmoths fly, more often, in a direction aligned with the main axis of the pattern presented (Bigge et al, 2021). Here, the authors go further and put ventral/lateral and dorsal visual cues into conflict. They found that the different visuomotor pathways act in parallel, and they identified a 'hierarchy': the avoidance of dorsal patterns had the strongest weight and optic flow-based speed regulation the lowest weight. The authors linked their behavioral results to visual scene statistics in the hawkmoths' natural environment. The partition of ventral and dorsal visuomotor pathways is well in line with differences in visual cue frequencies. The response hierarchy, however, seems to be dominated by dorsal features, that are less frequent, but presumably highly relevant for the animals' flight safety.

      Strengths

      The data are very interesting and unique. The manuscript provides a thorough analysis of free-flight behavior in a non-model organism that is extremely interesting for comparative reasons (and on its own). These data are both difficult to obtain and very valuable to the field.

      Weaknesses

      While the present manuscript clearly goes beyond Bigge et al, 2021, the advance could have perhaps been even stronger with a more fine-grained investigation of the visual responses in the dorsal visual field. Do hawkmoths, for example, show optomotor responses to rotational optic flow in the dorsal visual field?

      I find the majority of the data, which are also the data supporting the main claims of the paper, compelling. However, the measurements of flight height are less solid than the rest and I think these data should be interpreted more carefully.

      Reviewer #3 (Public review):

      The authors have significantly improved the paper in revising to make its contributions distinct from their prior paper. They have also responded to my concerns about quantification and parameter dependency of the integration conclusion. While I think there is still more that could be done in this capacity, especially in terms of the temporal statistics and quantification of the conflict responses, they have a made a case for the conclusions as stated. The paper still stands as an important paper with solid evidence a bit limited by these concerns.

      Recommendations for the authors:

      Reviewer #1 (Recommendations for the authors):

      The edits have significantly improved the clarity of the manuscript. A few small notes:

      Figure 2B legend - describe what the orange dashed line represents

      We added a description.

      Figure 2B legend - references Table 1 but I believe this should reference Table S1. There are other places in the manuscript where Table 1 is referenced and it should reference S1

      We changed this for all instances in the main paper and supplement, where the reference was wrong.

      Figure S1 legend - some figure panel letters are in parentheses while others are not

      We unified the notation to not use parentheses for any of the panel letters.

      Reviewer #2 (Recommendations for the authors):

      I couldn't find the l, r, d, v indications in Fig. 1a. This was just a suggestion, but since you wrote you added them, I was wondering if this is the old figure version.

      We added them to what is now Fig. 2, which was originally part of Fig. 1. After restructuring, we did indeed not add an additional set to Fig. 1, which we have now adjusted.

      Fig. 2: Adding 'optic flow' and 'edges' to the y-axis in panels E and F, would make it faster for me to parse the figure. Maybe also add the units for the magnitudes? Same for Figure 6B

      We added 'optic flow' and 'edges' to the panels E and F in Fig. 2 and Fig. 6.

      Fig. 2: Very minor - could you use the same pictograms in D and E&F (i.e. all circles for example, instead of switching to "tunnels" in EF)?

      We used the tunnel pictograms, because we associated those with the short notations for the different conditions summarised in Table S1. Because we wanted to keep this consistent across the paper, we used the “tunnel” pictograms here too.

      In the manuscript, you still draw lots of conclusions based on these area measurements (L132-142, L204-209 etc). This does not fully reflect what you wrote in your reply to the reviewers. If you think of these measurements as qualitative rather than quantitative, I would say so in the manuscript and not use quantitative statistics etc. My suggestion would be to be more specific about potential issues that can influence the measurement (you mentioned body size, image contrast, motion blur, pitch across conditions etc) and give that data not the same weight as the rest of the measurements.

      We do express explicit caution with this measure in the methods section (l. 657-659) and the results section (l. 135-137). Nevertheless, as the trends in the data are consistent with optic flow responses in the other planes, and with responses reported in the literature, we felt that it is valuable to report the data, as well as the statistics for all readers, who can – given out cautionary statement – assess the data accordingly.

      The area measurements suggest that moths fly lower with unilateral vertical gratings (Fig. S1, G1 and G2 versus the rest). If you leave the data in can you speculate why that would be? (Sorry if I missed that)

      We agree, this seems quite consistent, but we do not have a good explanation for this observation. It would certainly require some additional experiments and variable conditions to understand what causes this phenomenon.

      Fig.4 - is panel B somehow flipped? Shouldn't the flight paths start out further away from the grating and then be moved closer to midline (as in A). That plot shows the opposite.

