Reviewer #2 (Public review):

Summary:

The manuscript by Kelman and coauthors investigates how viral communities differ in the genes they encode in healthy and degraded coral reef ecosystems. Across 19 viral metagenomes from Central Pacific reefs, the authors assess the frequency of integration/excision genes as a proxy for viral community temperateness and ask whether genes associated with central carbon metabolism covary with signatures of temperateness. The main finding is that viral communities with more temperate-related genes encode more genes from the Entner-Doudoroff pathway and other reactions interpreted as anaplerotic, whereas more lytic-associated viral communities show greater representation of some pentose phosphate pathway, TCA, and redox-associated genes interpreted as cataplerotic. The authors propose a model based on these patterns in which lytic viral metabolism helps suppress bacterial overgrowth on healthy reefs, while temperate viral metabolism may promote microbialization on degraded reefs. The study addresses an interesting and potentially important concept - that viral auxiliary metabolic genes are important components of microbial communities and can affect ecosystem functioning. Linking viral metabolism to coral reef microbialization is a creative conceptual advance. The manuscript is clearly written, and the reported enrichment of anaplerotic genes in temperate-associated viromes is an interesting pattern that could motivate future work on how viral metabolic potential varies across reef states.

Strengths:

(1) The study connects viral lifestyle, central carbon metabolism, bacterial overgrowth, and reef degradation in a framework that could be useful for future studies of coral reef ecosystems and viral ecology. This is an interesting synthesis that links viral auxiliary metabolism to broader questions about microbialization and reef state.

(2) The manuscript is generally clearly organized around a testable prediction: viral metabolic gene content should vary along a lytic-to-temperate viral community gradient. The reported enrichment of anaplerotic genes in viromes with a larger fraction of temperate viruses is a compelling result.

(3) The authors highlight several virus-encoded metabolic genes that may not have been previously reported in viral datasets or genomes. If supported by further validation, these observations could expand the known repertoire of viral metabolic potential.

(4) The modeling helps clarify the feedbacks the authors propose may connect viral lifestyle, bacterial metabolism, and coral reef degradation. It provides a foundation for generating hypotheses about how viral metabolic genes could influence reef microbial dynamics.

Weaknesses:

(1) The main limitation is that the evidence for several key claims remains indirect. The core analysis is based on correlations between metabolic gene frequencies and integration/excision-related genes. This does not demonstrate that the metabolic genes occur in temperate viral genomes, are physically linked to lysogeny genes, are expressed during infection, or alter host metabolism. Thus, the data support an association between VLP-associated metabolic annotations and a community-level temperateness proxy, but not a direct link between temperate phages and these metabolic functions.

(2) It is important not to equate community-level gene frequencies with genome-level or infection-level metabolic programs. A virome may contain more anaplerotic genes overall, but that does not demonstrate that individual viruses reprogram their hosts in an anaplerotic manner nor that infection produces a net anaplerotic effect. Individual viruses may encode both anaplerotic and cataplerotic genes, and a smaller number of cataplerotic genes could have stronger metabolic consequences depending on expression, enzyme efficiency, pathway position, and host context. This is an important limitation that should be acknowledged and, if possible, addressed with contig- or genome-level analyses.

(3) The ecological interpretation assumes that viral infection is strong enough to influence reef-scale bacterial population dynamics. However, the study does not directly measure infection frequency, lysis rates, viral production, burst size, lysogeny frequency, prophage induction, gene expression, or bacterial mortality. If viral mortality or lysogenic conversion were rare in these systems, the observed gene-frequency patterns could have limited ecosystem-level consequences. This makes claims about viral metabolism suppressing bacterial overgrowth, accelerating microbialization, or acting as a conservation lever more speculative than suggested.

(4) There are statistical limitations related to the use of relative gene frequencies. Because genes are normalized as percentages of known genes, the data are compositional. Apparent increases in some categories may partly reflect decreases in others. Bootstrapped Spearman correlations are useful for assessing the robustness of these associations, but they do not address compositionality or multiple testing.

(5) The anaplerotic/cataplerotic classification is central to the manuscript's conclusions and would benefit from more support. The framework is useful, but it depends on both annotation confidence and biochemical context. Sequence-similarity annotations alone may be vulnerable to misannotation, especially for central metabolic enzymes that share conserved domains across functionally distinct proteins. Stronger evidence that key genes contain key functional domains and/or are phylogenetically related to characterized enzymes would help support the proposed functions. In addition, many central carbon enzymes are reversible or context-dependent, so a clearer rationale for each classification would strengthen the interpretation.

Overall, the manuscript presents a valuable hypothesis and highlights new ecological patterns in coral reef viral metagenomes, but falls short of the evidence needed for the strongest claims. The work would be strengthened by analyses that directly link metabolic genes to viral genomes or lysogeny markers, address compositional effects, validate key annotations, and more clearly distinguish observed gene-frequency associations from hypothesized effects on infection, host metabolism, and reef state.

The John & Calvin Podcast has just published a pretty critical review of the article.

Reviewer #1 (Public review):

Summary:

The review by Dorrell and Whittington synthesizes the progress made over the past few years with respect to a normative theory of grid cells. The core question addressed by normative frameworks of grid cells is what primary computational function grid cells serve. The review discusses evidence from mechanistic models and experimental data that point to path integration as the computational function of grid cells, consistent with results from normative models. The main goal of the review is to clarify the normative grid cell theory literature. However, the current version of the article reads at times more like a perspective or opinion article in support of the path integration hypothesis rather than a critical review of normative frameworks in the grid cell literature that contrasts the benefits and limitations, as well as pitfalls and caveats, with other modelling approaches.

Some specific comments are as follows:

(1) Abstract: "The first question quickly attracted an answer: grid cells subserve path integration ..." - I am not sure if this statement is correct. The first grid cell paper by Hafting and Fyhn in 2005 suggested that grid cells are part of a path integration-based map, and the paper emphasizes the map part. It remained unclear, and is still debated, whether grid cells are part of a system performing path integration or whether grid maps reflect the output/result of a path integration process. Other theories about the function of grid cells were brought forward as well. Although the main competing theory is discussed in this review, this review article at times appears more as a perspective or opinion article with a clear bias toward the path integration hypothesis rather than objectively discussing the evidence.

(2) Grid cells may serve multiple functions. What would be the implications for our understanding of grid cells and for interpreting the results of normative models? In general, the review could discuss some pitfalls or caveats of normative models in more detail.

(3) A normative framework can be helpful in two ways: (a) Given sufficient details on biological constraints, a normative model can help identify the computational function of grid cells. If a computational function is given and - under the given simulated biological constraints - grid cells were part of the solution, the results of the model would support the hypothesis that grid cells serve the computational function in question. (b) If a computational function were identified beyond any doubt (e.g., assume experimental data demonstrated that grid cells are necessary and sufficient for path integration), a normative model would help identify biological parameters necessary to produce grid cell firing. Unfortunately, the review falls short in making this clear distinction between (a) and (b) and in discussing important caveats regarding mixing up these two ways. E.g., the neural network model approaches by Sorscher et al. and others have been criticized because they try to achieve two things at the same time: find support for the computational function of grid cells and identify optimal parameters that result in grid cells. But doing both at the same time provides a strong bias in tweaking the parameters in exactly the way you need for the model to produce grid cells as a solution (other solutions may be possible given other parameters), preventing strong conclusions regarding the computational function of grid cells and preventing conclusions about what the parameter choices mean for biological connectivity motifs. These caveats in setting up normative models and interpreting them could be discussed in greater detail.

(4) A common assumption underlying most grid cell models is that head direction is viewed as identical to movement direction. However, head direction can differ at times from movement direction, and entorhinal head direction cells code head direction rather than movement direction (Raudies et al., 2015; 10.1016/j.brainres.2014.10.053). This missing link in how movement direction signals reach and inform grid cells could be discussed.

(5) "Knowing that one neuron in a module is active and that you make a movement north uniquely determines which neuron in that module should be active next" - I agree that this rule follows from the fact that grid cells within one module differ in phase but share spacing and orientation. However, I am surprised that the authors do not also make the argument here for the value of a normative model. Rebecca R.G. et al. (10.7554/eLife.96627) use exactly the rule cited above as a normative function. They demonstrate that this rule begets grid cells. Isn't this a prime example of how a normative approach can contribute to scientific inquiry? First, a hypothesis about a computational function is derived from experimental data. And in turn, using a normative framework, the experimental data are derived from the computational function (under appropriate biological results). The paper is discussed later together with Nicolai Waniek's work (10.1162/neco_a_01255). However, in my opinion, their work seems to be somewhat misrepresented in that later paragraph. E.g., velocity is still required as an input to determine which neuron should be active next, neurons do not need to be binary units, and space is not discretized beyond the fact that space is encoded by neurons with spatial firing fields.

Reviewer #2 (Public review):

Summary:

This review by Dorrell and Whittington covers a number of aspects related to normative modeling of grid cells. They begin by discussing key experimental insights on grid cell phenomenology. Then, they discuss how grid cells can be used to perform path integration and how they size up as efficient codes of space. These two sections then lead the authors to discuss how combining path integration and efficient coding objectives leads to models of axis-aligned grid cells in a single module. Discussion on non-linear objectives leading to multi-modules is presented. The review ends with several outstanding questions and an optimistic outlook of how normative models (particularly, task-optimized RNNs) can be used as tools for advancing understanding in neuroscience.

Strengths:

(1) The review is timely and covers an area that has seen a lot of recent activity. This discussion around many of the different results (and kinds of models), I think, will be generally helpful for the field.

(2) Although I think the story could be a little more coherently made (see below), in general I enjoyed the author's flow from efficient coding -> efficient coding + path integration -> efficient coding + path integration + non-linear objective. This framing supports the specific conclusion the authors arrive at.

(3) I also really liked the message that the review made of how normative modeling, despite some of its challenges/limitations, can be used effectively in neuroscience. The discussion of cycling between "experimental" modeling (e.g., vanilla RNNs) and theoretically-grounded models was nice, and I think it helps demonstrate the value of this approach.

(4) Showing how the metric loss could be seen as a bandpass filter (Figure 3C) was nice and a contribution of the review.

(5) While the focus of P4 (conjunctive HD-grid cells) felt initially a little cast aside, the discussion around "brain and task-optimised RNNs with standard architectural choices use fundamentally different path-integration mechanism" was nice and I think helpful for steering the community to an interesting open problem.

(6) Identifying how "non-linear functionality" can lead to multi-modules was nice and not something that I have seen as clearly presented before.

Weaknesses:

(1) The authors view the experimental evidence for grid cells being linked to path integration as "specific and strong" and that the " key computational feature that defines entorhinal cortex [is] path-integration". I think experimentalists (at least the ones I work with) would push back on that. First, it's hard to isolate path integration in rodent experiments. So while Gil et al. (2018) did about as good a job as you could do, there are still other interpretations of the results that are not purely path integration dependent. And second, as the authors point out later in the review, there is experimental work finding that grid cells are disrupted in large environments and 3D. Path integration certainly happens (to some extent) in these spaces, which begs the question of how it is achieved with weakened grid coding. Thus, I think reducing the claims about how strongly grid cells are experimentally linked to path integration is called for.

(2) The authors introduce the idea of efficient coding of space and discuss how grid cells are not optimal. It is later clarified (Sec. 5.3) that multi-module codes can be efficient (even if not the most optimal). I was confused reading Section 3, because in Section 2 the multiple modules are discussed, but then in Section 3, they are dropped, and only a single module is being considered. Equation 2 was also a little confusing to me. Alpha is not defined, and I would have thought that it would be x^Tx' - g(x)^T g(x') and not x^Tx' g(x)^T g(x'). Given that there is no page limit here, I think a little more detail in Section 3 would be helpful.

(3) In Section 3, the authors make use of P2 (translation invariance within a module) to rule out (or, at least, question) certain models/approaches. While this is certainly a standard assumption made in theoretical work, it is not very well supported by experimental findings. In particular, Diehl et al. (2017), Ismakov et al. (2017), and Dunn et al. (2017) all found that individual grid fields systematically vary in their peak firing rate. In addition, Redman et al. (2025) found that, within a given module, there was a small but robust diversity of grid orientations and spacings. These suggest that grid cells within a single module may actually be able to encode properties of local space and give some support to normative models that find efficient space coding with grid cells by finding non-axis-aligned grid fields. I think this is all important to mention because: a) it provides more biological nuance to the question about spatial coding; b) it provides more ways in which to test models. For instance, in Redman et al. (2025), the Sorscher et al. (2022) model was shown to produce variability in grid properties that loosely matched what was found in real data. For tests like this (e.g., how much does a model reproduce variability in grid firing field peak rates), I think it is going to be important for continuing to evaluate models.

(4) The focus of the review, I know, is grid cells, but of course, grid cells are part of the MEC and the larger hippocampal network. I totally understand, at some level, you have to make a decision of what to model, but it seems that there are other functional classes of neurons (border cells, head direction cells) that all play an important role in path integration. And while the models the authors consider at the end of the review capture properties of grid cells really well, they do so at the cost of not modeling anything else. The authors mention this in the context of the models not capturing conjunctive grid-head direction cells, but I think the point is a deeper one, and more discussion of at what level it makes sense to consider grid cells only is important.

(5) As I mentioned in the Strengths section, I did enjoy the flow of the paper on how path integration + efficiency is needed to get grid single modules and path integration + efficiency + non-linearity is needed to get multiple grid modules. This creates the story that adding more of these theory-driven constraints helps lead to more "accurate" models of grid cells. But one alternative view is that, if path integration + efficiency is enough to get a single grid module (but only a single grid module), then maybe the utility (or need) of multiple grid modules comes from something else. That is, instead of saying "we need more constraints to get multiple modules", it could be evidence for "we need to re-think whether multiple modules might need a different theory to explain". While I understand this is a big picture question that maybe isn't entirely fair to ask of the authors, I think: 1) the authors do a nice job of positioning their review as a kind of discussion on what normative modeling can provide to neuroscience, so having this discussion on when the failure of a model to capture ALL aspects of the biological features motivates further constraints as opposed to a new approach, would be useful; 2) this question connects with the title of the paper, i.e. "what is the question?"

Reviewer #3 (Public review):

Summary:

The authors present an extensive review of the literature on normative grid cell theory, asking what kind of cost function might be minimized by the entorhinal grid cell code. The authors show which of the main features of grid cells emerge from combinations of terms in a cost function that optimizes for spatial fidelity, biological plausibility, and path integration. They conclude by outlining potential future directions for the field.

Strengths:

The structure of the review makes it particularly useful for researchers who are familiar with grid cells but not necessarily with normative models. Equations are kept to a minimum and are usually explained conceptually.

Weaknesses:

I identified one main weakness, related to the fact that the introduction to experimental results around grid cells and what they allow us to conclude is less nuanced than the rest of the review. However, since this is not the main focus of the manuscript, I consider this a secondary limitation.

The review organizes the current literature on the subject within a coherent conceptual framework, helping to define possible paths forward for the field.

Reviewer #1 (Public review):

Summary:

Extracellular electrophysiology datasets are growing in both number and size, and recordings with thousands of sites per animal are now commonplace. Analyzing these datasets to extract the activity of single neurons (spike sorting) is challenging: signal to noise is low, the analysis is computationally expensive, and small changes in analysis parameters and code can alter the output. The authors address the problem of volume by packaging the well-characterized SpikeInterface pipeline in a framework that can distribute individual sorting jobs across many workers in a compute cluster or cloud environment. Reproducibility is ensured by running containerized versions of the processing components.

The authors apply the pipeline in two important examples. The first is a thorough study comparing the performance of two widely used spike-sorting algorithms (Kilosort 2.5 and Kilosort 4). They use hybrid datasets created by injecting measured spike waveforms (templates) into existing recordings, adjusting those waveforms according to the measured drift in the recording. These hybrid ground truth datasets preserve the complex noise and background of the original recording. Similar to the original Kilosort 4 paper, which uses a different method for creating ground truth datasets that include drift, the authors find Kilosort 4 significantly outperforms Kilosort 2.5. The second example measures the impact of compression of raw data on spike sorting with Kilosort 4, showing that accuracy, precision, and recall of the ground truth units is not significantly impacted even by lossy compression. As important as the individual results, these studies provide good models for measuring the impact of particular processing steps on the output of spike sorting.

Strengths:

The pipeline uses the Nextflow framework, which makes it adaptable to different job schedulers and environments. The high-level documentation is useful, and the GitHub code is well organized. The two example studies are thorough and well-designed and address important questions in the analysis of extracellular electrophysiology data.

Weaknesses:

There are no major weaknesses in the revised manuscript. While no data analysis pipeline can cover the needs of all experiments, the authors have added and significant flexibility in the pipeline. Even experimenters who might opt for a simpler pipeline will benefit from this work as a model.

Reviewer #2 (Public review):

Summary:

This work presents a reproducible, scalable workflow for spike sorting that leverages parallelization to handle large neural recording datasets. The authors introduce both a processing pipeline and a benchmarking framework that can run across different computing environments (workstations, HPC clusters, cloud). Key findings include demonstrating that Kilosort4 outperforms Kilosort2.5 and that 7× lossy compression has minimal impact on spike sorting performance while substantially reducing storage costs.

Strengths:

(1)Extremely high-quality figures with clear captions that effectively communicate complex workflow information.

(2) Very detailed, well-written methods section providing thorough documentation.

(3) Strong focus on reproducibility, scalability, modularity, and portability using established technologies (Nextflow, SpikeInterface, Code Ocean)

(4) Pipeline publicly available on GitHub with documentation.

(5) Clear cost analysis showing ~$5/hour for AWS processing with transparent breakdown.

(6) Good overview of previous spike sorting benchmarking attempts in the introduction

(7) Practical value for the community by lowering barriers to processing large datasets.

Weaknesses

No significant weaknesses. The authors have responded to all my review critiques and suggestions.

Reviewer #3 (Public review):

Summary:

The authors provide a highly valuable and thoroughly documented pipeline to accelerate the processing and spike sorting of high-density electrophysiology data, particularly from Neuropixels probes. The scale of data collection is increasing across the field, and processing times and data storage are a growing concern. This pipeline provides parallelization and benchmarking of performance after data compression that helps address these concerns. The authors also use their pipeline to benchmark different spike sorting algorithms, providing useful evidence that Kilosort4 performs the best of out the tested options. This work, and the ability to implement this pipeline with minimal effort to standardize and speed up data processing across the field, will be of great interest to many researchers in systems neuroscience.

Strengths:

The paper is very well written and clear. The accompanying GitHub and ReadTheDocs are well organized and thorough. Benchmarks are exceptionally well applied to support the authors' claims, and it is clear that the pipeline has been very thoroughly tested and optimized by users at the Allen Institute for Neural Dynamics. The pipeline incorporates existing software and platforms that have also been thoroughly tested (such as SpikeInterface), so the authors are not reinventing the wheel, but rather putting together the best of many worlds. In the latest revision, the authors add a nice analysis showing that compression mostly affects the lowest SNR units. This is a great contribution to the field and it is clear the authors have put a lot of thought into making the pipeline as accessible as possible.

Weaknesses:

None noted. The authors have addressed all previous questions and requests for clarification.

Reviewer #1 (Public review):

Summary:

This manuscript examines how Streptococcus pyogenes regulates expression of the virulence factor SpeB in response to both bacterial and host-derived cues. The authors propose that Vfr acts as a repressor of speB expression and that degradation of Vfr by SpeB or by neutrophil-derived proteases relieves this repression. This creates a model in which S. pyogenes can sense proteolytic activity during infection and use that information to tune virulence factor expression.

Strengths:

The main strength of the study is the bacterial regulatory mechanism. The dual reporter system provides a useful way to follow speB and hasABC expression, and the genetic analysis of known regulators helps validate the system. The media-swap experiments, recombinant Vfr experiments, and SpeB-mediated degradation of Vfr support the conclusion that Vfr represses speB and that proteolysis can relieve this repression. The finding that SpeB can degrade Vfr is particularly interesting because it suggests an autoregulatory mechanism that could reinforce SpeB expression once it has been initiated.

Weaknesses:

The host side of the model is less completely supported. The authors show that neutrophil lysates and protease-containing fractions can induce the speB reporter and degrade Vfr, which supports the idea that neutrophil-derived proteases can affect this circuit. However, the in vivo interpretation relies heavily on PAD4-deficient mice to implicate neutrophil extracellular traps. PAD4 deficiency is a useful perturbation, but it does not by itself distinguish loss of extracellular trap formation from changes in neutrophil recruitment, survival, degranulation, phagocytosis, oxidative killing, or other neutrophil death pathways. As a result, the current data support a role for neutrophil-associated proteolytic activity more strongly than they support a specific role for extracellular traps. This distinction is important for interpreting the central model. The bacterial circuit is well developed, but the host-derived cue remains somewhat underdefined. If the relevant signal is extracellular protease activity more broadly, then the model is still interesting, but the conclusion should be framed around neutrophil-derived proteolytic stress rather than extracellular traps specifically. If extracellular traps are the key in vivo source of protease exposure, then additional evidence would be needed to separate that mechanism from other neutrophil effector functions that remain intact in PAD4-deficient cells.

Overall:

This is a valuable study with solid evidence for a bacterial protease-sensing regulatory mechanism controlling SpeB expression. The work should be useful to investigators interested in bacterial virulence regulation, host-pathogen interactions, and how pathogens integrate immune-derived cues during infection. The impact of the study would be stronger if the host-derived signal were defined more precisely, but the bacterial Vfr-SpeB circuit provides a compelling framework for thinking about how S. pyogenes links proteolytic activity to virulence gene expression.

Reviewer #2 (Public review):

Summary:

The study examines how Streptococcus pyogenes integrates bacterial and host-derived signals to regulate SpeB, proposing that Vfr acts as a protease-sensitive repressor whose degradation relieves repression of speB. The authors further suggest that neutrophil-derived serine proteases, including those associated with inflammatory conditions, may promote this transition, and thereby counterbalance LL-37/CovRS-associated suppression of speB. The conceptual framework is interesting and potentially important for understanding how host inflammation feeds into bacterial virulence regulation.

Strengths:

The work addresses a biologically significant question and does so using a broad and generally well-integrated experimental approach, including bacterial genetics, reporter assays, recombinant protein analyses, neutrophil-derived material, human blood infection, and mouse infection models. A particular strength is the effort to connect host inflammatory processes to bacterial regulatory behavior, which gives the study conceptual reach beyond a narrow mechanistic observation. The data support the view that Vfr is relevant to speB control and that neutrophil-associated protease activity may influence this pathway.

Weaknesses:

The main limitations are mechanistic. The physiological form, localization, and abundance of Vfr are not sufficiently defined to support the proposed model at full strength, and the evidence that Vfr functions as a SpeB-labile repressor under biologically relevant conditions remains incomplete. The relationship between Vfr and the broader RopB/SIP regulatory framework is also not yet firmly established. In addition, the reporter system is not yet benchmarked closely enough against endogenous SpeB protein output, and its growth-phase dependence is insufficiently resolved, which makes it difficult in some settings to distinguish promoter activity from mature protease production. The neutrophil protease component is likewise not defined beyond a general serine protease signal, and the potentially important LL-37/CovRS/Vfr connection is underdeveloped in the main text. Overall, the conceptual advance is promising, but several of the central mechanistic claims would benefit from more direct experimental support and more cautious framing.

Reviewer #3 (Public review):

Summary:

SpeB is a cysteine protease secreted during infection by Streptococcus pyogenes (Spy). SpeB has been extensively investigated for its role in pathogenesis, which involves proteolytic processing of both Spy virulence factors and host proteins. Regulation of speB expression is complex and includes growth phase regulation, a quorum-sensing system, the transcription factor RopB, and the global regulatory system CovRS (CsrRS). Guerra et al now attempt to refine the current model of regulation of SpeB expression, focusing on the Spy protein Vfr, which has been suggested previously to act as a negative regulator of SpeB expression. In the current study, neutrophil lysates (representing proteases released during NETosis) are shown to degrade Vfr and to relieve repression of SpeB. At high cell density, SpeB itself also degrades Vfr, which may allow autoregulation of SpeB expression. These observations are unsurprising as the broad protease activities of both neutrophil proteases and SpeB are well known. Nonetheless, the data presented fill in additional details in our understanding of the complex regulation of an important Spy virulence factor.

Strengths:

(1) Construction of a GFP reporter strain provided a facile methodology for tracking speB promoter activity in a variety of experimental setups.

(2) A Vfr deletion mutant was a useful tool to investigate the role of Vfr in SpeB regulation, and mutants in speB and ropB were important controls.

(3) Experiments using neutrophil lysates in vitro, as well as in vivo studies of mice depleted of neutrophils with anti-Ly6G or in PAD4-/- mice (that cannot form NETs) support the hypothesis that neutrophil proteases derepress speB expression by degrading Vfr.

Weaknesses:

(1) The introduction and all the experiments in Figure 1 focus on CovRS, which turns out to be largely tangential to the overall story developed by the rest of the study. On the other hand, the complex and well-studied regulation of speB expression by RopB and the SIP quorum-sensing system is only minimally described. A better framing would be a more detailed introduction to the current model of speB/RopB/SIP/quorum sensing/growth phase regulation. CovRS could be introduced later as its relevance is really just to show that neutrophil lysates or NETs do more than simply providing LL-37, which signals through CsrS, as another regulator of speB expression.

(2) Vfr, as the central focus of the paper, also deserves a more thorough introduction to provide context for the study. For example, reference 19 (Shelburne et al, 2011) showed reduced transcription of speB in a vfr mutant, an effect that could be complemented by expressing vfr or a 39-aa N-terminal fragment in trans. That study presented evidence that the N-terminal peptide binds to RopB, which may prevent RopB from upregulating SpeB expression. Do the authors concur with that model? As it stands, the discussion and model in Figure 1A imply a direct regulatory effect of Vfr on speB expression rather than an indirect one through regulation of RopB. If direct regulation of speB by Vfr is a consideration, it should be investigated more thoroughly, e.g., by promoter-binding assays, CHIP-seq, etc.

(3) Use of single-cell flow cytometry generally confirmed results observed in batch culture. The authors also comment repeatedly on the heterogeneity of individual cell fluorescence representing both speB and has operon expression. However, the reason(s) for heterogeneity in gene expression are not explored, e.g., differences in individual cell growth rate in batch culture, variable loss of reporter plasmid during infection experiments, etc).

(4) Lines 116-118 and Figure 3C: Incubation of recombinant Vfr with Spy Dvfr reduced SpeB expression, but the degree of suppression is modest compared to that seen in wild-type Spy. How does the concentration of rVfr added compare to that present in the culture fluid of wild-type Spy? (Also, the concentration of rVfr used is unclear: the figure says 3 µg/ml and the legend says 0.3 mg/ml, i.e., 300 µg/ml).

(5) Lines 125-126: "...the Vfr structure contains several potential protease SpeB cleavage sites..." The role of Vfr in degrading SpeB could be clarified by identifying the predicted cleavage products, e.g., by mass spec, after co-incubation of the two recombinant proteins.

(6) Lines 122-124: "Notably, speB expression in Spy Dvfr is unaffected by LL-37 or MgCl2, further validating its [Vfr's?] dominance over CovRS regulation." This statement is an oversimplification and is potentially misleading: LL-37 is degraded by SpeB (Nyberg et al, JBC 2004), which likely explains why the addition of LL-37 fails to signal through CovRS to repress SpeB in Spy Dvfr since SpeB is produced continuously in that strain. By contrast, SpeB is only produced during the stationary phase in the wild type, so LL-37 remains active throughout the exponential phase and represses SpeB expression. The response to the CovRS ligand MgCl2 is similar (or greater) in Spy Dvfr compared to wild type (Figure S2C).

(7) Lines 153-154 and Figure 6E: Growing wild type Spy in the presence of neutrophil lysates with or without a protease inhibitor stimulated or repressed speB expression in a manner consistent with degradation (or not) of Vfr. It would be confirmatory and informative to do the same experiment with the Spy Dvfr strain.

(8) Clarity of writing could be improved, particularly by eliminating pronouns of indefinite reference (it, its, this) in contexts in which the subject is ambiguous (examples at lines 62, 89, 111, 114, 115, 123, 183, 190, 193, 204, 205, 210, 217, 221, 222, 224).

Reviewer #1 (Public review):

Summary:

The authors presented a simplified E. coli cell-free protein synthesis (eCFPS) system reduces core reaction components from 35 to 7, improving protein expression levels. They also presented a "fast lysate" protocol that simplifies extract preparation, enhancing accessibility and robustness for diverse applications.

Strengths:

The authors present a valuable new protocol for eCFPS, which simplifies its application.

Weaknesses:

The authors provide data for optimization but offer insufficient explanation of the fundamental mechanisms underlying the phenomenon based on data.

Comments on revised version.

The authors have satisfactorily addressed the concerns raised by the reviewers. However, the mechanistic basis of the observed performance gain remains insufficiently substantiated. The attribution of this improvement to enhanced transcription is currently speculative. This point could be directly tested by quantifying mRNA levels, for example, using real-time PCR, in both the initial and optimized systems. Such analysis would significantly strengthen the mechanistic interpretation of the results.

Reviewer #2 (Public review):

Summary:

The authors have made a convincing argument that the current system of in vitro translation using E. coli extracts can be significantly optimized to work with much lesser components, while maintaining activity. They have showcased their improved activity using not only physical but also functional readouts.

Strengths:

The experiments are designed in a very logical and easy to understand manner, which makes it easier not only to follow the paper, but also reproduce the results. Functional assays with the synthesized proteins are a good way to demonstrate functionality and applicability of the system. They also benchmark their system against a commercial kit to show superior performance of their system.

Weaknesses:

The production of the lysate requires special instrumentation, limiting accessibility.

Comments on revised version:

Thank you to the authors for addressing the concerns both textually and experimentally. This work has significant value.

Reviewer #3 (Public review):

Summary:

The authors aimed to overcome the challenges associated with complex, conventional prokaryotic cell-free protein synthesis (CFPS) systems, which require up to thirty-five components, by developing a streamlined and efficient E. coli CFPS platform to encourage broader adoption. The main objective was to reduce the number of reaction components from thirty-five to seven, while also developing an accessible 'fast lysate' preparation protocol that eliminates time-consuming runoff and dialysis steps. The authors also sought to demonstrate the robustness and translational quality of this streamlined system by efficiently synthesising challenging functional proteins, including the cytotoxic restriction endonuclease BsaI and the self-assembling intermediate filament protein vimentin.

Strengths:

This study presents several key strengths of the optimised E. coli cell-free protein synthesis system in terms of its design, performance and accessibility.

- The reaction mixture has been dramatically simplified, with the number of essential core components successfully reduced from up to thirty-five in conventional systems to just seven.

- The "fast lysate" protocol is a significant advance in terms of procedure.

- The system's ability to synthesise challenging, functional proteins is evidence of its robustness.

Weaknesses:

(1) Title: "A simplified and highly efficient cell-free protein synthesis system for prokaryotes".

- This title is misleading since one would expect a simplified and highly efficient cell-free protein synthesis system to yield similar protein levels compared to current cell-free protein synthesis systems. What this study shows is that the composition of cell-free protein synthesis systems can be simplified while maintaining a certain level of protein synthesis. Here, optimisation does not involve maintaining protein synthesis yield while simplifying the cell-free protein synthesis system; rather, it involves developing a simplified cell-free protein synthesis system. As mentioned in my comments below, this study lacks a comparison of protein levels with a typical cell-free protein synthesis system.

- What do the authors mean by "highly efficient"? Highly efficient compared to what experimental conditions? If one is interested by the yield of protein synthesis, is this simplified system highly efficient compared to current systems?

(2) Figure 1, 3-5:

- What do relative luciferase units represent? How are these units calculated?

- In this system, the level of expression depends mainly on the level of NLuc transcripts and the efficiency of NLuc translation. How did the authors ensure that the chemical composition of the different eCFPS buffers only affected protein translation and not transcript levels? In other words, are luciferase units solely an indicator of protein synthesis efficiency, or do they also depend on transcription efficiency, which could vary depending on the experimental conditions?

- How long were the eCFPS reactions allowed to proceed before performing the luciferase activity measurement? Depending on the reaction time, the absence or presence of certain compounds may or may not impact NLuc expression. For example, it can be assumed that tRNA does not significantly affect NLuc levels over a short period of time, and that endogenous tRNA in the lysate is present at sufficient concentrations. However, over a longer period of time, the addition of tRNA could be essential to achieve optimal NLuc levels.

- The authors show that tRNA and amino acids are not strictly essential for the expression of NLuc, likely due to residual amounts within the cell lysate. However, are the protein levels achieved without added amino acids and tRNA sufficient for biochemical assays that require a certain amount of protein? It is important to note that the focus here is on optimising the simplicity of the buffer rather than the level of protein expression. In fact, the simplicity of the buffer is prioritised over the amount of protein produced. This should be made clear.

- How would the NLuc level compare if all the components were optimised individually and present in an optimised buffer, compared to a buffer optimised for simplicity as described by the authors?

(3) Line 71, Streamlining eCFPS: removal of dispensable components. This title is misleading because it creates the false impression that proteins can be produced in vitro without the addition of certain compounds. While this is true, the level of protein produced may not be sufficient for subsequent biochemical analyses. This should be made clear.

(4) Figure 2: In the legend, change "(A) Protein expression levels of the eCFPS system measured at varying concentrations of KGlu and MgGlu2" to "(A) Protein expression levels of the eCFPS system using an Nanoluciferase (NLuc) reporter DNA measured at varying concentrations of KGlu and MgGlu2".

(5) Lanes 302-303: "The thorough optimization of the seven core components was a critical step in achieving high protein expression levels". What are "high expression levels"? Compared to what?

Comments on revised version.

The authors have adequately addressed my previous concerns.

Reviewer #1 (Public review):

Summary:

Pecak et al have deciphered the conformational dynamics of a heterodimeric model ABC transporter, TmrAB, a functional homolog of the human antigen transporter TAP, using single molecule Forster resonance energy and fluorophores attached to residues at either nucleotide binding domains or periplasmic gate. The analysis not only differentiated ATP-free and bound states, but also enabled the real time monitoring of protein conformational changes precisely dissecting transport cycles and resolving transient intermediates. This study is absolutely significant in providing and establishing a general pipeline delineating the conformational dynamics in heterodimeric ABC transporters.

Strengths:

The scientific study is very well documented for experimental design, results and conclusions supported by the experimental data. Authors have determined the conformational dynamics of TmrAB across different ATP concentrations including physiological ones and resolved an outward open state and other conformational states consistent with previous cryoEM and DEER studies. Authors have also mentioned limitations in the study.

Comments on revised version.

Authors have worked on most of the revisions stated in previous feedback and included in the newer version, which has been significantly improved. Other comments have been described to be out of scope from this study.

Reviewer #2 (Public review):

In their manuscript entitled 'ATP-driven conformational dynamics reveal hidden intermediates in a heterodimeric ABC transporter', Pečak et al. use elegant single-molecule FRET experiments in detergent to investigate the heterodimeric ABC transporter TmrAB. By combining simulations of the transporter's accessible volume with elegant trapping strategies, the authors identify an unresolved outward-facing open state and conclude that it is usually obscured by a rapidly interconverting ATP-bound ensemble. Overall, the study demonstrates that smFRET can resolve the short-lived intermediate states of TmrAB and potentially other ABC transporters that are obscured in ensemble measurements.

It is a very interesting study that highlights the power of combining high-resolution structural information with spectroscopic approaches. I had three major concerns with the original version, all of which have been addressed by the authors in this revised version.

Reviewer #1 (Public review):

WIPI1 is a PROPPIN family protein that has been implicated in Retromer-mediated membrane fission events. Although the cargos that it has been tested to be important for are diverse, one of the cargos that is unaffected is Beta1-Integrin. This leads the authors to assess another PROPPIN family protein - WIPI2, which is a homolog of WIPI1. KD using siRNA is effective and had no consequences on LAMP1, EGFR trafficking or GLUT1 trafficking. Integrin-B1, however, had a large and significant defect in its recycling from the endosome, with a clear endosomal colocalisation. Complementation experiments with WT WIPI2 recovered the phenotype, but various mutant WIPI2 complements resulted in elongated tubules, and there was also a dominant negative effect of the mutant. Integrin is a classic retriever cargo, so the authors rationalise that WIPI2 may be playing a role with retriever that WIPI1 plays with retromer. To assess this, they perform a set of immunoprecipitations. SNX17, the retriever-associated sorting nexin, co-IPs with WIPI2 in a VPS26C-dependent manner. VPS26C but not VPS26 co-IPs with WIPI2, and the reciprocal with WIPI1. These interactions were not present for the FSSS mutation of WIPI2. WIPI2 localises to Rab11 endosomes mainly, as does retriever. Mutations of WIPI2 not only affected WIPI2 localisation, but also VPS35L mutations, indicating that there is a functional relationship between the two.

Comments on revised version.

The reviewers have responded appropriately to all the points. I have no remaining concerns.

Reviewer #3 (Public review):

Summary:

The manuscript of Mayer and colleagues analyzes the function of WIPI proteins in mammalian cells. The authors identified previously CROP as a complex consisting of WIPI1 and the retromer complex, primarily in yeast cells. In mammalian cells, both WIPI1 and WIPI2 exist, whereas retromer has a homologous complex termed retriever. The now find that WIPI2 can form a complex with retriever subunits. They name this complex CROP2. Their data further indicate that CROP2 and CROP1 have distinct substrate specificities as knock down of CROP2 subunits affect beta1 integrin sorting, whereas knock down of CROP1 affects EGFR and GLUT1. The further identify a similar sequence (FSSS) in both WIPI1 and WIPI2, which is required for their specific binding to retromer and retriever.

Strengths:

CROP1 and CROP2 seem to use similar features for their formation, and have different substrates, which is convincingly shown.

Weaknesses:

The analysis lacks information that this is a complex as claimed. It can be deduced from the immunoprecipitation analysis.

Comments on revised version.

The authors answered my questions and adjusted the text accordingly. Figure 10 was not part of the submitted version. It should be checked by the editor.

Reviewer #1 (Public review):

Summary:

This paper reports the findings of a neuroimaging experiment that tested the hypothesis that the cortex, specifically early visual areas, reinstates the content from single events during our lives. The researchers tested this hypothesis by presenting to-be-remembered pictures of objects at spatial locations on the computer screen and then testing subjects with both recall and recognition. They show that during memory testing, the spatial location of the object can be decoded from the pattern of cortical BOLD responses measured with fMRI. They go on to show that the spatial tuning is higher during recognition than recall, that the tuning is correlated with memory retrieval accuracy, and that the retrieved precision is predicted by the encoded precision, particularly in the higher-level visual areas. Thus, the paper finds evidence of cortical reinstatement of details from a single event in a human life.

Strengths:

This is a strong manuscript that I have had the luxury of commenting on during a round of review at another prestigious journal. As a result, the authors have already made changes to address previous comments about highlighting the complementary learning systems approach more to motivate the alternative prediction that the cortex should only show evidence of reinstatement after repeated presentations. In addition, the authors have fleshed out the discussion of working memory in this task. They also revised their review of the literature to include citations suggesting spatial locations are normal parts of our episodic representations, likely obligatory in nature, as my group and others have argued in completely unrelated work. I applaud the authors for being responsive to a previous round of review and using the comments to address relatively minor issues with the paper, even though they moved on to a different journal. Thus, I found the paper even stronger than at first approach, and at first blush, the results were intriguing and the paper well written.

Weaknesses:

There is a logical perspective in the narrative that seems to unnecessarily weaken the paper. The paper shows evidence consistent with the conclusion that mnemonic representations are contained in early visual cortex, but then argues that those representations are not actually stored therein. For example, the first half of the last sentence of the conclusions (see page 19 of the manuscript). I understand the perspective that subcortical mechanisms must be involved in the act of retrieval, given the neuropsychology and other evidence. But if storage is elsewhere with the same fidelity so as to code this information, then how would such a memory system work? The MTL neurons would need to have the real, precise representation of all the orientations encoded at all the retinotopic locations, a mirror to V1 in terms of precision, because that's the actual memory representation being retrieved, so its fidelity will be limited by what is stored in the file, so to speak. Then, at retrieval, the paper proposes that the brain just reactivates the encoding context in V1 to help with the response output and ensure the precision of the behavioral responses. This must mean that the hippocampus/MTL has cells and networks with tuning functions that match the precision in all the cortical sensory systems that they are integrating context across, given the episodic memory models like Polyn and colleagues (2009, Psych Rev). So, there are little MTL maps that are completely redundant with V1, M1, A1, S1, etc.? Why such redundancy?

Why not propose that what the subcortical systems do is to encode a unique pattern for that episode, that is separated from others, that just links (or provides pointers to, in computer science jargon) the contextual details stored in the cortical networks themselves? In this way, we can explain why neglected patients also neglect their memories of the town square. This has always been my interpretation of the results of the Polyn et al. (2006, Science) paper and the models tested with those whole-brain results. That is, you see widespread cortical context reinstatement during (one-shot) free recall events that included visual selective cortex for faces when faces were being recalled, but included a broad network, probably V1, and activating sounds in A1, body posture in M1, etc., though the latter three examples did not discriminate between categories of memoranda, in their experiments. Given that you show that activity in V1 during retrieval looks like it is being used, you should propose that the early cortex really participates in memory storage functions. V1 neurons are wired up to neurons of other selectivities in a competitive network with plastic synaptic connections. How would experience be prevented from changing activity in the cortex? Yes, cortical changes slow after the critical periods, as studied in the classic eye suturing experiments to study ocular dominance, but changes in cortical representations do not stop with maturity, with the pinwheel centers looking like they are context sensitive, thus, changing rapidly to events across time (Okamoto, Ikezoe, et al., 2011, Sci Reports). The brain would need a no-plasticity mechanism, and instead, it looks like the cortex can completely rewire even in adulthood (Buonomano & Merzenich, 1998, Annu Rev Neuro).

I believe that the paper needs to describe the strong/radical interpretation of the current findings; that they are consistent with the view that the entire brain may be a memory structure, with encoding linking representations across sensory cortices. But also activating semantic and lexical systems, emotional networks encoding those aspects of context which we know can sometimes strongly drive effects, a nice prediction that could be made in the discussion/conclusions. Here you are looking at how precise the visual reinstatement is in V1 during retrieval following one exposure. One parsimonious mechanism to explain this effect is that the brain stores details of events using the neurons that do the high-fidelity perception of the event. Given that our goal is to stimulate thinking among fellow scientists so that this paper can be a citation classic, I think the paper should be revised so that it paints a complete picture of the theoretical possibilities of its findings.

Reviewer #2 (Public review):

Summary:

The study aims to show that the early visual cortex is not merely a sensory-perceptual region that encodes stimuli while they are physically present, but also supports the formation and retrieval of long-term episodic memories. Instead, the authors demonstrate that spatially tuned reactivation of early visual cortex after a single encoding event supports memory-guided behavior, such as recalling an object's original location.

Strengths:

The study provides solid evidence that location information for single, trial-unique objects is reinstated in early visual cortex during both recognition and recall, even without explicit spatial demands, and the remembered vs. forgotten analyses link spatial tuning to behavior. The one-shot design and absence of explicit spatial instructions are important strengths that bring the paradigm closer to everyday, incidental episodic experiences and go beyond highly trained cue-target associations.

Weaknesses:

(1) Conceptually, the main findings would appear less surprising without a sharper theoretical contrast. Given basic retinotopic coding, it is natural that object identity and location are jointly encoded when an object is presented at a particular position, so spatially tuned reinstatement in V1-V3 can be interpreted as a reconfirmation of known properties unless more clearly contrasted with theories that emphasize more abstract, position-invariant cortical representations following hippocampal-cortical recoding. As currently framed, the introduction does not fully articulate what existing accounts might predict, or what pattern of results would have challenged those accounts, which somewhat weakens the perceived theoretical payoff.

(2) It also remains somewhat unclear why early visual cortex (V1-V3), specifically, is the critical locus for the spatial information of interest, as opposed to higher-level visual or parietal regions that could also provide a spatial scaffold; clearer rationale and, if possible, control analyses in additional regions would help here.

(3) Since gaze behavior is central to any spatial account, it would be helpful to report basic eye-tracking analyses comparing remembered versus forgotten trials, especially at encoding, to rule out systematic differences in fixation patterns that could contribute to the spatial tuning results.

Reviewer #3 (Public review):

Summary and Overall Evaluation:

This is an elegant paper addressing an important question: whether spatial location is automatically activated during the recall of object memories. Building on prior work that relied on trained or repeated stimuli, the present study uses unique objects with one-time encoding across four spatial locations - a meaningful advance in ecological validity. The experimental design is clean, the data analysis is well-executed, and the reported effects, while small, are intriguing and open up interesting questions about the role of spatial structure in visual memory. Overall, this is a solid contribution, and my comments below are intended to help the authors strengthen the paper further.