      Absolutely right, thank you for spotting this, it was indeed an intermediate and not the final figure which was uploaded to the manuscript. It also had outdated letter-number identifiers, which we now updated.

      L198 - should be "they avoided"

      Corrected.

    1. Reviewer #1 (Public review):

      Summary:

      The aim of the experiment reported in this paper is to examine the nature of the representation of a template of an upcoming target. To this end, participants were presented with compound gratings (consisting of tilted to the right and tilted to the left lines) and were cued to a particular orientation - red left tilt or blue right tilt (counterbalanced across participants). There are two directly compared conditions: (i) no ping: where there was a cue, that was followed by a 5.5-7.5s delay, then followed by a target grating in which the cued orientation deviated from the standard 45 degrees; and (ii) ping condition in which all aspects were the same with the only difference that a ping (visual impulse presented for 100ms) was presented after the 2.5 seconds following the cue. There was also a perception task in which only the 45 degrees to the right or to the left lines were presented. It was observed that during the delay, only in the ping condition, were the authors able to decode the orientation of the to-be-reported target using the cross-task generalization. Attention decoding, on the other hand, was decoded in both ping and non-ping conditions. It is concluded that the visual system has two different functional states associated with a template during preparation: a predominantly non-sensory representation for guidance and a latent sensory-like for prospective stimulus processing.

      Strengths:

      There is so much to be impressed with in this report. The writing of the manuscript is incredibly clear. The experimental design is clever and innovative. The analysis is sophisticated and also innovative - the cross-task decoding, the use of Mahalanobis distance as a function of representational similarity, the fact that the question is theoretically interesting, and the excellent figures.

      Weaknesses:

      While I think that this is an interesting study that addresses an important theoretical question, I have several concerns about the experimental paradigm and the subsequent conclusions that can be drawn.

      (1) Why was V1 separated from the rest of the visual cortex, and why the rest of the areas were simply lumped into an EVC ROI? It would be helpful to understand the separation into ROIs.

      (2) It would have been helpful to have a behavioral measure of the "attended" orientation to show that participants in fact attended to a particular orientation and were faster in the cued condition. The cue here was 100% valid, so no such behavioral measure of attention is available here.

      (3) As I was reading the manuscript I kept thinking that the word attention in this manuscript can be easily replaced with visual working memory. Have the authors considered what it is about their task or cognitive demand that makes this investigation about attention or working memory?

      (4) If I understand correctly, the only ROI that showed a significant difference for the cross-task generalization is V1. Was it predicted that only V1 would have two functional states? It should also be made clear that the only difference where the two states differ is V1.

      (5) My primary concern about the interpretation of the finding is that the result, differences in cross-task decoding within V1 between the ping and no-ping condition might simply be explained by the fact that the ping condition refocuses attention during the long delay thus "resharpening" the template. In the no-ping condition during the 5.5 to 7.5 seconds long delay, attention for orientation might start getting less "crisp." In the ping condition, however, the ping itself might simply serve to refocus attention. So, the result is not showing the difference between the latent and non-latent stages, rather it is the difference between a decaying template representation and a representation during the refocused attentional state. It is important to address this point. Would a simple tone during the delay do the same? If so, the interpretation of the results will be different.

      (6) The neural pattern distances measured using Mahalanobis values are really great! Have the authors tried to use all of the data, rather than the high AMI and low AMI to possibly show a linear relationship between response times and AMI?

      (7) After reading the whole manuscript I still don't understand what the authors think the ping is actually doing, mechanistically. I would have liked a more thorough discussion, rather than referencing previous papers (all by the co-author).

      Comments on revisions:

      I am impressed with the thoroughness with which the authors addressed my concerns. I don't have any further concerns and think that this paper makes an interesting and significant contribution to our understanding of VWM. I would only suggest adding citations to the newly added paragraph where the authors state "It could be argued that preparatory attention relies on the same mechanisms as working memory maintenance." They could cite work by Bettencourt and Xu, 2016; and Sheremata, Somers, and Shomstein (2018).

    2. Author response:

      The following is the authors’ response to the original reviews.

      Public Reviews:

      Reviewer #1 (Public review):

      (1) Why was V1 separated from the rest of the visual cortex, and why the rest of the areas were simply lumped into an EVC ROI? It would be helpful to understand the separation into ROIs.

      We thank the reviewer for raising the concerns regarding the definition of ROI. Our approach to analyze V1 separately was based on two key considerations. First, previous studies consistently identify V1 as the main locus of sensory-like templates during featurespecific preparatory attention (Kok et al., 2014; Aitken et al., 2020). Second, V1 shows the strongest orientation selectivity within the visual hierarchy (Priebe, 2016). In contrast, the extrastriate visual cortex (EVC; comprising V2, V2, V3AB and V4) demonstrates broader selectivity, such as complex features like contour and texture (Grill-Spector & Malach, 2004). Thus, we think it would be particularly informative to analyze V1 data separately as our experiment examines orientation-based attention. We should also note that we conducted MVPA separately for each visual ROIs (V2, V3, V3AB and V4). After observing similar patterns of results across these regions, we averaged the decoding accuracies into a single value and labeled it as EVC. This approach allowed us to simplify data presentation while preserving the overall data pattern in decoding performance. We now added the related explanations on the ROI definition in the revised texts (Page 26; Line 576-581).

      (2) It would have been helpful to have a behavioral measure of the "attended" orientation to show that participants in fact attended to a particular orientation and were faster in the cued condition. The cue here was 100% valid, so no such behavioral measure of attention is available here.

      We thank the reviewer for the comments. We agree that including valid and neutral cue trials would have provided valuable behavioral measures of attention; Yet, our current design was aimed at maximizing the number of trials for decoding analysis due to fMRI time constraints. Thus, we could not fit additional conditions to measure the behavioral effects of attention. However, we note that in our previous studies using a similar feature cueing paradigm, we observed benefits of attentional cueing on behavioral performance when comparing valid and neutral conditions (Liu et al., 2007; Jigo et al., 2018). Furthermore, our neural data indeed demonstrated attention-related modulation (as indicated by MVPA results, Fig. 2 in the main texts) so we are confident that on average participants followed the instruction and deployed their attention accordingly. We now added the related explanations on this point in the revised texts (Page 23; Line 492-498).

      (3) As I was reading the manuscript I kept thinking that the word attention in this manuscript can be easily replaced with visual working memory. Have the authors considered what it is about their task or cognitive demand that makes this investigation about attention or working memory?

      We thank the reviewer for this comment. We added the following extensive discussion on this point in the revised texts (Page 18; Line 363-381).

      “It could be argued that preparatory attention relies on the same mechanisms as working memory maintenance. While these functions are intuitively similar and likely overlap, there is also evidence indicating that they can be dissociated (Battistoni et al., 2017). In particular, we note that in our task, attention is guided by symbolic cues (color-orientation associations), while working memory tasks typically present the actual visual stimulus as the memorandum. A central finding in working memory studies is that neural signals during WM maintenance are sensory in nature, as demonstrated by generalizable neural activity patterns from stimulus encoding to maintenance in visual cortex (Harrison & Tong, 2009; Serences et al., 2009; Rademaker et al., 2019). However, in our task, neural signals during preparation were nonsensory, as demonstrated by a lack of such generalization in the No-Ping session (see also Gong et al., 2022). We believe that the differences in cue format and task demand in these studies may account for such differences. In addition to the difference in the sensory nature of the preparatory versus delay-period activity, our ping-related results also exhibited divergence from working memory studies (Wolff et al., 2017; 2020). While these studies used the visual impulse to differentiate active and latent representations of different items (e.g., attended vs. unattended memory item), our study demonstrated the active and latent representations of a single item in different formats (i.e., non-sensory vs. sensory-like). Moreover, unlike our study, the impulse did not evoke sensory-like neural patterns during memory retention (Wolff et al., 2017). These observations suggest that the cognitive and neural processes underlying preparatory attention and working memory maintenance could very well diverge. Future studies are necessary to delineate the relationship between these functions both at the behavioral and neural level.”

      (4) If I understand correctly, the only ROI that showed a significant difference for the crosstask generalization is V1. Was it predicted that only V1 would have two functional states? It should also be made clear that the only difference where the two states differ is V1.

      We thank the reviewer for this comment. We would like to clarify that our analyses revealed similar patterns of preparatory attentional representations in V1 and EVC. During the Ping session, the cross-task generalization analyses revealed decodable information in both V1 and EVC (ps < 0.001), significantly higher than that in the No-Ping session for V1 (independent t-test: t(38) = 3.145, p = 0.003; Cohen’s d = 0.995) and EVC (independent t-test: t(38) = 2.153, p = 0.038, Cohen’s d = 0.681) (Page 10; Line 194-196). While both areas maintained similar representations, additional measures (Mahalanobis distance, neural-behavior relationship and connectivity changes) showed more robust ping-evoked changes in V1 compared to EVC. This differential pattern likely reflects the primary role of V1 in orientation processing, with EVC showing a similar but weaker response profile. We have revised the text to clarity this point (Page 16; Line 327-329).