Major Comments

(1) Incidental encoding.<br /> Was the memory task fully incidental - that is, were participants unaware that a subsequent memory test would follow encoding? This seems important for interpreting the automaticity claim that is central to the paper's contribution, and should be clarified explicitly.

(2) Spatial extent of the analysis - higher visual regions and negative pRFs.<br /> The analysis appears restricted to regions V1-V3. Have the authors examined higher visual areas as well? This seems like an important omission given that object memory likely engages regions well beyond the early visual cortex. Relatedly, recent work by Adam Steel and colleagues suggests that spatially tuned negative pRFs may play an important role in memory. Have the authors considered examining these? Expanding the analysis in these directions could substantially enrich the findings.

(3) Mechanism - retinotopic or spatiotopic?<br /> The paper makes a compelling case that spatial structure supports memory, but the nature of that spatial structure deserves more discussion. Are the effects retinotopic or spatiotopic in nature? The current design may not be able to fully dissociate these possibilities, but this distinction is theoretically important, and the authors should engage with it directly. Even a careful discussion of what the current data can and cannot tell us on this point would be valuable.

(4) Relationship between encoding failure and retrieval failure.<br /> For trials where memory performance is worse, and the encoding models fail, is there a systematic relationship between how the pRFs fail at object retrieval versus spatial retrieval? In other words, are the pRFs wrongly tuned in the same way at both stages? This analysis could provide meaningful insight into whether object and location retrieval draw on shared spatial representations.

(5) Object shape and spatial mapping.<br /> Real-world objects vary considerably in surface structure and shape, which may affect how cleanly they map onto a specific spatial location. Was this considered in the analysis? What was taken as the correct or peak location for each object, and how was this defined when objects extended across space? Apologies if this was addressed in the methods and I missed it.

(6) Time course of pRF activation.<br /> Is there a way to examine the time course of pRF activation within a trial? Do the spatially tuned responses arise immediately upon retrieval, or do they build up over time? Even a preliminary analysis of this would be of considerable theoretical interest, as it would speak to whether spatial reinstatement is an early automatic process or a later, more deliberate one.

(7) Effect size and functional significance.<br /> The authors acknowledge that the reported effects are very small, which I appreciate. However, this does raise genuine questions about functional significance that I think deserve a more direct response. One approach that would help contextualize the spatial effects would be to compare their magnitude to that of another feature - object identity, for example - to give readers a sense of the relative importance of spatial versus non-spatial information in memory representations. I recognize this may not be straightforward with the current design, but even a brief discussion of how one might benchmark the spatial effects would be helpful.

(8) The attention account.<br /> I found the discussion of attention less than fully convincing. The authors appear to argue against an attentional interpretation of the spatial effects, but it is not clear why participants wouldn't attend to the encoded location during retrieval - particularly in a design with relatively few retrieval cues, where spatial location may be one of the most useful available. The attention account thus seems difficult to rule out on the basis of the current data, and the discussion should engage more seriously with this alternative rather than setting it aside.

(9) Later-remembered versus later-forgotten objects - BOLD signal.<br /> Were later-remembered objects associated with stronger overall BOLD responses during encoding compared to later-forgotten objects, or was the effect specific to the pRF modelling? Clarifying this would help readers understand whether the spatial effects are part of a broader pattern of stronger encoding or something more specific to the spatial reinstatement mechanism.

Reviewer #1 (Public review):

This study examines the mechanisms underlying retinal toxicity associated with certain AAV gene therapy vectors, particularly in the retinal pigment epithelium (RPE) and photoreceptors following expression of transgenes such as GFP. The findings suggest that AAV-related retinal toxicity is driven less by transgene identity itself and more by distinct pathogenic mechanisms, including stress-induced injury in RPE cells and interferon-mediated damage in photoreceptors. The comments are as follows:

(1) The AAV vectors were manufactured in-house, and the production method is described in sufficient detail. However, were any characterization assays performed beyond qPCR-based titer determination, such as vector genome titer, capsid titer, empty/full capsid ratio, sterility, bioburden, endotoxin, mycoplasma, residual host cell DNA, residual plasmid DNA, or residual host cell protein testing? These analyses, particularly those assessing residual impurities and microbial contamination, are critical, as such contaminants may provoke inflammatory responses following subretinal injection. This, in turn, could confound the interpretation of the results, including the identification of the molecular pathways contributing to toxicity as well as the specific role of GFP-associated toxicity. Please provide any characterization information for the AAV vectors.

(2) The study uses contralateral or uninjected eyes as controls, but this choice may not adequately account for changes induced by the subretinal injection procedure itself. Because the earliest assessment of RPE toxicity was performed at 2 weeks post-injection, any injury, inflammation, retinal detachment-related stress, or wound-healing responses triggered by the surgical procedure could have contributed to the observed phenotype. As a result, comparisons to uninjected eyes alone make it difficult to distinguish vector or transgene-specific toxicity from procedure related effects. Inclusion of a more appropriate procedural control, such as sham-injected eyes or eyes injected with vehicle/buffer alone, would have strengthened the study by enabling clearer discrimination between injection-related retinal responses and toxicity attributable to the AAV construct or transgene expression.

(3) The authors used phalloidin staining on RPE-choroid flatmounts to evaluate RPE toxicity, which provides useful information on RPE morphology and structural disruption. However, it would be highly informative to also assess the presence and distribution of subretinal microglia/macrophages, for example, by Iba1 immunostaining, in the same preparations. Specifically, determining whether Iba1-positive cells accumulate in or around areas of RPE dystrophy would help clarify the contribution of local inflammatory responses to the observed pathology. Such analysis could strengthen the interpretation of the toxicity phenotype by revealing whether RPE degeneration is accompanied by focal immune cell recruitment and whether these cells spatially associate with regions of tissue damage. This would also provide additional insight into whether inflammation is likely to be a downstream consequence of RPE injury or a more direct contributor to disease progression, especially in light of publications by Danial Saban's group regarding the characterization of microglia phenotypes using RNA-seq analysis.

(4) The Discussion should also address the anatomical and procedural differences between neonatal and adult mouse eyes, particularly with respect to retinal thickness and the potential impact of subretinal injection-related injury. Because the RPE toxic effects appeared less severe in adult mice, it would be valuable for the authors to consider whether this difference reflects true age-dependent biological susceptibility or, at least in part, differences in the mechanical consequences of the injection procedure. Neonatal retinas are thinner and structurally less mature than adult retinas, which may render them more vulnerable to injection-associated stress, retinal detachment, or secondary tissue injury following subretinal delivery. In contrast, the greater retinal thickness and maturity of the adult eye may provide some degree of resilience to procedural trauma, thereby reducing the apparent severity of RPE damage. Expanding the Discussion to consider these factors would strengthen the interpretation of the age-related differences observed in toxicity and help distinguish vector- or transgene-driven effects from potential confounding effects introduced by the delivery method itself.

Overall, this manuscript presents a detailed and comprehensive analysis of transgene-induced retinal toxicity and makes effective use of multiple mouse models to dissect the contribution of relevant molecular pathways. The study is particularly strengthened by its systematic approach, combining histologic, transcriptomic, and genetic loss-of-function strategies to distinguish the mechanisms underlying toxicity in the RPE versus photoreceptors. By evaluating several knockout mouse lines, the authors can move beyond descriptive observations and begin to assign causality to specific stress and immune signaling pathways, thereby providing important mechanistic insight into AAV-associated retinal injury. These findings are timely and relevant to the broader field of ocular gene therapy, as they highlight the complexity of vector- and transgene-related toxicity and underscore the need for careful pathway-level evaluation during preclinical development.

Reviewer #2 (Public review):

Summary:

Adeno-associated viruses (AAVs) are popular gene therapy vectors, but AAVs can cause toxicity. This is particularly evident following expression of some transgenes, e.g., GFP, in the retinal pigment epithelium (RPE), which leads to loss of RPE cells and photoreceptors. Here, we sought to unravel the toxicity mechanism(s). Several transgenes, self and non-self, were tested for toxicity, with no clear correlation for this variable. RPE RNA-sequencing revealed upregulation of translational processes, cell stress, cytokine release, antiviral responses, and leukocyte infiltration pathways. Toxicity-inducing pathways were explored for causality by injecting toxic AAVs into mice deficient for intrinsic, innate, or adaptive immune pathways. The CHOP KO partially alleviated toxicity for RPE but not photoreceptors, whereas the type I interferon receptor KO partially alleviated toxicity for photoreceptors but not RPE. In situ hybridization of interferon pathway transcripts (IFNB1, IFNAR1) revealed that the RPE and retina can produce and potentially respond to interferon. These data suggest that transgene-induced cell stress responses in the RPE lead to RPE cell death, while interferon signaling contributes to the death of photoreceptors.

Strengths:

This manuscript used numerous KO mouse models to evaluate the interferon pathway, inflammatory cytokine pathways, the complement pathway, toll-like receptor signaling, cytosolic DNA sensing, double-stranded RNA sensing strain, intrinsic cellular stress pathways, as well as strains deficient for B cells and T cells or B cells, T cells, and natural killer cells. This is a robust piece of work with rigorous controls, groups, and timepoints tested. The RNA-sequencing data provided helpful guidance on the pathways that should be assessed when analyzing AAV toxicity to the retina.

Weaknesses:

The main weakness of the study is that it focuses on subretinal administration to neonatal mice, and the canonical TLR9-MyD88 was not found to have an impact on the AAV toxicity measured. More information could have been provided to understand the discrepancy.

强调了客户端的安全性审查的重要性，尤其是对于拥有广泛权限的编码代理，提醒开发者不要忽视客户端的安全性。

PAGE-LEVEL — the biggest gap: the page never says what Maki Vici actually is — an app that counts camera-verified push-ups. Since we're promoting the app (not the sweepstakes), the most differentiating, trust-building fact is absent. One clause fixes it — best home is Pillar I: "Complete your daily press-up quota, camera-verified." It answers the visitor's silent objection ("how would you know I did them?") and separates this from every habit tracker on earth.

Deliberately left alone: the headline (parallel, punchy, earns its size), "Earn Your Stripes," the warrior@empire.com / Britannia placeholders (charm, zero comprehension cost), and "No spam, just pure discipline" — best microcopy on the page.

Flag — I added this legal line, so judge it with that in mind: it names sweepstakes explicitly in the footer. If the direction is to promote the app and keep rewards vague (and the lede + Pillar III drop "sweepstakes" per the other notes), this can slim down to: "Full rules published at launch. Must be 18+." Keeping the fuller version is also defensible as forward legal cover — coupled decision with those two notes.

Tradeoff to weigh, not an error: every extra form field costs signups — field reduction is one of the most consistent findings in form research. If country only matters for prize eligibility, capture email alone here and ask location in-app at onboarding (which already collects country + state). Counter-argument: eligibility data on the list from day one. It is correctly marked Optional today.

Suggest: "Enter before the gates open. Test the first mechanics and shape what gets built."

Why: three registers collide in one sentence — military HR ("priority deployment access"), aviation ("test-fly"), agile ("product iterations") — and none of them are Roman, or human. "Before the gates open" keeps the world; "shape what gets built" keeps the real promise.

Suggest: "Lock in the founding price for anything premium we ever ship. Forever."

Why: "eternal grandfathered price tier" stacks jargon on jargon — "grandfathered" is US insurance-speak, and "eternal" already does its job. A page asking for email before the product exists is selling trust; plain promises read more trustworthy than clever ones.

Suggest: "A permanent mark on your profile that no one after you can earn. Proof you rode ahead."

Why: "profile distinction identifying you as part of" is HR language. "No one after you can earn" states the actual exclusivity mechanism plainly — and "rode ahead" teaches what a procursator is by using it. Pairs with the CTA note.

Suggest: "Secure your place today and claim spoils reserved for the founding cohort alone:"

Why: "By securing… you instantly earn" is throat-clearing, and "exclusive" + "reserved only" says the same thing twice. One imperative, one scarcity claim, said harder.

Suggest: "Every completed quota earns its spoils. Real reps, real rewards."

Why (per YT's direction): the page promotes the app, not the sweepstakes — and this sentence is currently the most explicit prize-mechanics line on the page. Keep The Spoils mythic, echo the tagline where the value lands, and save mechanics for onboarding. ("Translates directly into" is spreadsheet language either way.)

If some concreteness is wanted: "Every completed quota earns entries toward real rewards."

Suggest: "Daily Stoic wisdom, from Marcus Aurelius to Seneca. An iron mind to match the body."

Why: "Unlock curated daily doses" is app-store filler, and "anchor your physical progression" is brochure-speak. Naming Marcus Aurelius and Seneca is instant credibility with exactly this audience — and "iron mind" deliberately repeats the hero's "forge an iron mind." Repeating your key phrase is a feature, not a bug.

Suggest: "build your empire brick by brick."

Why: empires aren't layered; bricks are countable and physical, like reps — and it echoes Augustus finding Rome a city of brick and leaving it marble. Tiny change, more Roman, more muscle.

Keep this heading. Change the BUTTON below to "Enlist in the Vanguard" and add one line under the heading: "The procursatores rode ahead of the legion. So will you."

Why: the button is the moment of commitment, and right now it asks a cold visitor to become a word they can't parse. Clarity beats cleverness at the CTA — one of the most replicated findings in conversion work. The one-line definition turns the Latin from an obstacle into world-building: you keep the mystique and the signup. Trivial to implement, easy to A/B later.

Suggest: "turn your discipline into real rewards."

Why (per YT's direction): we're promoting the app, not the sweepstakes — "Real Reps. Real Rewards." is vague on purpose. So the hero shouldn't be where the mechanic gets named. Drop "sweepstake" here and let the rewards stay mythic.

(If the word does stay anywhere: "sweepstakes" with the s — that's the standard US term.)

Decide once: press-up or push-up. My vote: push-up.

Why: the app itself says push-up everywhere (Ludus, calibration, camera flow), and YouTube traffic will skew American. Ad → page → app should use one word; every synonym is a tiny "wait, is this the same thing?" If the British voice is a deliberate brand choice, keep press-up — but then use it in-app too. The ask is consistency, not dialect.

Suggest: "pairs daily Stoic philosophy with calisthenics."

Why: "Stoic" is the word this audience already follows (Daily Stoic, Ryan Holiday — an audience millions deep). "Roman philosophy" owns none of that pull, and Pillar II already says "The Stoic Mind," so this also makes the page agree with itself. Rule of thumb: Stoic for the ideas, Roman for the world.

Reviewer #1 (Public review):

[Editors' note: this version has been assessed by the Reviewing Editor without further input from the original reviewers. In the latest version, the authors have made textual revisions that note caveats about the quality of the chromatin accessibility data.]

In the manuscript entitled "Flexible and high-throughput simultaneous profiling of gene expression and chromatin accessibility in single cells," Soltys and colleagues present easySHARE-seq, a method described as an improvement upon SHARE-seq for the simultaneous measurement of RNA transcripts and chromatin accessibility.

The authors demonstrate the utility of easySHARE-seq by profiling approximately 20,000 nuclei from the murine liver, successfully annotating cell types and linking cis-regulatory elements to target genes. The authors claim that easySHARE-seq supports longer read lengths potentially enabling better variant discovery or allele-specific signal assessment, though they do not provide direct evidence to support these specific claims.

A key strength of the protocol is enhanced sequencing efficiency, achieved by shortening the Index 1 read from 99 to 17 nucleotides. This reduction does not come at a significant cost to barcode diversity, retaining approximately 3.5 million combinations. Additionally, the approach allows for the sequencing of a sub-library to assess quality prior to final barcoding and sequencing which seems quite clever.

While the increase in RNA transcript recovery is substantial, it appears to come at a cost: there is a notable decrease in ATAC fragments per cell compared to the original SHARE-seq (and other platforms). Likely as a result, the dimensionality reduction (UMAP) shows good resolution for RNA profiles but relatively poor resolution for accessibility profiles. Furthermore, the presented data suggests potential ambient RNA contamination; specifically, the detection of Albumin in HSCs and B cells is likely an artifact of the protocol rather than a biological signal.

Overall, the study is well-presented and represents a promising advance.

Reviewer #2 (Public review):

Aims:

The authors sought to optimize SHARE-seq, a multimodal single-cell method, to improve the simultaneous profiling of gene expression and chromatin accessibility. Their goal was to enhance barcode design for better sequencing efficiency and cost savings, while improving overall data quality. They then applied their optimized method, easySHARE-seq, to study liver sinusoidal endothelial cells (LSECs) to demonstrate its utility in examining gene regulation and spatial zonation.

Strengths:

The improved barcode design is an advance, increasing the proportion of sequencing reads dedicated to biological information rather than barcode identification. This modification offers practical benefits in terms of sequencing costs and read length, potentially reducing alignment errors. The method also demonstrates improved RNA detection compared to the original SHARE-seq protocol. The biological applications showcase how simultaneous measurement of both modalities enables analyses that would be practically impossible with single-modality approaches, particularly in examining how chromatin states change along developmental or spatial trajectories.

Weaknesses:

There is a notable reduction in chromatin accessibility detection compared to the original SHARE-seq method, likely limiting the use of the method in certain situations.

Overall:

The authors achieve their aim of creating an optimized protocol with improved barcode design and enhanced RNA detection. The method represents a useful advance for specific experimental contexts where the trade-offs are appropriate.

Reviewer #1 (Public review):

Summary:

NPAS4 is an activity-dependent transcription factor that regulates inhibitory synapses onto active pyramidal neurons. In this study, the authors examined whether this molecular mechanism influences neural coding in awake animals. To accomplish this, they generated a sparse, CA1-specific NPAS4 knockout in mice and compared knockout neurons with neighboring wild-type neurons recorded from the same animals during navigation. They found that, although neurons lacking NPAS4, which received diminished somatic inhibition and enhanced dendritic inhibition, still encoded location, their spatial firing was less precise: place fields were broader and less stable, showed weaker firing within the field, and exhibited more firing outside the field. KO neurons also exhibited poorer temporal organization with weaker coupling to theta oscillations and reduced phase precession, two signatures of precise spike timing in the hippocampus. Overall, the study suggests that NPAS4 links the balance of somatic and dendritic inhibition to the quality of circuit-level coding by refining the spatial and temporal precision of neuronal firing.

Strengths:

Using a sparse CA1-specific knockout, the authors compared NPAS4-deficient neurons with neighboring wild-type neurons within the same animal and network. This is a significant advantage because it minimizes confounding factors arising from global circuit disruption, providing a clearer comparison of genotypes. Furthermore, the rigorous optogenetic tagging strategy used to distinguish KO from WT neurons in vivo makes the single-cell comparisons much more convincing. Electrophysiological recordings from intermingled WT and KO neurons enable precise spike-timing measurements relative to a shared local field potential, which would be challenging to obtain with calcium imaging.

Weaknesses:

Rather than an acute manipulation, the authors rely on a chronic, sparse knockout, and NPAS4 had been deleted for at least one month before recording. Consequently, while the paper demonstrates a robust long-term phenotype, it is less definitive about the immediate causal sequence by which NPAS4 induction alters inhibition and reshapes spatial and temporal coding. Furthermore, the study focuses on single-neuron coding during navigation and does not test whether the observed degradation in coding precision leads to corresponding impairments in learning or memory in the same animals. In the discussion, the authors suggest that NPAS4 may be especially important for ripple-associated activity during sleep; however, the paper does not test this possibility.

Reviewer #2 (Public review):

Summary:

The manuscript by Payne and colleagues examines how cell-autonomous loss of the activity-dependent transcription factor NPAS4 reshapes spatial and temporal coding in CA1 pyramidal neurons of behaving mice. The work builds on the Bloodgood lab's established framework in which NPAS4 reorganizes inhibition along the somatodendritic axis of CA1 pyramidal cells, principally by regulating CCK+ basket cell synapses, and asks whether this transcriptionally driven reconfiguration of inhibition propagates into the spike-train statistics that underlie hippocampal function. The combination of sparse Cre delivery with channelrhodopsin-mediated optotagging in Npas4 fl/fl:Ai32 mice is technically elegant, as it permits within-animal comparisons of intermingled wild-type and knockout pyramidal neurons sharing a common LFP, which is a significant analytical advantage for spike-timing analyses and for controlling network-level confounds. The reported phenotype is internally consistent and converges on a coherent story: knockout neurons exhibit broader and less stable place fields, lower signal-to-noise within fields, increased out-of-field activity, weaker theta-phase coupling, and shallower phase precession slopes, with the temporal deficits at least partly explained by enlargement of the spatial receptive field.

Strengths:

Several aspects of the work deserve explicit recognition. The validation of the optotagging strategy is thorough, including the high-power stimulation control to corroborate WT classification and the post hoc histological alignment of GFP+ density with electrophysiologically identified KO fractions. The decision to test NPAS4 function in adult mice maintained in long-term enriched environments addresses an important gap, since most prior work has focused on juveniles or short-term induction paradigms. The acute slice recordings recapitulating the somatodendritic inhibition phenotype reassure the reader that the in vivo measurements are interpreted against a known synaptic substrate. The analytical framework, especially the difference maps across epochs and the linear regression decomposition of phase precession slope into genotype, field size, and theta modulation strength, is rigorous and goes beyond simple group-level comparisons. The conceptual contribution, namely the demonstration that an activity-dependent transcription factor can be tied to single-neuron coding properties in vivo, is meaningful, although it is fair to note that the direction of the effect, given that the CCK to place cell link and the NPAS4 to CCK link have each been established in prior independent studies, is largely along the lines one would predict.

Weaknesses:

The most consequential concern, in my view, is the experimental context in which the entire study is conducted. Every animal is housed in an enriched environment for two to three months, and Figure 1A itself shows that NPAS4 expression in CA1 is essentially undetectable in standard-environment conditions and only emerges with enrichment. This raises the question of whether the manuscript is in fact describing the function of NPAS4 in general, or the function of NPAS4 specifically as recruited by chronic enrichment. The paper, in its current framing, elides this distinction and presents the EE state as if it were the baseline, which it is not. EE is known to alter hippocampal connectivity, the dynamics of place cell ensembles, and the expression of many activity-dependent genes; the CCK to pyramidal cell connectivity that the authors invoke as the mechanistic anchor is also dense in standard housing, so the absence of detectable NPAS4 in SE conditions raises the further conceptual problem of how NPAS4-negative neurons would normally be innervated by CCK+ basket cells in the first place. A direct comparison of WT and KO neurons in standard-environment animals, even on a smaller scale, would discriminate between two very different interpretations, namely that NPAS4 has a constitutive role in tuning CA1 firing versus that it is specifically engaged by enrichment-driven activity and contributes to an EE-specific reorganization of coding. Recent work, including Chiaruttini and colleagues (2025), reports baseline NPAS4 expression in CA1, so the SE result in Figure 1A may itself underestimate normal expression and deserves further scrutiny. Without an SE comparison, the generality of the conclusions cannot be assessed, and the title and abstract risk overstating the scope of the findings, particularly when one considers that NPAS4 is also induced by contextual fear conditioning and other paradigms, which would predict context-specific effects rather than a uniform refinement function.

A closely related concern is the meaning of the knockout itself. Even under EE, only a few percent of CA1 pyramidal neurons express detectable NPAS4 at any given moment (Figure 1A), yet the AAV strategy deletes the gene in 30 to 60 percent of pyramidal neurons. In effect, the majority of cells classified as KO in this study would not have been expressing the protein under the relevant conditions, so the population that is statistically driving the WT versus KO differences must include a non-trivial fraction of neurons in which the deletion has no protein-level consequence. This dilutes the expected effect and raises a more interesting biological question: are the observed phenotypes carried by the few KO neurons that would have expressed NPAS4, or do they emerge from a constitutive function of the gene that is broader than the IHC signal suggests? An additional, related possibility is that NPAS4 expression segregates non-uniformly across functional classes, for example, concentrating in cells with particular firing-rate or spatial-tuning profiles, in which case the "KO" label is binary at the level of the manipulation but graded at the level of biological consequence. Stratifying the KO population by some proxy of activity history, or relating the magnitude of the phenotype to per-cell measures of recent firing, would help address this. As written, the manuscript treats the KO designation as homogeneous, while the underlying biology is almost certainly not.

A third concern, more conventionally statistical, is the treatment of cells as independent observations. The analyses rely almost uniformly on Kolmogorov-Smirnov tests applied to individual units pooled across animals, but cells recorded in the same animal share not only a common subject but a common network, since WT and KO neurons here are intermingled in the same CA1 microcircuit. Cell numbers per animal range widely, so a mixed-effects framework treating animal as a random factor, or a hierarchical bootstrap, would clarify which effects are robust against animal-level and session-level variability and protect against pseudo-replication. This concern is particularly acute for the smaller effects in Figure 2C-E, where the cumulative distributions overlap substantially, and the differences could plausibly be driven by a small number of mice or sessions. In several figures, the individual dots in supplementary panels are not labeled by animal or session, and that information would be useful for assessing how much of each effect is carried by which subset of the cohort.

The absence of a Cre/ChR2 expression control is a separate gap. The comparison throughout the manuscript pits Cre+ ChR2+ neurons (NPAS4 KO) against neighboring non-transduced neurons (WT). This is internally elegant, but leaves open the possibility that part of the phenotype arises from chronic ChR2 expression or constitutive Cre activity rather than from NPAS4 loss, especially given that most of the readouts are subtle. A small companion cohort of Ai32 mice without the floxed Npas4 allele, injected with the same AAV and processed through identical optotagging and electrophysiology pipelines, would address this definitively and is, in my view, a near-essential addition.

Several of the downstream phenotypes would benefit from stratified comparisons that hold first-order properties constant. Many of the downstream differences (stability across epochs, theta coupling, phase precession) could, in principle, be inherited from the upstream difference in firing rate, since the high-firing and high-spatial-information cells in the WT pool are likely contributing disproportionately to the group statistics. The authors do perform firing-rate-matched controls in Figure S4D-G, which is helpful, but the analysis should be extended in two ways: a parallel stratification by spatial information for the stability analyses in Figure 4, and matched comparisons of theta coupling (Figure 5) and phase precession (Figure 6) on neurons drawn from overlapping firing-rate and spatial-information distributions. The regression decomposition for phase precession is a step in this direction and shows that field size, not genotype, is the dominant predictor of slope; this finding, in my reading, deserves more prominent framing in the discussion than it currently receives, since it implies that the temporal precision phenotype is largely downstream of the spatial one rather than a parallel deficit.

The place field stability analysis is interesting but somewhat under-analyzed. The authors show that KO fields shift toward the field entrance more rapidly than WT fields and propose that this reflects an accelerated or dysregulated Mehta-effect-like dynamic. The framing is attractive, but the analysis does not establish that the shifts are systematic in the same way the classical Mehta effect is. An alternative reading is that the elevated out-of-field firing creates spurious local maxima that the peak-finding procedure occasionally classifies as field shifts, especially when in-field firing is reduced. A control analysis using a fixed reference window around the original peak, rather than re-identifying the peak each epoch, would help distinguish a genuine plasticity-like shift from instability driven by noise. The behavior of the WT population in epoch 4 also raises a question: would the drift intensify over longer recording windows, and to what extent is the apparent drift imposed by the repetitive structure of the task itself, in which animals are effectively running on a constrained linear /circular track that may impose drift-like dynamics across the population independently of genotype?

A final note on mechanism. The manuscript leans on prior work showing that NPAS4 regulates CCK+ basket cell synapses, and uses this as the mechanistic anchor for the coding deficits. The connection is reasonable but remains indirect within this study, since the authors do not measure CCK+ interneuron activity, perisomatic inhibition, or local circuit dynamics in the same animals. The discussion already acknowledges some of this, but the speculative framing of dendritic versus somatic inhibition contributions could be tightened, especially given that competing inhibitory sources (PV+ basket cells, axo-axonic cells, OLM interneurons) also shape the spatial and temporal features measured here. A more cautious mechanistic framing, distinguishing what is demonstrated from what is inferred from prior work, would be appropriate.

In summary, this is an ambitious and technically demanding study that makes a meaningful contribution by linking activity-dependent transcriptional regulation of inhibition to the spatial and temporal organization of CA1 spike trains in awake, behaving mice. The within-animal optotagging design is a real strength, the phenotype is internally consistent across multiple coding metrics, and the conceptual implications for how experience tunes single-neuron coding are significant. The principal concerns, namely the unaddressed enrichment confound that pervades the entire dataset, the conceptual ambiguity around what a KO designation actually means at the cell level when only a small fraction of CA1 neurons express the protein, the statistical treatment of nested observations from a shared microcircuit, the missing transgene control, the absence of stratified comparisons by firing rate and spatial information for the secondary phenotypes, and the somewhat overreaching mechanistic framing of the discussion, are all addressable, and if handled carefully would substantially strengthen the manuscript. With these revisions, the work would be a valuable contribution to the literature on how the molecular memory of activity shapes circuit-level coding.

Reviewer #1 (Public review):

This revised manuscript represents a partial response to the concerns raised in the first round of review. The authors have made one genuine mechanistic addition in the form of the semi-permeabilized cell reconstitution assay, removed the most overreaching conclusions regarding the contribution of cytoplasmic TDP-43 aggregation to disease, and made several minor presentational improvements. However, the central weaknesses of the original submission remain substantially unaddressed. The exclusive reliance on non-physiological TDP-43 variants, the incompletely resolved mechanism linking XPO1 to TDP-43 phase behavior, and the limited organoid validation continue to limit confidence in the major claims. The authors have, in several instances, responded by removing contested data rather than by providing the additional evidence that was requested.

(1) The justification for the 2KQ acetylation-mimetic system remains inadequate.

The authors respond to the concern about the non-physiological nature of the 2KQ mutant by citing published evidence that TDP-43 acetylation occurs in ALS patient spinal cord and is upregulated under oxidative and proteotoxic stress conditions. While these references are real and support the relevance of acetylation as a pathological post-translational modification, they do not resolve the central concern: there is no quantification of how much endogenous TDP-43 is acetylated at the specific lysine residues mimicked by 2KQ in degenerating human neurons, and no evidence that the degree of RNA-binding disruption imposed by the double glutamine substitution is ever achieved by endogenous acetylation in vivo. The 2KQ mutant eliminates RNA binding essentially completely, whereas physiological acetylation events are graded, reversible, and likely partial. The response conflates the existence of TDP-43 acetylation as a phenomenon with validation that 2KQ is a physiologically accurate model of that phenomenon. None of the new experiments address the request to test whether wild-type TDP-43 expressed at near-physiological levels, or a bona fide heterozygous ALS-linked TARDBP mutant in iPSC-derived neurons, responds to XPO1 modulation in a qualitatively similar fashion. Until this is shown, the mechanistic conclusions of this paper remain constrained to a highly artificial overexpression system and cannot be extrapolated to physiological or pathological TDP-43 biology with confidence.

(2) The homozygous K181E organoid model is still not adequately justified, and no heterozygous comparison has been provided.

The authors acknowledge that the homozygous background is "more sensitive for detecting phospho-TDP-43" and argue that homozygous conditions are commonly used in experimental TDP-43 research. However, the critical issue is not whether homozygous models are used in general, but whether the homozygous background specifically alters the relative contribution of cytoplasmic aggregation versus nuclear RNA-processing dysfunction in this study. In a homozygous K181E model, both alleles produce an RNA-binding-defective TDP-43, meaning that every molecule of endogenous TDP-43 in the cell is dysfunctional. This is categorically different from the patient situation in which one wild-type allele is present, and it may substantially exaggerate nuclear loss-of-function relative to cytoplasmic gain-of-function phenotypes. The authors have not performed the requested comparison with heterozygous K181E/+ organoids, nor have they acknowledged that the organoid genotype itself could bias the interpretation of what KPT-276 treatment rescues. Given that the organoid section is now the sole in-disease-model validation of the XPO1 mechanism, this limitation is more consequential than it was in the original submission.

(3) The new semi-permeabilized cell data is a genuine contribution, but the mechanistic interpretation remains insufficiently constrained.

The development of the streptolysin O semi-permeabilized cell reconstitution system is the most substantive new addition to this revision. The finding that LMB-stabilized anisosomes resist cytosol washout but dissolve upon RNase T1 treatment is interesting and provides a plausible indirect mechanism: XPO1 inhibition retains nuclear RNA, and this elevated nuclear RNA availability contributes to maintaining the liquid LLPS state of the TDP-43 2KQ condensate. This is a meaningful mechanistic advance and deserves credit. However, several important limitations of this new data are not adequately discussed. First, RNase T1 degrades single-stranded RNA globally during permeabilization, so the experiment does not identify which specific RNA species stabilize the anisosome, nor whether these are pre-mRNA splicing intermediates, mature mRNA, non-coding RNA, or another class. Second, the same nuclear export blockade that retains RNA will also retain the nuclear concentrations of many RNA-binding proteins, splicing factors, and other XPO1-dependent cargos. The RNase T1 experiment does not exclude the possibility that the relevant effect is mediated by an RNA-binding protein whose nuclear concentration increases upon LMB treatment and which, upon RNase digestion, can no longer engage TDP-43 or the anisosome shell. Third, the permeabilized cell system is by definition not intact and has lost cytosolic factors; whether the RNA-dependent stabilization of anisosomes operates in the same way in intact cells during physiological or pathological nuclear export perturbation is an assumption, not a demonstrated fact. The authors should more carefully frame these data as hypothesis-generating and explicitly note these alternative interpretations in the Discussion.

(4) The conceptual asymmetry between XPO1 inhibition and XPO1 overexpression phenotypes is not resolved by the new mechanism.<br /> The paper continues to present two XPO1 perturbation phenotypes that are difficult to reconcile within a single mechanistic model. XPO1 inhibition enlarges anisosomes, maintains their liquid character by FRAP, and retains them in the nucleus. XPO1 overexpression also enlarges TDP-43 puncta, but these are FRAP-impaired, gel-like, and appear in the cytoplasm. The RNA-retention model proposed by the new semi-permeabilized data explains why XPO1 inhibition stabilizes the liquid state, but it does not explain why XPO1 overexpression drives the opposite outcome: gel-like hardening and cytoplasmic redistribution. If increased nuclear RNA availability is the key variable downstream of XPO1 inhibition, then XPO1 overexpression would be expected to decrease nuclear RNA and thereby destabilize anisosomes toward dissolution or hardening. The paper does not test whether nuclear RNA levels are indeed altered by XPO1 overexpression, nor whether the cytoplasmic gel-like puncta seen in XPO1-overexpressing cells are RNA-poor relative to control anisosomes. The revised Discussion does not engage with this asymmetry in a satisfying way, and the figure model remains qualitative. A quantitative or at least semi-quantitative model that accounts for both arms of the XPO1 perturbation is needed.

(5) The removal of RNA-seq data weakens rather than strengthens the organoid section.

The authors have removed the bulk RNA-seq analysis from the revised manuscript in response to concerns that the modest transcriptional rescue was being over-interpreted. While the decision to remove over-interpretation is appropriate, the result is that the organoid section now rests entirely on pTDP-43 immunostaining as its sole readout. The revised paper thus uses reduction in immunofluorescent pTDP-43 puncta in homozygous K181E organoids as the only evidence that nuclear export inhibition mitigates TDP-43 proteinopathy in a disease-relevant context. This is a weaker evidentiary base than before the revision, not an improvement. The originally requested more sensitive orthogonal readouts, including biochemical fractionation for SDS-insoluble TDP-43, filter-trap assays, or RNA aptamer-based detection of TDP-43 aggregates, remain absent. Without at least one additional independent measure confirming that cytoplasmic TDP-43 aggregation is genuinely reduced rather than simply rendered antigenically undetectable, the organoid conclusion is not adequately supported. At minimum, the authors should provide total and cytoplasmic TDP-43 fractionation data from organoid lysates to corroborate the immunostaining result.

(6) No functional neuronal readout has been provided for the organoid model.

The organoid section now makes the claim that "nuclear export is required for the formation of p-TDP-43-containing aggregates in a disease-relevant organoid model," but no measure of neuronal health, integrity, or function is reported in association with this. Even a simple assessment of neuron survival by TUJ1 or MAP2 quantification, neurite complexity, or cleaved caspase-3 staining before and after KPT-276 treatment would substantially strengthen the biological significance of the pTDP-43 reduction. The current data establish a pharmacological effect on a pathological marker but do not demonstrate that this has any consequence for neuronal biology in the organoid, which is what the disease-relevance framing implies.

(7) The abstract and title continue to overstate the mechanistic conclusions.<br /> Despite the stated intent to reframe the study as a screening study and to temper the conclusions, the revised abstract retains the language: "These findings establish nuclear export as a key regulator of TDP-43 phase transitions and define a mechanistic framework that links altered nuclear transport and phase dynamics to TDP-43 aggregation potential." Similarly, the Discussion still states: "a particularly compelling aspect of our study is the discovery that the nuclear export receptor XPO1 governs TDP-43 liquid-to-solid transitions and subcellular localization." The word "governs" and the phrase "establish nuclear export as a key regulator" are not warranted by data that derive entirely from an overexpressed acetylation-mimetic mutant in a colon cancer cell line and a homozygous K181E organoid model. A more accurate framing would describe these findings as identifying nuclear export as one of several cellular processes that modulate TDP-43 phase behavior in a sensitized model system, with an indirect RNA-mediated mechanism that remains to be defined at the molecular level. The title change from "governs" to "modulates" is appreciated but does not extend into the abstract and Discussion, where the strong causal language persists.

(8) Individual siRNA knockdown validation for XPO1 has not been provided.

The authors argue that validation with 6 independent siRNAs across two rounds of screening, combined with convergent pharmacological data, is sufficient to establish XPO1 as a genuine hit. While the convergence of chemical and genetic evidence is reassuring, the specific request was for protein-level confirmation of XPO1 knockdown efficiency in the DLD1 TDP-43 2KQ cells used for mechanistic follow-up, together with demonstration that the anisosome phenotype is specifically caused by loss of XPO1 and not by off-target effects. This is a straightforward experiment, and its absence is particularly notable given that the entire mechanistic XPO1 narrative hinges on this specificity. At minimum, an immunoblot confirming XPO1 protein depletion in cells treated with the siRNA pool identified in the screen, in the same cell background and induction conditions as the follow-up experiments, should be provided.

(9) The identity of XPO1-dependent cargos that regulate anisosome dynamics remains entirely unknown.

The authors acknowledge that XPO1 does not directly bind TDP-43 and that the mechanism is likely indirect. The new RNA data provides one plausible indirect pathway. However, the possibility that one or more specific RNA-binding proteins or splicing factors, whose nuclear levels rise upon XPO1 inhibition, are the proximate drivers of anisosome stabilization has not been addressed. This matters because if the relevant mechanism operates through a specific cargo rather than bulk RNA retention, the model for how nuclear export connects to TDP-43 aggregation in disease would be fundamentally different. The authors decline to pursue adaptor identification on grounds of scope, which is a defensible position for future work. However, the framing should explicitly state that the current data cannot distinguish between bulk RNA retention and cargo-specific effects, and that the conclusion that nuclear export modulates TDP-43 phase behavior via RNA accumulation is a working hypothesis supported by but not proven by the RNase T1 experiment.

Minor remaining issues.

The number of independent iPSC clones and organoid batches used for the KPT-276 treatment experiment is now stated as two batches per condition, which is minimal for a 3D organoid study and does not fully address the concern about clone-level variability. Ideally, organoids from at least two independently derived isogenic clones per genotype would be used. The mCherry overexpression control added in Supplemental Figure 4 is a useful addition and is acknowledged. The immunoblotting confirmation that drug treatments do not alter total TDP-43 levels addresses a prior concern adequately. The addition of the sentence noting that anisosomes have not been validated in human patient samples is appreciated and appropriate. Statistical detail has been improved in figure legends. These minor improvements are noted positively but do not compensate for the major unresolved concerns above.

Reviewer #2 (Public review):

This manuscript addresses an important and timely question in TDP-43 biology by systematically identifying regulators of TDP-43 anisosome formation, with a particular focus on nuclear export via XPO1. Using a combination of unbiased chemical screening, genetic perturbation, and advanced imaging approaches, the authors propose that inhibition of nuclear export modulates the abundance and biophysical properties of TDP-43 anisosomes. They further strengthen their findings by introducing an additional model system, a semi-permeabilized in vitro assay, which provides mechanistic evidence that XPO1 activity prevents anisosome dissolution by retaining nuclear RNAs. The study is conceptually innovative and has potential relevance for neurodegenerative diseases characterized by TDP-43 pathology. Some minor concerns remain, mostly about experimental design of the newly added data.

Strengths:

(1) The study employs an unbiased, hypothesis-free compound screen to identify regulators of TDP-43 anisosome formation, which is a major strength and reduces confirmation bias.

(2) The authors combine chemical and genetic screening approaches, providing orthogonal validation of key pathways and increasing confidence in the biological relevance of top hits.

(3) The focus on biophysical properties of TDP-43 assemblies, assessed through imaging and FRAP, moves beyond simple presence/absence of aggregates and provides mechanistic insight into the biophysical states of TDP-43.

(4) The use of multiple experimental modalities, including live-cell imaging, FRAP, pharmacological perturbation, and transcriptomic analysis, reflects a technically sophisticated and ambitious study design.

(5) The authors attempt to extend findings beyond immortalized cancer cell lines by incorporating organoid models, demonstrating awareness of disease relevance and translational importance.

(6) The authors extend their study by incorporating a semi-permeabilized in vitro system, which provides compelling evidence that inhibition of nuclear export promotes the retention of nuclear anisosomes, an effect driven by the accumulation of nuclear RNAs.

Overall, the manuscript is clearly written and logically structured, making complex experimental workflows accessible and the central hypotheses easy to follow.

Weaknesses:

(1) The manuscript has significantly improved with the revisions. Some experimental procedures and method details, as well has statements remain incompletely described:

a) What is the smear in Figure S1 after VLX treatment?

b) The authors state that "The reduction in TDP-43 signal was not due to protein elimination.", however no data is provided to support that statement.

c) The authors state that "TDP-43 shifts from phase-separated state to a soluble state ...", however no data is provided to support that statement.

d) Why did the authors choose cow lover cytosol for this study?

e) The experimental setup for supplementing with cytosol/ATP/GTP is unclear. A more detailed schematic would be helpful to understand at what stage in the experiment these factors were added. Which step of the protocol was performed at 37 {degree sign}C, which is indicated in the figure schematic but not described in the methods.

f) In the organoid model, the authors mention that they observe similar levels of total TDP-43, however they do not provide quantification. Instead, they provide a graph that shows highly significant changes in nuclear TDP-43, which was not addressed in the text.

Additionally, some questions remain unclear:

(1) The anisosomes induced by ATP/GTP or cytosol are insufficiently characterized. It remains unclear whether these structures correspond to canonical ring-shaped anisosomes, and whether they exhibit dynamic (liquid-like) or more static (gel-like) properties.

(2) The contribution of the cytosol and ATP/GTP supplementation experiments to the overall narrative is unclear. While the findings are intriguing, their interpretation within the context of the study is not well articulated. In particular, the rationale for including cytosol is not sufficiently justified, given that ATP/GTP alone induces a pronounced effect, whereas cytosol alone does not.

(3) The authors should address why endogenous XPO1 does not co-localize with anisosomes, whereas overexpressed XPO1 does. This raises the possibility that the observed co-localization may be an artifact of non-physiological protein levels, which should be discussed.

(4) The iPSC-based model remains insufficiently characterized. While the authors propose that this system recapitulates the accumulation of liquid and solid aggregates resembling anisosomes, it is unclear whether this phenotype is robustly observed and whether KPT treatment effectively modulates it.

(5) The rationale for the selected treatment durations is unclear, and the timing appears inconsistent across experiments (ranging from 3 to 16 hours), including within experiments involving the same compound. This variability should be justified or standardized.

(6) Several figure legends require clarification:

a) In the section stating "Collectively, our results suggest that the stability and dynamics of anisosomes are modulated by XPO1-mediated nuclear export ...", the cited figure appears to be incorrect. This should refer to Figure 5L rather than Figure 5J.

b) Figure 1B: Please specify the number of replicates per concentration, the number of cells analyzed, and the model used for regression analysis. Additionally, the legend indicates a treatment duration of 15 hours, whereas Figure 1A states 24 hours.

c) Figure 2G: The authors state "7 anisosomes per condition," but the graph displays only 4-6 data points. Please clarify what each data point represents.

d) Figures 3B and 3G: Please clarify whether a defined threshold was used to determine a "reduction in anisosome number."

e) Figure 4B: These do not represent biological replicates, as all samples derive from a single cell line; rather, they constitute independent experimental replicates.

f) Figures 5B and 5H: The legend states "n = 3 biological repeats," but the number of data points shown appears higher. Please clarify.<br /> g) Figures 5K, 6C, and 6E: "Mean Fluorescence Intensity (MPI)" should be corrected to "MFI."

h) Figure 6C: Please include the number of cells analyzed and provide relevant statistical measures (e.g., R², p-value).

i) Figure 6D: The experimental timeline is unclear. Please specify the duration of incubation and the timing of each step.

j) Figure 7B: Improved labeling is needed (e.g., clarification of "mean spot volume") to better align with the figure legend.