      (5) My primary concern about the interpretation of the finding is that the result, differences in cross-task decoding within V1 between the ping and no-ping condition might simply be explained by the fact that the ping condition refocuses attention during the long delay thus "resharpening" the template. In the no-ping condition during the 5.5 to 7.5 seconds long delay, attention for orientation might start getting less "crisp." In the ping condition, however, the ping itself might simply serve to refocus attention. So, the result is not showing the difference between the latent and non-latent stages, rather it is the difference between a decaying template representation and a representation during the refocused attentional state. It is important to address this point. Would a simple tone during the delay do the same? If so, the interpretation of the results will be different.

      We thank the reviewer for this comment. The reviewer proposed an alternative account suggesting that visual pings may function to refocus attention, rather than reactivate latent information during the preparatory period. If this account holds (i.e., attention became weaker in the no-ping condition and it was strengthened by the ping due to re-focusing), we would expect to observe a general enhancement of attentional decoding during the preparatory period. However, our data reveal no significant differences in overall attention decoding between two conditions during this period (ps > 0.519; BF<sub>excl</sub> > 3.247), arguing against such a possibility.

      The reviewer also raised an interesting question about whether an auditory tone during preparation could produce effects similar to those observed with visual pings. Although our study did not directly test this possibility, existing literature provides some relevant evidence. In particular, prior studies have shown that latent visual working memory contents are selectively reactivated by visual impulses, but not by auditory stimuli (Wolff et al., 2020). This finding supports the modality-specificity for visually encoded contents, suggesting that sensory impulses must match the representational domain to effectively access latent visual information, which also argues against the refocusing hypothesis above. However, we do think that this is an important question that merits direct investigation in future studies. We now added the related discussion on this point in the revised texts (Page 10, Line 202-203; Page 19, Line 392395).

      (6) The neural pattern distances measured using Mahalanobis values are really great! Have the authors tried to use all of the data, rather than the high AMI and low AMI to possibly show a linear relationship between response times and AMI?

      We thank the reviewer for this comment. We took the reviewer’s suggestion to explore the relationship between attentional modulation index (AMI) and RTs across participants for each session (see Figure 3). In the No-Ping session, we observed no significant correlation between AMI and RT (r = -0.366, p = 0.113). By contrast, the same analysis in the Ping condition revealed a significantly negative correlation (r = -0.518, p = 0.019). These results indicate that the attentional modulations evoked by visual impulse was associated with faster RTs, supporting the functional relevance of activating sensory-like representations during preparation. We have now included these inter-subject correlations in the main texts (Page 13, Line 258-264; Fig 3D and 3E) along with within-subject correlations in the Supplementary Information (Page 6, Line, 85-98; S3 Fig).

      (7) After reading the whole manuscript I still don't understand what the authors think the ping is actually doing, mechanistically. I would have liked a more thorough discussion, rather than referencing previous papers (all by the co-author).

      We thank the reviewer for this comment regarding the mechanistic basis of visual pings. We agree that this warrants deeper discussion. One possibility, as informed by theoretical studies of working memory, is that the sensory-like template could be maintained via an “activity-silent” mechanism through short-term changes in synaptic weights (Mongillo et al., 2008). In this framework, a visual impulse may function as nonspecific inputs that momentarily convert latent traces into detectable activity patterns (Rademaker & Serences, 2017). Related to our findings, it is unlikely that the orientation-specific templates observed during the Ping session emerged from purely non-sensory representations and were entirely induced by an exogenous ping, which was devoid of any orientation signal. Instead, the more parsimonious explanation is that visual impulse reactivated pre-existing latent sensory signals. To our knowledge, the detailed circuit-level mechanism of such reactivation is still unclear; existing evidence only suggests a relationship between ping-evoked inputs and the neural output (Wolff et al., 2017; Fan et al., 2021; Duncan et al., 2023). We now included the discussion on this point in the main texts (Page 19, Line 383-401).

      Reviewer #2 (Public review):

      (1) The origin of the latent sensory-like representation. By 'pinging' the neural activity with a high-contrast, task-irrelevant visual stimulus during the preparation period, the authors identified the representation of the attentional feature target that contains the same information as perceptual representations. The authors interpreted this finding as a 'sensory-like' template is inherently hosted in a latent form in the visual system, which is revealed by the pinging impulse. However, I am not sure whether such a sensory-like template is essentially created, rather than revealed, by the pinging impulses. First, unlike the classical employment of the pinging technique in working memory studies, the (latent) representation of the memoranda during the maintenance period is undisputed because participants could not have performed well in the subsequent memory test otherwise. However, this appears not to be the case in the present study. As shown in Figure 1C, there was no significant difference in behavioral performance between the ping and the no-ping sessions (see also lines 110-125, pg. 5-6). In other words, it seems to me that the subsequent attentional task performance does not necessarily rely on the generation of such sensory-like representations in the preparatory period and that the emergence of such sensory-like representations does not facilitate subsequent attentional performance either. In such a case, one might wonder whether such sensory-like templates are really created, hosted, and eventually utilized during the attentional process. Second, because the reference orientations (i.e. 45 degrees and 135 degrees) have remained unchanged throughout the experiment, it is highly possible that participants implicitly memorized these two orientations as they completed more and more trials. In such a case, one might wonder whether the 'sensory-like' templates are essentially latent working memory representations activated by the pinging as was reported in Wolff et al. (2017), rather than a functional signature of the attentional process.

      We thank the reviewer for this comment. We agree that the question of whether the sensory-like template is created or merely revealed by visual pinging is crucial for the understanding our findings. First, we acknowledge that our task may not be optimized for detecting changes in accuracy, as the task difficulty was controlled using individually adjusted thresholds (i.e., angular difference). Nevertheless, we observed some evidence supporting the neural-behavioral relationships. In particular, the impulse-driven sensory-like template in V1 contributed to facilitated faster RTs during stimulus selection (Page 12, Fig. 3D and 3E in the main texts; also see our response to R1, Point 6).

      Second, the reviewer raised an important concern about whether the attended feature might be stored in the memory system due to the trial-by-trial repetition of attention conditions (attend 45º or attend 135º). Although this is plausible, we don’t think it is likely. We note that neuroimaging evidence shows that attended working memory contents maintain sensory-like representations in visual cortex (Harrison & Tong, 2009; Serences et al., 2009; Rademaker et al., 2019), with generalizable neural activity patterns from perception to working memory delay-period, whereas unattended items in multi-item working memory tasks are stored in a latent state for prospective use (Wolff et al., 2017). Importantly, our task only required maintaining a single attentional template at a time. Thus, there was no need to store it via latent representations, if participants simply used a working memory mechanism for preparatory attention. Had they done so, we should expect to find evidence for a sensory template, i.e., generalizable neural pattern between perception and preparation in the No-Ping condition, which was not what we found. We have mentioned this point in the main texts (Page 18, Line 367-372).

      (2) The coexistence of the two types of attentional templates. The authors interpreted their findings as the outcome of a dual-format mechanism in which 'a non-sensory template' and a latent 'sensory-like' template coexist (e.g. lines 103-106, pg. 5). While I find this interpretation interesting and conceptually elegant, I am not sure whether it is appropriate to term it 'coexistence'. First, it is theoretically possible that there is only one representation in either session (i.e. a non-sensory template in the no-ping session and a sensory-like template in the ping session) in any of the brain regions considered. Second, it seems that there is no direct evidence concerning the temporal relationship between these two types of templates, provided that they commonly emerge in both sessions. Besides, due to the sluggish nature of fMRI data, it is difficult to tell whether the two types of templates temporally overlap.

      We thank the reviewer for the comment regarding our interpretation of the ‘coexistence’ of non-sensory and sensory-like attentional template. While we acknowledge the limitations of fMRI in resolving temporal relationships between these two types of templates, several aspects of our data support a dual-format interpretation.

      First, our key findings remained consistent for the subset of participants (N=14) who completed both No-Ping and Ping sessions in counterbalanced order. It thus seems improbable that participants systematically switched cognitive strategies (e.g., using non-sensory templates in the No-Ping session versus sensory-like templates in the Ping session) in response to the task-irrelevant, uninformative visual impulse. Second, while we agree with the reviewer that the temporal dynamics between these two templates remain unclear, it is difficult to imagine that orientation-specific templates observed during the Ping session emerged de novo from a purely non-sensory templates and an exogenous ping. In other words, if there is no orientation information at all to begin with, how does it come into being from an orientation-less external ping? It seems to us that the more parsimonious explanation is that there was already some orientation signal in a latent format, and it was activated by the ping, in line with the models of “activity-silent” working memory. To address these concerns, we have added the related discussion of these alternative interpretations in the main texts (Page 19, Line 387-391)

      (3) The representational distance. The authors used Mahalanobis distance to quantify the similarity of neural representation between different conditions. According to the authors' hypothesis, one would expect greater pattern similarity between 'attend leftward' and 'perceived leftward' in the ping session in comparison to the no-ping session. However, this appears not to be the case. As shown in Figures 3B and C, there was no major difference in Mahalanobis distance between the two sessions in either ROI and the authors did not report a significant main effect of the session in any of the ANOVAs. Besides, in all the ANOVAs, the authors reported only the statistic term corresponding to the interaction effect without showing the descriptive statistics related to the interaction effect. It is strongly advised that these descriptive statistics related to the interaction effect should be included to facilitate a more effective and intuitive understanding of their data.