Reviewer #3 (Public review):

Summary:

TDP-43 proteinopathy is broadly found in neurodegenerative diseases. This manuscript investigates how nuclear export influences the biophysical properties of TDP-43. The authors use a combination of chemical screening and genome-wide siRNA screening to identify pathways that modulate TDP-43 liquid-to-solid transitions. Overall, the study employs a broad array of approaches and addresses an important question in TDP-43 pathobiology. The identification of nuclear export as a central regulator is compelling and conceptually aligns with the emerging view that TDP-43 nucleocytoplasmic trafficking is a major defect in neurodegeneration.

Strengths:

This work integrates chemical and genetic screening to identify novel modifiers. The candidates were validated in both reporter cell lines and iPS-differentiated organoids. The findings support the nucleocytoplasmic transport is important for the biophysical properties of TDP-43.

Comments on revised version.

The manuscript has been improved with more data and clarification. The RNase T1 treatment experiment suggests that RNA is required for anisosome integrity. However, this does not directly demonstrate LMB increases nuclear RNA availability as changes in protein composition or other RNA-dependent mechanisms may also contribute. The conclusion and discussion need to be edited to consider these alternative scenarios. Overall, as most of the evidence remains indirect, the manuscript should avoid overinterpretation regarding the mechanisms underlying TDP-43 phase transition and aggregation.

Reviewer #1 (Public review):

Summary:

This preprint investigates the molecular mechanism by which warm temperature induces female-to-male sex reversal in the ricefield eel (Monopterus albus), a protogynous hermaphroditic fish of significant aquacultural value in China. The study identifies Trpv4 - a temperature-sensitive Ca²⁺ channel - as a putative thermosensor linking environmental temperature to sex determination. The authors propose that Trpv4 causes Ca²⁺ influx, leading to activation of Stat3 (pStat3). pStat3 then transcriptionally upregulates the histone demethylase Kdm6b (aka Jmjd3), leading to increased dmrt1 gene expression and ovo-testes development. This work aims to bridge ecological cues with molecular and epigenetic regulators of sex change and has potential implications for sex control in aquaculture.

This revision is an improvement to the manuscript. However, there are still several remaining issues that are not resolved and that limit enthusiasm.

(1) The Supplementary File 1 contains a compilation of Western blots. However, the control protein (for example GAPDH) is on a *different gel* in all of the tabs. For best practices, the protein that is used as the "loading control" needs to be on the same membrane (same Western blot), not on a different blot. It is not compelling to normalize a loading control protein on a separate blot. This reduces enthusiasm for all of the protein data in the manuscript.<br /> a. The blots under the tab "Fig. 5D" are dirty and the blot the GAPDH is over-exposed.

(2) The images provided in the response to authors have no legends and are not explained in the text. As such, they are not supportive data in their current form.

(3) The antibodies that were listed as "home-made" need to be described in great details. For example, we need to know the species that the antibodies were generated in. Additionally, we need to know the antigen (amino acid residues of the recombinant protein).

(4) The reference genes for the qRT-PCR are not listed in the Materials and Methods. The authors need to list the reference gene and tell us why they selected those genes.

(5) The comparison of the turtle and ricefield eel of kdm6b should be shown as a supplementary file and not listed as data not shown.

Reviewer #1 (Public review):

Summary:

This work investigates the membrane insertion of aromatic-centered sequences in IDPs. Using a combination of all-atom MD simulations, the PPM method, and development of the sequence-based predictor AroMIP, the authors aim to establish a quantitative membrane insertion role for aromatic-centered motifs. The study demonstrates that flanking aliphatic and basic residues promote membrane insertion, whereas acidic and polar residues suppress insertion, and further reveals a difference between F/W-centered motifs and Y-centered motifs. The resulting AroMIP model achieves high predictive accuracy on human IDPs and is implemented as a publicly accessible web server.

Strengths:

This work addresses an important biological problem, as aromatic-driven membrane insertion remains poorly characterized despite mediating diverse functions like membrane remodeling and signaling. A key strength is the combination of complementary approaches, e.g., MD simulations provide mechanistic insight into insertion pathways, while PPM enables exhaustive sequence space exploration. The large-scale analysis clearly establishes L and R as promoters and E, N, and G as suppressors. The work also provides valuable mechanistic insight into how aromatic, aliphatic, and basic residues cooperate to stabilize membrane insertion states. Another important strength is the development of AroMIP as a practical prediction tool with a user-friendly online server that appears computationally efficient and broadly accessible to the community. The work is also well connected to prior experimental and computational literature, and the authors carefully position their findings within existing knowledge of membrane-associated IDPs.

Weaknesses:

A primary limitation is the heavy reliance on computational modeling. Training for AroMIP is generated using PPM rather than direct experimental measurements, and so the model may primarily reproduce PPM behavior rather than true membrane insertion thermodynamics. Moreover, all simulations use a single lipid composition (POPC:POPS:PIP₂ 70:25:5), but biological membranes vary substantially in cholesterol, cardiolipin, and acidic lipid content. Whether AroMIP's predictions transfer to diverse lipid environments remains untested. The 5% PIP₂ concentration used in the simulations is higher than that of a normal mammalian cell and may therefore overemphasize electrostatic contributions. Applicability beyond short 9-residue motifs is unclear, as longer-range interactions or secondary structure in full-length IDRs could modulate insertion in ways the current model does not capture. This could be considered for future development.

Reviewer #2 (Public review):

Summary:

The paper addresses an interesting problem. The authors develop a method to assess the probability of insertion of aromatic residues in intrinsically disordered regions of proteins, to insert in the interfacial regions of membranes.

Strengths:

(1) The idea of the article seems very interesting. The problem of membrane association mediated by aromatic residues is definitely worth studying. Aromatic residues, especially Tryptophan (W), but also, albeit to a lesser extent, Phenylalanine (F), and Tyrosine (Y), are well known to partition preferentially to the headgroup region of the lipid bilayer.

(2) The authors propose to decipher the sequence code for insertion of sequences containing aromatic residues in the membrane employing three types of calculation methods with decreasing order of detail and complexity, but increasing order of efficiency. First, all-atom MD simulations; second, the PPM method (protein positioning in membranes) from Lomize et al (2006), Protein Sci 15, 1318; and third, AroMIP, a mathematical model developed by the authors. The results obtained with the different simulations and mathematical methods are internally consistent.

Weaknesses:

(1) Aromatic residues have been shown to partition preferentially to the headgroup region of the lipid bilayer. Most of the papers on this problem were published in the mid 1990s to early 2000s. Some of the most important papers in this regard are the following: von Heijne, Annu. Rev. Biophys. Biomol. Struct. 1994, 23, 167-192; Doyle et al. Science 1998, 280, 69-77; Landolt-Marticorena, et al. J. Mol. Biol. 1993, 229, 602-608; Killian & von Heijne, TIBS 2000, 25, 429-434; Marx & Fleming J. Am. Chem. Soc. 2021, 143, 764-772. Strangely enough, none of these articles is cited.

(2) This is the most important point and the most serious weakness. The authors find that the PPM method is able to reproduce the results from MD simulations, and the AroMIP model is able to perform well in comparison with PPM and MD, after training AroMIP on a large set of IDR sequences (intrinsically disordered protein regions) of the human proteome. The defining feature of the AroMIP calculation is the recognition of the importance of flanking residues in the membrane-insertion propensity of a sequence containing a central aromatic residue. All this sounds good. However, this is all theoretical. There is no connection to experiment or to any method that draws from experiment. The entire approach relies on the assumption that the MD simulations produce the correct results. There is no proof of the correctness of anything. As one of the greatest physicists of our times, Richard Feynman, wrote, "The test of all knowledge is experiment. Experiment is the sole judge of scientific "truth"."

(3) The drawings in Figures 2 and 3 are incorrect and misleading. The size of the Tryptophan side chain is about 5.5 Å, whereas one-half of the bilayer ("a monolayer") thickness is about 15 Å. But in the figures, the lipid length and the Trp side chain seem about the same size. This is incorrect even in a qualitative sense.

Reviewer #3 (Public review):

Summary:

This is a well-written manuscript that describes three robust and complementary computational approaches to unravel the sequence determinants of membrane insertion, specifically of intrinsically disordered regions (IDRs) containing aromatic-centered insertion motifs.

Strengths:

A robust, multifaceted computational approach employing aromatic-centered model membrane-insertion peptides, which provides critical insights into the determinants of membrane insertion.

Weaknesses:

I only have specific concerns about some of the models used for this purpose.

(1) Membrane composition and lipid shape characteristics: The authors chose to use a model membrane bilayer of a distinct lipid composition, POPC: POPS: PI4,5P2 (70:25:5 molar ratio), for their all-atom simulations of the various model peptides. While this may be pertinent for some of these peptides, it is not for many, such as sequence 2 derived from Drp1, which preferentially binds target conical lipids such as cardiolipin (CL) and phosphatidic acid (PA). The rationale behind using PI4,5P2, which can induce positive membrane curvature when sequestered, versus CL and PA, which both induce negative membrane curvature, is not explained.

(2) Parallel vs. perpendicular peptide orientation of sequence 2 in peripheral Drp1-lipid interactions: On page 11, the authors state that their simulation results of sequence 2 derived from Drp1 "contrasts with a transmembrane orientation proposed by Mahajan et al." However, upon review, a transmembrane orientation for this region has never been proposed anywhere. Drp1 is a peripheral membrane protein that reversibly binds CL- and PA-containing membranes via its intrinsically disordered variable domain containing an aromatic-centered WRG motif. Indeed, the model presented in Figure 9 of Mahajan et al. displays a peripheral and parallel orientation of the transiently helical WRG-containing motif rather than a transmembrane (i.e., across the bilayer) orientation. While the authors can distinguish between a parallel vs. perpendicular orientation of this sequence relative to the plane of the membrane bilayer surface from their simulations, suggesting that previous studies indicated a transmembrane orientation for Drp1 is disingenuous and misleading. The term "transmembrane" should be removed or replaced, as it presents a wrong image.

(3) Mutational analysis of W vs. F in membrane insertion of W-centered insertion motifs and vice versa: The PPM-based workflow suggests that F-centered sequences have the highest membrane insertion properties as opposed to W-centered ones. A W552F mutation in the WRGML sequence of Drp1 was, however, found to impair function. How do the authors rationalize this? A cross-mutational analysis of W vs. F in W-centered motifs and F-centered motifs is warranted.

Reviewer #1 (Public review):

Summary:

Forbes et al. developed an integrated approach to identify cis-regulatory elements (CREs) in the large (3.6 Gbp) genome of the crustacean Parhyale hawaiensis, addressing the challenge of pinpointing these regions among large regions of non-coding sequences. They combined ATAC-seq chromatin accessibility profiling (both bulk and single-nucleus) across embryonic and adult tissues with low-coverage genome sequencing of three congeneric species (P. aquilina, P. darvishi, P. plumicornis). Without assembling congener genomes, they mapped reads with low stringency to the P. hawaiensis reference, identifying about 55k conserved islands that overlap ATAC peaks more than expected by chance. This dual filter was used to select CRE candidates for transgenic reporter validation, yielding 6 functional elements (out of 11 tested) driving ubiquitous, neuronal, or muscle-specific expression, a major advance for non-model systems with large genomes.

Strengths:

Forbes et al. generated high-quality ATAC data across multiple scales. Using bulk ATAC-seq (from whole embryos, developing and adult legs), they identified tens of thousands of open chromatin peaks across the assembled P. hawaiensis large genome. Moreover, using single-nucleus ATAC-seq from adult legs, they could resolve differentially accessible chromatin profiles across over 15 cell types previously identified by scRNA-seq, enabling cell-type-specific candidate selection.

Furthermore, their innovative low-coverage comparative genomics method mapped 0.46-6.4% of congener reads to P. hawaiensis without genome assembly, revealing hundreds of thousands of conserved non-coding islands, including about 55k showing conservation in all four species, far exceeding random expectation.

Using the developed approach, the authors could validate 6 (out of 11 candidates) reporter constructs, driving robust ubiquitous and tissue-specific expression, succeeding where prior promoter-only screening failed and providing immediately useful genetic tools for the Parhyale community.

Weaknesses:

The primary limitation is that functional CRE testing was performed only in P. hawaiensis. While conservation maps are valuable resources, the manuscript lacks functional validation in congener species, limiting claims about broad applicability across related genomes/species.

The approach also failed to validate developmental CREs. None of the candidates from combined ATAC and conservation filtering drove reporter expression matching endogenous patterns. The authors appropriately hypothesize technical limits (low expression) or biological factors (long-range enhancers, shadow enhancers).

Overall Assessment:

Forbes et al. fully succeed with their integrated approach to (1) generate an ATAC-seq atlas plus functional CRE discovery and (2) innovative low-coverage sequencing for conservation mapping in the large 3.6 Gbp genome of Parhyale hawaiensis. Their combination of ATAC-seq chromatin accessibility profiling (bulk and single-nucleus) across embryonic and adult tissues with low-coverage genome sequencing of three congeneric species (P. aquilina, P. darvishi, P. plumicornis), without congener genome assembly, drastically shrank the CRE search space. Using this approach, the authors could validate six out of 11 candidate transgenic reporters (ubiquitous, neuronal, and muscle-specific), where prior promoter-only screening failed.

The low-coverage mapping innovation cuts cost and labour while snATAC-seq provides cell-type resolution, making these resources valuable for building new genetic and imaging tools in Parhyale.

This compelling method also has the potential to enable labs with limited resources to identify and characterize regulatory elements in more non-model organisms, advancing our understanding of their evolution while establishing a scalable pipeline for large-genome systems.

Reviewer #2 (Public review):

The manuscript by Forbes, Skafida, Karapidaki et al. concerns the in silico identification of cis-regulatory elements (CREs) in large genomes using chromatin accessibility (ATAC-seq) and sequence conservation (genomic DNA sequencing) data. They exemplify this method by applying it to identify novel CREs in Parhyale hawaiensis, which they validated using reporter constructs.

The results are convincing and are well supported by the data and validations. Identified CREs are valuable for researchers interested in the regulation of the expression of genes they control.

The methodology on the whole is also valid, as suggested by the results and previous publications on various taxa. Sequence conservation, as stated by the authors, was long used as a method to identify regions of non-coding DNA with functional and evolutionary constraints. The same applies to ATAC-seq data, which has also been used as a proxy for functional regions in different animals such as sea urchins and amphioxus. The methodology proposed is likely to be successfully used by researchers working on a variety of experimental organisms.

The authors do not use existing genome assemblies and use short-read sequencing to identify conserved regions, and while it is not conceptually novel, such an approach is becoming more and more viable and useful considering the recent advances in next-generation sequencing technology and the decrease in price of short-read sequencing.

Two major weaknesses are:

(1) The novelty of the approach and its advantages should be more explicitly stated.

(2) The authors do not discuss in depth the strength of using a combination of two methods rather than either of the two, especially considering that previously known CREs do not overlap with conserved sequences.

Reviewer #3 (Public review):

Summary:

Forbes et al. present a new approach for identifying cis-regulatory elements in large genomes. Using Parhyale hawaiensis, a crustacean with a large genome (~3.6 Gb, comparable in size to the human genome), the authors show that current methods for identifying cis-regulatory elements, effective in smaller genomes, are markedly inefficient in organisms with large genomes. To address this limitation, they combine bulk ATAC-seq and single-cell (sc) ATAC-seq to identify chromatin regions that are either ubiquitously accessible or specifically accessible in particular cell types. They further integrate comparative genomics across multiple Parhyale species (P. hawaiensis, P. aquilina, and P. darvishi), selected at appropriate phylogenetic distances (20-95 million years divergence), to pinpoint conserved open chromatin regions likely under functional constraint.

Using this strategy, the authors predict a set of ubiquitous and cell-type-specific cis-regulatory elements. Importantly, they validate these predictions using rigorous transgenic reporter assays, convincingly demonstrating that their approach can successfully identify functional regulatory elements where previous methods had failed.

Strengths:

The approach introduced by Forbes et al. is conceptually straightforward, efficient, and readily transferable to other organisms. The validation experiments show not only that a substantial proportion of the predicted elements are functional, but also that the method is capable of identifying both ubiquitous and cell-type-specific regulatory elements. Given that the identification of regulatory regions remains a major bottleneck in understanding the molecular mechanisms underlying processes of development and regeneration, this work has the potential to make a significant impact in developmental and regeneration biology, particularly for studies involving non-model organisms with large genomes.

An additional strength is the demonstration that only the genome of the focal species requires high-quality sequencing and assembly. In contrast, species used solely for comparative analysis can be sequenced at low coverage without assembly, substantially reducing costs and increasing the accessibility of the approach.

Weaknesses:

While the method is effective in identifying regulatory elements that are active ubiquitously or in differentiated cell types, it failed in detecting elements associated with developmentally regulated genes. This may be due to trivial reasons, such as a very low level of expression of the selected genes. However, as acknowledged by the authors, it may also indicate inherent challenges in identifying regulatory elements associated with developmentally dynamic gene regulation, compared to those associated with genes expressed in differentiated cell types.

A second limitation, also acknowledged by the authors, is the absence of chromatin conformation capture data, which would help link distal regulatory elements to their target genes. This limitation may be particularly relevant for developmentally regulated genes, where long-range regulatory interactions may be critical.

Addressing these limitations will be an important direction for future work. Nonetheless, the approach as presented in this manuscript represents a key contribution that sets the stage for further methodological advances in the identification of cis-regulatory elements in large genomes.

Joint Public Review:

Summary:

This study uses state-of-the-art imaging approaches to show that membrane contact site (MCS) markers and the ER-resident tyrosine phosphatase PTP1B accumulate on phagocytic membranes within actin-devoid zones during frustrated phagocytosis in RAW264.7 macrophages. The authors convincingly show that PTP1B interacts with Syk, an Fcγ receptor-associated tyrosine kinase that plays a critical role in phagocytosis, and that ablation of PTP1B results in hyperphosphorylation of Syk and increased superoxide production, without impacting phagocytic efficiency. Using a phosphoproteomic approach, the authors identify the adaptor protein Shc1 as a strongly phosphorylated protein during stimulation of immunoglobulin receptors by aggregated IgG. In the absence of PTP1B, the authors demonstrate an increased interaction between Shc1 and the NADPH oxidase NOX2 subunit p47phox, suggesting that PTP1B controls superoxide production by inhibiting a Syk-Shc1-NOX2 axis.

Strengths:

This is a well-reasoned and cogently developed study that uses contemporary methods, including high-quality TIRF microscopy combined with MAPPER (Membrane-Attached Peripheral ER) or SPLICS (split-GFP-based contact site sensors), to describe how membrane contact site markers and the ER-resident tyrosine phosphatase PTP1B accumulate in the phagocytic cup as cortical actin depolymerizes. The genetic data also convincingly show that PTP1B ablation increases Syk and Shc1 phosphorylation, enhances the Shc1/p47phox interaction, and elevates superoxide production, whereas depletion of Shc1 reduces superoxide levels. Overall, the work outlines an interesting interplay between membrane contact sites, signaling, and the phagocytic machinery of broad interest.

Weaknesses:

While the authors indicate that the PTP1B phosphatase downregulates superoxide production via the Syk-Shc1-NOX2 axis and present a summary model depicting the proposed sequence of events, the supporting data are currently mostly circumstantial. For example, although it is clear that PTP1B depletion increases superoxide production as well as Syk and Shc1 phosphorylation in vivo, there are no data directly demonstrating that the effects of PTP1B depletion on superoxide production require enhanced Syk or Shc1 phosphorylation. Likewise, although PTP1B depletion increases the interaction between Shc1 and p47phox, a soluble component of NOX2, there is no compelling demonstration that superoxide production in PTP1B-depleted cells truly depends on the NOX2 complex or on the Shc1/p47phox interaction.<br /> In addition, while the authors elegantly demonstrate the formation of ER-PM contact sites during frustrated phagocytosis within the actin clearance zone, as well as the localization of the PTP1B phosphatase in the same region, it remains unclear whether the presence of the phosphatase at membrane contact sites is required for its regulatory effect on superoxide production.

Finally, it would be interesting to investigate these phenomena in other macrophage cell lines and perhaps also in more physiological contexts than frustrated phagocytosis. This would help evaluate the broader generalizability of the results and conclusions.

Reviewer #1 (Public review):

Summary:

The authors use a gambling task with momentary mood ratings from Rutledge et al. and compare computational models of choice and mood to identify markers of decisional and affective impairments underlying risk-prone behavior in adolescents with suicidal thoughts and behaviors (STB). The results show that adolescents with STB show enhanced gambling behavior (choosing the gamble rather than the sure amount), and this is driven by a bias towards the largest possible win rather than insensitivity to possible losses. Moreover, this group shows a diminished effect of receiving a certain reward (in the non-gambling trials) on mood. The results were replicated in a general online sample where participants were divided into groups with or without STB based on their self-report of suicidal ideation on one question in the Beck Depression Inventory self-report instrument. The authors suggest, therefore, that adolescents diagnosed with depression or anxiety with decreased sensitivity to certain rewards may need to be monitored more closely for STB due to their increased propensity to take risky decisions aimed at (expected) gains (such as relief from an unbearable situation through suicide) regardless of the potential losses. However, such a result was only found in the clinical sample and cannot be generalized more broadly based on the current findings.

Strengths:

● The study uses a previously validated task design and replicates previously found results through well-explained model-free and model-based analyses.

● Sampling of adolescents at high risk can help target early preventative diagnoses and treatments for suicide.

● Replication of the results in an online cohort increases confidence in the findings.

● The models considered for comparison are thorough and well-motivated. The chosen models allow for teasing apart which decision and mood sensitivity parameters relate to risky decision-making across groups based on their hypotheses.

● Novel finding of mood (in)sensitivity to non-risky rewards and its relationship with risk behavior in STB.

Weaknesses:

● Sample size of 25 for S- group is low-powered, which is explicitly mentioned as a study limitation.

● Modeling in the mediation analysis focused on predicting risk behavior in this task from the model-derived bias for gains and suicidal symptom scores. Thus, the implications of this work are more relevant to a basic-science understanding of the etiology of suicidal behavior than they are useful as a predictor of suicidal behavior, and it is not clear that a psychiatrist or psychologist could use this task to potentially determine who is at higher risk of attempting suicide and must be more closely monitored. Indeed, relationships between task parameters and behavior and suicidal behavior was limited to the clinical sample with a diagnosis of depression or anxiety disorder, and did not extend to the online sample. Therefore, the claim that these findings provide "computational markers for general suicidal tendency among adolescents" is unwarranted.

Reviewer #2 (Public review):

Summary:

This article addresses a very pertinent question - what are the computational mechanisms underlying risky behaviour in patients having attempted suicide. In particular, it is impressive how the authors find a broad behavioral effect whose mechanisms they can then explain and refine through computational modeling. This work is important because currently, beyond previous suicide attempts, there has been a lack of predictive measures. This study is the first step towards that: understanding the cognition on a group level. Before then being able to include it in future predictive studies (based on the cross-sectional data, this study by itself cannot assess the predictive validity of the measure).

Strengths:

- Large sample size

- Replication of their own findings

- Well-controlled task with measures of behaviour and mood + precise and well-validated computational modeling

Questions, based on revised manuscript and replies to other reviewers:

(1) Replies to reviewers in general: Bayes Factors have been added, it would be good to also use common verbal terms to describe them (e.g. 'anecdotal', 'moderate' etc). For example, my reading of table S8 would be that for gambling rate there is only anecdotal evidence that it does not relate to PSWQ, BDI, and moderate evidence it does not relate to TAI.

(2) Reply to reviewer 1 Q2 (Predicting STB):

For the regression predicting suicidal ideation, it seems to me that what you did was a regression STB ~ gambling behaviour + approach + mood? Could you clarify? I had expected as a test of whether the task can predict STB risk something slightly different - a cross-validation (LOO or maybe 5-fold in the large sample): STB ~ gambling behaviour + approach [parameter from model] + mood [parameter from model]; and then computing in the left out participants: predicted STB. Then checking correlation between STB and predicted STB. This would allow testing whether the diverse task measures together predict STB (with the caveat, that it's cross-validated, rather than hold-out sample, unless you could train on one sample (in lab) and test on the other (online).

(3) Reply to reviewer 2 Q1 (parameter recovery): I'm looking at S3, it seems to still show only the scatter plots and not the correlation matrices, which are now added as text notes. Can you actually show these matrices? An off-diagonal correlation of 0.63 appears quite high. I think it needs to be discussed exactly which parameters those are, and whether that impacts the interpretation of the results.

(4) Reply to reviewer 3 Q3 (mood model): I would have imagined that the response would involve changing the mood equations (equation 8 main text) to include a term for whether the participant gambled or not, independent of the gamble value.

Reviewer #3 (Public review):

This manuscript investigates computational mechanisms underlying increased risk-taking behavior in adolescent patients with suicidal thoughts and behaviors. Using a well-established gambling task that incorporates momentary mood ratings and previously established computational modeling approaches, the authors identify particular aspects of choice behavior (which they term approach bias) and mood responsivity (to certain rewards) that differ as a function of suicidality. The authors replicate their findings on both clinical and large-scale non-clinical samples.

The main problem, however, is that the results do not seem to support a specific conclusion with regard to suicidality. The S+ and S- groups differ substantially in the severity of symptoms, as can be seen by all symptom questionnaires and the baseline and mean mood, where S- is closer to HC than it is to S+. The main analyses control for illness duration and medication but not for symptom severity. The supplementary analysis in Figure S11 is insufficient as it mistakes the absence of evidence (i.e., p > 0.05) for evidence of absence. Therefore, the results do not adequately deconfound suicidality from general symptom severity.

The second main issue is that the relationship between an increased approach bias and decreased mood response to CR is conceptually unclear. In this respect, it would be natural to test whether mood responses influence subsequent gambling choices. This could be done either within the model by having mood moderate the approach bias or outside the model using model-agnostic analyses.

Additionally, there is a conceptual inconsistency between the choice and mood findings that partly results from the analytic strategy. The approach bias is implemented in choice as a categorical value-independent effect, whereas the mood responses always scale linearly with the magnitude of outcomes. One way to make the models more conceptually related would be to include a categorical value-independent mood response to choosing to gamble/not to gamble.

The manuscript requires editing to improve clarity and precision. The use of terms such as "mood" and "approach motivation" is often inaccurate or not sufficiently specific. There are also many grammatical errors throughout the text.

Claims of clinical relevance should be toned down, given that the findings are based on noisy parameter estimates whose clinical utility for the treatment of an individual patient is doubtful at best.

Comments on revisions:'

The authors adequately addressed my comments and I find the manuscript substantially strengthened.

Reviewer #2 (Public review):

Summary:

The authors present a computational framework for generating "cell-specific" digital twins of human iPSC-CMs from a single optimized voltage clamp recording. Using deep learning trained on > 1 million artificial cells, the authors demonstrate that the model can infer 52 biophysical parameters governing 6 major ionic currents, and the resulting digital twins can reproduce experimentally recorded action potentials.

Comments on revised version:

The authors propose an interesting platform for digital twin construction of iPSC-CMs using an AI-based approach. However, regarding the fundamental concerns raised in the previous review round "lack of experimental validation" and "overstatement of the claims", the authors have merely added text to the "Limitations" in the Discussion, without providing any new wet-lab experimental data. This cosmetic revision fails to demonstrate the scientific validity of the platform, and the core issues remain completely unresolved.

I think the authors need to either provide substantial additional experimental data or drastically tone down the claims throughout the manuscript based on the following three major concerns.

(1) Lack of wet validation

The authors show that their AI model can infer 52 parameters from a single patch-clamp recording and reproduce the overall action potential waveform. However, the most critical validation (whether the individual ion channel parameters, such as IKr/ICaL, inferred by the AI actually match the true parameters of that specific cell) is still missing. Without a direct head-to-head comparison between the parameters inferred by the model and the exact values measured using conventional wet experiments, it is impossible to determine whether the platform is providing accurate prediction (or merely performing a curve-fitting).

(2) Absence of experimental validation for drug response simulations (Cell 1 vs. Cell 2)

In Figure 6, the authors present a simulation result where the administration of an IKr blocker (E-4031) induces EADs in the digital twin of Cell 1, but not Cell 2. However, there is absolutely no wet-lab validation for this prediction. Unless the authors actually administer the same drug to the live Cell 1 and Cell 2 from which the recordings were taken, this "computational drug response prediction" remains purely hypothetical. There is no evidence provided that the prediction accurately reflects real biological responses.

(3) Significant overstatement regarding "inter-individual variability" and "personalized medicine"

The authors state in the very first sentence of the Abstract: "Individual variability shapes how diseases manifest, how patients respond to therapy, and how rare phenotypes arise". However, this opening sentence is severely disconnected from the actual conclusions and data presented in this study. The platform can capture only "cell-to-cell variability within the same dish" (which is not even validated), and thus claiming "patient-to-patient differences" is an overstatement.

Reviewer #3 (Public review):

Summary:

This work use convolution neural network to optimize a voltage clamp protocol to identify features and parameters from human pluripotent stem cell-derived cardiomyocytes.

Strengths:

The major strength is the methodology used to bridge in silico prediction of cell behavior and mechanistic insights from experimental dataset.

Comments on revised version.

As highlighted by the authors, due to the variability of the hPSC-CM model, to increase the applicability of this method, additional experimental dataset from different hPSC-CM lines would increase the translation of this approach.

I personally found that the detailed description of the methods, including the rationale of including/excluding some parameters, is extremely helpful to whoever would like to use this approach in their research.

Reviewer #1 (Public review):

[Editors' note: this version has been assessed by the Reviewing Editor without further input from the original reviewers. The authors have addressed the comments raised in the previous round of review.]

Summary:

In the manuscript by Winke et al, the authors present evidence that fear-induced analgesia is mediated by somatostatin projection cells from the vlPAG to the RVM. This study uses a mouse model of fear-induced analgesia, and incorporates optogenetic circuit manipulation with behaviour and electrophysiology to gain a meaningful insight into a novel circuit involved in fear-induced analgesia.

Strengths:

(1) This is a well-constructed study with appropriate controls and analyses.

(2) Alternative interpretations of the data are systematically considered and eliminated via rational experiments. The authors are commended for a nice piece of experimental work.

(3) The vlPAG is a known region of pain modulation, and this study adds valuable insight to the circuit involved in fear-associated analgesia.

Weaknesses:

Only male mice are included in this study. [This has been explained and noted as a limitation.]

Reviewer #2 (Public review):

Summary:

Wenke et al. investigated the role of vlPAG somatostatin-expressing neurons in the mediation of analgesia during defensive states. A newly developed paradigm of cued fear-conditioned analgesia, which consists of a combination of an auditory fear retrieval session and a pain test, was used to evaluate this cell population's contribution to fear-mediated analgesia. Optogenetic manipulation of vlPAG SST+ neurons modulated the responses to a nociceptive cue (Hot Plate) presented concomitantly with an aversively conditioned tone. At the same time, alterations in the freezing levels could be observed during optogenetic activation of vlPAG SST+ neurons. In order to disentangle the impact of these cells on analgesia from their impact on the expression of defensive behaviors, the authors performed electrophysiological recordings from the dorsal horn in the spinal cord of anesthetized mice. A vlPAG-RVM-DH pathway was identified to trigger nociceptive C-fibers upon optic activation of the RVM. Finally, pathway-specific activation of SST+ vlPAG-RVM neurons could abolish CS-induced analgesia.

Strengths:

The study addresses a relevant topic, that is, brainstem circuits for pain-modulatory mechanisms as part of defensive states evoked by threat. This is important because the circuit mechanisms underlying pain are still not fully understood, and defining molecular markers of cellular circuit substrates may support the identification of potential pharmaceutical targets in treating pain. The authors confirm a previous study in that a somatostatin-positive cellular population presents a crucial vlPAG circuit element mediating anti-nociceptive effects. Key novelty aspects of the present study are the demonstration that these neurons seem to play a role specifically in threat-induced analgesia. This was possible by the elegant design and application of a novel fear analgesia paradigm, combined with cell- and pathway-specific optogenetics.

Reviewer #3 (Public review):

Summary:

Conditioned analgesia refers to the ability of a learned fear cue to suppress pain-related behavior and neural activity. Understudied, the authors developed a novel conditioned analgesia procedure in which a cue that had been paired or unpaired with shock was played while a hot plate increased temperature. Compared to several control conditions, the authors found increased latency to a nociceptive response (paw licking). The authors identified somatostatin neurons in the periaqueductal gray as a likely mediator of the behavior. They then showed that: (1) stimulating vlPAG-SST neurons blocked nociceptive response latency increases to the CS+, (2) stimulating vlPAG-SST neurons suppressed fear retrieval freezing, (3) stimulating vs. inhibiting vlPAG-SST neurons drove opposing modulation of c-fibers and Aδ-fibers, (4) direct-projecting vlPAG SST neurons modulate freezing while RVM-projecting vlPAG SST neurons modulate conditioned analgesia.

Strengths:

These experiments have many strengths. The behavioral assay is chief among them. The assay is robust and controls for confounding factors to reveal a repeatable effect of a shock-paired cue to delay nociceptive responding. The optogenetic experiments provide the correct level of temporal precision, given the authors' time-specific interest in cued responding. Combining neuronal manipulations with spinal recordings is particularly innovative, especially in the context of more behavioral neuroscience-based assays. All-in-all, I found this to be an exceptionally strong set of experiments.

Weaknesses:

No obvious weaknesses were identified by this reviewer.

Joint Public Review:

[Editors' note: this version has been assessed by the Reviewing Editor without further input from the original reviewers.]

The major strengths of the manuscript are in the Plasmodium falciparum genetic and phenotyping approaches. PfMSP2 knockouts are made in two different strains, which is important as it is know that invasion pathways can vary between strains, but is a level of comprehensiveness that is not always delivered in P. falciparum genetic studies. The knockout strains are characterised very thoroughly using multiple different assays and the authors should be commended for publishing a good deal of negative data, where no phenotype was detected. This is not always done but is very helpful for the field and reduces the potential for experimental redundancy, i.e., others repeating work that has already been performed but never published. The quality of the writing, referencing and figures is also generally strong.

There are certainly some areas of the manuscript that would benefit from deeper exploration, such as electron microscopy/other imaging approaches to explore whether deletion of PfMSP2 has a visible impact on merozoite surface structure, further replicates of the video microscopy assays to see whether trends in the data could reach significance (although these are very time-consuming and technically difficult assays), and follow up of some of the genes where expression is changed by PfMSP2 knockout (as the authors point out, there are no candidates that have a very obvious link to invasion suggesting that they may be compensating for PfMSP2 function, although several are expressed in schizont stages). However, there is already a substantial amount of data in the manuscript, and more detailed follow-up is reasonable to leave to future work. Overall, with the modifications made through the review process, including the addition of new controls for key experiments, the claims and conclusions are justified by the data, and the manuscript generates important new information about a highly studied Plasmodium falciparum merozoite surface protein. The studies are important and have potential for directing vaccine design targeting erythrocyte invasion, a critical step in bloodstream expansion of malaria parasites.

Reviewer #1 (Public Review):

Summary:

This study aims to understand how cell fusion contributes to wound healing using a laser-induced injury in the notum epithelium of a developing fruit fly. The authors meticulously characterize the epithelial fusion events using a live imaging approach and report that syncytia arise by 'border breakdown' and 'cell shrinking'. The syncytial epithelial cells also appear to outcompete mononucleated cells and preferentially dissolve their tangential borders, which correlates with the accumulation of actin at the leading edge.

Strengths:

The strength of this study is the authors' live imaging approach to capture these dynamic fusion events that are a fundamental yet poorly understood biological process.

Comments on revised version.

The manuscript overall is significantly improved and authors addressed majority of my concerns. The addition of the computational vertex model (Figure 7) as well as Atg1 RNAi (Figure 4) to inhibit cell fusion provide more mechanistic insight to their study. However, the analysis of Atg1 RNAi wound assay falls short as it does directly measure changes in syncytium frequency nor size to confirm that cell fusion is reduced. The authors should quantify the number of nuclei per syncytium over the 2hr wound healing period as performed for WT in Figure 1C. It would have been ideal if they could have also performed the Act-GFP spreading assay in WT and Atg1 RNAi strains to determine if Act-GFP movement is dependent on cell fusion as purposed. At the least, further quantification of Atg1 RNAi phenotype is warranted to support their conclusions.

Reviewer #2 (Public Review):

Summary:

Overall, this study provides a thorough description of the formation of syncytia following wounding of the proliferation-competent diploid epithelium of the pupal notum. While this phenomenon has already been described briefly for this particular tissue by the Galko lab in Wang et al 2015, the authors provide a much more detailed description and characterisation of the process providing some novel insights (radial versus tangential border breakdown, cell shrinkage, timings, syncytia outcompeting mononucleated cells, etc.).

Strengths:

This paper provides an elegant, thorough, descriptive characterisation of syncytia-driven wound closure using state-of-the-art confocal live imaging of the pupal notum. The authors show that laser-induced wounding of this diploid, proliferation-competent epithelium results in the formation of syncytia of various sizes in the first few cell rows around the wound edge, which progressively become bigger as healing proceeds. This results in ~50% of cells becoming part of these syncytia. The cell fusion events were convincingly demonstrated by showing the disappearance of p120ctnRFP and E-Cadherin-GFP from cell-cell borders as well as cytoplasmic GFP mixing of GFP-positive cells with a GFP-negative cell.

Apart from cell-cell fusion by border breakdown that mostly happens in the first 2h following wounding, the authors also found that at later stages of wound healing cell shrinkage following cytoplasmic mixing contributed to syncytia formation.

Next, the authors provided some convincing evidence that syncytia outcompete mononuclear cells for being positioned in the first cell row around the wound.

The authors then show that radial border breakdown occurs much less frequently than tangential border breakdown. They suggest that radial border breakdown reduces the requirement for cell-cell intercalations. They also hypothesise that tangential border breakdown might allow fused cells to share resources and provide more resources to be used near the wound edge, e.g. for actomyosin cable formation. To test this, the authors generate single-cell clones that overexpress Actin-GFP. They then show convincingly how a single Actin-GFP-positive cell in the second cell row fuses with one GFP-negative cell in the first cell row. The Actin-GFP signal then spreads in the fused cell and labels some previously unlabelled actin-rich structure near the wound edge which most likely is the actomyosin cable. This provides some evidence for resource sharing by cytoplasmic mixing following fusion.

Comments on revised version:

The authors have extended their original manuscript by adding two key parts. First, they show a role of Atg1 in mediating cell fusion (Figure 4). Second, they provide additional evidence for a contribution of radial border fusions to wound closure through its effect on tissue fluidity and through computational modelling (Figure 7).

This new version of the manuscript is greatly improved and provides significant new insights into the role of syncytia in aiding wound repair. There are just a few minor, yet important, additions needed to back up Figure 4 which should not require new experiments.

Minor but important points:

The authors show a role of Atg1 in mediating syncytia formation in Figure 4. However, since the Pnr>+ side of the wound closes slower than the non-Pnr side (control side), a few additions to this figure would be important and should not require additional experiments.

(1) The authors should show, similar to the data shown in Figure 4D of the wound radius over time for control versus Pnr>Atg1RNAi, also the same type of data for control versus Pnr>+.

(2) Since Pnr>+ also slows down wound healing, albeit to a lesser extent than Pnr>Atg1, the authors should also show an extra graph that provides evidence that Pnr>Atg1RNAi reduces syncytia formation more than Pnr>+ does. E.g. Two graphs could be added that show individual cell size at 4 or 5h post wounding for control versus Pnr>Atg1RNAi as well as for control versus Pnr>+ and also another graph with the same data but comparing cell size between Pnr>+ and Pnr>Atg1RNAi. Otherwise, if the expected minimum cell size for a syncytium is easy to estimate, a graph could be added that shows the percentage of cells that are above this threshold (e.g. above 100 square micron) for control versus Pnr>Atg1RNAi and control versus Pnr>+ and Pnr>+ versus Pnr>Atg1RNAi.

Reviewer #3 (Public Review):

In this revised manuscript, White et al. aimed to understand the wound-induced syncytia formation behavior in wound repair of Drosophila melanogaster pupal notum. For this purpose, the authors characterized two different types of adherens junctions' outcomes during syncytia formation around the wound region - border breakdown versus apical shrinking which appear to happen in different time points and for different time durations. The authors characterized cell-cell fusion events using cytoplasmic, junctional and nuclear markers. They determined that about half of the cells within 70 um radii from the wound undergo cell-cell fusion. They studied wound induction on the border between control epithelia and pnr domain suggesting that Atg1 is required for post-wound syncytia formation and wound closure. They showed that during wound closure syncytia gradually invade the wound leading edge mostly by radial fusion events. The data suggests that intercalation of cells from the leading edge slows down the wound closure process. They propose that cell fluidity of syncytial cells plays a role in wound closure speed. Finally, the authors showed that actin is concentrated to the front edge of syncytia located in the wound leading edge. The authors described some aspects of syncytia formation during wound closure using different approaches. Some clarifications are needed as described below.

Major suggestions:

(1) Introduction, page 4. The examples of developmental syncytia formation of invertebrates and vertebrates are confusing. The authors may want to make the examples clear and add additional examples. Currently, readers may assume that C. elegans cell fusions occur only in the hypodermis - other structures can be mentioned like the vulva, pharyngeal muscles, glia, tail. In addition, the authors may want to add injury-induced fusions like the C. elegans' PLM and PVD neurons (Ghosh-Roy et al., 2010; Newman et al., 2015; Oren-Suissa et al., 2017).

(2) In cases where it is not clear whether fusion has occurred or whether mononucleated cells were ejected from the leading edge, membrane markers can be used. Page 6. Lines 96-99. The authors may want to use a membrane marker like RFP-PH driven by the epithelial cell promoter.

(3) Pages 8-10. The authors may want to clearly explain that apical junctions shrinking is a post fusion event. That the apical shrinking is caused by the expansion of fusion pores and the migration of apical junctions towards the basolateral domain. This is something that was clearly shown during physiological epidermal cell-cell fusion in C. elegans by Mohler et al., 1998 and 2002. A cartoon showing the process of cell-cell fusion, pore expansion and apical junction dynamics would make the manuscript much clearer.

(4) Page 9. Line 170. "...as these cells represent fusion initiation events (fusion pore) but were unable to productively stabilize and expand the site of fusion and so returned to the diploid state." The authors may want to make clear that this is an assumption that needs to be tested. Live imaging using a membrane marker may resolve whether a reversible fusion pore was generated.

(5) Page 11. It is not clear whether Atg1 is directly required for cell fusion, or that autophagy is required for efficient cell fusion or both Atg1 and autophagy participate in the fusion process.

(6) Page 12. Line 235. "Indeed, we observed that several hours after wounding, the entire leading edge was occupied by syncytia." This observation is based only on the adherens junction marker. Can they test basal cell membrane marker? Is it possible that the mononucleate cell in the leading edge is under the two syncytia?

Reviewer #1 (Public review):

Summary:

This study presents a systematic behavioral characterization of object classification abilities in macaque monkeys using a high-throughput touchscreen-based paradigm. The work shows that monkeys can learn and generalize many binary object classification rules, and compares their behavior with humans and computational models. A key finding is that monkey behavior is more closely aligned with visual deep neural networks, whereas human behavior is better captured by language-informed models. The study provides a useful benchmark for understanding visually grounded object categorization in nonhuman primates.

Strengths:

The study introduces a scalable and well-controlled behavioral paradigm for testing many object classification rules in macaques. The comparison across monkeys, humans, and computational models is a major strength and makes the work broadly relevant to visual neuroscience, comparative cognition, and computational modeling. The results provide an informative framework for distinguishing categorization based primarily on visual representations from categorization supported by semantic or language-based knowledge.

Weaknesses:

Some aspects of the interpretation would benefit from clarification. In particular, it remains somewhat unclear what stimulus-level factors drive image difficulty, how much training performance reflects general rule learning versus repeated reinforcement of specific images, and whether monkeys and humans apply the same category rules. The link between macaque IT representations and monkey behavior is also suggestive but not yet fully resolved, given the limited and separate neural dataset.

Reviewer #2 (Public review):

Summary:

The paper tackles a very interesting question and provides a solid and systematic piece of data that may be useful for numerous NeuroAI works in the future. The question is how well can macaque monkeys with a "pretrained" visual system without human knowledge learn to categorize images based on different kinds of (sometimes arbitrary) category definitions. In general, I love the paper, and I think both the data and presentation of it are beautiful.