      We thank the reviewer for this comment. We expected greater pattern similarity between 'attend leftward' and 'perceived leftward' in the Ping session in comparison to the Noping session. This prediction was supported by a significant three-way interaction effect between session × attended orientation × perceived orientation (F(1,38) = 5.00, p = 0.031, η<sub>p</sub><sup>2</sup> = 0.116). In particular, there was a significant interaction between attended orientation × perceived orientation (F(1,19) = 9.335, p = 0.007, η<sub>p</sub><sup>2</sup> = 0.329) in the Ping session, but not in the No-Ping session (F(1,19) = 0.017, p = 0.898, η<sub>p</sub><sup>2</sup> = 0.001). These above-mentioned statistical results were reported in the original texts. In addition, this three-way mixed ANOVA (session × attended orientation × perceived orientation) on Mahalanobis distance in V1 revealed no significant main effects (session: F(1,38) = 0.009, p = 0.923, η<sub>p</sub><sup>2</sup> < 0.001; attended orientation: F(1,38) = 0.116, p = 0.735, η<sub>p</sub><sup>2</sup> = 0.003; perceived orientation: (F(1,38) = 1.106, p = 0.300, η<sub>p</sub><sup>2</sup> = 0.028). We agree with the reviewer that a complete reporting of analyses enhances understanding of the data. Therefore, we have now included the main effects in the main texts (Page 11, Line 233).

      We thank the reviewer for the suggestion regarding the inclusion of descriptive statistics for interaction effects. However, since the data were already visualized in Fig. 3B and 3C in the main texts, to maintain conciseness and consistency with the reporting style of other analyses in the texts, we have opted to include these statistics in the Supplementary Information (Page 5, Table 1).

      Reviewer #3 (Public review):

      (1) The title is "Dual-format Attentional Template," yet the supporting evidence for the nonsensory format and its guiding function is quite weak. The author could consider conducting further generalization analysis from stimulus selection to preparation stages to explore whether additional information emerges.

      We thank the reviewer for this comment. Our approach to investigate whether preparatory attention is encoded in sensory or non-sensory format - by training classifier using separate runs of perception task – closely followed methods from previous studies (Stokes et al., 2009; Peelen et al., 2011; Kok et al., 2017). Following the reviewer’s suggestion, we performed generalization analyses by training classifiers on activity during the stimulus selection period and testing them preparatory activity. However, we observed no significant generalization effects in either No-Ping and Ping sessions (ps > 0.780). This null result may stem from a key difference in the neural representations: classifiers trained on neural activity from stimulus selection period necessarily encode both target and distractor information, thus relying on somewhat different information than classifier trained exclusively on isolated target information in the perception task.

      (2) In Figure 2, the author did not find any decodable sensory-like coding in IPS and PFC, even during the impulse-driven session, indicating that these regions do not represent sensory-like information. However, in the final section, the author claimed that the impulse-driven sensorylike template strengthens informational connectivity between sensory and frontoparietal areas. This raises a question: how can we reconcile the lack of decodable coding in these frontoparietal regions with the reported enhancement in network communication? It would be helpful if the author provided a clearer explanation or additional evidence to bridge this gap.

      We thank the reviewer for this comment. We would like to clarity that although we did not observe sensory-like coding during preparation in frontoparietal areas, we did observe attentional signals in these regions, as evidenced by the above-chance within-task attention decoding performance (Fig. 2 in the main texts). This could reflect different neural codes in different areas, and suggests that inter-regional communication does not necessarily require identical representational formats. It seems plausible that the representation of a non-sensory attentional template in frontoparietal areas supports top-down attentional control, consistent with theories suggesting increasing abstraction as the cortical hierarchy ascends (Badre, 2008; Brincat et al., 2018), and their interaction with the sensory representation in the visual areas is enhanced by the visual impulse.

      (3) Given that the impulse-driven sensory-like template facilitated behavior, the author proposed that it might also enhance network communication. Indeed, they observed changes in informational connectivity. However, it remains unclear whether these changes in network communication have a direct and robust relationship with behavioral improvements.

      We thank the reviewer for the suggestion. To examine how network communication relates to behavior, we performed a correlation analysis between information connectivity (IC) and RTs across participants (see Figure S5). We observed a trend of correlations between V1-PFC connectivity and RTs in the Ping session (r = -0.394, p = 0.086), but not in the NoPing session (r = -0.046, <i.p\</i> = 0.846). No significant correlations were found between V1-IPS and RTs (\ps\ > 0.400) or between ICs and accuracy (ps > 0.399). These results suggests that ping-enhanced connectivity might contributed to facilitated responses. Although we may not have sufficient statistical power to warrant a strong conclusion, we think this result is still highly suggestive, so we now added the texts in the Supplementary Information (Page 8, Line 116121; S5 Fig) and mentioned this result in the main texts (Page 14, Line 292-293).

      (4) I'm uncertain about the definition of the sensory-like template in this paper. Is it referring to the Ping impulse-driven condition or the decodable performance in the early visual cortex? If it is the former, even in working memory, whether pinging identifies an activity-silent mechanism is currently debated. If it's the latter, the authors should consider whether a causal relationship - such as "activating the sensory-like template strengthens the informational connectivity between sensory and frontoparietal areas" - is reasonable.

      We apologize for the confusions. The sensory-like template by itself does not directly refer to representations under Ping session or the attentional decoding in early visual cortex. Instead, it pertains to the representational format of attentional signals during preparation. Specifically, its existence is inferred from cross-task generalization, where neural patterns from a perception task (perceive 45º or perceive 135º) generalize to an attention task (attend 45 º or attend 135º). We think this is a reasonable and accepted operational definition of the representational format. Our findings suggest that the sensory-like template likely existed in a latent state and was reactivated by visual pings, aligning more closely with the first account raised by the reviewer.

      We agree with the reviewer that whether ping identifies an activity-silent mechanism is currently debated (Schneegans & Bays, 2017; Barbosa et al., 2021). It is possible that visual impulse amplified a subtle but active representation of the sensory template during attentional preparation and resulted in decodable performance in visual cortex. Distinguishing between these two accounts likely requires neurophysiological measurements, which are beyond the scope of the current study. We have explicitly addressed this limitation in our Discussion (Page 19, Line 395-399).

      Nevertheless, the latent sensory-like template account remains plausible for three reasons. First, our interpretation aligns with theoretical framework proposing that the brain maintains more veridical, detailed target templates than those typically utilized for guiding attention (Wolfe, 2021; Yu et al., 2023). Second, this explanation is consistent with the proposed utility of latent working memory for prospective use, as maintaining a latent sensory-like template during preparation would be useful for subsequent stimulus selection. The latter point was further supported by the reviewer’s suggestion about whether “activating the sensory-like template strengthens the informational connectivity between sensory and frontoparietal areas is reasonable”. Our additional analyses (also refer to our response to Reviewer 3, Point 3) suggested that impulse-enhanced V1-PFC connectivity was associated with a trend of faster behavioral responses (r = -0.394, p = 0.086; see Supplementary Information, Page 8, Line 116-121; S5 Fig). Considering these findings in totality, we think it is reasonable to suggest that visual impulse may strengthen information flow among areas to enhance attentional control.

      Recommendation for the Authors:

      Reviewer #1 (Recommendation for the authors):

      I hate to suggest another fMRI experiment, but in order to make strong claims about two states, I would want to see the methodological and interpretation confounds addressed. Ping condition - would a tone lead to the same result of sharpening the template? If so, then why? Can a ping be manipulated in its effectiveness? That would be an excellent manipulation condition.

      We thank the reviewer for the comments. Please refer to our reply to Reviewer 1, Point 5 for detailed explanation.

      Reviewer #2 (Recommendation for the authors):

      It is strongly advised that these descriptive statistics related to the interaction effect should be included to facilitate a more effective understanding of their data.

      We thank the reviewer for the comments. We now included the relevant descriptive statistics in the Supplementary Information, Table 1.

      Reviewer #3 (Recommendation for the authors):

      In addition to p-values, I see many instances of 'ps'. Does this indicate the plural form of p?

      We used ‘ps’ to denote the minimal p-value across multiple statistical analyses, such as when applying identical tests to different region groups.

      References

      Aitken, F., Menelaou, G., Warrington, O., Koolschijn, R. S., Corbin, N., Callaghan, M. F., & Kok, P. (2020). Prior expectations evoke stimulus-specific activity in the deep layers of the primary visual cortex. PLoS Biology, 18(12), e3001023.

      Badre, D. (2008). Cognitive control, hierarchy, and the rostro–caudal organization of the frontal lobes. Trends in Cognitive Sciences, 12(5), 193-200.