Strengths:

(1) The authors developed a scalable method for training and studying this behavior, and did an exhaustive evaluation of monkeys' behavior and learning process.

(2) Beyond the behavior result, they performed extensive analysis and control experiments to isolate the cue monkeys are using to perform the categorization.

(3) The extensive comparison of behavior with deep neural networks is also super interesting.

(4) The authors performed a very careful examination of generalization behavior in monkeys, similar to standard practise in machine learning.

(5) The presentation of the data is very beautiful and deliberately designed, kudos to the authors for their efforts!

(6) I really enjoyed the further categorization task based on human knowledge, and the arbitrary rule task; this really pushes our understanding of the visual categorization and learning capability of monkeys.

(7) The examination of *learning dynamics* in human vs monkey is also quite interesting, i.e., humans can "understand the rule" and learn much faster versus monkeys learning across a few days.

Weaknesses:

(1) Though all results are pretty cool, the organization of results, figures, and sections can be modified to flow even better.

(2) Maybe provide DNN categorization and generalization results for the non-main monkey experiments (Figures 2,3), those comparisons can be really interesting too!

Reviewer #1 (Public review):

Summary:

This study constructed engineered NK-92 cell extracellular vesicles displaying CD19 single-chain variable fragment and evaluated their therapeutic efficacy in MRL/lpr mouse models of systemic lupus erythematosus, demonstrating that these vesicles could deplete B cells, alleviate lupus nephritis, and improve mouse survival. However, this strategy lacks significant innovation compared to existing research. The current results are not sufficient to provide strong support for the experimental hypotheses.

Weaknesses:

(1) This study proposes using engineered EVs displaying CD19 scFv to target B cells for SLE treatment. However, similar core therapeutic strategies have been reported in previous studies. For instance, recently, studies have reported engineered EVs for SLE therapy (J Control Release. 2025, 384:113886; Ann Rheum Dis. 2025, 84(11):1811-1821; J Nanobiotechnology. 2026, 24(1):203). Another research team from China also constructed engineered EVs displaying anti-CD19 scFv for SLE treatment, which is highly consistent with the present work in targeting strategy, delivery vehicle, and disease model (Mol Ther. 2026:S1525-0016(26)00080-8). Moreover, the human trial of allogeneic CD19-targeted CAR-NK therapy for SLE has been published (Lancet. 2026, 406(10522):2968-2979). This study has not made original improvements in therapeutic vectors, targeting modules, therapeutic mechanisms, and indications, and thus finds it difficult to meet the requirements of high-level journals for originality and novelty.

(2) Numerous core experiments are missing, including the validation of CD19 scFv fusion protein expression on EVs, systematic characterization of engineered EVs, verification of EVs functions and therapeutic mechanisms, and in vitro and in vivo safety assessments. The available data are insufficient to support complete conclusions.

(3) The stable expression of CD19 scFv on EVs should be further verified by Western blot or flow cytometry. The anchoring of CD19 scFv on the outer membrane surface of EVs must be confirmed. In addition, the loading capacity of CD19 scFv on exosomes should be quantified for the dosage selection in SLE treatment.

(4) In vitro experiments are required to confirm the specific targeting ability of CD19 scFv-EVs to B cells and clarify the precise mechanism of B cell depletion, particularly whether it is mediated by effector molecules carried by exosomes such as perforin and granzyme B.

(5) The key quality control parameters, such as the stability, purity, buoyant density, and particle/protein ratio of engineered exosomes, should be characterized and identified.

(6) For the in vivo treatment experiments, the author needs to explain how the treatment dose of CD19scFv-EVs was determined in order to clarify the dose-effect relationship.

(7) It is necessary to supplement with in vivo imaging and tissue distribution data to prove that the CD19 scFv-EVs can specifically accumulate in B-cell organs such as the spleen or lymph nodes.

(8) The author needs to clarify the mechanism by which CD19 scFv-EVs reduce B cells in vivo and verify the caspase apoptosis pathway.

(9) For the in vivo therapeutic experiments, the clinical first-line drugs and the free CD19scFv should be used to supplement the control group to highlight the advantages of the engineered EVs.

(10) Safety assessment in this manuscript is completely absent. Routine toxicity examinations, including hepatic and renal function tests, routine blood tests, and histopathological analysis of major organs in mice, must be supplemented. In addition, the systemic inflammatory cytokine profile and anti-drug antibody levels should be determined to rule out critical safety risks such as cytokine release syndrome and immunogenicity. The authors only focused on alterations in B cells; the impacts of the treatment on T cell subsets, NK cells, and monocytes/macrophages should be further investigated.

Reviewer #2 (Public review):

Summary:

Sun and colleagues report the development of an engineered extracellular vesicle platform derived from NK-92 cells that display an anti-CD19 single-chain variable fragment (scFv) on their surface via fusion with LAMP-2B (V-CD19-Exo). In an MRL/lpr mouse model of SLE, the authors demonstrate that intraperitoneal administration of V-CD19-Exo reduces splenic CD19+CD20+ B cells, attenuates proteinuria and lupus nephritis pathology, downregulates pro-inflammatory cytokines (IL-17A, IFN-γ) and autoantibodies (anti-dsDNA, ANA), and improves survival from approximately 25% to 80%. The authors propose that this "cell-free" targeted extracellular vesicle strategy offers advantages over conventional cell therapies, including lower immunogenicity, scalable production, and no requirement for lymphodepletion.

The study addresses an important question in autoimmune disease therapeutics: how to achieve targeted B cell depletion while avoiding the complexities and safety risks associated with CAR-T/CAR-NK cell therapies. The concept is novel, and the initial in vivo efficacy data are encouraging. However, several significant limitations in experimental design, mechanistic depth, and evidence rigor temper the strength of the conclusions.

Strengths:

(1) Novel conceptual approach.

The adaptation of CAR targeting principles to extracellular vesicles represents a creative and potentially impactful strategy. By displaying CD19 scFv on NK-92-derived vesicles, the authors successfully confer B cell-targeting capability while retaining the cytotoxic effector functions of the parental NK cells. This "cell-free" concept addresses genuine limitations of live cell therapies, including the need for lymphodepletion, risks of cytokine release syndrome, and manufacturing complexity.

(2) Comprehensive in vivo efficacy readouts.

The study evaluates therapeutic effects across multiple clinically relevant endpoints: B cell depletion (flow cytometry), renal function (proteinuria, UPCR), renal histopathology (HE staining with semi-quantitative scoring), systemic inflammation (IgE, IL-17A, IFN-γ), autoantibody production (anti-dsDNA, ANA), and survival. This multi-dimensional characterization strengthens the phenotypic evidence for efficacy.

(3) Appropriate control groups.

The inclusion of non-targeted NK92-Exo as a control allows attribution of the observed effects to CD19-mediated targeting rather than non-specific vesicle-associated activities.

(4) Significant survival benefit.

The improvement in survival from 25% to approximately 80% in V-CD19-Exo-treated mice is substantial and represents arguably the most compelling evidence for therapeutic potential in this model.

Weaknesses:

(1) Mechanism of B-cell reduction remains unclear.

The manuscript reports a dramatic reduction in splenic CD19+CD20+ B cells (from 10.53% to 1.51%) following V-CD19-Exo treatment. However, the authors do not establish whether this results from direct cytotoxicity (e.g., perforin/granzyme-mediated killing, apoptosis induction) or from functional suppression/downregulation of CD19 expression. The authors speculate that the effect is likely mediated by cytotoxic proteins carried by NK-92-derived vesicles, but no data are provided to support this mechanism. Essential experiments would include the detection of apoptosis markers (Annexin V, activated caspase-3/7) in B cells, assessment of perforin/granzyme B content within V-CD19-Exo, or in vitro co-culture assays demonstrating direct B cell killing.

(2) Small sample sizes.

Most experimental endpoints were assessed with n=5 per group, which is marginal for detecting modest effect sizes and may amplify the influence of individual biological variation. While the survival study had n=10 per group, the main mechanistic and endpoint analyses would benefit from larger cohorts (n=8-10) to increase statistical power and robustness.

(3) No dose-response or dosing optimization studies.

All experiments used a single dose (10⁹ particles per injection) and a fixed schedule (twice weekly for three weeks). The absence of dose-response data leaves unclear whether the observed effects represent maximal efficacy or could be achieved with lower doses, and whether alternative dosing regimens could improve outcomes or reduce potential off-target effects.

(4) Lack of safety assessment.

The authors emphasize the theoretical safety advantages of extracellular vesicles over cell therapies, but no systematic safety evaluation is presented. Key missing data include: histopathological examination of non-target organs (liver, lung, heart, gastrointestinal tract), assessment of off-target immune activation (T cell responses, cytokine profiles beyond those measured), and evaluation of potential accumulation or toxicity with repeated dosing.

(5) Incomplete characterization of the engineered vesicles beyond targeting.

While the manuscript successfully demonstrates CD19scFv display and vesicle enrichment of exosomal markers, it does not characterize whether V-CD19-Exo retains the full spectrum of NK-92 effector molecules (perforin, granzymes, FasL, TRAIL, cytokines such as IFN-γ) at functional levels. Quantitative or semi-quantitative comparison of cargo between V-CD19-Exo and parental NK-92 cells or non-engineered NK92-Exo would help contextualize the observed in vivo effects.

(6) Sex as a biological variable is not systematically addressed.

The authors note in the Discussion that the same treatment showed more significant efficacy in male mice compared to females (data not shown), yet all main experiments were conducted exclusively in female mice. Given the strong sex bias in SLE epidemiology (approximately 9:1 female-to-male ratio) and potential differences in immune responses between sexes, this observation warrants systematic investigation rather than a footnote. Presenting the sex-differential data or alternatively, conducting adequately powered sex-stratified analyses would substantially strengthen the manuscript.

(7) Translational claims are premature.

The manuscript repeatedly emphasizes advantages over cell therapy (low immunogenicity, scalable production, no requirement for lymphodepletion) as if these are established properties of V-CD19-Exo. However, no experiments directly compare V-CD19-Exo to CAR-NK or CAR-T cells in terms of efficacy, immunogenicity, or safety. Similarly, claims of "scalable production" and "high batch-to-batch consistency" are not supported by any manufacturing or quality control data. These statements should be toned down or supported with empirical evidence.

Reviewer #3 (Public review):

Summary:

This manuscript describes the development of engineered NK-92-derived extracellular vesicles (EVs) displaying CD19scFv for targeted treatment of systemic lupus erythematosus (SLE). Using a CD19scFv-LAMP2B fusion strategy, the authors generated EVs intended to selectively target pathogenic B cells in the MRL/lpr lupus mouse model. The study reports reductions in CD19⁺CD20⁺ B-cell populations, improvements in proteinuria and renal histopathology, decreased inflammatory cytokines and autoantibody levels, reduced splenomegaly, and improved survival outcomes following treatment. The work aims to position engineered EVs as a cell-free alternative to CAR-T/CAR-NK therapies for autoimmune disease treatment. While the concept is interesting and potentially translational, the study currently lacks sufficient methodological rigor, EV purification standards, mechanistic validation, and comprehensive characterization to fully support many of the claims presented.

Strengths:

(1) The study addresses an important unmet clinical need in systemic lupus erythematosus and explores an innovative cell-free therapeutic strategy.

(2) The concept of combining CAR-like targeting approaches with engineered EVs is interesting and potentially translational.

(3) The manuscript includes both in vitro and in vivo experiments, including functional renal assessments, immune profiling, histopathology, and survival studies.

(4) The authors attempt to evaluate multiple disease-associated readouts, including proteinuria, cytokines, autoantibodies, splenomegaly, and survival outcomes, which strengthens the overall biological relevance of the work.

(5) The use of engineered NK92-derived vesicles as a scalable alternative to CAR-NK therapy represents a potentially attractive therapeutic platform.

(6) The in vivo therapeutic observations in the MRL/lpr lupus model are encouraging and warrant further mechanistic investigation.

Weaknesses:

(1) The EV isolation strategy is not sufficiently rigorous for defining the isolated particles as "exosomes" according to current International Society for Extracellular Vesicles/MISEV guidelines. The precipitation-based workflow without density gradient purification or SEC raises major concerns regarding EV purity and identity.

(2) No direct validation was provided demonstrating successful surface localization or functional accessibility of CD19scFv on EV membranes.

(3) The characterization of EVs is incomplete and insufficient. Additional positive/negative EV markers, purity metrics, and orthogonal characterization methods are required.

(4) The absence of density gradient ultracentrifugation is particularly concerning, given the systemic injection of EV preparations into mice, as contaminating soluble factors and non-vesicular particles may contribute to the observed therapeutic effects.

(5) The manuscript lacks adequate mechanistic studies explaining how engineered EVs mediate B-cell depletion or immune modulation.

(6) The in vitro functional assays are weakly designed, particularly the use of A549 cells for evaluating CD19-targeted vesicle function.

(7) Important methodological details are missing, including EV normalization strategies, flow cytometry gating controls, blinding procedures, and randomization approaches.

(8) Several figures, particularly TEM and western blot images, are of low quality and difficult to interpret.

(9) The study does not sufficiently exclude the possibility that observed therapeutic effects result from contaminating soluble immune mediators rather than EV-specific activity.

(10) Broader immune profiling is lacking despite the systemic immune complexity of SLE.

(11) The statistical analysis section includes tests that are not reflected in the Results section, creating concerns regarding data presentation and consistency.

(12) Overall, while the concept is interesting, the manuscript currently falls short of the experimental rigor expected for high-impact translational EV studies.

Reviewer #1 (Public review):

Summary:

The manuscript from Ali Guler's lab intends to test the impact of an integrated lifestyle around the timing of food, exercise, and light on circadian rhythm, metabolic health, and sleep in wild-type mice. After observing positive outcomes from short-term studies, they applied this integrated chronobiologically anchored lifestyle to mouse models of neurodegenerative diseases. They found some encouraging trends of health improvement that largely did not reach statistical significance.

Strengths:

Good experimental design to systematically test the effects of shorter day, timed voluntary exercise, and time-restricted feeding in rodents. The authors started with an experimental design that incorporated some findings from published papers. They used a shorter photoperiod of 8 h, which was shown to improve SCN synchrony and amplitude of the molecular clock. The use of time-restricted feeding with feeding aligned with the dark phase also has precedence. The late-night access to the running wheel is based on the published data on treadmill exercise in the late active phase, imparting better metabolic benefits. No other study has systematically integrated all three interventions into a single study. This is one of the uniqueness of the study.

Weaknesses:

Since the B6 strain of mice on normal chow does not show many health impairments, the choice of this strain and diet did not enable fine-grained analyses of each intervention on health outcomes. Although the authors used male and female mice, sex differences (if any) should have been explicitly addressed.

Reviewer #2 (Public review):

Summary:

The LiFE protocol provides shortened light exposure, as well as timed food availability and exercise (running wheel) availability. It causes mice to sleep for the first half of the active phase and to be active during the second portion, thus consolidating activity. This has some positive effect on metabolic markers and some (but not other) behavioral markers. In two AD models, there is the suggestion of a protective effect, though most of the data is not significant.

Strengths:

The concept is important and builds on previous studies showing cognitive benefits and decreased brain pathology in mice with time-restricted feeding or shortened light exposure. The comparison to multiple different light, food, and exercise timing regimens in Figure 1 is quite interesting and informative. The use of 2 different mouse models (5xFAD and 5xFAD::PS19) is a strength, as this latter model is rarely used. The pathological endpoints are appropriate.

Weaknesses:

The LiFE protocol is strange in that it induces sleep during the first several hours of the active phase. The mice seem to show food anticipatory activity, then suddenly go to sleep for a few hours during what should be their most active time of day. Is this good? Would we want such a thing in humans? Why does this happen? What is the real-life implication? How do the mice eat if they are sleeping so much during their food period?

While many of the cognition and brain pathology experiments seem to trend in a positive direction, most are not significant, which calls into question the value of the intervention. There are a few that are significant, but the overall effect seems weak. The experiments with AD mouse models are generally underpowered and not controlled for sex, as female mice get pathology much faster in the 5xFAD model, and males have more severe pathology in the PS19 model. Combining them may mask effects.

In all, it is an interesting and thought-provoking study which shows striking effects of the LiFE intervention on activity patterns and sleep, with modest/inconclusive effects on cognition and brain pathology. While it feels very preliminary, the study does provide some valuable information for planning future studies of circadian interventions in neurodegenerative models, even if the protective effects here are not fully solidified.

Reviewer #3 (Public review):

Summary:

This manuscript presents a multimodal circadian intervention ("LiFE") that combines short photoperiod exposure, time-restricted feeding, and scheduled exercise and examines its effects on circadian activity structure, SCN rhythmicity, sleep, glucose regulation, cognition, and Alzheimer's disease-related phenotypes in mice. The study is ambitious in scope and conceptually appealing. In wild-type mice, the authors report that LiFE consolidates activity rhythms, enhances SCN PER2::LUC amplitude, increases sleep, lowers baseline glucose, reduces glycemic variability, and improves novel object recognition. They then extend the paradigm to 5xFAD and 5xFAD/PS19 mice, where the effects are more modest and mostly trend-level, with limited evidence for improved behavior or reduced pathology.

Strengths:

Overall, the work is interesting and potentially important because it moves beyond single-zeitgeber manipulations and tests the idea that combining multiple entrainment cues may produce broader physiological benefits than light, feeding, or exercise alone. The WT dataset is the strongest part of the paper and provides evidence that the combined intervention changes circadian organization and metabolic physiology.

Weaknesses:

Alzheimer's disease claims are considerably less convincing than the title and framing suggest. The manuscript would be stronger if the authors more clearly separated the robust conclusions in WT animals from the preliminary, underpowered, and largely non-significant findings in the disease models. In its current form, the paper contains substantial merit, but several interpretive and methodological issues should be addressed before publication.

Reviewer #2 (Public review):

Summary:

The authors perform confirmation studies of Paul Basch's seminal schistosome work from 1981, demonstrating the development of transformed schistosomules into sexually dimorphic adult parasites, albeit without successful egg production. In addition to the findings from Basch's earlier work, the authors add some new molecular data in the form of analysis of proliferative cells in in-vitro derived animals.

Strengths:

The authors successfully confirm experimental results from earlier schistosome researchers, providing a potential new tool for studying schistosome biology without the need for vertebrate hosts.

Weaknesses:

The display of data from the authors is sometimes difficult to follow/understand where it comes from. For example:

(1) Line 136: the authors claim state that parasites in HS and FBS conditions have substantially different mortality rates (11.3 +/- 2.7 vs 5 +/- 2.3) but a quite high p-value (0.8). Analyzing the raw data myself, this reviewer obtained a mean of 8.2 +/- 1.7% vs 4.8% +/- 4.3% with a p-value 0f 0.15. Either the data are not clearly presented, and this reviewer did not follow them, or the data presented in the text do not match the raw data in the supplemental files.

(2) Line 187/Figure 4: though it is not clearly stated, it appears that the authors treat their EdU counts as an ordinal data set of 61 steps (from 0 to >60) rather than a continuous measure of EdU+ cells per animal. In this author's opinion, the graph strongly suggests a continuous data set, and the fact that this reviewer had to dig through poorly-labeled raw data to discover the nature of the data is problematic. The authors should either switch to a continuous data set or make it explicit that the data shown are ordinal. If counting EdU+ cells is too arduous, the authors could consider comparing the amount of EdU+ area to the amount of DAPI+ area in maximum intensity projections of their confocal images, as this would roughly approximate the amount of proliferative cells in the animals.

There are some minor issues as well:

(1) Line 122: it is perhaps incorrect to refer to humans as "the" definitive host of schistosomes, as S. japonicum is primarily considered a zoonotic infection with water buffalo/cows being the primary definitive host.

(2) Line 185/298 the authors refer to EdU pulse-chase experiments, but the experiments described here are EdU pulse experiments.

Comments on revised version.

Following the initial submission of the manuscript and a round of peer review, the authors updated the manuscript and addressed all of this reviewer's concerns. As such, this reviewer believes that the manuscript is substantially clearer and will serve as useful literature in the field of schistosome research.

Reviewer #3 (Public review):

Summary:

This study is significant as it established a protocol for the long-term culture of Schistosoma mansoni newly transformed cercariae which developed in vitro into sexually dimorphic forms. The impact of two different sera, Fetal Bovine Serum (FBS) and Human Serum (HS), added to the culture medium supplemented with human red blood cells was evaluated. The authors demonstrated that HS-cultured parasites were able to digest red blood cells, a critical step for long term parasite development. Furthermore, while most FBS-cultured parasites did not progress beyond an early liver stage, sexual dimorphism was clearly evident in the HS-cultured worms, albeit delayed compared to in vivo development.

Strengths:

This study could contribute to further in vitro studies for a better understanding of the unique sexual biology of Schistosoma mansoni and for screening novel schistosomicidal compounds. By increasing parasite development in in vitro studies this protocol could have a positive impact on the principles of the 3Rs (Replacement, Reduction and Refinement) for animal research.

Weaknesses:

As the authors mentioned "pairing between male and female parasites was rare. Pairing was rarely observed and only after day ~ 80 in culture. Egg production was also not achieved with this protocol.

Comments on revised version.

Some data presentation has been improved as suggested by other reviewers in the revised manuscript. The authors have also clarified the limitations of their long-term culture protocol for Schistosoma mansoni newly transformed cercariae which develop in vitro into sexually dimorphic forms with regards to male and female pairing. Additionally, they addressed my specific question regarding the culture conditions used for ex vivo/in vitro mating. The experimental conditions tested for in vitro developed parasites were the same as those for the pairing experiments. It remains to be investigated the factors that negatively influence pairing during the long-term in vitro culture of Schistosoma.

Reviewer #1 (Public Review):

Zeng et al.'s work links several key issues in Cryo Electron Tomography in ways that reinforce each other, inspired by the cycleGAN model, leading to very positive results across several benchmark datasets. The related topics include tomogram cleaning and simulations (two crucial areas in the field), with "spin-off" outcomes in automatic annotation and the completion of the missing wedge. The manuscript covers nearly all essential topics in Tomography, making it very comprehensive and potentially critical in the field. The generalization capabilities on the SHREC 2021 data set are very interesting, although difficult to quantify. I appreciate the approach, but I have serious concerns about some of the limitations of the results presented by the authors.

1. Simplified data versus nowadays challenging tomography data. It is acknowledged the difficulty in making general tests. In this work, the method shows excellent results on potentially simple data sets (the SHREC 2021, which was used for a benchmark in ET several years ago, but not much used since then) and, even more, the old Relion data set for picking).

2. Reproducibility by the average user. I have found many cases in which a specific software produces excellent results when run by the authors. Still, the average user is lost with the parameters and cannot reproduce these promising results. I propose that the authors address this issue by involving some experimental colleagues and ask them to repeat the work. This is a general concern that applies not only to this work but to many others. I think this consideration is crucial for a field that is growing very quickly and where method development happens at an extraordinary pace... but are all of them generally useful?

Reviewer #2 (Public Review):

This study introduces DUAL (Deep Unsupervised simultAneous denoising and simuLation), an unsupervised deep learning framework that jointly addresses denoising and realistic data simulation for cryo-electron tomography (cryo-ET). By leveraging a cyclic, unpaired learning strategy, DUAL avoids reliance on paired clean ground-truth tomograms, which represents a practical advantage over many existing supervised approaches.

Through extensive quantitative evaluations on benchmark datasets, together with qualitative and downstream analyses on diverse experimental tomograms, the authors show that DUAL performs robustly across both denoising and simulation tasks. For denoising, DUAL outperforms several widely used methods on the SHREC 2021 benchmark and achieves the highest particle-picking accuracy on the RELION benchmark, indicating strong downstream utility.

For tomogram simulation, the study presents an unsupervised framework that jointly denoises experimental tomograms and generates synthetic volumes that closely resemble experimental data. These simulated tomograms outperform existing approaches in downstream tasks such as particle picking and enable additional applications, including missing-wedge compensation and cross-domain adaptation, without requiring labeled training data.

Overall, this work represents a substantial contribution to the cryo-ET field by providing a versatile unsupervised tool that reduces dependence on labor-intensive manual annotation, enables realistic data augmentation for training downstream models, and facilitates artifact mitigation. As such, DUAL has the potential to accelerate methodological development and progress toward comprehensive in situ structural biology.

Reviewer #3 (Public Review):

The paper is titled "DUAL: Deep Unsupervised Simultaneous Simulation and Denoising for Cryo-Electron Tomography." The authors provided two closely related code branches: one for denoising and one for missing-wedge correction. However, I did not find the simulation component. This is important, as the authors state that "the simulation branch provides learning-based cryo-ET simulation to generate synthetic tomograms indistinguishable from experimental ones."

In addition, no pre-trained models were provided. Given that the authors indicate that all training data are publicly available, sharing trained models together with references to the corresponding datasets would significantly facilitate evaluation of the reported performance.

The provided instructions are quite minimal and do not currently support reproduction of the reported findings. Compared with other cryo-ET software packages, the documentation is insufficient for installation and practical use. The software also does not consistently support standard cryo-ET file formats, particularly during inference for denoising and missing-wedge correction. In particular, volume preparation (in the first notebook of either pipeline) expects MRC input, whereas inference requires NPZ input. This inconsistency makes me believe that the shared code is not tested, and likely is a new wrap up that does not correspond to the version used to generate the results in the paper.

I also found the denoising workflow difficult to interpret. The notebooks require a "clean" target volume as input, but it is not explained how such a volume should be obtained. It is unclear whether any clean volume may be used or whether this should be simulated based on what the user expects to contain in the input. The logic about this introduced prior is not clear. Additionally, it is not clear whether the default configuration parameters provided in the notebooks correspond to those used in the paper or are intended as illustrative examples. I had requested the exact configurations used to produce the reported results to avoid ambiguity.

After many hours of trial, debugging, and experimentation, I was able to train a model for missing-wedge correction using the default parameters, although the process was slow and memory-intensive. However, despite sustained effort over two days, I was not able to perform inference using the trained model. Full-volume inference fails due to shape mismatches, as the network is trained on fixed-size 3D patches but does not support whole-volume inputs. Patch-based inference also fails at the stitching stage due to incompatible output dimensions, even when using standard volume sizes (e.g., 1024 × 1024 × 400 voxels) that work correctly during patch preparation.

While less central, I also found the training time to be close to prohibitive. The notebook sets the number of epochs to two for a toy example and notes that more epochs are required for real experiments. In practice, training for a single tomogram required approximately 16 hours of computation on two high-end GPUs to reach only six epochs, and likely more would be required (100s?). Due to the inference issues described above, I was not able to evaluate the trained model.

Reviewer #1 (Public review):

[Editors' note: this version has been assessed by the Reviewing Editor without further input from the original reviewers. The authors have addressed the comments raised in the previous round of review.]

Summary:

The authors provide a resource to the systems neuroscience community by offering their Python-based CLoPy platform for closed-loop feedback training. In addition to using neural feedback, as is common in these experiments, they include a capability to use real-time movement extracted from DeepLabCut as the control signal. The methods and repository are detailed for those who wish to use this resource. Furthermore, they demonstrate the efficacy of their system through a series of mesoscale calcium imaging experiments. These experiments use a large number of cortical regions for the control signal in the neural feedback setup, while the movement feedback experiments are analyzed more extensively. The revised preprint has improved substantially upon the previous submission.

Strengths:

The primary strength of the paper is the availability of their CLoPy platform. Currently, most closed-loop operant conditioning experiments are custom built by each lab, and carry a relatively large startup cost to get running. This platform lowers the barrier to entry for closed-loop operant conditioning experiments, in addition to making the experiments more accessible to those with less technical expertise.

Another strength of the paper is the use of many different cortical regions as control signals for the neurofeedback experiments. Rodent operant conditioning experiments typically record from the motor cortex, and maybe one other region. Here, the authors demonstrate that mice can volitionally control many different cortical regions not limited to those previously studied, recording across many regions in the same experiment. This demonstrates the relative flexibility of modulating neural dynamics, including in non-motor regions.

Finally, adapting the closed-loop platform to use real-time movement as a control signal is a nice addition. Incorporating movement kinematics into operant conditioning experiments has been a challenge due to the increased technical difficulties of extracting real-time kinematic data from video data at a latency where it can be used as a control signal for operant conditioning. In this paper, they demonstrate that the mice can learn the task using their forelimb position, at a rate that is quicker than the neurofeedback experiments.

Reviewer #2 (Public review):

Summary:

In this work, Gupta & Murphy present several parallel efforts. On one side, they present the hardware and software they use to build a head-fixed mouse experimental setup that they use to track in "real-time" the calcium activity in one or two spots at the surface of the cortex. On the other side, they present another setup that they use to take advantage of the "real-time" version of DeepLabCut with their mice. The hardware and software that they used/develop is described at length, both in the article and in a companion GitHub repository. Next, they present experimental work that they have done with these two setups, training mice to max out a virtual cursor to obtain a reward, by taking advantage of auditory tone feedback that is provided to the mice as they modulate either (1) their local cortical calcium activity, or (2) their limb position.

Strengths:

This work illustrates the fact that thanks to readily available experimental building blocks, body movement and calcium imaging can be carried out using readily available components, including imaging the brain using an incredibly cheap consumer electronics RGB camera (RGB Raspberry Pi Camera). It is a useful source of information for researchers that may be interested in building a similar setup, given the highly detailed overview of the system. Finally, it further confirms previous findings regarding the operant conditioning of the calcium dynamics at the surface of the cortex (Clancy et al. 2020) and suggests an alternative based on deeplabcut to the motor tasks that aim to image the brain at the mesoscale during forelimb movements (Quarta et al. 2022).

Reviewer #3 (Public review):

The study demonstrates the effectiveness of a cost-effective closed-loop feedback system for modulating brain activity and behavior in head-fixed mice. Authors have tested real-time closed-loop feedback system in head-fixed mice two types of graded feedback: 1) Closed-loop neurofeedback (CLNF), where feedback is derived from neuronal activity (calcium imaging), and 2) Closed-loop movement feedback (CLMF), where feedback is based on observed body movement. It is a python based opensource system, and the authors call it CLoPy. Authors also claim to provide all software, hardware schematics, and protocols to adapt it to various experimental scenarios. This system is capable and can be adapted for a wide use case scenarios.

Authors have shown that their system can control both positive (water drop) and negative reinforcement (buzzer-vibrator). This study also shows that using the closed-loop system, mice have shown to better performance, learnt arbitrary tasks and can adapt to changes in the rules as well. By integrating real-time feedback based on cortical GCaMP imaging and behavior tracking authors have provided strong evidence that such closed-loop systems can be instrumental in exploring the dynamic interplay between brain activity and behavior.

Reviewer #1 (Public review):

Summary:

This article presents a study consisting of two experiments, which aim to dissociate and quantify the distinct motivational functions of phasic and tonic pain within a naturalistic and immersive VR setting. Specifically, the Authors test two hypotheses: (i) that phasic pain acts as a punishment signal that drives avoidance learning; (ii) that tonic pain reduces motivational vigor, promoting energy conservation and recuperation. In both experiments, participants performed a free-operant foraging task, where they collected virtual pineapples to earn points.

In Experiment 1, phasic pain was delivered as a brief electric shock to the grasping hand when picking up green pineapples. As phasic pain intensity increased, participants were less likely to choose painful fruits. A reinforcement learning model that incorporated reward, pain cost and effort cost was able to successfully capture behavior.

Experiment 2 combined effects of phasic and tonic pain. Tonic pain was induced by a pressure cuff on the non-dominant arm, simulating sustained discomfort. Interestingly, tonic pain did not affect the perceived intensity or avoidance of phasic pain. However, it significantly reduced movement velocity and pineapple collection rate, interpreted as a reduction of motivational vigor. A temporal decision model incorporating vigor cost successfully captured these effects.

Concomitant EEG recordings showed that tonic pain was associated with reduced alpha and beta power in parietal and temporal areas. Phasic pain ratings and decision values distinctively correlated with skin conductance responses.

Overall, these findings indicate that phasic and tonic pain have distinct and dissociable motivational effects.

Strengths:

This is an ambitious study that provides a quantitative dissociation of the roles of phasic and tonic pain in adaptive behavior, by integrating ecological neuroscience, motivational theory, and computational modeling. The use of immersive VR combined with a free-operant foraging task offers a more ecologically valid context to study pain-related behavior compared to traditional paradigms. Furthermore, the study employs a multimodal approach by combining behavioral data, computational frameworks, physiological signals and EEG. In particular, one of the main strengths of the study is the use of sophisticated computational modeling to capture phasic and tonic pain effects. The experiment codes are available on GitHub, increasing reproducibility.

Weaknesses:

As recognized by the Authors, there is no control condition involving an innocuous salient stimulus to rule out non-specific effects of distraction.

Reviewer #2 (Public review):

Summary:

The study investigated the distinct roles of phasic and tonic pain in adaptive behavior. Phasic pain was proposed to function as a teaching signal, promoting avoidance of further injury, while tonic pain was hypothesized to support recuperative behavior by reducing motivational vigor. This hypothesis was tested using an immersive virtual reality (VR) EEG foraging task, in which participants harvested fruit in a forest environment. Some fruits triggered brief phasic pain to the grasping hand, which in turn reduced the likelihood of choosing those fruits. Concurrently, tonic pressure pain applied to the contralateral upper arm was associated with reduced action velocities. The authors employed a free-operant computational framework to quantify how phasic and tonic pain modulate motivational vigor and decision value. Importantly, model parameters were found to correlate with EEG responses, providing neurophysiological support for the hypothesized functional distinctions.

Comments on revised version.

All my comments have been well addressed.

Reviewer #3 (Public review):

Summary:

This study investigates how phasic and tonic pain modulate behaviour in a free-operant foraging paradigm. The authors apply a computational modeling approach to the behavioural data to quantify the decision value of phasic pain, as well as the degree to which tonic pain reduces motivational vigour. EEG assessments showed, e.g., reduced signal power at alpha and beta frequencies in tonic pain conditions compared to no-tonic-pain conditions, but no association between these neural measures and motivational vigour. The authors conclude that tonic and phasic pain serve different motivational functions, with phasic pain acting as a punishment signal promoting avoidance and tonic pain reducing motivational vigour.

Strengths:

The experimental paradigm is highly innovative. Assessing human behaviour in a naturalistic yet highly controlled setting represents a promising approach to pain research. Notably, assessing pain magnitude implicitly, via its motivational value, offers insights about the overall pain experience that are not usually accessible via common pain ratings.

Reviewer #1 (Public review):

Summary:

This manuscript is an excellent follow-up to your 2022 study, in which Sox17 expression was localized to the rete testis and shown to be required for proper formation of the Sertoli cell valve (transition region). By using Nr5a1-Cre to drive conditional deletion of Sox17 specifically in rete testis cells, you demonstrate that testis weights remain normal at 2 weeks of age but become significantly reduced by 8 weeks in Sox17-cKO males. At the later time point, the seminiferous epithelium is severely disrupted, with apparent arrest of spermiogenesis: the epididymal lumen is essentially devoid of sperm, and most tubules lack elongated spermatids.

Strengths:

The study clearly shows the role of Sox17 in Sertoli cells as being important to SV function. The SV (transition region) between the rete testis and seminiferous tubules remains an understudied domain of testicular biology. The present work, together with the authors' prior study, highlights intriguing mechanisms operating in this specialized niche.

Weaknesses:

At the same time, the available data do not yet fully explain either the developmental assembly of the Sertoli valve or the precise consequences of its functional disruption. These studies are nonetheless valuable precisely because they raise more questions than they answer; the conceptual implications are thought-provoking.

Reviewer #2 (Public review):

This manuscript investigates the role of SOX17 in the formation and function of the Sertoli valve (SV) at the interface between seminiferous tubules and the rete testis (RT). Building on previous work showing that rete testis-specific deletion of Sox17 disrupts SV formation, leading to defective spermiogenesis and male infertility, the authors explore how SOX17 overexpression in Sertoli cells regulates the SV of rodent testes.

Using transgenic mouse models with ectopic Sox17 expression in Sertoli cells, the study demonstrates that SOX17 is not only required but can also modulate SV formation. Ectopic expression in Sertoli cells induces expansion of the SV structure and partially rescues SV defects and spermatogenesis in RT-specific Sox17 conditional knockout animals. The data support a model in which SOX17 acts through paracrine signaling to regulate SV formation, although the precise mechanisms remain to be clarified.

Overall, this is a well-executed study with novel and significant findings. The ability to experimentally manipulate SV size is particularly compelling and provides a valuable framework to study fluid dynamics and epithelial interactions in the testis. This work will be of broad interest to the reproductive biology and developmental biology communities.

Reviewer #3 (Public review):

Summary:

These studies are based on previously published work that showed that deletion of expression of the Sox17 gene in the testis essentially deleted the formation of the Sertoli valve in the Rete testis. The authors extended this work by constructing a vector that resulted in increased Sox17 expression by Sertoli cells and enhanced formation of the Sertoli valve in both wild type and Sox17 knockout mice. The work provides strong evidence supporting the requirement for Sox17 expression to allow formation of the Sertoli valve.

Strengths: The general approach was to express Sox17 from a Tg mouse that expressed Sox17 from Sertoli cells. This Tg mouse was bred into both the WT and the Sox17 KO mouse. The Sertoli valve was enhanced in both the WT/Tg mouse and KO/Tg mouse, showing that ectopic Sox17 could compensate in the Sox17 Ko and act in a concentration-dependent manner in the WT mouse. The results are strong and support the conclusions from the authors. The results were as expected from the original paper describing the KO of Sox 17. These results strengthen these conclusions and provide ideas for additional conclusions. These studies were technically challenging, and the authors provided a very solid manuscript.

Weaknesses:

The authors refer several times to high or low expression, but it all appears to be based on immunohistochemistry, and there is no real quantification using PCR, for example. The process used for cell quantification lacks a rationale for why certain numbers were assigned.

Reviewer #1 (Public review):

This study by Li and colleagues examines how defensive responses to visual threats during foraging are modulated by both reward level and social hierarchy. Using a semi-naturalistic paradigm, the authors test how the availability of water or sucrose, with sucrose being more rewarding than water, shapes escape behavior in mice exposed to looming stimuli of different intensities, which are used to probe perceived threat level and defensive responses. In parallel, the study compares dominant and subordinate animals to assess how social rank biases the trade-off between reward seeking and threat avoidance. By combining behavioral analyses with computational modeling, the work addresses how reward level and social context jointly influence escape decisions in an ethological setting.

Across the different experimental conditions, perceived threat level is the main determinant of behavior. The authors show that looming stimuli associated with higher threat (contrast) consistently elicit faster and more robust escape responses than lower threat stimuli. This effect is particularly evident during early exposures, when animals are highly vigilant and have not yet habituated to the looming stimulus (learned that it is not dangerous). Later they described that as animals gain experience and habituate, behavior becomes more flexible, and reward level begins to exert a graded modulation of the escape response. Importantly, the authors show that under high threat conditions increasing reward value leads to more frequent and faster escape rather than greater reward pursuit, specifically in dominant mice. This finding is particularly relevant, as it suggests that highly valued rewards can heighten vigilance and thereby enhance responsiveness to threat, highlighting that reward does not simply compete with defensive behavior but can also reshape it depending on the perceived level of danger, in contrast to low threat conditions, where threat can be more easily outweighed by reward. However, it is worth noting that the authors use an extremely low contrast for the low threat condition (20%), which may to some extent be insufficient to reliably trigger escape responses. Thus, an important conceptual contribution of the study is the introduction of vigilance as a useful framework to interpret these effects. Vigilance is treated as a behavioral state reflecting heightened attention to potential danger. In line with what is known from natural foraging, mice initially maintain high vigilance when confronted with an innate threat. This perspective helps clarify a finding that might otherwise appear counterintuitive. One might expect higher rewards to motivate animals to tolerate risk, explore more, and habituate faster in any scenario. Instead, the data suggest that highly rewarding outcomes can elevate vigilance, making animals more responsive to threat and leading to faster or more frequent escape under high threat conditions. In this sense, reward does not simply compete with threat but can also amplify sensitivity to it, depending on the internal state of the animal.

The social results are particularly interesting in this context as well. Dominant mice consistently prioritize avoidance over reward, showing stronger escape responses and slower habituation than subordinates. This behavior is well captured by the vigilance framework proposed by the authors: dominant animals appear to maintain higher vigilance, which biases decisions toward threat avoidance. The authors further suggest that stable social relationships sustain high vigilance and slow habituation, framing this as an evolutionarily conserved strategy that may enhance survival. This interpretation provides a valuable perspective on how social structure shapes defensive behavior beyond immediate physical interactions. At the same time, there are important limitations to this interpretation. All experiments were conducted in male mice, and it is possible that the relationship between social hierarchy, vigilance, and defensive behavior would differ substantially in females. In addition, the idea that stable social relationships sustain elevated vigilance should be interpreted carefully, as it does not fully align with broader views of social stability as protective against anxiety and stress and generally beneficial for mental health and resilience. These points do not undermine the findings but suggest that the social effects described here should be interpreted with caution and within the specific context of the task and sex studied.

Another important limitation is that the neural mechanisms underlying these effects remain highly speculative. Although the manuscript includes an extensive discussion of candidate circuits, particularly involving the superior colliculus and downstream structures, these interpretations go far beyond the data presented in the study and are not directly supported by experimental evidence within the paper itself. The discussion gives substantial weight to potential circuit mechanisms based primarily on previous literature rather than on findings from the current study. Given the complexity and distributed nature of the circuits likely involved in integrating vigilance, reward, social context, and defensive behavior, the present work is better viewed as providing a strong behavioral framework rather than direct mechanistic insight into the underlying neural substrates. In this context, some references discussing how animals learn to suppress defensive responses to repeated looming threats and the neural mechanisms supporting this process could further strengthen the discussion (Salay et al 2021; Fratzl et al. 2021; Conway et al. 2025; Mederos et al. 2025).

Methodologically, the behavioral paradigm is well suited for studying escape decisions in socially housed animals, and the machine learning based classification of defensive responses is a strength. The computational model provides a useful formalization of how threat level, reward level, and vigilance interact and may be valuable for other laboratories studying escape, approach avoidance, or conflict situations, particularly as a way to classify behavioral outcomes after pose estimation. More generally, the work will be of interest to the neuroethology community for its detailed characterization of escape behavior under naturalistic conditions. At the same time, some statements in the discussion slightly overstate the novelty of the methodological approach. For example, the claim that the study differs from earlier work by using machine learning rather than manual annotation overlooks that several previous studies have already implemented automated or semi-automated strategies to classify looming evoked defensive behaviors beyond manual scoring alone.

Given the ethological nature of the study and the high inter individual variability reported by the authors, clarity and precision in the methods are especially important for reproducibility. While the revised manuscript addresses many earlier concerns, some aspects remain slightly difficult to follow. For example, the main text states that animals were not water deprived to minimize differences in internal state across conditions, whereas parts of the methods describe experiments in which animals were water deprived. This distinction is not always clearly explained across the different experimental sections, despite internal state being central to the interpretation of the behavioral findings. A clearer separation and description of these conditions would further strengthen confidence in the work. In addition, it was somewhat surprising that the low contrast (20%) looming condition was still sufficient to trigger robust escape responses, and additional clarification or discussion regarding stimulus saliency at this contrast level could help readers better contextualize these findings.

Overall, this study provides a rich analysis of how reward level and social hierarchy modulate defensive behavior through changes in vigilance. It offers a useful conceptual advance for thinking about escape behavior in semi-naturalistic settings and lays a solid foundation for future work aimed at linking these behavioral states to underlying neural circuits.

Reviewer #1 (Public review):

Summary:

The manuscript uses large-scale existing datasets that span almost the full range of human life (5-100 years) to identify two distinct architectural cortical gradients within visual cortex. These gradients are distinct in that in one cytoarchitecture and myeloarchitecture converge and in the other they diverge. The authors tested whether these gradients mapped onto known functional properties of visual cortex, as well as accounting for visual behaviours that are impacted throughout the lifespan. The manuscript also reports the identification of a hitherto unknown cluster of visual field maps in the anterior temporal lobe.

Strengths:

A major strength of the current manuscript is the use of large-scale measurements of human brain structure throughout the lifespan, courtesy of the Human Connectome Project Initiative. The scope of this cross-sectional analysis would be rare, if not impossible to achieve through an individual project.

The approach employed holds promise for assessing the link between large-scale anatomical gradients in the brain and functional/behavioural properties. The current manuscript focuses on visual cortex, but the approach could easily be implemented across the brain in general.

Weaknesses:

While the evidence for a new topographic visual field map cluster in the anterior temporal lobe is less convincing than for clusters in posterior cortex, new analyses strengthen the claim for a visuospatially tuned cluster that shared signatures of topographically organised clusters (e.g., contralateral representations) but might lack clear evidence, at present, for such topography. Investigation of how age-related and SNR confounds contribute to gradients and their life-span development could be expanded.

Comments on revised version.

The authors have taken the comments onboard and performed a number of analyses that strengthen the argument for these clusters being visuospatial in nature. I appreciate the additional analyses and effort. It may be helpful to discuss the evidence for contralateral biases in the absence of clear topographic maps in cortex in the context of what others have terms visuospatial coding (Groen et al., 2021, TiCS) where just such a mechanism is described.

Reviewer #1 (Public review):

This manuscript addresses how PGCs migrate towards SGPs in the Drosophila embryo. It's been shown that Hh produced by SGPs acts as an attractive cue, and that Wunnen(s) act as repulsive cues. In this work, the authors propose that Wun and Wun2 refine PGC guidance by attenuating Hedgehog signalling coming from other tissues.

Overall, the study is potentially interesting and could make an important contribution to the field. The data shown support the idea that Wun/Wun2 negatively regulate Hh signalling and produce PGC migration phenotypes associated with Hh. However, in my opinion, there are two major questions that should be addressed.

(1) Which is the mechanism by which Wun/Wun2 attenuates Hh signalling? The authors propose that Wun/Wun2 block Hh ligand transmission, but their data could also be explained by other possibilities, such as altered Hh production, uptake, retention or degradation, among others. The authors should either show the effect of Wun/Wun2 in Hh transmission mechanistically or attenuate their claim.

(2) How do Wun/Wun2 attenuate Hh signalling in PGCs? The authors propose that Wun/Wun2 function both in somatic tissues and in PGCs, but these two sites of action may have very different mechanistic implications. In the soma, Wun/Wun2 could affect Hh transmission, but a PGC-autonomous role cannot be explained simply by reduced Hh ligand transmission from producing cells; it would more likely involve ligand uptake, receptor trafficking, intracellular degradation or altered PGC responsiveness. This distinction should be central to the interpretation of the data.

Reviewer #2 (Public review):

Summary:

In this submission, Roy et al. examine the process of Drosophila PGC migration. Directed cell migration requires the concerted activities of chemoattractants and repellents to guide cells to the correct locale. In their submission, the authors describe a role for regulated Hedgehog (Hh) signaling to inform PGC migration. In prior work, the authors reported that Hmgcr potentiates Hh signaling, providing a permissive axis. A gap in the field, however, was the identification of the repulsive cues that guide PGCs out of the midgut and toward the future gonad. In the current work, the authors report that two wunen genes (wunen and wunen 2) inhibit Hh signaling, thereby repressing Hh activity. The model is that Hmgcr and wunen(s) balance the transmission of Hh signals to enable effective PGC migration.

Strengths:

A strength of this work is the comprehensive genetic analysis performed by the authors. The authors examine zygotic versus maternal contributions, autonomous versus non-autonomous requirements, and use a variety of RNAi and mutant allele combinations to examine genetic requirements and interactions. Another strength is that the data presented are generally clear and well quantified. Insets are provided to enhance visualization, and relevant data are quantified through replicated experiments.

Weaknesses:

Weaknesses of the work include a lack of biochemical data to validate some of the proposed interactions. Although the authors do report lipidomics data, little is done with these findings to validate or place the results in the context of a mechanistic model. Despite these issues, the conclusions stated are generally well supported by the results.

Reviewer #1 (Public review):

Summary:

In this manuscript, the authors present a method to detect natural selection on transcription factor binding sites (TFBSs), which is an upgraded version of a previously published method (Liu and Robinson-Rechavi, 2020). This upgraded version of the test implements more explicit models of evolution and is shown to outperform its predecessor in terms of both power and false positive rate. I think this method can be a valuable resource for the community and can be helpful not only to studies of TFBSs but also broader evolutionary questions related to genotype-phenotype maps or fitness landscapes.

Major comments:

(1) Questions related to Figure 1

Figure 1, along with the first section of the Results, shows that the SVM score and its sensitivity to mutations are generally correlated with the strength of ChIP-seq signals. It is not very clear to me, however, what the motivation is behind this part of the paper. It seems that the model used to predict binding strength is a pre-existing one, and it is unclear what is new in this section. Was the prediction model retrained using different data? Was its validity confirmed using new data? I would appreciate some more elaboration on how these results differ from what was presented in the previous study of Liu and Robinson-Rechavi (2020).

The existence of weak or negative correlations between SVM and coverage, which reportedly reflects low-quality peaks, seems applicable not only to this paper, but also to previous ones, so I would like to have it confirmed whether the question and the authors' answers apply to previous studies as well.

It is reported that SVM scores capture TF binding signals better than conservation-based statistics do. My intuitive interpretation is that both ChIP-seq peaks and SVM scores are supposed to reflect binding strength, whereas conservation is supposed to reflect selection (i.e., different definitions of "function" as mentioned above). It is not explicitly explained in the Results, however, what the difference indicates, leaving only an impression that the SVM score is "better" than the conservation statistics.

In summary, I think further elaboration on the above problems would make the flow of thought of this paper easier to follow.

(2) Lack of directional selection for low binding affinity

In the analysis of Drosophila melanogaster ChIP-seq peaks, there were more cases of directional selection for higher binding affinity than directional selection for lower binding affinity. The authors suggested that this observation is "likely biological" because the same pattern was not seen in simulations (line 412-413). I wonder if this could have resulted from a difference in the distribution of ancestral binding affinity across TFBSs between real and simulated data. If binding affinity was generally low in the common ancestor of D. melanogaster and D. simulans, selection for low binding affinity would manifest mainly as purifying selection against mutations that increase affinity instead of directional selection. Ancestral sequences for simulations, if I understood correctly, are observed peaks in D. melanogaster (line 715-719), which would include high fraction sequences that could be rarer in the real ancestral sequences.

The description of this particular result does not refer to a figure or table, nor is it revisited in the Discussion. Figure 5 treats peaks under directional selection as a single category. Taken together, it is hard to tell how this observation should be interpreted. If the authors consider this result as biologically meaningful, I would suggest adding more details (e.g., the number of each side).

(3) Selection in non-focal lineages

Regarding the detected signals of directional selection for stronger binding in certain tissues (Figure 6), I wonder if it is the focal species or those very tissues that are "special": did the human lineage undergo more adaptive regulatory evolution than the chimpanzee lineage, or do nervous and male reproductive systems have a high "propensity" for adaptive regulatory evolution? Assuming that the binding preference of the same TF did not undergo a significant change since human-chimpanzee split (which, I believe, is a built-in assumption in both RegEvo and the permutation test), it should be possible to perform the same test using chimpanzee sequences that are homologous to the human ChIP-seq peak regions. In the case of coding sequences, for example, Bakewell et al. (2007) found that it was the chimpanzee that had more genes under positive selection than humans; I wonder if TFBSs show the same or a different pattern.

(4) Comments on terminology

a) Meaning of "function"

The word "function" has had different meanings in the biology literature, with some authors using "functional" to refer to anything with a phenotypic effect and some using it only for targets of selection. A (putative) TFBS would be considered "functional" as long as it has TF binding affinity if we follow the effect-based definition, but only if its binding affinity is under selection if we follow the selection-based definition. In this manuscript, the term "function" appears to have been used to refer to TF binding but not selection, most notably in the first Results section. There are also places where it is less clear what "function" means exactly (e.g., "deeply conserved elements that are likely to be functionally important" of line 61). Since this paper is about evolution, it is likely that many readers prefer the selection-based definition or assume that the selection-based definition would be used. Thus, using "function" to refer to just TF binding could be confusing. To this end, I would suggest that the authors drop the word "function" or give an explicit definition early in this paper.

b) Directional selection in different directions

In this paper, selection for increased TF binding affinity is referred to as "positive directional selection", and selection in the opposite direction is called "negative directional selection" (as exemplified in Figure 2). I understand that using such shorthand names would make the text less clumsy, but these two terms could potentially be confusing, as "positive selection" and "negative (purifying) selection" are also terms referring to specific types of selection and have some connection to directional and stabilizing selection. Therefore, I suggest that the authors use something like "selection for increased/decreased binding affinity" instead, or note explicitly in the text that "positive/negative directional selection" would be used as shorthand.

Reviewer #2 (Public review):

Summary:

The manuscript by Laverre et al. provides an interesting new test of selection on TF binding. Rather than focusing on sequence changes, this test is specifically for changes in predicted TF binding affinity. The authors report directional selection on 5.1% of tested regions in Drosophila, as well as a signal of selection on CTCF binding in the human CNS and male reproductive system.

Strengths:

Overall, I think this represents an important direction for the field of molecular evolution: now that TF binding can be predicted fairly well from sequence, it can be a very useful focus for tests of selection.

Weaknesses:

As mentioned several times in the manuscript, Jiang and Zhang (2024) pointed out some issues with a previous permutation-based version of this test. Foremost among these was the issue of ascertainment bias: when testing only experimentally supported TF binding sites from a focal species, and then asking what type of selection (or lack of selection) led to those sites, one is guaranteed to find more substitutions that increase affinity, simply because the sites were selected in the first place as those with maximum (empirically measured) affinity.

To address this issue, the authors simulated Drosophila CTCF peaks evolving neutrally and then tested different ascertainment cutoffs in Figure 4D. It was not entirely clear to me what is shown in Figure 4D: the text says the bins were stratified by derived delta-SVM, whereas the figure says SVM, and the legend says derived SVM (both without the delta). I was unable to find any clarification of this in the Methods section. In any case, I am not really convinced by this, for two main reasons. First, when analyzing empirical ChIP-seq data, I would guess that only a tiny fraction of the genome is bound (far less than 1%, especially in mammalian genomes). However, the most extreme bin in Figure 4D is taking the top 10% of (delta?) SVM values. What would Figure 4D look like at bins of the highest 0.1%, 0.001%, etc? My guess is there would be a strong uptick in the FPR. The second reason is actually more important and fundamental than the first. As long as this method is working as described, I cannot see any way that it would ‘not’ be impacted by ascertainment bias. As an extreme case, imagine that all TF binding sites tested had the maximum possible SVM scores; then none of them would have any chance of showing directional selection against binding, while even those that evolved neutrally would appear to have directional selection in favor of binding. Of course, real empirical data are not as extreme as this, but the same concept applies in less extreme scenarios.

This bias could explain patterns observed in the real data. For example: "We observe much more positive than negative directional selection, a pattern likely biological rather than methodological, since it is absent from simulations." This is exactly the pattern predicted under ascertainment bias (in the extreme-scenario thought experiment above). I suspect it is absent from simulations simply because the authors did not properly account for this bias in their simulations.

If the main result reported by the authors had been a lack of any directional selection in favor of binding, and instead only neutrality or directional selection against binding, then this ascertainment bias would not be an issue- it would only have made their results conservative. Unfortunately, this is not the case, and the directional selection in favor of binding, which is the main result emphasized from the empirical analysis, could be inflated by this bias.

Minor point:

The following statement: "In contrast, phastCons and phyloP scores lack such enrichment and have a lower dynamic range, suggesting that the conservation scores are less sensitive to fine-scale variation of TF occupancy and thus regulatory region function" is only true if one assumes that TF binding is the only function of this region. One could even turn this around and say the fact that the sites affecting TF binding are not the most conserved is actually evidence that TF binding is not a good indicator of these regions' entire function. I suggest the authors soften this claim that conservation scores are less sensitive to regulatory region function.

Reviewer #1 (Public review):

Summary

The authors aim to understand, in the context of leaf shape, how the constraints imposed by development inform evolution. Leaf shape is a good place to study the influence of development on evolution because it is a trait that exhibits a lot of diversity, and the developmental mechanisms that give rise to leaf shapes are apparently rather conserved across angiosperms.

As part of the motivation for their work, the authors cite a previous study (Geeta et al), which found that in angiosperm phylogenies, transitions from complex to simple leaf shapes occur through evolution more often than transitions in the opposite direction. Is this due to developmental constraints or adaptation?

The authors undertake two parallel lines of work:

(1) Extending the study of Geeta et al with more data, consisting of both phylogenies and a shape classification dataset. The conclusion from this line of inquiry is that transitions from lobed to unlobed leaves are more common than transitions away from unlobed leaves.

(2) The authors conduct evolution simulations in a computational model of leaf development. Here, they look at {\it neutral} mutations and whether simply neutral evolution is sufficient to drive the observed trend.<br /> The conclusion of the second part of the work is that the driver of the evolution toward simple leaf shape is entropy: there are more ways to make unlobed leaves than to make lobed leaves (at least in terms of gene regulation parameters that will produce the two leaf types). The argument is that random gene regulatory networks are more likely to produce unlobed leaves than lobed leaves; therefore, neutral evolution drives this trend.

Data Analysis

Roughly $9000$ images of leaves were classified into 4 categories: unlobed, lobed, dissected, and compound. These labels were applied to the tips of 5 phylogenetic trees of angiosperms (3 resolved at the genus level and 2 at the species level). By fitting a continuous-time Markov chain to the labelled trees, the authors claim that there is a significantly higher rate of transition to the unlobed leaf shape compared to transitions to more complex shapes.

Simulation

First, the authors validate a computational model (Runions et al) for leaf growth on an experimental dataset. By changing parameters in the model, they can recapitulate the morphological changes in the shapes of Arabidopsis leaves engendered by expression of two particular genes.

Then the authors run an evolutionary model (without selection, just random mutations) on top of the computational leaf development model. As the random walk in parameter space reaches a stationary distribution, they look at both the proportions of the leaf categories in the steady state as well as the transition rates between different categories. The result is that transitions to unlobed leaves are more common than from unlobed leaves.

General Comments

The authors use angiosperm phylogenies from other works as the basis for the data analysis part of their work. Given the centrality of these phylogenies for their conclusions, more information is needed about how these phylogenies were constructed and what they mean. What is the timescale that they span? What method is used to infer them? What regions of DNA were sequenced in order to build the phylogenies? Also, maybe some more discussion of angiosperm evolution (e.g., when was the most recent common ancestor of all angiosperms?) would help put the study in context.

We also need a more in-depth discussion of the computational model. What are all the $>100$ parameters doing, and what informs the seemingly strange mutational model that changes parameters by 3 orders of magnitude?

I am confused about how the rates of transitions were inferred from the phylogeny. Here, one has a phylogeny inferred by some method (which needs to be described in more detail), and just the leaves are labelled. It is stated in the methods that BayesTraits was used to infer the transition rates. I realize this method is probably documented elsewhere, but a bit of a summary of how it works and how to interpret its results would (1) make the paper more self-contained and (2) if the algorithm is credible, make the results firmer.

I am a bit skeptical of the authors' interpretation of the biological trend (of complex to simple leaf shapes) as being driven by neutral evolution. Why does one expect that the mutations generated by the random walk models described in the work are in fact neutral mutations?

- If the entropy of simple leaf shapes is higher than that of complex leaf shapes, why did we have complex leaves at all? I suspect the authors might argue that this is due to selection. In that case, what allows these complex shapes to become simpler? Wouldn't they be losing the selective advantage that drove them to be more complex in the first place? Or maybe the idea is that the rates are inferred assuming some steady state that generates the phylogeny? I did not understand this point.

Are the rates of transitions between leaf types inferred for the phylogeny assuming that the phylogeny is generated by the steady state of some Markov process? (I think the answer is no: in that case, how does one explain the initial condition?) If I take the mutation model (random walk) seriously, then shouldn't I expect that this steady state obeys detailed balance? In that case I should have $p_i r_{i\to j} = p_j r_{j\to i}$ for each of the occupancies $\{ p_i\}$ and transition rates $r_{i\to j}$ for the shape categories. How close are the rates inferred from the phylogenies to obeying detailed balance? Presumably, the Markov chain fitted to the simulation data obeys detailed balance because the mutation model itself does?

I find it hard to take the discussion of development seriously without some consideration of mechanics. Presumably, the mechanics are hidden in the computational leaf development model, but this model is not discussed in enough detail for the reader to know. It seems to me that the interesting question is: what are the {\it mechanical} constraints on development that drive the apparent trend in evolution towards simpler leaf shapes? Maybe it is something about the type of differential growth needed to make complex leaf shapes less robust to mutation. But in this case, I would assume that selection plays a role in the complexity of shape. In any case, a better understanding (or explanation) of the computational model is needed to make this interpretation.

Some discussion of timescales is needed, especially when invoking neutral evolutionary arguments. If a neutral mutation occurs, its time to fix in a population of size $N$ is $\sim N$ generations. What are the relevant angiosperm population sizes and the number of mutations that separate branches on the tree? Are timescales remotely consistent with e.g., the age of angiosperms on Earth?

Reviewer #2 (Public review):

Strengths:

The paper's underlying question is interesting, extending the authors' prior work on RNA along similar conceptual lines. The paper combines both image analysis of leaves and a computational analysis of a simple model of leaf development.

Weaknesses:

The entire paper is based on the Runion model. More intuition about the Runion model would be useful for a broader readership that cares about the evolutionary aspect of this, but may not know the developmental model in question. Obviously, this is prior well-established work, but 2 - 3 sentences highlighting the key structural aspects of such a model would be great. Currently, that intuition is found implicitly in a sentence on page 2 ("complex leaf shapes need more specificity in their GRNs than their simpler unlobed leaf shape"), but the reader is left wondering - is the Runion model a detailed mechanistic one with multiple interacting genes/proteins? If so, how many? Or is it just 2 - 3 genes but with complexity entirely in how long they are each expressed/when they are turned off, etc.

The Runions model has nearly 100 free parameters. Random walks in 100-dimensional spaces have generic properties like a tendency to move toward regions of larger volume that have nothing to do with leaf biology. How do you disentangle the geometry of high-dimensional random walks from genuinely biological developmental bias? Would a toy model with 100 parameters and arbitrary phenotype categories also show "bias toward simplicity" if "simple" phenotypes occupy more volume?

The discussion of Figure 4 (PCA of parameter space) uses "area" loosely when what's actually being measured is bin count in a 2D projection of a high-dimensional space. I would think that, in general, PCA projections can be misleading about volume in the full parameter space, but I can't tell if that's an issue in this case. Some comments/thoughts here would be useful.

The classifier validation section is in the Methods section, but it seems critical to the whole story. The < 80% agreement with manual classification could propagate to the rest of the estimates in the paper. Again, some comments/thoughts here would be useful.

The authors should explain Mut2 and Mut5 in the main paper with a sentence or two, at least schematically, because how you mutate is obviously very relevant to interpreting a paper about biases in variation.

The two mutational schemes use additive perturbations to individual parameters. Real mutations presumably affect regulatory networks in more structured ways (e.g., changing binding affinities that affect multiple parameters simultaneously). How sensitive are the results to the assumption of independent single-parameter mutations?

The connectedness argument is made using a 2D PCA projection. Is there a way to check this statement in the full parameter space or perhaps in higher-dimensional projections to test the robustness of this result? Connected components can merge/split under different projections.

Reviewer #1 (Public review):

This study presents a new model of phenotypic variation incorporating direct and indirect genetic effects, as well as a new implementation (RAINBOWR) for quantification, genomic prediction and GWAS. It includes a simulation study to test the model and implementation, and three applications to plant species.

The abstract describes the main novelty and significance of the study as follows: "Recent studies have utilized high-resolution polymorphism data to enable genomic prediction (GP) and genome-wide association study (GWAS) of IGEs, but unified methods remain limited". I disagree with this statement (e.g., using ASREML: https://doi.org/10.1186/s12711-018-0409-7, using LIMIX: https://doi.org/10.1186/s13059-021-02415-x; etc.).

The parameterisation of genetic effects in the model is not standard and complex. Hence, the simulation study is key, and the results need to be presented in a very rigorous manner. I have several points to make on this:

(1) L172 says the estimated parameters are "close to" the real parameters. The results of the simulation study need to be quantitative (see https://www.biorxiv.org/content/10.64898/2026.03.10.710784v1.supplementary-material for example).

(2) Figure 2h: the estimates seem to be biased, no?

(3) Figure 2 in general: why isn't there a difference between cov and noncov? Do we not expect the inclusion or non-inclusion of a covariance term to affect the other genetic parameters and the results presented in Figure 2?

(4) Does "total BLUPs were highly correlated between models with and without 𝜌" really validate the model?

(5) As far as the GWAS is concerned, the results of the simulation study should include a figure showing whether the p-values are inflated (as observed in the grape application), and not just a ROC curve.

The model only includes IID residuals, whereas the importance of including non-genetic social effects (IEE) has been demonstrated in many settings, and other IGE plant studies have used sophisticated spatially structured residuals (e.g. 10.1111/nph.12035). Can the authors justify why they considered only IID residuals? In the three applications presented, wouldn't it be appropriate to include spatially structured residuals and potentially other relevant covariates?

It remains unclear why the authors chose such an unconventional parameterisation of the DGE IGE models for the questions asked in this study. It seemed appropriate to study frequency-dependent selection (previous paper), but for this study, focused on IGE quantification and GWAS, the classical models (e.g. early models by P. Bijma but also more recent models that allow for distance-dependent IGE) seem appropriate, and they are much simpler and easier to interpret, and have been validated in many settings). The Discussion paragraph L274-284 only strengthens my doubts.

Reviewer #2 (Public review):

Summary:

In this study, Sato and Hamazaki have expanded upon previous work, describing quantitative genetic models for direct and indirect genetic effects and applied this to both simulated and real plant datasets of three different tree species. The methods are clearly described and accompanied by a number of R packages freely available to the wider community.

Strengths:

The main strength lies in the joint modelling of DGE, IGE and their covariance while also simultaneously modelling single-SNP fixed effects (including SNP interactions across neighbours) and a polygenic effect that goes beyond a simple kinship correction as found in many traditional GWAS models, to a compound kinship structure that accounts for DGE, IGE and their interaction.

Weaknesses:

There were some aspects that deserved more attention from the authors. For example, the authors found that a very large amount of phenotypic variation in citric acid content in grapes was explained by neighbour identity, along with over 1000 significant SNPs, yet there was little to no discussion of this result and how it could have arisen (apart from some mention of volatiles and ethylene - but without being explicit on the mechanism here). The simulation study also only considered the scenario of equal direct and indirect genetic variances, while previous studies, as well as the 3 real datasets presented in this study, show that DGE variance is almost always larger than IGE variance. A simulation study cannot be exhaustive, of course, but it seems more likely that in reality and for most traits, IGE will be more difficult to detect than DGE.

Reviewer #3 (Public review):

Summary:

The authors aimed at studying the genetics of interactions between individuals, notably the genetic architecture of indirect genetic effects. For that, they mobilized a technique known as "genome-wide association" study. GWASs are typically formalized as linear mixed models (LMMs) with fixed effects to identify the oligogenic component of the genetic architecture (usually SNPs tested one by one, as done here), and with random effects to quantify the overall contribution of the polygenic component of the genetic architecture (using a kinship matrix). They used an LMM with a few corrections and improvements from one of their already-published model, assessed it on data they had already simulated in a previous work, and applied it to three datasets generated and originally analyzed by others, focusing only on direct genetic effects. The results on simulated data confirmed that it was necessary to adapt their previous model. The results on real data confirmed the presence of negative correlation between direct and indirect genetic effects (for two out of three species), as was already known from other studies. They found a few SNPs with significant, indirect effects, which led them to identify candidate genes, but they did not validate them.

Strengths:

The main strength of the manuscript lies in the question tackled by the authors, i.e., related to indirect genetic effects, with the ambition to go beyond the estimation of overall effects towards the distinction between polygenic and oligogenic components of genetic architecture. They also found, in an apple dataset, a significant IGE SNP that also happens to be in a DGE-associated region.

Weaknesses:

(1) Overall, the authors do not engage sufficiently with the existing literature, and do not provide strong evidence that their approach is more powerful or more interpretable than others. Hence, this work seems rather incremental.

(2) The authors used an LMM that corresponds to a previous LMM they already published in 2021, with a few changes that appeared more like corrections than improvements. Their model raised several questions.

(3) First of all, their previous model included the polygenic component of direct genetic effects (modeled as random with a kinship matrix), but not the polygenic component of indirect genetic effects. As a consequence, the initial model did not allow both direct and indirect genetic effects to be correlated, although this correlation is the hallmark of the topic: a negative correlation can lead to selection on direct effects only to deliver a negative genetic gain (Griffing, 1967). This was corrected in their new model here, so that it is similar in this respect to the other models. They highlighted that, on simulated data, their new model could "infer a trade-off between DGEs and IGEs", but that was the very goal of introducing the correlation parameter, so it was reassuring at least to know that they could estimate it on simulated data. On real data, they found evidence for it being negative, which was already the case in Cappa and Cantet (2008) for a tree species, in Haug et al (2023) for annual crops, in Montazeaud et al (2023) for A. thaliana, etc. They tested for significativity but did not provide any confidence interval. They showed the proportion of variance explained by the covariance, but did not discuss the sign or magnitude of this correlation.

(4) Although the authors included a correlation parameter between DGE and IGE in their updated model, they did not specify if the residual errors were correlated, too. In fact, they did not even specify a distribution for them. It is already known that allowing for correlated errors may not change the estimates (Haug et al, 2021), but in some settings it can be important (Bergsma et al, 2008).

(5) In appendix S4, they say that the "ordinal" model (I am not sure of what they meant by this word) "defines polygenic DGE and IGE by random effects without fixed effects for each SNP". However, this is not correct; see Baud et al (2021), for instance. In any LMM, it is straightforward to include a single fixed effect for a given SNP, and to do it one SNP at a time. Moreover, they claimed that "compared to the ordinal model (Equation S4), the proposed model (Equation 1) is more extensible to incorporate SNP-wise fixed effects while distinguishing variance-covariance matrices", without providing more evidence than this statement.

(6) The authors seemed keen to convince us that the fact that their model is analogous to the Ising model of ferromagnetics was an advantage in itself. But why would it be? Beyond the mere analogy, it should be a matter of modelling choice, and thus be clearly motivated. For instance, they chose to assess the strength of the association between the trait in the focal individual (y_{k_i}) and the average (dis)similarity between the focal individual and all its neighbors (in neighborhood k), calling the latter "indirect genetic effect". Moreover, it is not clear if what they called "IGE" is \beta_{q,2}, u_2, both, or also \beta_{q,12}, etc? Furthermore, they should have used another term as this is not the same as the "indirect genetic effects" of the other models. In these models, what is called the indirect genetic effects can be modeled as depending on group size (see Hadfield and Wilson, 2007; Bijma, 2010). In which sense would the approach of the authors be better? How does it relate to the other models? Do they have more power? Is their term more interpretable?

(7) Another way in which the authors' model may be different from the other models is in the way it models interactions between direct genetic effects and aggregate (dis)similarity between focal and neighbors. At the level of the polygenic components, other models simply have a (DGExIGE) term capturing the deviations from the additivity of DGE + IGE (e.g., Wright, 1985, in the multispecific context). Here, the authors indeed mentioned "interactions between polygenic DGEs and IGEs" and introduced the K_12 matrix, but it is not clear how different (or similar) it is from the more classical (DGExIGE) term. At the level of the oligogenic component, the authors introduced \beta_{q,12}, but it is not clear, to me at least, how it relates to K_12 and K_21.

(8) The authors checked their model on simulated data for various levels of correlation between u_1 (GE) and u_2.

(9) It is not clear why they have higher absolute errors with negative covariance than with a positive one.

(10) As a causative IGE SNP, the authors considered one with a beta_{q,2} significantly different from 0. However, they also have two other coefficients, beta{q,_}1 and beta_{q,12}, for each SNP q. How is the FDR in RAINBOW controlled in such a case? This is not detailed.

(11) In their simulations, the causative IGE SNPS were also causative DGE SNPs. However, this may increase power. From the manuscript title, one could assume that the authors' goal was to distinguish between the SNPs that are both DGE and IGE, versus the ones that are IGEs only.

(12) From what I understood, the authors first estimated the (co)variance components once and for all on the model without any SNP, and they then used the values to fit the GWAS model one SNP at a time. This assumes that the inclusion of SNP effects modeled as fixed would not change anything regarding the (co)variance components, but this is not warranted.

(13) The authors applied their model to three datasets of perennial plants.

(14) They only used their model and did not provide evidence that their model gave a significant improvement compared to other models, such as the one of Baud et al (2021).

(15) In Figures 3, 4 and 5, having an indication of which cases have a significant correlation between u1 and u2 would have helped.

(16) Concerning the Aspen dataset, it is not clear why the authors claimed that "the negative effects of neighboring genotypes were amplified as trees matured" as the PVE_cov in Figure 3 in 2015 are not systematically more negative than those of Figure 3 in 2014.

(17) When discussing their results, the authors should engage more with the literature estimating DGE-IGE correlations (see some of the references above).

(18) Concerning the apple dataset, they mentioned that "metabolite accumulation in ripening fruits may be facilitated by volatile chemicals, such as ethylene", but they did not find any evidence for significant IGE SNPs localized close to a gene involved in ethylene production. Claiming that these are testable hypotheses should have been made earlier, in the introduction, than a posteriori in the discussion.

Reviewer #1 (Public review):

Marconcini et al. report results of an ambitious study on the genetic mechanisms that contribute to resistance of Drosophila flies to the toxin octanoic acid (OA). This study was motivated by two observations: first, Drosophila sechellia, a close relative of D. melanogaster, has evolved specialized feeding on fruits of Morinda citrifolia, which contain high concentrations of OA and second, that artificial selection on Drosophila simulans, a sister species of D. melanogaster, can generate higher resistance to OA. Previous studies had performed genetic mapping studies between D. simulans and D. sechellia that implicated certain genomic regions in resistance to OA and, in particular, implicated several Osiris gene paralogs as contributing to resistance, though the molecular mechanisms of resistance remain unclear. In this study, Marconcini et al. performed two major experiments. First, they performed evolution-and-resequence on Drosophila simulans populations exposed to OA for 50 generations and identified candidate regions with excessive shifts in allele frequencies as candidate regions containing OA resistance genes in D. simulans. Second, they performed a CRISPR knock-out screen in a D. melanogaster cell line to identify genes that contribute to OA resistance and susceptibility.

Evolve-and-resequence yielded many candidate genomic regions with extreme allele frequency shifts, which may be regions containing OA resistance genes, or linked genes, or regions that happen to show a strong shift in all replicate populations by chance. As the authors note, detecting significant shifts in allele frequencies is a challenging problem, and the authors use two measures of allele frequency shifts (the Cochran-Mantel-Haenszel method and Bait-ER) and perform simulations under neutrality to estimate a reasonable significance threshold. I am not entirely convinced by this method of estimating significance levels, because the simulations involve assumptions that may not be met by the real populations. I would think that a permutation test would provide an assumption-free method of estimating significance levels. I have tried to think whether there is something about the design of these experiments that would preclude the use of permutation tests (which are used widely for genome-wide studies, such as QTL), but I can't think of one. Perhaps the authors are aware of a reason permutation tests would be invalid here, and if so, they should state this reason.

There is overlap between regions detected by the two methods, but the methods disagree for many regions. The authors state that a "majority of prominent peaks were found by both methods," but I am unclear on what "prominent" means here. It would be more helpful to be more quantitative about the extent of overlap.

The authors hypothesized that the response would be at similar genomic loci in all populations (line 222). It seems at least possible that epistatic interactions would lead to different combinations of alleles evolving in each population. I wonder if it would be possible to test whether there is heterogeneity in the responses across the replicate populations.

The evolve-and-resequence method yielded many possible regions contributing to OA resistance in D. simulans, but perhaps too many regions to test directly or even to build sensible hypotheses about the genes involved. Thus, the authors performed a second experiment to try to narrow down the list of possible candidate genes. They performed a CRISPR knockout screen in a D. melanogaster cell line for genes that contribute to resistance or susceptibility to OA. The authors identify several limitations of this experiment, but they nonetheless identified several genes where knockouts contribute to OA susceptibility or resistance. Intersecting top hits with regions that experienced selection identified two "resistance" genes: kraken and Alkbh7. The selection hit at kraken is quite compelling, whereas the evidence at Alkbh7 is less strong because only two SNPs were marginally significant. Further functional assays, including gene knockouts in D. melanogaster and D. sechellia, provide some support for the claim that both of these genes can contribute to resistance to OA in flies.

Beyond the few issues raised above, I do not have significant questions about methodology or the results. I do think, however, that the authors should be more conservative about the implications and significance of their results. For example, on line 139, the authors claim that this intersection approach provides a "powerful paradigm to investigate ecotoxicology." I am not sure I agree that the identification of two genes that may contribute to OA resistance, after a seemingly heroic selection experiment and CRISPR screen, suggests that this method is all that powerful. It seems that most of the genes that contribute to the selection response remain unidentified.

Finally, given that one motivation of this project was to identify genes that contribute to evolved resistance to OA, I am surprised that the authors did not generate CRISPR alleles of kraken and Alkbh7 in D. simulans and then use these together with the existing alleles in D. sechellia to perform reciprocal hemizygosity tests to determine if these two genes actually contribute to evolved resistance in D. sechellia. This test is simpler to perform and may be more sensitive than the allelic replacement that the authors propose (lines 446-449).

Reviewer #2 (Public review):

Summary:

The authors studied the resistance against octanoic acid, a compound of the noni fruit, in D. simulans, using experimental evolution and resistance/susceptibility in D. melanogaster cells. They identified novel candidate genes and performed functional tests.

Strengths:

The idea of using experimental evolution of a non-resistant species to develop resistance is interesting, and the idea of narrowing down a large list of candidate loci by CRISPR-based gene knockout in cell culture is innovative. The reviewer also liked the (easy) follow-up experiments to validate the results.

Weaknesses:

The reviewer is not convinced of the conceptual idea behind their approach: the intersection of the two approaches implicitly assumes that null alleles (or at least compromised alleles) should be selected during experimental evolution. The reviewer considers this unlikely, and the authors made no attempt to test this implicit hypothesis in their data. Along the same lines, it is not clear how to reconcile an upregulation of candidate genes in resistant flies with the knockout experiments.

The experiments to validate the effect of candidate genes did not match the experimental evolution conditions.

The statistical analysis suffers from some problems and an insufficient description of the analyses performed.

Although D. simulans GWAS data are available, the authors did not make an attempt to estimate the effect of selected variants in the candidate genes in the GWAS data set.

The reviewer would have liked to see more connection between the experimental evolution and the GWAS data. As some D. simulans genotypes have similar resistance to D. sechellia, it would have been interesting to test whether this genotype contributed to the observed resistance.

At several places, the authors discuss the challenge of studying a polygenic trait, but at the same time, they claim to have detected and validated candidate genes. It would be helpful if the authors could discuss why they consider that their assays could really detect the contribution of single loci to the polygenic trait. In particular, when GWAS did not detect their candidate genes.

It is not clear to the reviewer why the authors did not pay more attention to the highly significant peaks emerging from the experimental evolution study. Their functional validation would have been biologically more plausible.

Impact:

Given the obvious challenges of functional testing of polygenic traits and the clear limitations of the interpretation of the results, the study will be helpful for future studies aiming to characterize polygenic traits. Unfortunately, the results are just another piece of controversial results regarding resistance against octanoic acid, a trait that is rather easy to evaluate.

Reviewer #2 (Public review):

Summary:

The authors have used 1477 sequenced trios with available gene expression data in the offsprings to discover eQTLs that act in a parent-of-origin specific manner. The classified their associated SNPs are tested for enrichment for GWAS hits, drug target genes, etc.

Strengths:

The manuscript presents an impressive analysis of a very rich data set of parent-of-origin eQTLs. To my knowledge, it is one of the largest studies of its kind and most analyses are sound and the results are of interest to many in the field and potentially beyond. The different ideas of follow-up analyses are useful and make sense.

Weaknesses:

While in general the analyses are well-conducted, I noticed a major issue with the POE eQTL classification, which puts into question most of the downstream analysis. In the light of this problem, all claims of individual discoveries (apart from those in Table 1) should be removed. The enrichment analyses remain valid and are useful.

Reviewer #1 (Public review):

Summary:

The authors tackle a long-standing question in developmental theory: given a gene-regulatory network that includes extracellular signaling, which topologies are even capable of transforming an initial spatial profile into a genuinely new pattern? Building on the classical reaction-diffusion framework in one dimension, but imposing biologically motivated constraints, they prove that every one-signal sub-network must be either Hierarchical (H), self-activating (L+), or self-inhibiting (L-). They further demonstrate that only three composite classes of full networks - pure H, a coupled L+ L- "Turing" pair, and an L- module fed by an intracellular positive loop ("noise-amplifying")-can create non-trivial spatial transformations. Analytical criteria and illustrative simulations are provided, together providing a closed taxonomy, which is supposed to be relevant for real systems.

Strengths:

(1) Useful classification framework. Reducing a vast number of possible gene circuits to three canonical pattern-forming motifs is a valuable organizing insight for both theorists and experimentalists.

(2) Practical interpretability. Given a reaction network diagram, one can now decide (assuming the model applies to real systems) whether spatial patterning is even possible, saving experimental effort on in silico screens that could never succeed.

Weaknesses:

(1) After the resubmission, I still have concerns regarding the formal definition of "non-trivial transformations" (P1/P2) and its application to noisy or multi-dimensional systems. The criteria rely on counting "new" critical points (maxima/minima). In their response, the authors argue that the diffusion operator instantly smooths discontinuous white noise, allowing critical points to be properly defined. However, this very smoothing process passively generates a landscape of new, smooth local extrema from the initial noise. Consequently, trivial diffusive regularization could inadvertently fulfil the criteria for a "non-trivial" transformation, leaving the definition conceptually problematic. Furthermore, when extending the framework to 2D/3D, the manuscript assumes that starting from a central "spike" will robustly preserve radial symmetry, yielding concentric rings or shells. This overlooks the fundamental nature of macroscopic mean-field models like reaction-diffusion equations. The realization of the final multidimensional pattern depends strictly on the stability of the solution against ubiquitous perturbations (including angular modes) rather than solely on the deterministic symmetry of the initial condition. It remains unclear how the current framework accounts for spontaneous symmetry breaking in cases where these angular modes become unstable, challenging the assumption that radial symmetry will strictly dictate the outcome. We note that the authors' use of noise as an initial condition does not resolve this fundamental issue. Reaction-diffusion equations inherently describe mean-field dynamics, meaning that microscopic fluctuations are continuously present in any real system, regardless of whether explicit stochastic terms are written into the equations. Ultimately, if a symmetric mean-field solution is structurally unstable to these inherent fluctuations, it simply cannot be realized in nature.

(2) Theoretical limitations in the application of Linear Stability Analysis (LSA): I remain uncertain about the framework's reliance on LSA to categorize macroscopic transformations, especially those arising from large initial perturbations (spikes). In their rebuttal letter, the authors justify this by assuming the perturbation remains small over a short time interval. However, because the study aims to describe stationary, asymptotic states, applying a linear approximation that relies on transient t->0 conditions to predict long-term global stability is not fully resolved.

(3) In the previous round of the review, I suggested that a biomolecular sink, such as A+B -> AB reaction, could break the approach. In their response letter, the authors defend their approach by arguing that such reactions can be accommodated by their abstract constraints (R1-R5) as long as the signs of the Jacobian elements remain invariant. However, the problem I see here is not the sign of the interactions, but the severe loss of spatial homogeneity.

When a macroscopic initial perturbation (a "spike" of morphogen) is introduced into a domain with a strong bimolecular sink, it will inevitably cause massive local depletion of the consumed substrate near the source. Consequently, the background state of the system will rapidly evolve into a profile with macroscopic spatial gradients long before any spontaneous pattern-forming instability takes over. Mathematically, this dictates that the system no longer possesses a homogeneous steady state, and the Jacobian matrix becomes explicitly space-dependent, which should break the classical LSA approach.

Discussion:

The study offers a solid conceptual organization of pattern-forming networks. However, the theoretical bridge between infinitesimal linear stability and macroscopic, non-linear pattern emergence still presents some uncertainties. The way the current framework formally treats noise, multi-dimensional symmetry breaking, and large initial perturbations leaves some questions open regarding its broad analytical applicability to real biological tissues.

Reviewer #3 (Public review):

Pattern formation is responsible for generating the spatial organization of cells, tissues, and organs during embryogenesis. It operates within a multifactorial system including initial conditions, gene regulatory networks, extracellular signals, mechanical forces, stochastic noise and environmental inputs, and finally ensures the functional anatomy of an organism.

This study focuses on the one central aspect in pattern formation: how spatial heterogeneity arises from an initial condition and evolves into a more complex or distinct spatial pattern (non-trivial pattern formation as they termed). The authors made efforts to explore and characterize all possible ways to achieve the pattern formation by discussing how extracellular signals spread, how individual cells respond to those signals, and how those responses, in turn, modulate signal propagation.

Finally, their comprehensive analysis summarizes that there are three classes of interactions between extracellular signal and intracellular responses, corresponding to previously known mechanisms that can generate spatial patterns: Difference in morphogen concentrations in space, noise-amplification, and Turing pattern.

Reviewer #1 (Public review):

The manuscript by Lux et al. addresses how T-cell acute lymphoblastic leukemia (T-ALL) cells migrate into the central nervous system (leptomeninges), specifically through VLA-4 and LFA-1 integrins. VLA-4 and LFA-1 are important regulators of normal T-cell migration into the CNS, so the authors tested whether they also mediate T-ALL infiltration. They generated an intracellular NOTCH1 T-ALL mouse model and then used CRISPR/Cas9 gene targeting to delete VLA-4 and LFA-1. They show that integrin-deficient T-ALL cells accumulate in the CNS compared to control T-ALL cells. The authors performed a time course experiment and found that although WT T-ALL cells accumulated in the CNS before DKO T-ALL cells, over time, DKO T-ALL cells outgrew the WT T-ALL cells. Subsequently, they performed bulk RNA-sequencing and revealed that Integrin beta 7 (Itgb7) was upregulated in the DKO T-ALL cells. To test whether Itgb7 was compensating for the loss of VLA-4 and LFA-1, the authors generated a triple KO (TKO). The TKO T-ALL cells migrated to the CNS; however, CNS accumulation between the TKO and the DKO was not significantly different. To evaluate if there is reduced exit of T-ALL DKO cells from the meninges, they inhibited T-ALL exit via the dorsal meningeal lymphatics by generating an AAV VEGF-trap encoding the binding domain of VEGFR3, and then co-injected WT: DKO cells weeks later. There was no effect on the WT:DKO T-ALL ratio or on the overall number of T-ALL cells in the CNS with meningeal lymphatics regression, suggesting that the DKO does not preferentially accumulate in the CNS, or that delayed exit results in DKO T-ALL accumulation in the CNS.

Additionally, the authors tested whether DKO affected immune surveillance by injecting DKO:WT T-ALL cells into NRG mice. DKO T-ALL cells localized in the dura mater and were spread throughout the tissue, whereas WT T-ALL cells clustered near blood vessels. These observations lead the authors to hypothesize that differential access to nutrients or other signals may influence leukemic cell proliferation. However, EdU labeling revealed no differences, leading the authors to hypothesize that the unique stromal cell layer in the meninges supports the DKO proliferative advantage. Finally, the authors tested whether integrin blockade and chemotherapy might chemosensitize T-ALL cells in the CNS. After a single treatment with 5FU, DKO cells were depleted faster than the WT cells; however, a single treatment with integrin blockade was toxic. After combining 5FU with the integrin antibodies, the authors showed that T-ALL cells in the CNS were significantly more depleted than in treatment with either single therapy.

These data highlight how challenging it is to identify regulators of T-ALL migration and adherence. This study highlights the importance of these experiments and the clinical need to identify the molecules that influence leukemic infiltration into the CNS.

Overall, this study was well performed with appropriate statistical power to implicate integrins in T-ALL CNS infiltration and proliferation.

Reviewer #2 (Public review):

Summary:

In this study, the authors set out to understand how T cell leukemia cells enter and persist in the CNS, with a particular focus on the role of adhesion molecules known to regulate normal immune cell trafficking. Contrary to expectations, they find that loss of two key adhesion molecules does not impair CNS entry but instead leads to increased accumulation of leukemia cells, which is associated with enhanced cell proliferation in this environment. These findings challenge prevailing assumptions about how leukemia cells interact with tissue niches and suggest a potential therapeutic strategy combining adhesion blockade with chemotherapy.

Strengths:

The study addresses an important and longstanding question in leukemia biology using well-designed in vivo models and multiple complementary approaches. The key observation is robust and consistently supported across genetic models and experimental systems. The authors systematically test alternative explanations, including altered entry, exit, and immune evasion, which strengthens the interpretation that proliferation differences underlie the phenotype. The work has potential translational relevance, particularly in highlighting a possible strategy to enhance the efficacy of anti-proliferative therapies in the CNS.