      Barbosa, J., Lozano-Soldevilla, D., & Compte, A. (2021). Pinging the brain with visual impulses reveals electrically active, not activity-silent, working memories. PLoS Biology, 19(10), e3001436.

      Battistoni, E., Stein, T., & Peelen, M. V. (2017). Preparatory attention in visual cortex. Annals of the New York Academy of Sciences, 1396(1), 92-107.

      Brincat, S. L., Siegel, M., von Nicolai, C., & Miller, E. K. (2018). Gradual progression from sensory to task-related processing in cerebral cortex. Proceedings of the National Academy of Sciences, 115(30), E7202-E7211.

      Duncan, D. H., van Moorselaar, D., & Theeuwes, J. (2023). Pinging the brain to reveal the hidden attentional priority map using encephalography. Nature Communications, 14(1), 4749.

      Grill-Spector, K., & Malach, R. (2004). The human visual cortex. Annual Review of Neuroscience, 27(1), 649-677.

      Gong, M., Chen, Y., & Liu, T. (2022). Preparatory attention to visual features primarily relies on nonsensory representation. Scientific Reports, 12(1), 21726.

      Fan, Y., Han, Q., Guo, S., & Luo, H. (2021). Distinct Neural Representations of Content and Ordinal Structure in Auditory Sequence Memory. Journal of Neuroscience, 41(29), 6290–6303.

      Harrison, S. A., & Tong, F. (2009). Decoding reveals the contents of visual working memory in early visual areas. Nature, 458(7238), 632-635.

      Jigo, M., Gong, M., & Liu, T. (2018). Neural determinants of task performance during feature-based attention in human cortex. eNeuro, 5(1).

      Kok, P., Failing, M. F., & de Lange, F. P. (2014). Prior expectations evoke stimulus templates in the primary visual cortex. Journal of Cognitive Neuroscience, 26(7), 1546-1554.

      Kok, P., Mostert, P., & De Lange, F. P. (2017). Prior expectations induce prestimulus sensory templates. Proceedings of the National Academy of Sciences, 114(39), 10473-10478.

      Liu, T., Stevens, S. T., & Carrasco, M. (2007). Comparing the time course and efficacy of spatial and feature-based attention. Vision Research, 47(1), 108-113.

      Mongillo, G., Barak, O., & Tsodyks, M. (2008). Synaptic theory of working memory. Science, 319(5869), 1543-1546.

      Peelen, M. V., & Kastner, S. (2011). A neural basis for real-world visual search in human occipitotemporal cortex. Proceedings of the National Academy of Sciences, 108(29), 12125-12130. Priebe, N. J. (2016). Mechanisms of orientation selectivity in the primary visual cortex. Annual Review of Vision Science, 2(1), 85-107.

      Rademaker, R. L., & Serences, J. T. (2017). Pinging the brain to reveal hidden memories. Nature Neuroscience, 20(6), 767-769.

      Rademaker, R. L., Chunharas, C., & Serences, J. T. (2019). Coexisting representations of sensory and mnemonic information in human visual cortex. Nature Neuroscience, 22(8), 1336-1344.

      Serences, J. T., Ester, E. F., Vogel, E. K., & Awh, E. (2009). Stimulus-specific delay activity in human primary visual cortex. Psychological Science, 20(2), 207-214.

      Schneegans, S., & Bays, P. M. (2017). Restoration of fMRI decodability does not imply latent working memory states. Journal of Cognitive Neuroscience, 29(12), 1977-1994.

      Stokes, M., Thompson, R., Nobre, A. C., & Duncan, J. (2009). Shape-specific preparatory activity mediates attention to targets in human visual cortex. Proceedings of the National Academy of Sciences, 106(46), 19569-19574.

      Wolfe, J. M. (2021). Guided Search 6.0: An updated model of visual search. Psychonomic Bulletin & Review, 28(4), 1060-1092.

      Wolff, M. J., Jochim, J., Akyürek, E. G., & Stokes, M. G. (2017). Dynamic hidden states underlying working-memory-guided behavior. Nature Neuroscience, 20(6), 864 – 871.

      Wolff, M. J., Kandemir, G., Stokes, M. G., & Akyürek, E. G. (2020). Unimodal and bimodal access to sensory working memories by auditory and visual impulses. Journal of Neuroscience, 40(3), 671-681.

      Yu, X., Zhou, Z., Becker, S. I., Boettcher, S. E., & Geng, J. J. (2023). Good-enough attentional guidance. Trends in Cognitive Sciences, 27(4), 391-403.