Weaknesses:

While the central phenotype is clear, the mechanistic basis remains incompletely defined. Addressing the following points would strengthen the manuscript.

Major critiques:

(1) The central claim that integrin loss enhances CNS accumulation via increased proliferation is not mechanistically resolved; current data are correlative (EdU incorporation, distribution patterns) and do not establish that integrin-mediated signaling directly restrains cell cycle progression in the CNS niche. The authors should perform functional perturbation of candidate pathways identified (e.g., TGF-β) using pharmacologic inhibitors or genetic approaches (dominant-negative receptor or CRISPR knockdown) in vivo or in ex vivo CNS-derived T-ALL co-culture systems to test whether blocking this pathway rescues the WT proliferation phenotype; if not feasible, the mechanistic claims should be toned down and clearly presented as hypotheses.

(2) The relationship between altered spatial distribution and proliferation is suggestive but not directly demonstrated. The imaging data indicate differences in localization, but these observations are not quantitatively linked to cell cycle status. The authors could strengthen this point by incorporating spatially resolved proliferation analyses, such as combining EdU labeling with imaging or quantifying proximity to stromal or vascular niches, or alternatively by providing additional quantitative analysis of the existing imaging data.

(3) The conclusion that CNS accumulation is not due to altered trafficking (entry/exit) is suggestive but not definitive, as early seeding dynamics are not directly assessed. Authors should perform short-term homing or early time-point competitive trafficking assays (e.g., CNS quantification at 6-48h post-transfer) to rigorously exclude differences in entry kinetics; if such experiments are not feasible, this limitation should be explicitly acknowledged in the discussion.

(4) The therapeutic claim that integrin blockade synergizes with chemotherapy is promising but underdeveloped, as it lacks survival outcomes and a broader translational context. The authors should include survival analyses and, if possible, test combination treatment in a more clinically relevant setting (e.g., delayed intervention or alternative standard-of-care agents), or otherwise temper translational conclusions and discuss risks such as inducing proliferation in the absence of chemotherapy.

Reviewer #1 (Public review):

The manuscript by the Deppmann group is an important contribution to understanding how growth factor signaling is controlled at a per-cell basis, in contrast to bulk biochemistry results. Their system uses cell culture and single-cell signalling proteomics methods to measure responses of cells of different developmental stages (from E14 rat) with complex but relatively clear-cut phenotypes, allowing the effects of BDNF to be compared. This work validates the method for the discovery of future insights from less well-studied ligand-receptor investigations.

Strengths include:

(1) The methods are cutting-edge and powerful.

(2) Clearly written. It leads the reader through the rationale of methodological steps.

(3) Step-by-step data interrogation rather than leaping into complex models of analysis.

(4) "sanity check" controls e.g., mimicking bulk culture expected signaling /expression changes.

(5) Testing biologically of certain findings within the presentation of the results ( e.g., progenitors not responding to BDNF also not internalising TrkB).

(6) Effort to make complex figures/data as understandable as possible.

(7) Not overstating conclusions.

(8) Important conclusion of receptor stoichiometry sets the potential for BDNF sensitivity, and that the intrinsic environment allows for a cell to engage that potential, something possibly thought but not demonstrated previously.

Major points:

(1) Apply appropriate statistics: Student's t-tests are used throughout. It would be more appropriate to utilise ANOVA, at least one-way, to compare across timepoints for a given phospho-protein within one treatment condition (e.g., pERK following BDNF stim), or even multiple t-tests. Also, multiple testing adjustments. are likely needed (not my expertise).

(2) Some data points are n=2; for statistical rigour n=>3 would be appropriate.

(3) They measured pTrkB with antibody targeting site Y816, which couples to PLCy/PKC/Ca2+, but not Shc (for PI3K/MEK pathways), why? Did they get any measurements using an antibody targeting the phosphorylation sites in the activation loop of the kinase? Could this explain the relatively low abundance of active TrkB, compared to the measured TrkB-dependent signalling outcomes? Especially considering the "unresponsive" cells. E.g. https://doi.org/10.1016/S0896-6273(00)00035-0.

(4) Was TrkC ( or A) expressed in any TrkB population that could potentially mediate BDNF signaling?

Reviewer #2 (Public review):

In this study, Sewell et al. use a novel approach to understand cell-specific BDNF signaling in the developing spinal cord. Using cultured E14 spinal cord, the authors used a mass cytometry approach to identify the levels of TrkB and p75NTR receptor expression, as well as 19 signaling markers and cell identification markers, to delineate activation of BDNF signaling in different cell types within a complex population. They identified that the level of receptor expression, while necessary, is not sufficient to determine the activation of signaling cascades. It has been known for some time that TrkB, indeed all RTKs, have the capacity to activate certain canonical signaling pathways; however, not all these pathways are always activated upon ligand treatment. This study begins to identify the conditions under which specific signaling pathways are activated by ligand. Specifically, the type of cell and maturation state are critical for determining signaling. The cytometry approach allows the clustering of cell types according to expression of specific markers, and overlaying those clusters onto the expression status of TrkB and p75 receptors, as well as specific activated signaling proteins. This study provides greater insight into when specific signaling events can be activated by BDNF than was previously known.

The comparison of levels of expression of TrkB and p75NTR is interesting to demonstrate which pathways may require one or both receptors for specific signaling responses.

It is very interesting that progenitors do not respond to BDNF despite abundant expression of TrkB, although they responded to the rescue treatment with phosphorylation of Erk and Akt. The development of competence to respond to BDNF is an interesting question for future analysis, and the authors suggest some possibilities in their Discussion.

The responses of glial cells in their culture preparation are also interesting. They see signaling responses to BDNF in astrocytes and "laden" microglia (presumably phagocytic). E14 spinal would not be expected to have a large population of glia at this stage of development, although the serum in their plating media would allow for the proliferation of the progenitors. Astrocytes are generally considered to have the truncated TrkB receptor, yet they see P-Erk, P-Akt, etc. in these cells in response to BDNF. This raises the question of which receptors are expressed in the glial populations and whether the responses in these cells are also maturation dependent, since the glia in their culture conditions are also likely to be immature.

Some specific comments:

(1) The authors should specify what is meant by "rescue" in the text. What is rescuing the cells from trophic deprivation when no BDNF is added? Is it the B27 and GlutaMax in the Maintenance media, and does this actually rescue the cells?

(2) Figure 3 - K252a blocked activation in most, but not all, lineages, especially in mature neurons. Is some component of the P-Erk activation in these cells TrkB independent?

(3) Figure 5 E, F - The correlation between receptor surface depletion and signaling is based on "surface-specific staining". Does the staining allow you to see internalized receptors to confirm that the receptors are internalized?

(4) The drawbacks to the study - particularly capturing snapshots in time to represent signaling cascades, are fully acknowledged in the Discussion. The interplay between TrkB-T1, TrkB-FL, and p75NTR cannot be elucidated from this study, but again, that is acknowledged and will require a different approach.

Reviewer #3 (Public review):

This study addresses a fundamental and long-standing question in neurotrophin biology, how cellular context shapes the interpretation of a single trophic message, and tackles it with a technically demanding and well-executed single-cell mass cytometry approach. By simultaneously measuring 19 signaling effectors and 18 identity markers across a developmental gradient of spinal cord cell types, the authors substantially expand our understanding of BDNF signaling and provide a compelling demonstration of the limitations inherent to bulk biochemical readouts, which average across heterogeneous populations and obscure the discrete subpopulation behavior that the present data reveal.

The finding that only 47-75% of cells respond at peak activation, that maturation state dictates both the magnitude and the qualitative "signature" of the response, and that identical receptor stoichiometries can yield divergent outcomes across cell types collectively constitute an important conceptual advance. The proposed framework of "prepared competence" is thought-provoking and likely to stimulate follow-up work.

That said, several aspects of the data interpretation deserve more critical discussion. My specific comments are detailed below.

(1) Interpretation of TrkB-independent ERK activation (lines 194-196).

The authors state that the residual pERK induction observed in TrkB-negative ("None") cells and the incomplete suppression of pERK by K252a support the established notion that BDNF signaling is not mediated solely through TrkB. This interpretation is presented without sufficient mechanistic detail and, in its current form, is difficult to follow. If BDNF-induced ERK activation is not mediated by TrkB, which alternative receptors could account for it? Does this reflect signaling through p75NTR, transactivation of other receptor tyrosine kinases, or another mechanism altogether? Likewise, the partial resistance of pERK to K252a is interpreted as evidence of an additional regulatory layer, but the underlying activity is not specified. Is the authors' hypothesis that a distinct pool of ERK is engaged independently of Trk activity? If so, what kinase activity is proposed to drive it? These results are intriguing yet puzzling and merit a more critical and explicit discussion of the candidate mechanisms.

(2) The "progenitor paradox" in light of prior work on PC12 cells (lines 207-208).

The observation that TrkB-expressing progenitors remain insensitive to BDNF is presented as a paradox and interpreted through the lens of impaired internalization. This interpretation would benefit from explicit discussion in the context of the classical work on PC12 cells (Segal and colleagues, among others), which established that plasma membrane-restricted Trk receptors engage the Ras-MAPK pathway with rapid, short-duration kinetics that drive proliferation rather than differentiation, whereas internalized Trk receptors sustain MAPK signaling and promote differentiation. Under this framework, the apparent signaling silence of progenitors could, in fact, reflect transient plasma membrane signaling that the time points sampled in the present study (5 min onward) may not capture. The single-cell mass cytometry approach used here is, in principle, well-suited to resolving such rapid kinetics, and the authors are encouraged to address this possibility, both as an alternative interpretation of their data and as a potential extension of the study.

(3) Astrocyte responsiveness and the TrkB isoform issue.

The authors report that astrocytes are highly responsive to BDNF and exhibit robust ligand-induced depletion of surface TrkB, which they interpret as evidence of signaling-competent full-length TrkB (TrkB-FL) on these cells. However, it is well established that astrocytes predominantly express the truncated isoform TrkB-T1, which lacks the intracellular kinase domain and is thought to function in BDNF capture, clearance, and recycling at synapses rather than in canonical downstream signaling. The robust phosphorylation events observed in astrocytes are therefore difficult to reconcile with TrkB-T1-mediated signaling alone. Could these responses instead reflect transactivation of other receptors through neuron-astrocyte crosstalk, for instance, via ligands released by neurons in response to BDNF? Because the authors explicitly state that their antibody cannot distinguish TrkB-FL from TrkB-T1, this limitation directly impacts the interpretation of the astrocyte data and of the proposed isoform-switch hypothesis for progenitors. This caveat is briefly acknowledged but deserves more thorough discussion, ideally with explicit consideration of the alternative interpretations outlined above.

(4) Pathways resistant to K252a inhibition.

The authors note that K252a fails to fully abolish pERK induction in several lineages, but the specific pathways, differentiation states, and receptor stoichiometries that remain K252a-resistant are currently insufficiently described. A more systematic description would strengthen this section. In addition, it would be helpful to discuss whether the residual signal could reflect the proximity of the response to the detection threshold rather than a genuinely K252a-insensitive pool of activity. More broadly, K252a is a broad-spectrum tyrosine kinase inhibitor with well-documented off-target effects, and the present study relies on this single pharmacological tool to define Trk-dependence. The limitations of this approach, and the desirability of complementary inhibitors or genetic perturbations in future studies, should be acknowledged in the Discussion.

(5) The 12-hour trophic deprivation paradigm as a potential confounder.

All cells in the present study are trophically deprived for 12 hours prior to stimulation. This is a methodologically convenient choice, but sustained deprivation is not a neutral starting point: it activates stress-responsive pathways (JNK, p38, autophagy), alters receptor surface trafficking, and can sensitize cells to subsequent stimulation. Several of the reported observations - including the apparent synergy of p75NTR with TrkB on stress markers (p-c-Jun, p38) and the strong induction of trophic effectors immediately upon BDNF addition - could be amplified, or qualitatively altered, by the prior deprivation state, which does not reflect baseline in vivo physiology. The Rescue control, with complete medium, partially addresses this concern but is non-specific. The authors should explicitly acknowledge this limitation and, ideally, discuss the extent to which their conclusions about cell-type-specific signaling competence depend on the deprivation paradigm.

(6) Direct comparison of pseudobulk data with conventional bulk biochemistry.

The pseudobulk reconstruction of the single-cell data is presented as recapitulating canonical BDNF responses, but this comparison relies on general agreement with the published literature rather than on a direct, parallel measurement in the same cultures. Given that the central conceptual contribution of the manuscript rests precisely on departures from the bulk biochemical view of BDNF signaling, an explicit side-by-side comparison of the pseudobulk profile against a parallel bulk Western blot from sister cultures - for at least a subset of key markers such as pERK, pAkt, and pCREB - would substantially strengthen the validation of the platform. Such a comparison would reassure the reader that the discrete subpopulation behavior reported here is genuinely biological, and not in part a consequence of methodological differences between mass cytometry and conventional biochemistry (e.g., differences in fixation kinetics, epitope accessibility, or sensitivity to low-abundance phosphoproteins).

(7) Manuscript organization and balance between main and supplementary figures.

The manuscript presents an exceptionally rich dataset, but the current organization - seven main figures supported by thirteen supplementary figures, several of which are explicitly labeled as extensions of main-text figures - makes it difficult to follow the argument without continuous cross-referencing between documents. I would encourage the authors to consider a substantive reorganization with the following suggestions: (i) Figure S2 and Figure S3, which respectively define the threshold-based "responsiveness" criterion and assess its robustness, are foundational to the central 47-75% responsiveness claim and would be better integrated into the main text, for example as additional panels of Figure 2; (ii) the methodological and quality-control components of Figure S1 and Figure S2 would be more naturally placed within the Methods section; and (iii) the four "Extension" figures (S4, S7, S12, S13) contain considerable redundancy with the corresponding main figures and could be consolidated, with only the most diagnostic panels retained. Concurrent trimming of the denser main figures (Fig. 4, 5, and 6 each carry six or seven panels) would further improve readability.

Reviewer #1 (Public review):

[Editors' note: this version has been assessed by the Reviewing Editor without further input from the original reviewers. The authors have addressed the comments raised in the previous round of review.]

Summary:

In this review paper, the authors describe the concept of neural correlates of consciousness (NCC) and explain how noninvasive neuroimaging methods fall short of being able to properly characterise an unconfounded NCC. They argue that intracranial research is a means to address this gap and provide a review of many intracranial neuroimaging studies that have sought to answer questions regarding the neural basis of perceptual consciousness.

Strengths:

The authors have provided an in-depth, timely, and scholarly contribution to the study of NCCs. First and foremost, the review surveys a vast array of literature. The authors synthesise findings such that a coherent narrative of what invasive electrophysiology studies have revealed about the neural basis of consciousness can be easily grasped by the reader. The authors also succeed in describing how single-cell recordings can interface with task-design to help mitigate the impact of confounded neural activity when searching for NCCs.

The review is also, to the best of my knowledge, the first review to specifically target intracranial approaches to consciousness and to describe their results in a single article. This is a credit to the authors - as it becomes ever harder to apply strict tests to theories of consciousness using methods such as fMRI and M/EEG, it is important to have informative resources describing the results of human intracranial research so that theorists will have to constrain their theories further in accordance with such data. Additionally, the authors provide a compelling case for single-celled research in consciousness science, despite the dominance of theories situated at the system and circuit level of analysis. As far as the authors were aiming to provide a complete and coherent overview of intracranial approaches to the study of NCCs, I believe they have achieved their aim.

Weaknesses:

Overall, I feel positive about this paper. The authors have addressed my comments from my previous review and I see no significant weaknesses in the current version.

Comment on previous version:

No comments - congratulations to the authors!

Reviewer #2 (Public review):

Summary:

In this work, the authors review the study of the neural correlates of consciousness (NCCs). They discuss several of the difficulties that researchers must face when studying NCCs, and argue that several of these difficulties can be alleviated by using intracranial recordings in humans.

They describe what constitutes an NCC, and the difficulties to distinguish between an NCC proper from the prerequisites and consequences of conscious processing.

They also describe the two main types of experimental designs used to study NCCs. These are the contrastive approach (with its report and non-report variants), and the supraliminal approach, each with their own merits and pitfalls.

They discuss the limitations of non-invasive methods, such as fMRI, EEG and MEG, as well as the limitations of the use of invasive recordings in non-human animals.

After setting the stage in this way, the authors provide an extensive review on the knowledge acquired by using invasive recordings in humans. This included population level measurements in vision and in other sensory modalities, as well as single neuron level studies. The authors also discuss studies of subcortical NCCs.

The second half of this work discusses the theoretical insights gained through the use of intracranial recordings, as well as their limitations, and a perspective for future work.

Strengths:

This work offers an impressive review, which will serve as a useful reference document, both for newcomers to the study of NCC as for experienced researchers. The inclusion of non-visual and subcortical NCCs is of particular merit, as these have been understudied.

Besides serving as a review, this work includes a perspective, exploring several directions to pursue for the progress of the field.

Weaknesses:

No major weaknesses.

Appraisal of whether the authors achieved their aims:

In this work, the authors have gathered an impressive review, and have discussed several important problems in the field of study of NCCs, as well as provided a perspective on how the field could move forward.

Discussion of the likely impact of the work on the field:

This work has the potential of becoming a must read for anyone working in the field of consciousness research.

Comment on previous version:

The authors have addressed all my concerns. Once again, my compliments for a nice piece of work.

Reviewer #3 (Public review):

Summary:

This narrative review provides a clear, well-structured, and comprehensive synthesis of intracerebral recording work on the neural correlates of consciousness. It is written in an accessible manner that will be useful to a broad community of researchers, from those new to iEEG to specialists in the field.

Strengths:

The manuscript successfully integrates methodological and theoretical perspectives and offers a balanced overview of current sometimes contradicting evidence. As such, the manuscript is important as call for a concernted better exploration of NCCs using iEEG in the future.

Comments on latest version:

The current version of the manuscript is clear and complete. Kudos to the authors for their thorough revisions.

Reviewer #1 (Public review):

Summary:

This study uses optogenetics to activate CA3 while recordings from CA1 neurons and characterizing the excitation/inhibition (E/I) balance. They observe use-dependent alterations in the E/I balance as a result of STP and they develop a model to describe these observations. This is a very ambitious paper that deals with many issues using both experimental and modeling approaches.

Strengths:

This paper examines important principles regarding the manner in which synaptic circuitry and use-dependent synaptic plasticity can transform inputs and perform computations.

Weaknesses:

There are three issues that cause concern regarding the applicability of their slice recordings to physiological conditions and that make some aspects of their results difficult to interpret. First, they state that 2 mM added external calcium mimics calcium levels in CSF, but this is not the case. This will influence the plasticity they observe. Second, they indicate that there is a 2% decrease in activated fibers per stimulus and attribute this to ChR2 desensitization. Such use-dependent decreases in fiber activation are expected to build during their repetitive activation experiments and artifactually influence their results. Third, they do not know the responses of individual CA3 cells to stimulation. They do not know if each cell fires reliably during repetitive activation and whether each cell only fires once.

Reviewer #3 (Public review):

Summary:

This work shows experimentally and computationally that single CA1 neurons can perform mismatch detection on patterned CA3 inputs and that STP and EI balance underlie this detection.

Strengths:

It has been known that STP can enhance the EPSP when the corresponding presynaptic input exhibits abrupt changes in firing rate. This work provides experimental evidence and further computational support for the hypothesis that the basic computation through STP is useful for detecting abrupt changes in the spatial pattern of synaptic inputs at the Schaffer collaterals. Further, their results indicate the novel view that mismatch detection is most efficient when gamma-frequency bursting inputs exhibit mismatches between theta cycles. The authors included novel results in the revised manuscript to show that the effective frequency range of gamma oscillation is broad, including both slow and fast gamma bands.

In the initial submission, the dependence of mismatch detection performance on model parameters and experimental settings, such as pattern overlaps and other network parameters, was not sufficiently explored. In the revised manuscript, the authors extensively studied these points and summarized the novel results in Fig. 9. Furthermore, the authors clarified that jitters in input spikes can improve detection performance in some cases. These results show the robustness of their results against variations in external and internal conditions.

Weaknesses:

While this study shows an intriguing example of combined experimental and computational studies, some analytic results, for instance, regarding the complex contributions of jitters to detection performance, could have clarified the underlying mechanism deeper and further strengthened the manuscript.

Reviewer #1 (Public review):

Summary:

Using a computational modeling approach based on the Drift and Diffusion Model (DDM) introduced by Ratcliff and McKoon in 2008, the article by Shevlin and colleagues investigates whether there are differences between neutral and negative emotional states in:

(1) The timings of the integration in food choices of the perceived healthiness and tastiness of food options in individuals with bulimia nervosa and healthy participants

(2) The weighting of the perceived healthiness and tastiness of these options.

Strengths:

By looking at the mechanistic part of the decision process, the approach has potential to improve the understanding of pathological food choices.

Comments on revised version:

I went carefully through the answers of the authors to my last concerns - they answered all my points. I am grateful that they obtained consistent results with the different analyses.

Reviewer #1 (Public review):

Summary:

This manuscript examines the frequency-dependent effects of transcutaneous tibial nerve stimulation (TTNS) on bladder function in healthy volunteers, supported by a conductance-based computational model of lower urinary tract (LUT) neural circuitry. The authors show that 1 Hz TTNS modestly hastens the urge to void, while 20 Hz TTNS delays it - a finding with potential therapeutic relevance for underactive bladder (UAB). A computational model incorporating spinal, brainstem, and peripheral circuit elements provides a mechanistic framework suggesting brainstem-mediated pathways underlie these frequency-dependent effects. The revised manuscript addresses the majority of concerns raised in the initial review.

Strengths:

Novelty. Demonstrating a low-frequency excitatory effect of TTNS in humans is genuinely new. The possibility of inverting the therapeutic effect of an established neuromodulation intervention by simply adjusting stimulation frequency is clinically meaningful and opens a plausible treatment avenue for UAB.

Integrated approach. Combining a controlled human pilot study with a systems-level neural model is a notable strength. The model is physiologically grounded and serves well as a proof-of-concept tool for exploring mechanistic hypotheses.<br /> Improved reproducibility. The addition of a public GitHub repository with documented code, supplementary figures detailing electrode placement and stimulation parameters, and removal of the externally derived Figure 3 all meaningfully improve transparency.

Improved statistics. The shift to Bayesian modelling with ROPE analysis is well-justified given the small sample size and more appropriate than frequentist testing in this context.

Improved presentation. Unit standardization, figure label corrections, and replacement of imprecise terminology (e.g., "paradoxical", "analytically") make the revised manuscript considerably clearer.

Remaining Concerns:<br /> Afferent-efferent disconnect. The human study measures urgency (an afferent sensory endpoint), while the model's primary output is contraction duration (an efferent motor endpoint). The authors have added discussion of this mismatch, but should state more explicitly that the two lines of evidence are complementary rather than directly comparable, and that the mechanistic link between them remains a hypothesis.

Clinical contextualization of effect size. The excitatory effect of 1 Hz TTNS is modest. A brief reference to what a minimally clinically important difference might look like in UAB or urodynamics research would help readers gauge the translational significance of the finding.

Overall Appraisal:<br /> The authors have achieved their stated aims: providing proof-of-concept human evidence for frequency-dependent TTNS effects and a plausible neural circuit explanation. The manuscript is now appropriately cautious in its claims. The open-source computational model is a useful community resource. This work is best understood as a well-scoped proof-of-concept study that credibly motivates further investigation.

Reviewer #2 (Public review):

Strengths:

The main strength of the work is to call attention to a new possibility of inverting the effect of TNS in humans by manipulating stimulation frequency, opening new indications for the therapy. This is highly relevant because of the recent popularity of TNS and its non-invasiveness, which lends itself to rapid testing and evaluation for new conditions and high willingness to adopt. The authors convincingly demonstrate a modest excitatory effect on bladder sensation with low-frequency TNS, which clearly warrants further investigation.

The high-level design of the hypotheses, concepts, and experiments are clearly articulated in both the methods and in particularly clear diagrams, letting the reader focus their attention on the most important findings.

It is rare to develop a new computational model of the lower urinary tract at a systems level, and even more so for it to incorporate circuits in the spinal cord and brainstem centers, and this work undoubtedly advances the field's ability to engineer such systems. Further, because the model is comprised of linked conductance-based point-neurons, it is an excellent tool to investigate how an arguably plausible wiring diagram for neural control of the LUT could result in stimulation frequency dependent effects on pelvic efferents. It is a proof of concept demonstrating how their mechanistic hypothesis of TNS could be implemented neurophysiologically by the nervous system. Further, the model is shared openly, which conforms to good modeling practices.

Weaknesses:

The main drawback of the work is the overinterpretation of the results. The human study and computational model are both proof-of-principle. The human study effect size is small and the sample size is modest; the computational model is poorly validated and does not generate physiologically typical urodynamic responses when simulating even healthy nominal LUT conditions. Thus, both the existence of a TNS 1Hz inhibitory effect (human study) and the mechanistic interpretation of its origin (simulations) remain provisional. For example, despite some caveats later in the work, the abstract stating there is a "frequency-dependent effect of TNS via the ability to alter urge perception and down-regulate bladder activity, corroborating model predictions," could easily be misleading, since a) the reduction in time of first urge with 1Hz stimulation was quite small relative to overall void time, b) reported intensity was essentially not impacted, and c) the model does not directly make predictions about these experiment outcome measures. Similar overreaching statements appear in the second to last paragraph of the introduction, the first paragraph of the discussion, and so on throughout the paper. Many of the analyses are bespoke to the idiosyncrasies of the dataset rather than field standards, making spurious results also more likely and the effects provisional. One example is the use of robust linear regression to identify significance in the experiment between the 1Hz and control groups AND removing outliers before the analysis, since the typical approach is to use robust regression when the outliers are left in the data. Taken together, the potential excitatory effect and mechanism are interesting, and perhaps worth further investigation, but are considerably more tentative than stated.

It remains ambiguous whether a TNS excitatory effect size shown (even if it ends up being repeatable) is clinically meaningful. The ROPE analysis is a reasonable start, but no attempt to connect the parameters chosen (e.g. 60s) to clinical outcomes were made. This is especially true given the washout results and lack of effect on perceived urgency.

There remain several reasons to treat the model results questionable. First, as the authors now note, the model under normal conditions does not generate normal function; a voiding efficiency of 15% is severely underactive. Second, the 1 Hz stimulation simulation appears to create normal voiding, suggesting that the implementation of the neural control circuits may not produce results that would generalize to other experiments. Third, analysis focuses on the model outcome of "time to void", but this outcome is not reported for the experiment, so direct comparison is not possible.

Reviewer #1 (Public review):

[Editors' note: Given the minor nature of this revision, the editors have not sent this back to the original reviewers. The original reviews have been included.]

In this study, the authors set out to determine how two classes of kinase inhibitors, which stabilise a disease-relevant enzyme in either an active (Type I) or inactive state (Type II), influence its organisation and interactions with microtubule filaments in cells. Using the state-of-the-art in-cell structural imaging approaches, they examine how these compounds affect the formation of protein filaments and their association with microtubules, and succeed in defining the underlying structural basis for these differences.

A major strength of the work is the application of in-cell cryo-electron tomography combined with correlative imaging, which enables direct visualisation of protein organisation in a near-native cellular context. The data convincingly demonstrate that the Type I inhibitor compound stabilising the active state promotes extensive LRRK2 filament formation and microtubule bundling, whereas compounds stabilising the inactive state markedly reduce these interactions. The structural analysis further provides insight into how conformational states relate to filament organisation, including modelling of previously unresolved regions of the protein.

These findings are internally consistent and align well with prior biochemical and structural studies, many of which were performed by the same team.

There are, however, some limitations that should be noted. The experiments rely on overexpression of the I2020T mutant form of the LRRK2 protein, which is a rare variant, in a single cell type (293T cells), which may not fully reflect endogenous behaviour or wild-type LRRK2 in a physiological context. In addition, while the imaging data are compelling, the functional consequences of the observed filament formation and microtubule association remain unclear.

The study therefore provides strong descriptive and structural insight, but more limited evidence linking these observations to cellular or disease-relevant outcomes.

Overall, the authors largely achieve their aims, and the results support their central conclusion that different classes of kinase inhibitors have distinct effects on protein organisation in cells. The work represents an important advance in understanding how small molecules can reshape protein architecture in a cellular environment, with potential implications for therapeutic strategies. The methodological approach will also be of broad interest to the field, as it highlights the power of in-cell structural biology to study dynamic protein assemblies that are difficult to capture using traditional approaches.

Reviewer #2 (Public review):

Summary:

Mutations in Leucine-Rich Repeat Kinase 2 (LRRK2) are a major cause of Parkinson's disease. LRRK2 PD-related mutations all result in increased kinase activity. Therefore, LRRK2 has been the focus of the development of kinase inhibitors. So far, two classes of kinase inhibitors have been identified: type 1 LRRK2-specific inhibitors that stabilize LRRK2 in a closed active-like conformation and broad-range type 2 inhibitors that stabilize LRRK2 in an open inactive-like conformation. Basiashvili et al. used here in cell structural biology to study the effect of both type 1 and type 2 inhibitors on the localization and structural conformation of LRRK2-I2020T.

Strengths:

They showed that Type 1 and not Type 2 inhibitors induce LRRK2 filament/ on microtubules. Furthermore, they were able to build a structural map of full-length LRRK2 I2020T bound to a Type 1 inhibitor in a closed kinase confirmation. Together, this work thus confirms the data of previous studies that showed that LRRK2 Type 1 and 2 inhibitors differently affect filament formation.

Previous Weaknesses:

All conclusions are fully supported by the provided data. However, as the authors indicated themselves, the physiological relevance of LRRK2 microtubule binding is questionable. Furthermore, although the authors used a full-length LRRK2 protein, like in previously published structures, the resolution of the N-terminal domains is rather poor. Therefore, it also remains unclear what we learn from this structure compared to the previously published structures.

Reviewer #3 (Public review):

Summary:

This paper describes new insights into the effects of type-I and type-II LRRK2 inhibitors on HEK293T cells that over-express GFP-labeled LRRK2-I2020T. Using correlative light microscopy and cryo-electron tomography, a type-I inhibitor leads to the extensive decoration of microtubules with LRRK2, which is not seen for a type-II inhibitor. Subtomogram averaging reveals that LRRK2 binds to the microtubules in a closed-kinase conformation, with density for the N-terminal arms.

Strengths:

The paper is well written; the CLEM and cryo-ET appear to be done to a high standard. Consequently, I have only minor comments.

Weaknesses:

The resolution of the subtomogram averages is somewhat limited, but the authors have adequately limited the number of degrees of freedom in the fitting of their atomic models by only allowing rigid-body transformations of separate parts of LRRK2.

The authors should include FSC curves between the rigid-body fitted atomic models and the various sub-tomogram average maps.

Comment on the current version from the Reviewing Editor:

I do note that Ext Data Fig 8 does not yet contains the requested model-vs-map FSC curves. I guess this is an oversight and trust that the authors will remedy this during the production process. They might also want to explain what the black, red, green and blue FSC curves are in the current figure (or only show the black (solvent-corrected FSC) curve, together with the requested model-vs-map curve.

Reviewer #1 (Public review):

Summary:

In this study, the authors aim to identify the neural circuit mechanisms underlying dystonic crisis, a severe and life-threatening manifestation of dystonia, and to explore potential therapeutic targets. The authors combine retrospective clinical data from pediatric patients with mechanistic experiments in a genetic mouse model of dystonia. They focus on inhibitory cerebellar nuclei neurons (iCNNs), testing whether these neurons can trigger dystonic crisis and whether their modulation can alleviate symptoms. Using optogenetics, anatomical tracing, and deep brain stimulation (DBS), the authors propose that iCNNs drive dystonic crisis via projections to the centrolateral (CL) thalamus and that this pathway can be therapeutically targeted.

Strengths:

A major strength of the study is its integrative approach, bridging human clinical observations and mechanistic animal experiments. The clinical analysis provides suggestive evidence linking cerebellar abnormalities and inhibitory signaling to dystonic crisis, which motivates the subsequent experimental work. In the mouse model, the authors use cell-type-targeted optogenetic manipulation to show that activation of iCNN pathways induces dystonic crisis-like episodes, while inhibition alleviates spontaneous crises. These bidirectional manipulations provide strong support for a causal role of iCNN activity in modulating disease severity. The identification of a monosynaptic projection from iCNNs to the CL thalamus, combined with DBS experiments showing therapeutic effects, further strengthens the proposed circuit mechanism and highlights translational relevance.

The behavioral effects reported are robust and reproducible across animals, and the use of both activation and inhibition paradigms is a notable strength. The DBS experiments are particularly compelling in demonstrating that modulation of a downstream node can mitigate symptoms induced by upstream circuit activation, supporting the functional relevance of the identified pathway.

Weaknesses:

However, several limitations temper the strength of the conclusions.

First, the specificity of the genetic and optogenetic manipulations is not absolute. The Ptf1a-based strategy targets iCNNs but also labels other neuronal populations and projections, raising the possibility that off-target effects contribute to the observed phenotypes. Although the authors argue that light spread and anatomical considerations make this unlikely, more discussion on evidence of circuit specificity would strengthen the claims.

Second, the behavioral definition and quantification of "dystonic crisis" in mice, while carefully described, remain somewhat subjective and may not fully capture the complexity of the human condition. Additional quantitative or automated behavioral analyses could increase confidence in the interpretation of these episodes and facilitate comparison across conditions. If difficult to add, please at least discuss this aspect.

Third, while the anatomical tracing suggests a projection from iCNNs to the CL thalamus, the functional contribution of this specific synaptic connection is inferred rather than directly demonstrated. The DBS experiments support involvement of the CL but do not establish whether the iCNN→CL pathway is necessary or sufficient for the observed effects. More direct circuit-level manipulations would be required to fully validate this mechanism. If difficult to perform these experiments, please at least discuss the importance of such future studies.

Finally, the translational relevance, while promising, remains somewhat speculative. The clinical data are retrospective and correlative, and the therapeutic implications of targeting this pathway in humans will require further validation.

Overall, the authors have achieved their primary aim of identifying a cerebellar inhibitory circuit that can drive and modulate dystonic crisis in a mouse model. The results support their central conclusions, although some mechanistic aspects remain incompletely resolved. The study provides a valuable contribution to the field by highlighting a previously underappreciated role of inhibitory cerebellar output neurons and suggesting a new circuit-based framework for understanding and treating severe dystonia.

Reviewer #2 (Public review):

Summary:

The role of the cerebellum in producing and modifying dystonic motor phenotypes has been of increasing recent interest to understand the pathophysiology of movement disorders, as well as to develop novel pharmacological and surgical interventions to treat these disorders. Previous rodent and human imaging studies have shown that in genetic, drug-induced, and injury-acquired dystonia, cerebellar dysfunction and output from the deep cerebellar nuclei have correlated with the development of dystonia symptoms. In some genetic dystonia patients, the strength of connections between the cerebellum, thalamus, and cortex could explain reduced penetrance or severity of symptoms in these genetically defined dystonia patients. Altogether, these studies have pointed to abnormal output from the cerebellum as a driver of abnormal motor output. Some studies have even gone as far as to suggest that no cerebellum is better than a cerebellum with abnormal output (see PMID 8491286). This indicates a critical need to understand the neural circuits underlying dystonia development, how the cerebellum drives symptom onset or severity, and if the cerebellum could be therapeutically targeted for the benefit of patients with dystonia.

Hipolito et al. use rigorous mouse genetics-based approaches to understand how a specific cell type, inhibitory projection neurons from the cerebellar nuclei, can drive dystonic phenotypes, especially severe dystonic phenotypes. The authors demonstrate a number of novel findings that further support a critical role for disturbed cerebellar output in driving dystonic phenotypes, and that disrupting this disturbed output may provide a novel therapeutic approach for dystonia. Specifically, the authors define a novel role for inhibitory neurons of the cerebellar nuclei in driving disease, and these neurons have not previously been observed to have monosynaptic connections into a specific nucleus of the thalamus. Disruption of these connections via deep-brain stimulation alleviated severe dystonic crisis with quick onset, and repeated stimulation sessions possibly had a long-term disease-modifying effect. Overall, these findings present novel insight into the circuits and mechanisms by which inhibitory neurons of the cerebellar nuclei influence dystonic states, and how these may be a viable therapeutic target for severe dystonia. My specific comments are below:

Strengths:

The manuscript uses rigorous mouse genetics techniques to provide fundamental insight into the role of inhibitory projection neurons of the cerebellar nuclei in influencing dystonic states. Solid experimental evidence is used to step-by-step illustrate circuit-level consequences of inhibitory projections of the cerebellar nuclei, and whether these can be manipulated for therapeutic benefit.

Weaknesses:

There are mild weaknesses in the approach around proving the specificity of the vGlut2 knockout, the long-term effects of silencing inhibitory projections, as well as the degree to which activation specifically drives dystonic crisis. These are addressed in my specific comments below.

Reviewer #1 (Public review):

[Editor's note: This version has been assessed by the Reviewing Editor without further input from the original reviewers. The authors have addressed all concerns raised by the reviewers; no further changes are required at this point.]

Summary:

The manuscript by Yang et al. investigates the relationship between multi-unit activity in the locus coeruleus, putatively noradrenergic locus coeruleus, hippocampus (HP) sharp-wave ripples (SWR) and spindles using multi-site electrophysiology in freely behaving male rats. The study focuses on SWR during quiet wake and non-REM sleep, and their relation to cortical states (identified using EEG recordings in frontal areas) and LC units.

The manuscript highlights differential modulation of LC units as a function of HP-cortical communication during wake and sleep. They establish that ripples and LC units are inversely correlated to levels of arousal: wake, i.e. higher arousal correlates with higher LC unit activity and lower ripple rates. The authors show that LC neuron activity is strongly inhibited just before SWR detected during wake. During non-REM sleep, they distinguish "isolated" ripples from SWR coupled to spindles and show that inhibition of LC neuron activity is absent before spindle-coupled ripples but not before isolated ripples, suggesting a mechanism where noradrenaline (NA) tone is modulated by HP-cortical coupling. This result has interesting implications for the roles of noradrenaline in the modulation of sleep-dependent memory consolidation, as ripple-spindle coupling is a mechanism favoring consolidation. The authors further show that NA neuronal activity is downregulated before spindles.

Strengths:

In continuity with previous work from the laboratory, this work expands our understanding of the activity of neuromodulatory systems in relation to vigilance states and brain oscillations, an area of research that is timely and impactful. The manuscript presents strong results suggesting that NA tone varies differentially depending on coupling of HP SWR with cortical spindles. The authors place their findings back in the context of identified roles of HP ripples and coupling to cortical oscillations for memory formation in a very interesting discussion. The distinction of LC neuron activity between awake, ripple-spindle coupled events and isolated ripples is an exciting result and its relation to arousal and memory opens fascinating lines of research.

Reviewer #2 (Public review):

Summary:

In this study, authors studied the synchrony between ripple events in Hippocampus, cortical spindles and Locus Coeruleus spiking. The results in this study together with the established literature on the relationship of hippocampal ripples with widespread thalamic and cortical waves, guided authors to propose a role for Locus Coeruleus spiking patterns in memory consolidation. The findings provided here, i.e. correlations between LC spiking activity and Hippocampal ripples, could provide basis for future studies probing the directional flow or the necessity of these correlations in the memory consolidation process. Hence, the paper provides enough scientific advance to highlight the elusive yet important role of Norepinephrine circuitry in the memory processes.

Strengths:

Authors were able to demonstrate correlations of Locus Coeruleus spikes with hippocampal ripples as well as with cortical spindles. Specific strength of the paper is in the demonstration that the spindles that activate with the ripples are comparatively different in their correlations with Locus Coeruleus than those which do not.

Reviewer #3 (Public review):

This manuscript examines how locus coeruleus (LC) activity relates to hippocampal ripple events across behavioral states in freely moving rats. Using multi-site electrophysiological recordings, the authors report that LC activity is suppressed prior to ripple events, with the magnitude of suppression depending on ripple subtype. Suppression is stronger during wakefulness than during NREM sleep and least pronounced for ripples coupled to spindles.

The study is technically sound and addresses a timely and important question regarding how LC activity interacts with hippocampal and thalamocortical network events across vigilance states. While the findings are interesting, they remain observational in nature.

Reviewer #1 (Public review):

Summary:

The manuscript examines whether scene meaning guides overt attention in rhesus macaques. Two monkeys freely viewed naturalistic indoor scenes, including laboratory or housing scenes described as familiar and other indoor scenes described as unfamiliar. The authors compare fixation locations with matched non-fixated control locations using predictors derived from center proximity, image salience, and a DeepMeaning model intended to capture the spatial distribution of semantic informativeness. They report that meaning predicts fixation selection beyond salience and center bias, that meaning and salience interact, that familiar scenes produce broader exploration of low-meaning regions, and that the influence of meaning increases with attentional engagement.

Strengths:

A major strength of the study is its use of natural free-viewing behavior in macaques. The experimental approach takes advantage of intrinsic gaze allocation rather than relying on a more artificial task, which makes the work a useful bridge between human scene-viewing studies and future neurophysiological studies in nonhuman primates.

The statistical analyses are extensive. The authors model fixated and matched non-fixated samples with Bayesian generalized linear mixed models, including center proximity and salience as important controls, examined interactions among predictors, and reported diagnostics for multicollinearity and model convergence. These analyses support the basic observation that the human-derived meaning maps are associated with macaque fixation allocation beyond the particular center and salience terms included in the model.

The question is interesting and timely. If meaning-like scene structure can be operationalized for macaque viewing, this would provide a useful behavioral foundation for future work on the neural mechanisms that link scene analysis, gaze allocation, and natural behavior.

Weaknesses:

The main weakness is interpretive. The manuscript often treats the DeepMeaning map as though it measures scene meaning for the monkey, but the map is ultimately human-derived. Some of the examples make this issue especially salient: regions such as clocks, phones, dining tables, or other human artifacts may be meaningful to human observers, but it is not clear that they have semantic meaning for macaques. If meaning-based guidance is argued to emerge through experience, then unfamiliar human indoor scenes that the monkeys have never encountered cannot straightforwardly be meaningful to them in the same sense that they are meaningful to humans. Predictive success for these scenes may therefore indicate sensitivity to visual or object-level structure correlated with human-rated meaning, rather than macaque semantic understanding.

A related concern is that the DeepMeaning predictor may capture forms of visual salience, objectness, or high-level image structure not captured by the particular low-level salience model. For example, a clock or phone may attract gaze because of shape, contrast, face-like configuration, object boundaries, or other mid-level features rather than because it carries semantic meaning for a macaque. The present analyses show that this model is predictive, but they do not by themselves establish that the predictive variable is semantic meaning rather than visual structure beyond Itti-Koch-style salience.

The manuscript relies heavily on fitted model parameters and derived maps, with relatively little return to the raw behavioral data. The main claims would be easier to evaluate if the authors showed more direct fixation-density maps, scene-by-scene examples, and aggregate raw relationships between fixation behavior and map values. At present, much of the argument rests on interpreting fitted coefficients, without enough behavioral visualization to show what the monkeys actually did across the stimulus set.

It is also unclear whether model performance was evaluated on held-out data. The comparison to repeated viewing of the same images is useful as a behavioral benchmark, but a second viewing may itself be affected by familiarity or memory for the image. This makes it a potentially imperfect estimate of a noise ceiling for first-pass fixation predictability. Cross-validation or held-out prediction, ideally across held-out images as well as trials, would make the predictive claims more convincing.

Although the authors describe multicollinearity as negligible, Figure S2B-C appears to show some nontrivial correlations among predictors. These correlations may matter for interpretation even if variance inflation factors fall below conventional thresholds, especially when the signs of fitted effects point in directions that may be expected from the input correlations, such as relationships involving meaning and familiarity. The manuscript would benefit from reporting these correlations quantitatively and relating them to the fitted effects.

The familiarity analysis is interesting but would benefit from further control. Familiar scenes are photographs of the monkeys' housing and laboratory environments, whereas unfamiliar scenes are other indoor environments. These categories may differ not only in familiarity but also in clutter, spatial layout, object density, color distribution, luminance, contrast, edge density, texture statistics, or the distributions of salience and meaning values. Without additional characterization of the image sets, the conclusion that familiarity itself broadens exploration should be treated cautiously.

The engagement effects also appear less consistent across the two monkeys than some of the summary language suggests. The monkey-specific results should be emphasized, and claims about engagement strengthening meaning-based guidance should be stated in proportion to the cross-animal evidence.

Finally, the manuscript sometimes uses language that sounds more mechanistic than the behavioral data can support. The negative interaction between meaning and salience is an interesting result, but terms such as competitive integration in a shared priority map go beyond what can be concluded from overt fixation selection alone. The study lacks a causal or perturbational manipulation, such as image inversion or another transformation that preserves local features while altering semantic organization. The result would be clearer if described first as a model-based association or subadditive interaction in gaze allocation, with the priority-map interpretation presented as a plausible account rather than a direct conclusion.

Reviewer #2 (Public review):

Summary:

In prior work, the authors developed an ML algorithm that computes spatial maps of "meaning": image regions that are likely to be given semantic labels by human observers. They also previously showed that "meaning" predicts fixations in humans and human infants. Here, these observations were extended to macaque monkeys, testing the hypothesis that meaning is a phylogenetically preserved driver of overt attention across primates.

Strengths:

The paper reports that fixated locations had higher values of meaning compared to nearby, non-fixated locations. Specifically, it shows that meaning values - as inferred from a neural network model - are useful in differentiating these two classes of locations, beyond the established effects of image salience and centrality on gaze. The reported results were consistent in both monkeys.

Weaknesses:

It is difficult to understand what, precisely, is meant by meaning from this paper, although the prior work from this group may offer some insight. Given that, it is not clear if "high-meaning" image locations tend to be objects, for example, or faces, or other such behaviorally relevant image features. Indeed, the utility of the meaning maps was not evaluated against other algorithms that consider more complex natural scene information. This is a particular concern as the paper does not demonstrate that meaning predicts where the viewer will look within the image; instead, it shows that meaning is one of the variables that differentiates fixated locations from nearby non-fixated locations. Because this is not a causal study by necessity, caution is also needed in interpreting the results. In our view, the most parsimonious interpretation may not be that meaning guides gaze in monkeys, but instead that people tend to name things that primate brains evolved to fixate on at the expense of neighboring locations.

Reviewer #3 (Public review):

Summary:

This novel study asks whether meaning-based guidance of overt attention, well-established in humans through the "meaning map" framework, extends to non-human primates. The authors recorded eye movements from two rhesus macaques freely viewing naturalistic indoor scenes and modeled fixation selection using DeepMeaning maps, Itti-Koch salience maps, and center proximity. They report that scene meaning robustly predicts fixation selection after controlling for salience and center bias, that meaning and salience interact competitively rather than additively, and that the influence of meaning is modulated by scene familiarity and attentional engagement. The cross-species extension of the meaning map approach is a valuable contribution, and the Bayesian GLMM framework with variance partitioning is well-suited to the question.

Strengths:

(1) The cross-species extension itself is novel and well-motivated. Nobody has applied the meaning map framework to NHP gaze behavior before. Even with the interpretive caveats I raise below, creating this methodological bridge between human scene perception research and NHP circuit neuroscience is a valuable contribution.

(2) The statistical framework is strong. The Bayesian GLMM with posterior distributions, HDIs, and probability of direction is more informative than frequentist alternatives. The variance partitioning with ΔR² is the right approach for disentangling predictor contributions. Random intercepts for scene are appropriate. The convergence diagnostics (R-hat = 1.00, ESS > 8000 across all models) are exemplary.

(3) Transparent individual-subject reporting. With N = 2, reporting each monkey separately rather than pooling or averaging is the correct choice, and the authors do this consistently. The individual differences are visible because the reporting is honest.

(4) The experimental design is excellent. 200 scenes is a substantial stimulus set by NHP standards. The inclusion of both familiar and unfamiliar environments, the repeated-viewing design for reliability estimation, and the 5-second free viewing window that yields ~15 fixations per trial all reflect thoughtful design.

(5) The familiarity and engagement analyses go beyond the basic demonstration. Even with the limitations we identified, asking how behavioral context modulates the meaning-gaze relationship is more ambitious than simply showing that the correlation exists. These analyses generate testable predictions for future work.

(6) Data and code sharing commitment. The authors plan to release raw data, preprocessing, and analysis code on OSF and GitHub.

Weaknesses:

(1) The authors' central claim is that meaning-based attentional guidance is an "evolutionarily conserved component of primate vision." This claim rests on the finding that macaque fixation patterns correlate with DeepMeaning maps. However, DeepMeaning is trained on human ratings of local scene meaning using a vision-language transformer (CoCa) pretrained on billions of human image-text pairs. What the model captures, then, is the spatial distribution of visual structure that humans judge to be semantically informative. The authors acknowledge that DeepMeaning represents "structured visual representations of scene regions containing identifiable objects and informative relationships" (lines 261-262), but this acknowledgment actually highlights the problem: regions containing identifiable objects and informative spatial relationships would plausibly attract fixations in any visual system with object-selective neurons and a bias toward structured content, regardless of whether the observer is processing "meaning" in any semantic sense. That is, the correlation between macaque gaze and DeepMeaning maps is consistent with shared object-level visual processing, but doesn't uniquely implicate shared semantic processing. The critical adversarial test from Hayes & Henderson (2022a)-where meaning maps detected the removal of semantic content via diffeomorphic scrambling while deep saliency models did not-has not been applied to macaque viewing behavior. Importantly, such a test would require new data collection (showing monkeys scrambled scenes), which may not be feasible. A more tractable approach with the existing data would be to compare DeepMeaning against some other model that captures mid-level visual structure without semantic supervision, though this would be a weaker test. Given these constraints, I would ask the authors to (a) acknowledge this limitation explicitly and temper the evolutionary conservation claim accordingly-for example, framing the result as evidence that macaques and humans share attentional biases toward visually structured scene regions, with the semantic interpretation remaining an open question-and (b) note the diffeomorphic scrambling experiment as an important future direction for establishing whether macaque attention is guided by semantic content per se.

(2) The familiar/unfamiliar scene comparison confounds long-term familiarity with systematic differences in scene content. Familiar scenes are photographs of the vivarium and laboratory; unfamiliar scenes are restaurants, bedrooms, kitchens, and offices. These two categories almost certainly differ in visual complexity, object density, spatial layout, clutter, and the types of objects present. The familiar environments (vivarium caging, lab equipment) are likely more spatially repetitive and lower in object diversity than, say, a restaurant or residential kitchen. Any difference attributed to "familiarity" could therefore reflect these systematic content differences. The negative interaction between meaning and familiarity (Monkey V: β = −0.19; Monkey I: β = −0.19), which the authors interpret as familiarity broadening exploration, could instead reflect the fact that vivarium/lab scenes have a different distribution of meaning values or a different relationship between meaning and salience than human domestic environments. The authors should address this confound directly. At minimum, comparing the distributions of meaning and salience values across the two scene categories would help the reader evaluate whether the familiarity effect can be separated from content effects. Ideally, the authors would include a subset analysis using only scenes matched on feature distributions or include scene-level summary statistics of the meaning and salience maps as covariates in the familiarity model.

Reviewer #1 (Public review):

Summary:

The authors investigate the relationship between feedback responses and trial-to-trial learning. In their paradigm, participants were constrained to a channel trial, and a cursor was visually perturbed. Using a channel-perturbation-channel structure, the authors obtain feedback responses to the perturbation and the learning response that ensues. In Experiment 1, the authors demonstrate that temporal dynamics of the learning response (LR) are poorly linked to temporal dynamics of the feedback response (FBR). The LR responses are yoked to the start of the movement, even in cases where the FBR is very delayed. Then, in Experiments 2 and 3, the authors dissect FBR and LR responses into two components: (1) a phasic component that has a peak point mid-movement and then declines, and (2) a tonic component that grows over the movement time course and remains stable during the holding period. The authors provide evidence that LR responses are better predicted from the tonic component of the FBR than the phasic component. The idea that tonic FBR components drive learning over phasic components departs from prior models of error-based learning and provides a new theory to understand sensorimotor adaptation.

Strengths:

(1) The paper is well-written, and the contribution is important and timely. The authors provide clear experiments that change the way we conceptualize how trial-to-trial learning is driven by feedback responses to error.

(2) The paper provides solid evidence to demonstrate that feedback (FBR) and learning (LR) responses are not linked by a fixed delay, in contrast to prior models.

(3) The paper also introduces the concept that both tonic and phasic components of the FBR differentially influence the learning response. The paper provides solid evidence that the tonic forces maintained during holding still have an impact on the learning that proceeds on the next trial. This has implications for models of sensorimotor adaptation and our understanding of the physiology of learning.

Weaknesses:

While some conclusions are strong, I feel that the conclusions regarding FBR and LR relationships need additional analysis. All these concerns are elaborated below. Broadly speaking, there is a concern that some conclusions reached by the authors are linked to the particular phasic/tonic model they use to parse FBR and LR responses. Other models are not considered and could lead to differing results. Furthermore, it is assumed that LRs are scaled FBRs. This assumption excludes the possibility that LRs could be driven by FBRs and other mechanisms, which would alter the way the regression analyses are constructed. As described below, model-free analyses are warranted to corroborate the main findings. Further, the role that phasic-FBR plays in the adaptation process is understated in the Discussion despite evidence to the contrary in Figure 8. Much of the analysis is done on trial-averaged and participant-averaged responses, inflating R2 values. More analysis should be done at the trial level to better examine model performance and accuracy. And while valuable, the authors' experimental approach differs from standard force-field experiments that were initially used to test feedback error learning hypotheses. The paper could benefit from a Limitations section to discuss associated limitations.

Main Concern 1:

The decomposition of FBR and LR into phasic/tonic components is based on a specific model (i.e., Equation (1)). The notion that tonic FBR predicts phasic/tonic LR is based on responses estimated from the model. Thus, it is unclear whether critical findings (e.g., LR responses are predicted by tonic FBR) are true of the "data" or true when the "data are analyzed in the context of their model". In other words, had the authors proposed a different model to decompose the LR/FBR into tonic/phasic components, would they obtain different results?

There are many possible alternatives:

(A) In Equation (1), the phasic and tonic components are assumed to add linearly at all times to obtain the force profile. But the phasic and tonic components could be applied at separate times. The tonic component could be invoked during holding, and the phasic component could be invoked during moving. This type of model will differ from the current version, especially in how the peak force during the moving period is assigned to the phasic/tonic components.

(B) Another possibility is that the tonic and phasic components do indeed operate at the same time (like in Equation (1)), but they are separate, independent controllers. In the author's model, the tonic component is dependent on the phasic component.

(C) Another possibility is that the tonic and phasic components are linked, but not by an integral.

(D) Another possibility is that the phasic component is not a Gaussian function of time.

Concern 1-1:

While it is not possible to explore the entire model space described above, the authors should consider whether other phasic/tonic model classes could lead to qualitatively different results. The authors could also consider other phasic/tonic models if appropriate, and demonstrate that Equation (1) is superior based on an information criterion like AIC or BIC.

Concern 1-2:

I recommend that the authors pursue model-free, empirical analyses to support their findings. This would decrease the reliance on the "correctness" of a particular model. One logical choice would seem to be empirically estimating the phasic component as the peak force during the moving period and the tonic component as the average force during the holding period. In this model-free estimation of phasic and tonic commands, is it still the case that tonic FBR alone predicts LR components?

Concern 1-3:

Building on Concern 1-2, a clear case where the concern about using a model alone to estimate phasic and tonic components is in the across-subject variability analysis in Figure 7. Here, LR and FBR are compared to one another only in the context of the tonic-phasic model in Experiment 1. The result is that only the tonic FBR predicts the tonic LR. But investigating Figures 7b and 7c, it would appear that the peak force applied during the FBR during the moving period (which should reflect the phasic component in large part as in Figure 4a) would predict the peak (or average) force applied during the LR. Thus, the conclusion that tonic FBR only predicts tonic LR may be driven by how the model estimates tonic/phasic FBR/LR rather than a true property of the data. A model-free analysis, as suggested in Concern 1-2, would be helpful in addressing this concern.

Main Concern 2:

Analyses in Figures 4g, 4h, 6c, and 6d are based on relating LR and FBR components with no intercept: y = ax; the LR component is a scaled FBR component. It is unclear if the authors' conclusion would vary had a different model been used. For example, suppose that LR on trial n is partly determined by the FBR and also the sensory error (e) on trial n-1 (where c1 and c2 are constants):<br /> LR(n) = c1 FBR(n-1) + c2 e(n-1)

Another model could suppose that the LR on trial n is due to the FBR on trial n-1, and also a non-specific adaptive component that is independent of both FBR and the sensory error:<br /> LR(n) = c1 FBR(n-1) + c2

Concern 2-1:

For these alternate models, y=ax (i.e., zero intercept) is not an appropriate relationship between LR and FBR components. Had the authors allowed a non-zero intercept in Figs. 4g, 4h, 6c, and 6d, will they still observe that only tonic FBR predicts LR components? In other words, would R2 improve for phasic FBR relationships with a non-zero intercept?

Concern 2-2:

Why was a non-zero intercept allowed for the between-subject analyses in Figure 7, but not for similar analyses in Figures 4 and 6?

Main Concern 3:

The main results in Figures 4g, 4h, 6c, and 6d are based on an R2 value that is calculated on a linear fit to the mean response averaged across participants and trials. This raises the concern that the R2 value is being inflated, and it also misses the rich trial-to-trial variation and subject-to-subject variation that could be used to examine the model's accuracy. A couple of concerns here:

Concern 3-1:

As can be seen from the horizontal and vertical error bars in Figures 4g and 4h, there is considerable variability across participants. While not shown, it is almost certainly the case that there is considerable variability across trials within a participant (as alluded to in the Fig. 8 analyses). The authors should evaluate their model performance and report goodness-of-fit (or error) at the single-trial level. For example, the model could be fit to individual trial data, and the R2 values from the trial fits could be used for comparing the various relationships in Figures 4 and 6. Another idea would be to keep the alpha, beta, T and sigma estimates obtained from the average data, and then apply these parameters to individual trial responses and report the model error. Do phasic FBR commands similarly predict LR components at the trial level, or do trial-level analyses corroborate the current conclusions on tonic FBR superiority?

Concern 3-2:

The authors report on Line 200 that the R2 values of 0.635 and 0.698 have modest predictive power. It would be helpful for the authors to statistically compare the R2 values between Figures 4g and 4h. One idea would be to obtain an R2 value for each individual participant. Then the distribution of R2 values across participants could be compared between the different relationships in Figure 4g/4h (e.g., via a t-test). This would help to better support the idea that Figure 4h shows better model fits than Figure 4g. These analyses could also be conducted for the relevant parts of Figure 6 (Experiment 3). The authors should consider allow a y-intercept in this process as they do in Figure 7.

Main Concern 4:

The authors compare tonic and phasic FBR predictive power in Figure 4. There are other places where the analyses in Figures 4g and 4h should be repeated:

Concern 4-1:

Tonic and phases FBR responses appear to vary in Experiment 1 (Figure 2c), but the authors do not test whether they predict the LR component magnitudes in Figure 2d. Analyses in Figures 4e,4f, 4g, and 4h should be added to the Experiment 1 analysis.

Concern 4-2:

While I understand the rationale behind computing differences in Figure 6 to isolate the second-shift effect on FBR/LR, the authors should still perform the primary investigation in Figures 4e, 4f, 4g, and 4h on the FBR and LR responses in Figures 5b-g (without subtracting the "Maintained" component). In other words, before analyzing the contributions of the second shift in Figure 6, the authors should repeat their analysis in Figure 4 applied to the FBR and LR responses in Figure 5 (without subtracting off the maintained response). How well does Equation (1) and y=ax capture the FBR and LR responses in Figures 5b-g?

Main Concern 5:

Given current practices in human sensorimotor adaptation, the current n=10 (or n=12) group sizes appear limited in size, raising concerns on statistical power.

Concern 5-1:

The authors should consider a power analysis or provide some other justification to support their chosen sample sizes.

Concern 5-2:

It is unclear why cross-correlation analyses in Figure 2e, 3d, and 5h have error bars, but no other FBR or LR time courses have error bars. Error bars should be provided in Figures 2b, 2c, 2d, 3b, 3c, 5b, 5c, 5d, 5e, 5f, 5g, 6a, and 6b.

Concern 5-3:

The subject counts are reported as n=10 for Experiment 1, n=12 for Experiment 2, and n=12 for Experiment 13, but the subject-to-subject analysis in Figure 7 says n=33.

Main Concern 6:

I agree that the author's model suggests that LR responses are most strongly predicted by the tonic FBR component. But I feel the narrative and Discussion surrounding this point are too strong. They paint the picture that only tonic FBR is important in learning. To do this, the role that phasic FBR plays is discounted, and mixed results concerning tonic FBR are overlooked. I feel that the Discussion should be broadened to acknowledge that the authors find evidence that both tonic and phasic FBR appear to influence the learning response, with tonic FBR making the stronger contribution in this task. Here are key areas that require attention:

Concern 6-1:

Importantly, the authors downplay their result in Fig. 8h, that the phasic FBR predicts phasic LR in their Results on Line 350. This argues against the idea that only tonic FBR influence LR parameters. On Line 485, the authors state that "trial-by-trial variability in LR amplitude was explained by the tonic component of the FBR, but not by the phasic component (Fig. 8)." This is not correct. Both the tonic and phasic components of the FBR altered LR components in Figure 8.

Concern 6-2:

Again, it is stated on Line 502, that the phasic FBR component "had only a modest effect on the LR". This again seems to underplay the result. The authors should amend their Results and Discussion to better acknowledge that their data support a role for both tonic and phasic FBR contributions to LR, but the tonic component appears to make a larger contribution in their model.

Concern 6-3:

While the role of phasic FBR in determining LR amplitude appears to be understated, the role of tonic FBR is, on occasion, overstated. The Discussion should mention that there is mixed evidence for the role of tonic FBR in LR parameters. For example, in their between-subjects analysis in Figure 7f, the authors do not find that phasic LR can be predicted by tonic FBR. Thus, across subjects, no component of the FBR appears to predict phasic LR.

Concern 6-4:

To better investigate the role that both phasic FBR and tonic FBR may play in adaptation, it would be advisable for the authors to consider this hypothesis. As it stands, tonic LR or phasic LR is regressed only onto tonic FBR or phasic FBR individually. In Figures 1 (Experiment 1), 3 (Experiment 2), and 5 (Experiment 3), the authors could regress tonic LR and phasic LR onto both phasic FBR and tonic FBR simultaneously. Models where LR = c1 phasic-FBR + c2 tonic-FBR could be considered and compared against univariate models, LR = c phasic-FBR and LR = c tonic-FBR using AIC or BIC to determine whether a mixed model that predicts LR with both phasic and tonic FBR is warranted.

Irrespective of the result, the authors should be careful (Concerns 6-1 and 6-2) to state that when levels of tonic-FBR were controlled in Figure 8 (which is likely the cleanest way to look at the role phasic FBR plays in learning), phasic-FBR showed a clear influence on LR.

Major Concern 7:

On Line 577, it states the "hand was automatically returned to the starting position". Does this mean that the robot moved the hand back to the start location? If so, was the hand ever released from a force channel in between the perturbation trial and the following channel trial? A concern is that the holding forces from the perturbation trial could "bleed over" into the forces applied during the subsequent channel trial if the subject always remains in a channel trial in between the trials. Suppose we label the 3-trial structure as Channel 1 (C1) - Perturbation (P) - Channel 2 (C2). The authors should confirm that the holding forces on P are not correlated with baseline force (i.e., the channel force prior to movement onset) in C2. I do not expect there to be a strong correlation given that the learning responses in Figs. 2d, 3c, and 5e-g appear near-zero at t=-400ms, but this should still be verified.

Major Concern 8:

In Supplementary Figure 1, there appears to be an error in the "Amplitude of phasic LR (N)". In Supplementary Figure 1f, the phasic LR magnitudes appear in line with Supplementary Figure 1d, but there is a mismatch in the magnitudes for the phasic LR in Supplementary Figures 1e & 1d (the phasic LR magnitudes appear to be too low in Supplementary Figure 1e, peaking at around 0.1N when they should peak at around 0.15N).

Major Concern 9:

The authors should provide a Limitations section, highlighting unanswered concerns listed above, mixed results, and differences from prior work. These are touched upon in the Discussion section (particularly in Perspectives for future studies) but should be expanded further. At a minimum, the authors should consider including a discussion of the following points:

Differences from prior work:

9-1: There are methodological differences between this work and past studies highlighted by the authors. It could be that there are multiple error-based learning mechanisms that drive the FBR. Here, the authors find that visually-driven FBR responses do not drive LRs at a "common temporal shift". Instead, LRs are broadly expressed at the start of the movement (regardless of when the FBR was timed). However, tasks that have other components (e.g., a proprioceptive error) might invoke different learning mechanisms. For example, proprioceptive-driven FBRs might invoke LRs that have different temporal properties than visually-driven FRBs.

9-2: As noted by the authors, Reference [10] studied FBR-driven learning in muscle commands, as opposed to forces. Muscle responses may have differing temporal and/or magnitude (for phasic/tonic) components that qualitatively differ from the force-based conclusions made here. Thus, the learning mechanisms at the muscle level may differ from those observed at the force level.

9-3: While the tonic FBR is a strong predictor of the learning response in this experiment, most of the experimental conditions are done where the cursor remains deviated from the target throughout the trajectory and into the holding period. This differs from past work on feedback error learning, where feedback was veridical, and the cursor (and hand) ended on the target. This persistent displacement from the target during the prolonged holding period may influence the learning process and could enhance the tonic-FBR contribution to learning.

9-4: The authors state in the present study that subjects were told not to use "explicit strategies" and move as straight as possible to the target. For past work, participants were able to use explicit strategies during feedback and learning responses. It could be that the lack of (or reduction in) explicit responses alters single-trial learning mechanisms relative to past work.

Alternate models:

9-5: No alternate models are considered here for the tonic-phasic relationship. Other models could relate these two processes differently, which could lead to different conclusions.

9-6: It is assumed that both the tonic and phasic controllers are active at the same moment in time and sum linearly to generate the overall force output. Other models could have applied each "controller" to different phases of the reach in a differential manner (e.g., two separate controllers, a moving controller and a holding controller operating at different moments in time).

9-7: It is assumed here that the LR should be a scaled FBR: y = ax. Conclusions made here could change if the LR is due to multiple processes, FBR-driven learning only being one of them. Other models where the LR is driven by both FBR and the sensory error were not considered here.

Mixed results:

9-8: While tonic FBR was a good predictor of phasic LR at the group-level (e.g., 4g), it did not predict phasic LR between subjects (Fig. 7f) and in fact tended toward a negative relationship.

9-9: Phasic FBR predicts Phasic LR at the trial-level (Figure 8h) but not as well at the subject-level (Figure 7d).

9-10: Overall, with the exception of Figure 8, most analyses look at the relationship between LR and tonic FBR or phasic FBR separately. In Figures 4c, 4d, 6c, 6d, and 7d-g, the authors look at the marginal effect of tonic or phasic FBR on learning, but do not control for variations in the other FBR component (e.g., they look at phasic FBR on tonic LR, but do not control for tonic FR). The only analysis that controls for the other component is in Figure 8, suggesting that both tonic and phasic FBR contribute to LR.

Minor concerns

(10) I'm not sure I follow the cross-correlation analysis in Figure 3. Overall, to me, both the FBR in Figure 3b and the LR in Figure 3c look quite similar in their temporal profiles, irrespective of the shift magnitude. The authors state on Line 158 that their cross-correlation analysis "...revealed that the overall shape of the cross-correlation function changed systematically with error magnitude". However, to me, in Figure 3d, the shape of the many curves looks similar.

What is confusing to me here is including a phasic movement period and a tonic holding period inside the cross-correlation. The tonic "static" component during the holding period will likely greatly influence how well the cross-correlation is able to match the phasic peaks during the LR/FBR moving periods. In other words, the reach consists of a "movement" and a "holding" period. But the cross-correlation is blending the two together, and thus, I am not sure how reliable this measure will be for truly estimating the temporal shift between conditions. For example, if you look at the shaded gray area in Figure 3b, the "Movement period" looks almost identical in temporal properties. The "peaks" and "troughs" happen at nearly the same moment in time across all conditions. The onset of the FBR at approximately 200 ms is also identical across shift magnitudes. Thus, to me, the temporal properties of the FBR seem very similar during the moving period (where the FBR is responding to the error). But including the holding force (the tonic force after the 600ms period) seems to be causing the cross-correlation function to estimate differences at very high lags. If these differences are being driven solely by the holding forces, I am not sure this is meaningful.

It seems that the authors might want to repeat this analysis, excluding the holding force period from the calculation of the cross-correlation coefficients.

(11) It would appear that the authors have a significant main effect of their ANOVA (p=0.028) in Fig. 3f, but no post-hoc tests are reported to indicate which group means differ.

(12) When plotting FBR, a [0,600]ms period is shaded as the movement period. On Line 580, it says that feedback was provided on peak movement speed. Was any feedback provided as to the movement duration? If not, did participants complete the movement within the 600 ms window labeled as movement speed? Were movements during perturbation trials longer than non-perturbed trials?

(13) Over what time period is Equation (1) fit to the data? Is it the [-200,700]ms window shown in Figure 4a? A concern is that including too much of the "holding period" in the model fit will cause the model to be biased toward fitting the holding period well and not the moving period. This, in turn, might lead to better estimates for the beta parameter than the alpha parameter. In addition to clarifying the fitting process, the authors should also include R2 values for the moving and holding periods separately.

(14) The procedure is clear from Figure 1e, but it would be helpful on Line 91 to explain that "collapsing" FBR and LR across rightward and leftward means that the FBR and LR were negated for one of the directions (prior to collapsing).

(15) Are the "Amplitude of tonic LR (N)" supposed to be negative in Figures 6c and 6d?

(16) Overall, the parameter distributions in Figures 4e and 4f are similar to those in Supplementary Figures 1c and 1d. The FBR amplitudes look nearly identical. Only the Phasic LR amplitudes in Supplementary Figure 1d appear to be larger than the Phasic LR amplitudes in Figure 4f. Can the authors provide an intuition for why the phasic LR contributions increase when T and sigma parameters are allowed to vary between participants?

(17) There are two points where the authors should consider softening their language:

17-1: The authors state at multiple points (e.g., Line 154) that "...the waveforms of LRs remained largely similar across conditions, while their amplitudes showed only modest modulation with cursor shift magnitude". However, in Figure 3c, the LR amplitude for the 0.4 cm shift is approximately 0.2 N, and the LR amplitude for the 3 cm shift is approximately 0.3 N - a 50% increase. The authors should consider softening the language here to appreciate the variations in LR amplitude.

17-2: On Line 258, it is stated that the FBR during holding "diverged only slightly" for the 16 cm condition in Fig. 5b. This seems too strong a statement. The "Maintained" FBR holding force is about 0.2 N, and the reverse is about 0.1 N. Thus, the "Maintained" condition is doubled. While I agree that the LR diverges more than the FBR (i.e., 5b vs. 5e), I think the language choice here should be more careful.

Reviewer #2 (Public review):

Summary:

The authors find a strong trial-level relationship between tonic feedback responses and tonic learned responses.

Strengths:

The authors have performed several well-conducted experiments and thoughtful analyses to test the relationship between feedback responses and subsequent learned responses. The strength of the paper is the experimental control to probe this relationship and, eventually, oppugn the feedback error learning hypothesis.

Weaknesses:

In general, the processes studied in this manuscript and the past work have not explained the underlying mechanisms for the observed phenomena. Without knowing the mechanisms, the results are largely observational/correlational when linking feedback responses to learned responses, and there are no strong alternative hypotheses to explain the results. Most of the larger comments below stem from this theme, including:<br /> (i) what causes the phasic and tonic portions of the feedback response,<br /> (ii) justifying the phasic learned response,<br /> (iii) what are some alternative hypotheses that can explain the current results and past literature?

Suggestions to improve the paper are below.

(1) As mentioned above, it appears that there is limited mechanistic understanding of the underlying processes. For the feedback response, there is clearly a phasic and tonic component. It is not until one gets to the discussion that a potential mechanism is proposed, where presumably the phasic response may be velocity dependent, and the tonic response may be position dependent. On a somewhat related tangent, these responses somewhat mirror muscle spindles, which are known to have velocity and position-dependent responses, leading to the phasic and tonic firing during muscle stretch experiments.<br /> a) Can the authors provide more discussion on the work that they currently cite, which studied position and velocity dependent responses?<br /> b) Relatedly, did the authors put any thought into developing a model, using error inputs from the experimental trials, that can capture the feedback responses? For example, dF/dt * tau = a*pe + b*ve - cF + e, where F = force response, tau is a time constant to generate the force, a is a gain on position error (pe), b is a gain on velocity error (ve), c relates to the leak, and e is Gaussian noise. The leak would be needed to explain the equilibrium / steady state at the end of the trial. It could be very insightful if this, or some other similar flavour of model, could explain the phasic and tonic components of the feedback response. The advantage of a model in this form is that there are experimental inputs and the process evolves over time, rather than fitting static curves to the data.

(2) Aligned with past literature, the authors have characterized the early and late phases of both the feedback responses and learned responses as phasic and tonic. It is clear from the data that the feedback response data are composed of a phasic and tonic phase. However, it is less clear from the data in many of the figures that there is an actual phasic response in the learned response. Further, from a modelling perspective, it is conceivable that the fitting algorithm would partition the variance between the two components of equation 1, even though there may only be one true underlying process. This may also explain why there was no correlation between tonic feedback responses and phasic learned responses in Figure 7F.<br /> a) Can the authors provide more rationale on why the learned response would also have a phasic response? Is the assumption here that since the feedback response had a phasic response, the learned response should as well?<br /> b) Can the authors fit the learned response with only the tonic portion of the equation? Then, perform model comparison between the phasic+tonic learned response model and the tonic only learned response model using AIC/BIC, to justify whether or not a phasic portion of the model is needed to explain the data.<br /> c) Can the authors comment on the possibility that the learned response may just rise and then decay over time, without being the outcome of two distinct processes?

(3) The nicely controlled experiments do well to provide evidence against the feedback error learning hypothesis, which alone is a valuable contribution to the literature. However, the authors do not provide a strong alternative hypothesis. There is a proposal of alternative hypotheses. For example, on lines 494-498, referring to state estimation, which the authors then state could not explain all the results in the preceding paragraph. It would be beneficial to further bolster the possible explanations. Perhaps further discussion details on what the mechanisms are for the feedback responses (e.g., position or velocity dependence), and what states (position error, velocity error, motor commands, etc.) transfer into the learned response. Are they stored? Are they the outcome of a continuous process? This may be difficult given the current state of understanding in the literature, but it could substantially improve the paper.

Reviewer #3 (Public review):

I believe that the paper is excellent and very well executed. I have several reservations about the meaning of the tonic component of the feedback responses and about the more general interpretation from a computational standpoint. These aspects may not require extensive adjustments, but some key points could be discussed or better justified:

(1) It is true that most papers view adaptation as a trial-by-trial update and that several models summarise motor errors by a scalar quantity for a model fit. The importance of feedback control in visuomotor control has also been overlooked, as several studies explicitly instructed not to correct. I also agree about the fact that the temporal aspects of sensory encoding and control are often neglected in motor adaptation studies. However, there have been some developments about adaptive control in the context of force field learning to express the error signal and learning rule based on continuously evolving state variables as those formulated in online control models (Crevecoeur et al., 2020, eNeuro 7(1); Kalidindi and Crevecoeur, 2023, Curr Opin Neurobiol, 83, 102810). Could the authors consider discussing whether this framework could or not be consistent with the current dataset?

(2) The choice of a cursor jump may require more in-depth justification. From an experimental standpoint, it is clear from the authors' data that a cursor jump does evoke an aftereffect and hence the developments are clearly validated empirically. The nature of the adaptive response is less clear: indeed, cursor jumps can be represented as an external perturbation to a variable that may be independent of the hand (e.g. Kasuga et al., 2022, J Neurophysiol, 127 (2), 354-372). In contrast, a visuomotor rotation requires a change in state space representation parameters (it is not clear which ones) that is more closely related to the update of an internal model. Could the authors explain why they believe that a learning response to a cursor jump is consistent with adaptation in general?

(3) The relationship between the tonic component of the feedback response and the learning response is very clear from an experimental perspective again. However, I would suggest being very cautious about the interpretation of this effect. My concern is that it is not clear that this tonic response is irrelevant from a behavioural standpoint, and I am left wondering what the correlation with the learning response truly means. Indeed, in real-life conditions, there should be no net force produced in the end during a static phase, as the force during stabilisation is by definition zero; only the net force produced against constant external loads is required. There can be co-contraction but not net resultant force, unless external forces are applied. So if the tonic response vanishes in real conditions, should there be no learning response? This aspect is also relevant if one attempts to generalise the findings to force field learning: since velocity-dependent force fields vanish during stabilisation, how can there be a tonic component?

Reviewer #1 (Public review):

[Editors' note: this version has been assessed by the Reviewing Editor without further input from the original reviewers. The authors have addressed the major comments raised in the previous round of reviews, yet some inherent issues necessarily remain unresolved.]

The manuscript shows that different traits of adults and larvae correlate with Red List status. The authors argue that this shows a big gap in the conservation of amphibians and that the traits of all life stages should be taken into account in amphibian conservation. Specifically, amphibian conservation should do more for the habitats where the larvae live.

The manuscript is well written and easy to understand. The methods are sound.

Reviewer #2 (Public review):

Summary:

In this study, the authors tried to examine whether there are differences in the association between functional traits and extinction risk in adult and tadpole stages in Chinese anurans.

Strengths:

Overall, I think the basic idea of the study is interesting and important. It can be applied to other taxa with complex life cycles throughout the animal kingdom.

Original weaknesses:

I do not think the authors achieve their aims, as the results only partially support their conclusions. The study has several drawbacks that need to be clarified or revised, including the unclear threat categories for tadpoles, model selection and model averaging, the potential problem of AIC, and the omission of other important species traits.

Reviewer #1 (Public review):

Summary:

The authors have leveraged publicly available single-cell RNA sequencing datasets from isolated islets downloaded from the PANC-DB resource to study the transcriptional profile of insulin-producing beta and glucagon-producing alpha cells from pancreas donors with, or at-risk (islet autoantibody positive) of Type 1 diabetes and donors without diabetes. Their rationale is that any remaining beta cells in these donors with T1D have resisted the autoimmune attack and can therefore provide insights into the transcriptional pathways that mediate this protection. They have developed robust bioinformatic pipelines to address this hypothesis. Their analyses identify beta (and alpha) cells clustered by their differential transcriptional profiles and gene regulatory networks (GRNs), which are present in varying proportions in individuals with and without T1D. The Differentially expressed genes (DEGs) identified align with previously reported datasets. The use of the SCENIC tool, a pipeline for GRN inference using transcriptomic data, involves scoring transcription factor (TF) activity with a rank-based approach, which is considered robust to technical artefacts and adds a novel perspective to this study. Through GRN analysis and regulon score generation, the authors identify a specific cluster of beta cells, cluster 3 (C3), that is enriched in individuals with T1D. This cluster was also slightly enriched in individuals without diabetes (ND) who were > 35 years of age. Their data aligns, supports and extends upon many earlier studies identifying key protective genes, e.g. CD274 (PD-L1) and HLA-E. Together, this provides insights into the transcriptional profile of beta cells that have resisted immune-mediated destruction, which could help with the design of stem cell-derived islet therapies and guide targeted immunotherapy drug trials in the future.

Strengths:

This largely agrees with and extends previous studies from a range of groups using different tissue repositories. This strengthens the validity of the conclusions. The identification of key GRNs associated with preserved beta cells could also aid in the future design of cell and immunomodulatory-based therapies.

Weaknesses:

The regulon scores are hypothesis-generating, not proof of the mechanism by which beta cells are protected. The observation that C3 is enriched in ND >35y could indicate that it is a regulon associated with beta-cell senescence, for example. In the context of T1D, this regulon could reflect beta-cell senescence or stress, which incidentally co-occurs with survival and, as such, is not necessarily a true reflection of survival characteristics. The authors could perhaps expand upon this possibility in a revision.

The authors have leveraged valuable datasets to generate a detailed profile of residual beta cells in Type 1 diabetes and have successfully achieved their study aims. The findings are largely consistent with and extend the existing literature, highlighting key regulatory networks, some of which are supported at both the RNA and protein level (e.g., IRF1). However, a key interpretative consideration is that GRN-derived regulon activity does not distinguish between causal and reflective biological states. In particular, it remains unclear whether these networks represent mechanisms of immune protection or instead reflect underlying beta-cell states such as stress adaptation or senescence. Clarifying this distinction will be important for understanding the functional significance of these regulatory programs and their potential therapeutic relevance.

Reviewer #2 (Public review):

Summary:

This work identifies a novel beta cell population primarily present in the islets from individuals with Type 1 Diabetes (T1D). This population is defined by increased expression of previously described transcription factors, including IRF1, BCL6, JUNB, and CEBPD. The authors postulate that the activation of these genes in beta cells during immune infiltration could be protective against beta cell destruction. This hypothesis aligns with experiments in NOD mice identifying a protected beta cell population. Overall, this work provides a hypothesis for how some beta cell populations survive immune infiltration in T1D.

Strengths:

This work uses a clever analysis approach, defining regulons using SCENIC and using these to recluster the data. This approach identified a novel beta cell population enriched in islets from individuals with Type 1 Diabetes that was very stable to different clustering resolutions. The authors also took many potentially confounding technical factors into account, removing ambient RNA and doublets, and often controlling for batch effects using pseudobulk approaches.

In addition to identifying a novel cluster in one published single-cell dataset, the authors also downloaded additional single-cell datasets that included cytokine treatment of human beta cells to validate the presence of this population in other datasets. In these datasets, the authors were able to identify a similar population of cells, labeled by similar transcription factors.

Weaknesses:

While the authors use a sophisticated approach to identify a novel beta cell subpopulation, more analysis needs to be done to ensure this cluster is biologically meaningful. First, the authors did not take the duration of diabetes into account in this analysis. The duration of diabetes is important because there are different levels of immune infiltration at different stages of diabetes. It would also be important to consider age at diagnosis, as the progression of disease is very different in early vs late onset populations.

Additionally, more exploration of potential confounding factors should be done when looking at the novel population vs other populations in the dataset. This would be further strengthened by adding analysis from datasets that more directly measure transcription factor activity, like single-nucleus ATAC-seq from the different disease states.

Finally, these data can't distinguish the response to the environment (i.e., cytokines) and protective programs. Especially given the similar program in alpha cells, the response to the environment seems likely. More analysis should be done, looking for a similar signature in other populations in the data.

Reviewer #3 (Public review):

Summary:

The authors used a gene regulatory network inference-based clustering approach with existing scRNAseq data sets from cadaveric donors with T1D, auto-antibody positive, and non-diabetic donors and found a regulatory network associated with b-cell survival that is associated with increased expression of genes controlled by interferon regulatory factor 1.

Strengths:

Using established data sets of RNAseq previously performed, the authors identify an interesting population of surviving b-cells in T1D that express a key antiviral transcription factor (IRF1), antiviral genes such as GBPs and iFIT, and decreased expression of a limited number of genes that have been associated with the identity of b-cells.

Selective expression in T1D and not observed in islets from control or auto-antibody positive donors.

Expression changes, TFs identified are also identified in human islets treated with cytokines.

The lack of changes in genes associated with ER stress or the response of endocrine cells to ER stress.

Weaknesses:

The authors do an excellent job of identifying characteristics of the donors/islets in the methods; however, this needs to be addressed in the Figure Legends and Results. Specifically, the length of exposure to cytokines is critical in evaluating the comparisons made in this study.

Is it possible to evaluate sex as a variable in this analysis, and if yes, does one still observe similar changes in identity gene expression and IRF1-dependent gene expression?

Length of disease and evidence for the C3 populations? Does one observe the C3 population in alpha cells of islets with long-standing disease or in the samples that had too few b-cells to perform the analysis? Temporally, 24 h was used for ATACseq and 48 h for cytokine treatment. These are very late exposures, suggesting that secondary and tertiary effects are being compared.

Activation of stress response genes has been correlated with impaired cytokine signaling in islets (human and rodents), limiting the number of endocrine cells that are cytokine responsive. Was this observed in the authors' analysis?

Recent studies have identified induction of antiviral and antibacterial genes in islets in response to short exposures to IL-1, TNF, IFN's that are consistent with the C3 expression profile observed by the authors. While this work has mostly been performed in rodent islets, it has also been observed in human islets, and may be useful in comparing additional transcripts that may contribute to the observed profiles.

Reviewer #2 (Public review):

I have completed a thorough review of this paper, which seeks to use the large datasets of species occurrences available through GBIF to estimate variation in how large numbers of plant and animal species are associated with urbanization throughout the world, describing what they call the "species urbanness distribution" or SUD. They explore how these SUDs differ between regions and different taxonomic levels. They then calculate a measure of urban tolerance and seek to explore whether organism size predicts variation in tolerance among species and across regions.

The study is impressive in many respects. Over the course of several papers, Callaghan and coauthors have been leaders in using "big [biodiversity] data" to create metrics of how species' occurrence data are associated with urban environments, and in describing variation in urban tolerance among taxa and regions. This work has been creative, novel, and it has pushed the boundaries of understanding how urbanization affects a wide diversity of taxa. The current paper takes this to a new level by performing analyses on over 94000 observations from >30,000 species of plants and animals, across more than 370 plant and animal taxonomic families. All of these analyses were focused on answering two main questions:<br /> (1) What is the shape of species' urban tolerance distributions within regional communities?<br /> (2) Does body size consistently correlate with species' urban tolerance across taxonomic groups and biogeographic contexts?

Overall, I think the questions are interesting and important, the size and scope of the data and analyses are impressive, and this paper has a potentially large contribution to make in pushing forward urban macroecology specifically and urban ecology and evolution more generally.

Despite my enthusiasm for this paper and its potential impact, there are aspects that could be improved, and I believe the paper requires major revision.

Some of these revisions ideally involve being clearer about the methodology or arguments being made. In other cases, I think their metrics of urban tolerance are flawed and need to be rethought and recalculated, and some of the conclusions are inaccurate. I hope the authors will address these comments carefully and thoroughly. I recognize that there is no obligation for authors to make revisions. However, revising the paper along the lines of the comments made below would increase the impact of the paper and its clarity to a broad readership.

Major Comments:

(1) Subrealms

Where does the concept of "subrealms" come from? No citation is given, and it could be said that this sounds like an idea straight out of Middle Earth. How do subrealms relate to known bioclimatic designations like Koppen Climate classifications, which would arguably be more appropriate? Or are subrealms more socio-ecologically oriented? From what I can tell, each subrealm lumps together climatically diverse areas. It might be better and more tractable to break things in terms of continents, as the rationale for subrealms is unclear, and it makes the analyses and results more confusing. The authors rationalized the use of subrealms to account for potential intraspecific differences in species' response to urbanization, but that is never a core part of the questions or interpretation in the paper, and averaging across subrealms also accounts for intraspecific variation. Another issue with using the subrealm approach is that the authors only included a species if it had 100 observations in a given subrealm, leading to a focus on only the most common species, which may be biased in their SUD distribution. How many more species would be included if they did their analysis at the continental or global scale, and would this change the shape of SUDs?

(2) Methods - urban score

The authors describe their "urban score" as being calculated as "the mean of the distribution of VIIRS values as a relative species-specific measure of a response to urban land cover."

I don't understand how this is a "relative species-specific measure". What is it relative to? Figures S4 and S5 show the mean distribution of VIIRS for various taxa, and this mean looks to be an absolute measure. Mean VIIRS for a given species would be fine and appropriate as an "urban score", but the authors then state in the next sentence: "this urban score represents the relative ranking of that species to other species in response to urban land cover".

That doesn't follow from the description of how this is calculated. Something is missing here. Please clarify and add an explicit equation for how the urban score is calculated because the text is unclear and confusing.

(3) Methods - urban tolerance

How the authors are defining and calculating tolerance is unclear, confusing, and flawed in my opinion.

Tolerance is a common concept in ecology, evolution, and physiology, typically defined as the ability for an organism to maintain some measure of performance (e.g., fitness, growth, physiological homeostasis) in the presence versus absence of some stressor. As one example, in the herbivory literature, tolerance is often measured as the absolute or relative difference in fitness of plants that are damaged versus undamaged (e.g., https://academic.oup.com/evolut/article/62/9/2429/6853425?login=true).

On line 309, after describing the calculation of urban scores across subrealms, they write: "Therefore, a species could be represented across multiple subrealms with differing measures of urban tolerance (Fig. S4). Importantly, this continuous metric of urban tolerance is a relative measure of a species' preference, or affinity, to urban areas: it should be interpreted only within each subrealm".

This is problematic on several fronts. First, the authors never define what they mean by the term "tolerance". Second, they refer to urban tolerance throughout the paper, but don't describe the calculation until lines 315-319, where they write (text in [ ] is from the reviewer):

"Within each subrealm, we further accounted for the potential of different levels of urbanization by scaling each species' urban score by subtracting the mean VIIRS of all observations in the subrealm (this value is hereafter referred to as urban tolerance). This 'urban tolerance' (Fig. S5) value can be negative - when species under-occupy urban areas [relative to the average across all species] suggesting they actively avoid them-or positive-when species over-occupy urban areas [relative to the average across all species] suggesting they prefer them (i.e., ranging from urban avoiders to urban exploiters, respectively).<br /> They are taking a relativized urban score and then subtracting the mean VIIRS of all observations across species in a subrealm. How exactly one interprets the magnitude isn't clear and they admit this metric is "not interpretative across subrealms".

This is not a true measure of tolerance, at least not in the conventional sense of how tolerance is typically defined. The problem is that a species distribution isn't being compared to some metric of urbanness, but instead it is relative to other species' urban scores, where species may, on average, be highly urban or highly nonurban in their distribution, and this may vary from subrealm to subrealm. A measure of urban tolerance should be independent of how other species are responding, and should be interpretable across subrealms, continents, and the globe.

I propose the authors use one of two metrics of urban tolerance:

(i) Absolute Urban Tolerance = Mean VIIRS of species_i - Mean VIIRS of city centers<br /> Here, the mean VIIRS of city centers could be taken from the center of multiple cities throughout a subrealm, across a continent, or across the world. Here, the units are in the original VIIRS units where 0 would correspond to species being centered on the most extreme urban habitats, and the most extreme negative values would correspond to species that occupy the most non-urban habitats (i.e., no artificial light at night). In essence, this measure of tolerance would quantify how far a species' distribution is shifted relative to the most highly urbanized habitat available.

(ii) % Urban Tolerance = (Mean VIIRS of species_i - Mean VIIRS of city centers)/MeanVIIRS of city centers * 100%<br /> This metric provides a % change in species mean VIIRS distribution relative to the most urban habitats. This value could theoretically be negative or positive, but will typically be negative, with -100% being completely non-urban, and 0% being completely urban tolerant.

Both of these metrics can be compared across the world, as it would provide either absolute (equation 1) or relative (equation 2) metrics of urban tolerance that are comparable and easily interpretable in any region.

In summary, the definition of tolerance should be clear, the metric should be a true measure of tolerance that is comparable across regions, and an equation should be given.

(4) Figure 1: The figure does not stand alone. For example, what is the hypothesis for thermophily or the temperature-size rule? The authors should expand the legend slightly to make the hypotheses being illustrated clearer.

(5) SUDs: I don't agree with the conclusion given on line 83 ("pattern was consistent across subrealms and several taxonomic levels") or in the legend of Figure 2 ("there were consistent patterns for kingdoms, classes, and orders, as shown by generally similar density histograms shapes for each of these").

The shapes of the curves are quite different, especially for the two Kingdoms and the different classes. I agree they are relatively consistent for the different taxonomic Orders of insects.

Comments on revised version:

I believe their response is thorough and thoughtful. I still disagree with them on some fundamental points of their methodology. However, I would prefer to let my review and their response stand as is. This will allow engaged readers to see both sides of the arguments and judge for themselves whether they believe the revisions are sufficient and if my concerns are valid.

Reviewer #1 (Public review):

Summary:

This study demonstrates, through a series of EEG and MEG experiments, that the human brain automatically categorizes words from alphabetic and non-alphabetic languages, and it unpacks the neural mechanisms of this process from multiple angles. The work examines not only univariate repetition-suppression (RS) effects, but also how repeating or alternating languages influences the representational similarity of words within and across language categories.

Strengths:

The univariate RS effects across multiple experiments lend support to some of the main conclusions.

Comments on revised version.

The authors have made appropriate revisions and supplements in response to the issues I raised, which has largely resolved my concerns.

Reviewer #2 (Public review):

Summary:

This study investigates how the human brain categorizes visual words from distinct writing systems (alphabetic vs. non-alphabetic). Using a repetition suppression paradigm combined with electroencephalography and magnetoencephalography, the authors conducted nine experiments with independent participants to identify the neural network underlying language-based categorization, characterize its temporal dynamics, and test whether this process operates independently of linguistic properties such as semantic meaning and pronunciation.

Strengths:

The study employs a well-validated design with clear control conditions and systematically manipulates key variables including writing system, language familiarity, and native language background. The use of nine experiments with independent participant samples strengthens the reliability and replicability of the results. The work combines EEG and MEG, cross-validating findings across imaging modalities to support the reported neural effects. A combination of univariate, multivariate, and connectivity analyses is used to characterize neural responses and network interactions. Results are consistent across multiple language groups and for both familiar and unfamiliar languages, supporting the generalizability of the identified neural mechanism beyond specific languages or prior experience.

Comments on revised version.

Earlier versions of the manuscript framed these findings as more directly reflecting the social-categorization function of language. In the revised manuscript, the authors now more carefully distinguish language-based word categorization from broader claims regarding social categorization and explicitly acknowledge that the current experiments do not directly test social evaluation or intergroup processes. These revisions improve the conceptual precision of the work and address my major concern from the previous review.

The additional methodological clarifications and supplementary analyses also strengthen the manuscript. Overall, I believe the revised version provides solid evidence for rapid language-based categorization of visual words across different writing systems.

Reviewer #1 (Public review):

Summary

This manuscript addresses an important question in auditory neuroscience and neuroprosthetics: whether cortical responses to cochlear implant stimulation resemble those evoked by natural acoustic stimulation, or whether electrical stimulation engages a distinct cortical representation. The authors use high-density intracranial EEG recordings in rats to compare responses to pure tones in normal-hearing animals with responses to single-channel cochlear implant stimulation in deafened animals. They combine analyses of event-related potentials, high-gamma activity, trial-by-trial variability, PCA/TCA-based dimensionality reduction, and decoder-based measures of stimulus information.

Strengths

A major strength of the study is the question it addresses. Understanding how electrical cochlear stimulation is represented centrally is highly relevant for cochlear implant design, fitting strategies, and rehabilitation. The comparison between acoustic and electrical stimulation, including within-animal comparisons in a subset of cases, is valuable because it directly addresses whether implant-evoked activity can be interpreted within the framework of normal acoustic tonotopy.

The methodological approach is also a strength. Dense cortical surface recordings provide simultaneous access to spatial and temporal features of auditory cortical responses. The combination of PCA, TCA, and decoder analyses gives complementary views of the data, and the information-transfer analysis provides an interesting way to ask whether representations learned from acoustic stimulation generalize to electrical stimulation.

Weaknesses:

The main weakness is that the evidence for spatial organization remains difficult to interpret. In Figure 2, the authors argue that both tone-evoked and cochlear implant-evoked responses are spatially organized, but the slope analyses are not significant for the cochlear implant condition. The revised vector-strength analysis supports the presence of non-random spatial structure, but this is not the same as demonstrating a clear graded cochleotopic organization. The manuscript would be strongest if it consistently distinguished between non-random spatial structure, coarse topography, and true graded tonotopy or cochleotopy.

A related issue is that some figure titles and interpretive statements still appear stronger than the data justify. For example, the TCA results in Figure 7 are described as revealing topographically organized latent spatial factors, but the statistical support appears strongest for normal-hearing high-gamma responses, with weaker or non-significant results in other conditions. These data remain interesting, but they would be better framed as evidence for weak or coarse spatial structure rather than robust topographic organization across all modalities.

The decoder analyses are improved, especially with the added tone-to-tone control. This control supports the conclusion that poor acoustic-to-CI transfer is not simply a failure of the TCA/LDA pipeline. However, the analysis remains model-dependent, and the absolute information transfer values are low. It would be helpful either to include an analogous analysis using raw ERP/high-gamma features or to explain more explicitly why the TCA-based approach is the appropriate primary test. The data support poor generalization between acoustic and implant-evoked cortical responses, but claims about perceptual qualities should remain speculative because perception is not directly measured in these experiments.

Finally, although methodological reporting is much improved, some verification remains indirect. The authors provide useful implantation criteria and cite prior validation of their deafening approach, but the manuscript would be clearer if it explicitly distinguished between validation performed in the present animals and validation based on previous cohorts. This distinction is important because surgical variability, implantation efficacy, and deafening completeness can influence the interpretation of cochlear implant experiments.

Comments on revised version.

The revised manuscript is considerably improved. The authors have clarified several methodological details, added a statistical framework that better accommodates both paired and unpaired animals, provided a clearer account of animal cohorts, added peripheral ECAP/forward-masking data to support the cochlear specificity of implant stimulation, and included a useful positive control for the cross-modal decoder analysis. These additions make the manuscript stronger and help readers interpret the main findings more confidently.

The results support the conclusion that acoustic and cochlear implant stimulation evoke cortical responses with different properties. In particular, acoustic responses support better single-trial stimulus decoding than cochlear implant responses, and decoders trained on acoustic responses transfer poorly to implant-evoked responses. The evidence for spatial organization is more nuanced. The cochlear implant condition shows evidence of non-random spatial structure, but not a clear graded cochleotopic map. The normal-hearing condition is also less visually clear than might be expected from prior tonotopy studies, although the added analyses and comparisons to previous work help contextualize this result. Overall, the study makes a valuable contribution, provided that the claims about spatial organization and perceptual interpretation remain appropriately cautious.

The revision addresses several important concerns from the original version. The use of mixed-effects models better matches the partially paired experimental design. The expanded Methods improve reproducibility. The new cohort schematic helps clarify which animals contributed to behavioral and neural datasets. The ECAP forward-masking measurements add useful peripheral validation, and the within-modality decoder control strengthens the interpretation of the poor cross-modal transfer result. Together, these changes substantially improve the manuscript.

The work is likely to be of interest to auditory neuroscientists, cochlear implant researchers, and neuroengineers. Even where some conclusions require cautious wording, the dataset and analytical framework may be useful for future studies aiming to relate cortical responses to implant programming, perceptual learning, or closed-loop neuroprosthetic approaches.

Overall, the revised manuscript is stronger and addresses an important problem with useful methods and analyses. The results most convincingly show that acoustic responses support better single-trial decoding than acute cochlear implant responses, and that acoustic-trained decoders generalize poorly to implant-evoked activity. The evidence for robust spatial organization, especially in the cochlear implant condition, is more limited and should be presented with appropriate caution.

Reviewer #2 (Public review):

Summary:

This article reports measurements of iEEG signals on the rat auditory cortex during cochlear implant or sound stimulation in separate groups of rats. The observations indicate some spatial organization of cochlear implant stimuli, but that is very different from cochlear implants.

Strengths:

The study includes interesting analyses of the sound and cochlear implant representation structure based on decoders.

Weaknesses:

The observation that responses to cochlear implant stimulation (stimulation) is spatially organized is not new (e.g. Adenis et al. 2024)

The claim that spatial and temporal dimensions contribute information about the sound is also not new there is a large literature on this topic.

The analyses supporting the claim that there is a mismatch between cochlear implant and sound representation are still unclear, particularly in Fig. 8.

Reviewer #3 (Public review):

Summary:

Through micro-electroencephalography, Hight and colleagues studied how the auditory cortex in its ensemble respond to cochlear implant stimulation compared to the classic pure tones. Taking advantage of a double implanted rat model (Micro-ECoG and Cochlear Implant), they tracked and analyzed changes happening in the temporal and spatial aspects of the cortical evoked responses in both normal hearing and cochlear-implanted animals. After establishing that single trial responses were sufficient to encode the stimuli properties, the authors then explored several decoder architectures to study the cortex ability to encode each stimuli modality in a similar or different manner. They conclude that a) intracranial EEG evoked responses can be accurately recorded and did not differed between normal hearing and cochlear-implanted rats; b) Although coarsely spatially organized, CI-evoked responses had higher trial-by-trial variability than pure tones; c) Stimulus identity is independently represented by temporal and spatial aspect of cortical representations and can be accurately decoded by various means from single trials; d) and that Pure tones trained decoder can't decode CI-stimulus identity accurately.

Strength:

The model combining micro-eCoG and cochlear implantation and the methodology to extract both the Event Related Potentials (ERPs) and High-Gammas (HGs) is very well designed and appropriately analyzed. Likewise, the PCA-LDA and TCA-LDA are powerful tools that take full advantage of the information provided by the cortical ensembles.

The overall structure of the paper, with a paced and exhaustive progress through each step and evolution of the decoder is very appreciable and easy to follow. The exploration of single trial encoding and stimulus identity through temporal and spatial domains is providing new avenues to characterize the cortical responses CI stimulations and their central representation. The fact that single trials suffice to decode the stimulus identity regardless of their modality is of great interest and noteworthy. Although the authors confirm that iEEG remains difficult to transpose in clinic, the insights provided by the study confirm the potential benefit of using central decoders to help in clinic settings.

Weakness:

The conclusion of the paper, especially the concept of distinct cortical encoding for each modality, is unfortunately partially supported by the results as the authors ignored fundamental limitations of CI related stimulation.

First, the authors stimulated in a Monopolar mode which, albeit being clinically relevant, notoriously generates a high current spread in rodent models. Comparing the averaged BF maps for iEEG (Fig-2A, C), BFs ranged from 4 to 16kHz with a predominance of 4kHz BFs. The lack of BFs at higher frequencies might reveal a potential location mismatch between the frequency range sampled at the level of the cortex (low to medium frequencies) and the frequency range covered by the CI inserted mostly in the first turn-and-a-half of the cochlea (high to medium frequencies). Looking at Fig-2F (and to some extend 2A) most of CI electrodes elicited responses around the 4kHz regions and averaged maps show a predominance of CI-3-4 across cortex (Fig-2C, H and Sup Fig. 3) from areas with 4kHz BF to areas with 16kHz BF. It is doubtful that CI-3-4 are located near the 4kHz region based on Müller's work (1991) on the frequency representation in the rat cochlea. Moreover, Supplemental figure 3 shows that only a couple of CI electrodes are predominately represented at the level of the cortex. Thus, it seems possible that current spread ended stimulating indistinctly higher turns of the cochlea or even the modiolus in a non-specific manner, greatly reducing (or smearing) the place-coding/frequency resolution of each electrode, which in turn could explain the coarse topographic (or coarsely tonotopic according to the manuscript) organization of the cortical responses.

Second, although the authors acknowledge that post-lingual CI users always have an adaptation period, their conclusion is based on measurements that are relatively "early" in the CI-use timeline so to speak since iEEG were collected a) acutely right after mono-aural implantation and stimulation, b) under anesthesia, c) using unmodulated pulse train fixed at 900pps regardless of the electrode used and thus lacking any temporal information shifts in relationship to electrode cochleotopic placement. Basically, all CI electrodes had the same rate whereas you would expect basal CI electrodes to be amplitude modulated at higher frequencies than apical electrodes.

As much as the reviewer likes the overall approach with the use of PCA-LDA and TCA, and agrees that information transfer seems inexistant at time of measurement, authors should be more careful in their strong conclusion that two distinct encoding exist. The non-overlapping between sound and electric stimulation representations might exist only transiently and this should be acknowledged a bit more in the discussion. Without repetition of iEEG measurement at later period with chronic use of the CI, it is not possible to definitively claim that two distinct, non-overlapping coding co-exist at all times.

Nevertheless, the reviewer wants to reiterate that the study proposed by Hight et al. is well constructed, relevant to the field and that the overall proposal of improving patient performances and help their adaptation in the first months of CI use by studying central responses should be pursued as it might help establish new guidelines or create new clinical tools.

Reviewer #1 (Public review):

Summary:

This study investigates the impact of Pink1 loss on glial function and neuronal health in a Drosophila model, highlighting the role of mitochondria-organelle contacts and key genes such as Ccz1, Vps13, Mon1, and Rab7. The work provides insights into cellular processes underlying neurodegenerative diseases, with a focus on glia-neuron interactions.

Comments on revised version:

I have reviewed the revised manuscript and the authors' responses to previous comments. The authors have addressed the key concerns raised by the reviewers, including validation of the Mz-GAL4 line and additional control experiments. The remaining issues caused by experimental constraints are understandable in this study.

However, several concerns remain. Notably, some key results were removed due to the use of inadequately characterized fly lines, and the lack of follow-up experiments to address these issues raises concerns regarding the validity and reliability of the findings. Furthermore, the absence of experiments examining Rab7-mediated membrane trafficking or the interactions between mitochondria and lysosomes in the Pink1 mutant presents a limitation. These missing elements reduce the clarity and interpretability of Figure 5 for readers.

On a positive note, the data showing that reducing Vps35/Vps13 enhances neuronal function and rescues Pink1 mutant phenotypes in ensheathing glia contributes meaningfully to the overall narrative.

Despite these limitations, this research addresses an important question in neuroscience using the Drosophila model. It provides a novel perspective on Parkinson's disease and neurodegeneration by exploring mechanisms underlying Pink1 loss and suggesting a role for mitochondria-organelle interactions in ensheathing glia, potentially regulated via Vps35/Vps13-mediated pathways.

Overall, the current version presents a clear and meaningful contribution to the field.

Reviewer #2 (Public review):

Summary:

This study proposes a novel role for ensheathing glia (EG) in a Pink1-model of Parkinson's disease and shows that this cell population exhibits the highest number of DEG in a pre-symptomatic stage. In the olfactory system, there seems to be morphological changes in this cell-type that resembles an 'activated' state and the authors further show that the neuronal loss of Pink1 is responsible for this defect. The authors go on to show that manipulation of Pink1 in EG also leads to some defects in the visual system and in the dopaminergic neurons (DAN) that innervate the mushroom body (MB), and performed a screen based on the 'on-transient' defect of the ERG to identify potential genes that may modulate the function of EG in synaptic regulation. They focus on several genes related to vesicle trafficking including Vps13, and Vps35 and performed some additional experiments in the visual system and MB to propose the role of vesicle/lipid trafficking in EG as an important factor for PD pathogenesis.

Strengths:

The study proposes functional and mechanistic connections between several genes that have been linked to PD (PINK1, VPS35 and VPS13A/C). I feel that the data presented in Figure 1-Figure 3C are performed with rigor and are convincing/novel. The selection of Drosophila to study the questions is also a strength and the lab has extensive experiences in this field and model organism.

Weaknesses:

In this revised manuscript, a number of concerns raised by this and the other reviewer was addressed. The authors now admitted that some of the genetic reagents used in their screen and follow up assays were inappropriately utilized, and changed the latter half of the paper (Fig 3D-F4) quite significantly (e.g. now only 1 gene is considered as a hit in Fig3D, analysis of several genes in Fig4 have been removed and replaced by some experiments performed on Vps35). The transition between Figure 3D and Figure 4 is quite abrupt, and they don't seem to follow up on the CG17660 (the single hit from their screen, which is not further validated so it is not clear whether this genetic reagent is clean or not) and the effect of Vps35 RNAi in synaptic phenotype. Therefore, there is still a weakness in Figure 3D-Figure 4, which weakens the paper, especially since the new model diagram the authors provided in Figure 5 is not really investigated at the molecular level.

Reviewer #1 (Public review):

Summary:

In this study entitled "Linking Germline Telomere Removal to Global Programmed DNA Elimination in Tetrahymena Genome Differentiation" Nagao and colleagues examine the fate of germline chromosome ends during somatic genome differentiation in the ciliate Tetrahymena thermophila. During sexual reproduction, a new somatic genome is created from a zygotic, germline-derived genome by extensive programmed DNA elimination events. It has been known for some time that the terminii of the germline chromosomes are eliminated, but the exact process and kinetics of the elimination events has not been thoroughly investigated. The authors first use germline-specific telomere probes to show that the loss of these chromosome ends occurs with similar timing as other DNA elimination events. By comparative analysis of the assembled germline and somatic genomes, the authors find the ends of each of the germline chromosomes are composed of few hundred kilobases of micronuclear limited sequences (MLS) that are removed starting around 14 hours after the start of conjugation, which initiates sexual development. They then develop an in-situ hybridization assay to track the fate of one end of chromosome 4 while simultaneously following the adjacent macronuclear destined sequence (MDS) retained in the new somatic genome. This allows the authors to more clearly show that these adjacent chromosomal segments are initially amplified in the developing genome before the terminal MLS is eliminated. Finally, they mutate the chromosome breakage sequence (CBS) that normally separates the MLS terminus from the adjacent MDS region as show that strains that develop with only one mutant chromosome can produce viable sexual progeny, but it appears that both the MLS and the MDS from the mutant chromosome are lost. If both chromosome copies have the CBS mutation, the cells arrest during development and do not eliminate many germline limited sequences and fail to produce viable progeny. Overall, this study provides many new insights into the fate of germline chromosome ends during somatic genome remodeling and suggests extensive coordination of different DNA elimination events in Tetrahymena.

Strengths:

Overall, the experiments were well executed with appropriate controls. The findings are generally robust. Importantly, the study provides several novel findings. First, the authors provide a fairly comprehensive characterization of the size of the MLS at the end of each germline chromosome. They also report on the highly repetitive composition of these chromosome terminii. Second, the authors develop a novel method to study the fate of chromosome terminii during development and use it conclusively track the elimination of these terminii. Third, the authors show that the elimination of these terminii appears to occur concurrently with most other DNA elimination events during somatic genome differentiation. And fourth, the authors show that failure to separate these eliminated sequences from the normally retained chromosome alters the fate of these adjacent MDS and loss of the cells ability to produce viable progeny. The authors initially hypothesized that DNA elimination may be blocked due to inappropriate silencing of genes in the MDS region when the CBS is mutant, but gene expression analysis showed that this is not the case.

Weaknesses:

After revising the manuscript based on the initial reviewers' critique, most weaknesses have been addressed. On weakness remaining is that since the authors only mutated the end of one germline chromosome, it is not clear whether the elimination of the MDS adjacent to the terminal MLS on chromosome 4 when the CBS is mutated is a general phenomenon, i.e. would happen at all chromosome ends, or is unique to the situation at Chromosome 4R. Knowing whether it is a general phenomenon or not would provide important insight into the authors findings. The authors did attempt to look at other chromosome ends, but technical limitations currently stymie this effort.

The other weakness is that it remains unclear how failure to carry out DNA elimination appears to induce a checkpoint during development, but this open question is not unique to this study.

Comments on revised version.

The authors have significantly improved the study. The addition of the RNA-seq analysis allowed these researchers to show that their initial hypothesis - that loss of a CBS leads to inappropriate gene silencing in the neighboring MDS region - appears not to be the case. I do not have further suggestions for the authors.

Reviewer #2 (Public review):

Summary:

Mochizuki and colleagues investigated how the germline (MIC) telomere was removed during programmed genome rearrangement in the developing somatic nucleus (MAC). Using an optimized oligo-FISH procedure, the authors demonstrated that MIC telomeres were co-eliminated with a large region of MIC-limited sequences (MLS) demarcated on the opposite side by a sub-telomeric chromosome breakage site (CBS). This conclusion was corroborated by the latest assembly of the Tetrahymena MIC genome. They further employed CRISPR-Cas9 mutagenesis to disrupt a specific sub-telomeric CBS (4R-CBS). In the uniparental progeny (mutant X WT), DNA elimination of the sub-telomeric MLS was not affected, but the adjacent MAC-destined sequence (MDS) may be co-eliminated. However, in the biparental progeny (mutant X mutant), global DNA elimination was arrested, revealing previously unrecognized connections between chromosome breakage and DNA elimination. It also paves the way for future studies into the underlying molecular mechanisms. The work is rigorous, well-controlled, and offers important insights into how eukaryotic genomes demarcate genic regions (retained DNA) and regions derived from transposable element (TE; eliminated DNA) during differentiation. The identification of chromosome breakage sequences as a critical architectural element of the genome separating TE-derived regions from functional genes is a key conceptual contribution.

Strengths:

New method development: Oligo-FISH in Tetrahymena. This allows high-resolution visualization of critical genome rearrangement events during MIC-to-MAC differentiation. This method will be a very powerful tool in this area of study.

The conclusion is strongly supported by integrated analyses of PCR-based assays, as well as cytological, genomic, and transcriptomic data.

Rigorous genetic analysis of the role played by 4R-CBS in separating the fate of sub-telomeric MLS (elimination) and MDS (retention).

Reviewer #3 (Public review):

Programmed DNA elimination (PDE) is a process that removes a substantial amount of genomic DNA during development. While it contradicts the genome constancy rule, an increasing number of organisms have been found to undergo PDE, indicating its potential biological function. Single-cell ciliates have been used as a prominent model system for studying PDE, providing important mechanistic insights into this process. Many of those studies have focused on the excision of internally eliminated sequences (IES) and the subsequent repair using non-homologous end joining (NHEJ). These studies have led to the identification of small RNAs that mark retained or eliminated regions and the transposons that generate double-strand breaks.

In this manuscript, Nagao and Mochizuki examined the other type of breaks in ciliates that are healed with telomere addition. They specifically focused on the sequences at the ends of the germline (MIC) chromosomes, which have received relatively less attention due to the technical challenges associated with the highly repetitive nature of the sequences. The authors used the Tetrahymena model and developed a set of new tools. They used a novel FISH strategy that enables the distinction between germline and somatic telomeres, as well as the retained and eliminated DNA near the chromosome ends. This allows them to track these sequences at the cellular level throughout the development process, where PDE occurs. They also analyzed the more comprehensive germline and somatic genomes and determined at the sequence level the loss of subtelomeric and telomere sequences at all chromosome ends. Their result is reminiscent of the PDE observed in nematodes, where all germline chromosome ends are removed and remodeled. Thus, the finding connects two independent PDE systems, a protozoan and a metazoan, and suggests the convergent evolution of chromosome end removal and remodeling in PDE.

The majority of sites (8/10) at the junctions of retained and eliminated DNA at the chromosome ends contain a chromosome breakage sequence (CBS). The authors created a set of mutants that modify the CBS at the ends of chromosome 4R. CBS regions are challenging for CRISPR due to their AT-rich sequences, making the creation of the 4R-CBS mutants a significant breakthrough. They used the FISH assay to determine if PDE still occurs in these mutant strains with compromised CBS. Surprisingly, they found that instead of blocking PDE, its adjacent retained DNA is now eliminated, suggesting a co-elimination event when the breakage is impaired. Furthermore, in biparental mutant crosses, no PDE occurred, and no viable progeny were produced, indicating that the removal of chromosome ends is crucial for proper PDE and sexual progeny development. Overall, the work demonstrates a critical role for 4R-CBS in separating retained and eliminated DNA.

Reviewer #1 (Public review):

[Editors' note: this version has been assessed by the Reviewing Editor without further input from the original reviewers. The authors have addressed the comments raised in the previous round of review.]

Summary:

In this study, the authors propose that HSV-1 infection degrades the class I histone deacetylases HDAC1 and HDAC2. The MDM2 E3 ubiquitin ligase from the DNA damage response pathway is responsible for ubiquitinating these HDACs that are subsequently degraded via proteasomes. The authors hypothesize that HDAC degradation will cause hyperacetylation of viral chromatin and enable viral gene transcription.

Strengths:

The ubiquitination of HDAC1 & HDAC2 by Mdm2 and the mapping studies are clear.

Reviewer #2 (Public review):

Summary:

The authors discovered that HDAC1/2 are degraded in HSV-1 and PRV infections. They attempted to establish a new mechanism by which HDAC1/2 are translocated to the cytoplasm to be degraded in HSV-1 infection, and the degradation causes changes in histone acetylation to affect the DDR pathway.

Strengths:

(1) Interesting findings of HDAC1/2 degradation during HSV-1 and PRV infection, and it may impact more than the virology field.

(2) Significant work to identify the ubiquitin site in HDAC1/2 and K63 linkage.

Reviewer #1 (Public review):

[Editors' note: this version has been assessed by the Reviewing Editor without an additional round of formal review from the original reviewers. The authors have addressed the comments raised in the previous round of review.]

Summary:

In the manuscript "Pathogen-Phage Geomapping to Overcome Resistance," Do et al. present an impressive demonstration of using geographical sampling and metagenomics to guide sample choice for enrichment in human-associated microbes and the pathogen of interest to increase the chances of success for isolating phages active against highly resistant bacterial strains. The authors document many notable successes (17!) with highly resistant bacterial isolates and share a thoughtfully structured phage discovery effort, potentially opening the door to similar geomapping efforts across the field. While the work is methodologically strong and valuable for the community, there are a few areas where additional clarification and analysis could better align the claims with the data presented.

Strengths:

(1) The manuscript describes a well-executed and transparent example of overcoming a major obstacle in therapeutic virus identification, providing a practical success story that will resonate with researchers in microbiology and medicine.

(2) Many phage researchers have anecdotally experienced a similar phenomenon, that a particular wastewater treatment plant always seems to have the pathogens you need. Quantifying this with metagenomics modernizes and adds evidence to this phenomenon in a way that could help researchers reproduce this success in a methodical way.

(3) The methodology of combining environmental sampling, viral screening, and host-range analysis is clearly articulated and reproducible, offering a valuable blueprint for others in the field.

(4) The data are presented with appropriate analytical rigor, and the results include robust sequencing and metagenomic profiling that deepen understanding of local viral communities.

(5) The 17 successes yielding 35 phages have a lot of phylogenetic novelty beyond what the Tailor labs have typically found with previous methods.

(6) The work highlights a practical and innovative solution to an increasingly important clinical problem, supporting the development of personalized antiviral strategies.

Reviewer #2 (Public review):

Summary:

The manuscript by Do and colleagues aims to develop a workflow for isolating and identifying bacteriophages with potential applications in phage therapy against antibiotic-resistant pathogens. The workflow integrates geΦmapping as a strategy to identify potential phage sources, ΦHD as a device for phage concentration, and RΦ as a phage library constructed from the initial sampling, resulting in the discovery of 36 new phages. The paper is overall interesting, and the proposed method appears robust and effective.

Strengths:

The methods proposed combined state-of-the-art strategies to solve an ever-increasing problem of antibiotic resistance. The methods are robust, and the controls are appropriate. The integration of environmental sampling, concentration strategies, and downstream genomic characterization is a clear strength and provides a potentially scalable framework for identifying candidate therapeutic phages. The manuscript is clearly written overall, and the results support the main conclusions.

Comments on revised version:

The manuscript has been adequately improved and adjusted according to the comments. There are minor points such as Table S10 is labelled in the top of the page as Table S11. Also, is a little unconventional to cite result figures and tables in the introduction.

For the question 10, regarding why some of the most abundant vOTUs in the 5L sample were not detected in the concentrate. The answer does not satisfy, as it focuses on why very low abundant vOTUs will not be detected, but the question is why some of the most abundant vOTUs were not detected. This does not affect the results or interpretation made.

Reviewer #1 (Public review):

Summary:

Gurnani et al. explore how dynamical properties of neural networks influence capacity for and mechanisms of learning. Specifically, they focus on Brain Computer Interface (BCI) learning, in which manipulations are applied to a decoder that maps neural activity onto computer cursors. This paradigm was introduced by Sadtler et al. 2014, and has become an influential part of the neuroscience motor learning literature. A particularly fascinating outcome of that body of work is the observation that "within-manifold" perturbations (WMPs), which preserve covariance structure in the neural population, are easier to learn than "outside-manifold" perturbations (OMPs), which break this. Since deep network parameter access is challenging (to say the least) in monkey experiments, the intuition for this split in learnability is ripe for modeling and theory work. Indeed, the authors here introduce a feedback-driven recurrent neural network model whose output drives a simulation of a neural decoder commonly used in BCI studies like the Sadtler paper. While there have now been several modeling studies exploring how neural networks could solve this task, the feedback control perspective gives the authors' new model an interesting niche. Overall, this is a thoroughly done and well-written modeling study, and a solid contribution to the literature on within- and outside-manifold perturbations.

Strengths:

Reframing the OMP and WMP learning from a feedback-driven dynamical systems perspective, not just a geometric one, is an interesting take. The controllability analysis (along with the clear difference in input-driven and recurrence-driven learning) is quite a cool result that helps better frame what might be happening in the primate brain during similar tasks.

Weaknesses:

Some of the more interesting aspects, especially the controllability) and the differences between input-driven and recurrence-driven learning could be further developed, either by showing more analyses or running more comparisons. A few sections could benefit from some additional clarity on the strength and significance of results.

Reviewer #2 (Public review):

Summary:

The constraints on learning in the brain remain elusive. Using BCIs, Sadtler et al. demonstrated that the brain can rapidly learn new decoders that lie within the intrinsic neural manifold (short-term adaptation), while showing substantial difficulty learning decoders that lie outside the manifold. This finding suggests that neural manifolds impose constraints on learning. However, even among within-manifold decoders, there was considerable variability in learning rates that could not be explained solely by geometric factors.

Here, Gurnani et al propose that, in addition to manifold structure, neural dynamics (i.e., the flow field across states) impose critical constraints on learning. To test this idea, the authors trained RNNs that received real-time feedback (e.g., position error signals) during a BCI task in which the network controlled a cursor. The authors showed that short-term adaptation to a new decoder is facilitated by plasticity in sensory inputs, and that pre-existing dynamics influence the speed of adaptation across different decoders. These findings may explain previously unresolved constraints observed in BCI learning and suggest an important role for neural dynamics in constraining sensorimotor learning in the brain.

Strengths:

Overall, the work is highly impactful and is likely to motivate a new generation of BCI and learning experiments combining large-scale neural recordings with latent dynamical systems analyses. The paper is clearly written, and I only have minor comments, primarily for clarification.

Weaknesses:

There are no major weaknesses. Please see below for minor comments.

(1) If I understand correctly, most analyses do not distinguish between the preparatory phase and the movement phase. Given that the preparatory phase is largely controlled by feedforward input, I suspect that most of the dynamical constraints underlying learning variability arise during the movement phase. Is this correct? If so, could the authors clarify or directly test this distinction?

(2) P4: Position vs. velocity decoders: It would be helpful to describe whether and how the choice of velocity versus position decoders influences whether perturbations are learnable, and whether input-driven constraints arising in this task are similar.

(3) The variance criteria used to screen decoder perturbations may themselves covary with learning rate, behavioral asymmetry, and overlap with controllable subspaces. A quantification of this relationship would help contextualize the findings and inform the design of future BCI experiments.

(4) To support the comparison between Figures 3 and 7, and the conclusion that Figure 3 better matches the experimental data, which is an important point of the manuscript, could the authors provide quantitative values from the experimental data (e.g., how large is the change in variance within oPCs, etc)?

(5) Figure 8h: Is the variability in learning rates in models with different controller networks explained by the same dynamical constraints described in Figure 6? Demonstrating consistent dynamical constraints across model architectures would strengthen the paper's central conclusion.

(6) Figure 8f: Why does feedforward controllability differ between conditions? This is mentioned in the text, but no explanation is provided.

Reviewer #1 (Public review):

Summary:

This study investigates the role of the medial prefrontal cortex (mPFC) in generating goal-directed actions under threat, using a progressive behavioral paradigm, neural recordings, and optogenetic inhibition in mice. The authors demonstrate that while mPFC GABAergic neurons strongly encode cues, actions, and errors, particularly under high cognitive demand, this neural activity is not causally required for executing avoidance behaviors. By rigorously controlling for movement and arousal, the researchers found that much of the observed mPFC signaling actually reflects baseline behavioral states rather than the generation of the actions themselves. This dissociation between encoding and causality challenges traditional views of mPFC as an executive controller of action and provides a nuanced understanding of its role in evaluative and contextual processing.

Strengths:

The behavioral paradigm employed in this study is one of its greatest strengths, offering a rigorous, progressive, and well-controlled framework to dissect the neural mechanisms underlying avoidance under threat. This three-phase task design is particularly well-suited to tease apart the contributions of learning, discrimination, and cognitive load to both behavior and neural activity.

By tracking movement (speed, rotations) and including it as a covariate in statistical models, the authors also underscore the need to control for movement and baseline activity when interpreting cortical signals, which is relevant for all studies of brain-behavior relationships, ensuring that behavioral changes are not due to general arousal or motor activity.

Finally, the study combines multiple advanced techniques-fiber photometry, single-cell calcium imaging (miniscopes), and two distinct optogenetic inhibition methods-to provide a comprehensive look at both neural encoding and causal necessity.

Comments on revised version.

The authors adequately addressed all of the reviewers' comments and made great improvements to the manuscript, particularly enhancing the methods and figures to significantly improve clarity and readability.

Reviewer #2 (Public review):

Summary:

The manuscript by Sajid et al. describes a comprehensive behavioral, imaging and optogenetic dataset investigating the role of the mPFC in avoidance and escape behaviors. Although many movement- and task-related variables are encoded by mPFC GABAergic neurons, the main conclusion is that they are unlikely to control behavioral output.

Strengths:

The manuscript is generally well executed and plausible in its conclusions. It provides an alternative viewpoint to many articles describing the involvement of mPFC to behavior, based on a complex multi-stage behavioral paradigm acquired and analyzed in an unbiased way.

Weaknesses:

This reviewer sees two weaknesses.

(1) In some cases, the explained variance, marginal and conditional, is low, suggesting the models only modestly capture the complexity in the data.

(2) The manuscript is challenging to read due to the comprehensive and unbiased presentation style.

Comments on revised version.

The authors did a good job at addressing the reviewers' comments. One minor additional suggestion is to add references for the statement in the last paragraph of the discussion for the mPFC lesion studies.

Reviewer #1 (Public review):

[Editors' note: this version has been assessed by the Reviewing Editor without further input from the original reviewers. The authors have addressed the comments raised in the previous round of review.]

Summary:

Morgan et al. studied how paternal dietary alteration influenced testicular phenotype, placental and fetal growth using a mouse model of paternal low protein diet (LPD) or Western Diet (WD) feeding, with or without supplementation of methyl-donors and carriers (MD). They found diet- and sex-specific effects of paternal diet alteration. All experimental diets decreased paternal body weight and the number of spermatogonial stem cells, while fertility was unaffected. WD males (irrespective of MD) showed signs of adiposity and metabolic dysfunction, abnormal seminiferous tubules and dysregulation of testicular genes related to chromatin homeostasis. Conversely, LPD induced abnormalities in the early placental cone, fetal growth restriction and placental insufficiency, which was partly ameliorated by MD. The paternal diets changed placental transcriptome in a sex-specific manner and led to a loss of sexual dimorphism in the placental transcriptome. These data provide a novel insight on how paternal health can affect the outcome of pregnancies, which is often overlooked in prenatal care.

Strengths:

The authors have performed a well-designed study using commonly used mouse models of paternal underfeeding (low protein) and overfeeding (Western diet). They performed comprehensive phenotyping at multiple timepoints including of the fathers, the early placenta and late gestation feto-placental unit. The inclusion of both testicular and placental morphological and transcriptomic analysis is a powerful non-biased tool for such exploratory observational studies. The authors describe changes in testicular gene expression revolving around histone (methylation) pathways that are linked to altered offspring development (H3.3 and H3K4), which is in line with hypothesised paternal contributions to offspring health. The authors report sex differences in control placentas that mimic those in humans, providing potential for translatability of the findings. The exploration of sexual dimorphism (often overlooked) and its absence in response to dietary modification is novel and contributes to the evidence-base for the inclusion of both sexes in developmental studies.

Comments on revised version:

The authors have done a great job addressing my concerns. The description of the data analysis and the figures are now much clearer. The inclusion of the potential links between the microbiome and male reproductive fitness is informative and improves the flow of the discussion.

Reviewer #2 (Public review):

Summary:

The authors investigated the effects of a low-protein diet (LPD) and a high sugar- and fat-rich diet (Western diet, WD) on paternal metabolic and reproductive parameters and feto-placental development and gene expression. They did not observe significant effects on fertility; however, they reported gut microbiota dysbiosis, alterations in testicular morphology, and severe detrimental effects on spermatogenesis. In addition, they examined whether the adverse effects of these diets could be prevented by supplementation with methyl donors. Although LPD and WD showed limited negative effects on paternal reproductive health (with no impairment of reproductive success), the consequences on fetal and placental development were evident and, as reported in many previous studies, were sex-dependent.

Strengths:

This study is of high quality and addresses a research question of great global relevance, particularly in light of the growing concern regarding the exponential increase in metabolic disorders, such as obesity and diabetes, worldwide. The work highlights the importance of a balanced paternal diet in regulating the expression of metabolic genes in the offspring at both fetal and placental levels. The identification of genes involved in metabolic pathways that may influence offspring health after birth is highly valuable, strengthening the manuscript and emphasizing the need to further investigate long-term outcomes in adult offspring.

The histological analyses performed on paternal testes clearly demonstrate diet-induced damage. Moreover, although placental morphometric analyses and detailed histological assessments of the different placental zones did not reveal significant differences between groups, their inclusion is important. These results indicate that even in the absence of overt placental phenotypic changes, placental function may still be altered, with potential consequences for fetal programming.

Comments on revised version:

The authors have adequately addressed all my previous comments.

Joint Public Review:

[Editor's Note: The previous reviewers comments were felt to be addressed by the reviewers and myself and have improved the work.]

In this study, the authors suggest that DuoHexaBody-CD37, a biparatopic CD37-targeting antibody, can induce direct cytotoxicity in diffuse large B-cell lymphoma (DLBCL) cells through antibody clustering and SHP-1 activation, independent of complement. They further propose that DuoHexaBody-CD37 inhibits cytokine-mediated pro-survival signalling, suggesting a broader role for CD37-directed therapy in disrupting tumour supportive signalling networks.

A strength of the study is the systematic in vitro characterisation of signalling responses to DuoHexaBody-CD37 across both malignant and normal B-cells. The inclusion of phosphoproteomic profiling and mutant constructs provides mechanistic detail, and the findings may be of interest to researchers working on antibody therapeutics in lymphoma.

However, the evidence supporting key mechanistic processes - particularly the specific subtype requirement for Fc receptor crosslinking - is incomplete and would benefit from further functional validation. While CD37 has been explored previously as a therapeutic target, this study does add mechanistic insight into direct cytotoxicity and cytokine modulation. Nevertheless, the exclusive reliance on in vitro systems makes the translational relevance unclear.

Overall, the study provides valuable insight into CD37-mediated signalling in lymphoma cells, but the evidence remains incomplete to support broader conclusions about therapeutic impact. The additional mechanistic data included during revision are informative, but the precise basis of the observed cytotoxic effects remains incompletely defined.

Reviewer #1 (Public review):

The manuscript "Heterozygote advantage cannot explain MHC diversity, but MHC diversity can explain heterozygote advantage" explores two topics. First, it is claimed that the recently published by Mattias Siljestam and Claus Rueffler conclusion (in the following referred to as [SR] for brevity) that heterozygote advantage explains MHC diversity does not withstand an even very slight change in ecological parameters. Second, a modified model that allows an expansion of MHC gene family shows that homozygotes outperform heterozygotes. This is an important topic and could be of potential interest to the readership of eLife if the conclusions are valid and non-trivial.

The resubmitted manuscript addresses several questions from my previous review. In particular, there is a more detailed description of how the code of Siljestam and Rueffler ([SR]) was used for the simulations and the calculation of the factor 2.7 x 10^43 that is the key to the alleged breakdown of the numerical reasoning presented by in [SR].

Yet I think that important aspects of my critique of the first statement of the manuscript about the flaws of [SR] model remain unanswered. I guess the discussion becomes rather general about the universality and robustness of various types of models to parameter changes. My point is that none of the models is totally universal. The model in [SR] is not phenomenological as none of the parameters or functional forms were derived empirically. Instead, it is a proof of principle demonstration that inevitably grossly simplifies the actual immune response. The choice of constants and functions used in Eqs. (1-5) is dictated by the mathematical convenience and works in a limited range of parameter values. It is shown in [SR] that for 3 pathogens and reasonable "virulence " \nu, the alleles branch. These conclusions are supported by the analytically derived Adaptive Dynamics branching criteria (7), which, contrary to the statement is the cover letter (" It is clear from Fig. 4 of Siljestam and Rueffler that the branching condition is far from sufficient for high MHC diversity.") is perfectly confirmed by the simulation data shown in Fig. 4.

The mathematical simplicity of the [SR] model generates various artifacts, such as the mentioned by the Author reduction of the "condition" by an enormous factor 2.7 x 10^43 and the resulting decrease in the "survival" induced by the addition of a new pathogen. This occurs at the very large value of \nu=20, whose effect is enormous due to the Gaussian form of (1), which, once again, was chosen for the mathematical convenience. In reality, a new pathogen cannot reduce the "survival" by such a factor as it would wipe out any resident population. So to compensate for such an artifact, the additional factor c_max was introduced to buffer such an excess. There is no reason to fix c_max once for an arbitrary number of pathogens, because varying c_max basically reflects the observation that a well-adapted individual must have a reasonable survival probability. At the same time, there are many ways in which the numerical simulation may break down when the survival rates become of the order of 10^(-43) instead of one, so it comes to no surprise that the diversification, predicted by the adaptive dynamics, does not readily occur in the scenario with an addition or removal of the 8th pathogen with a very high virulence \nu=20.

I have doubts that the reported breakdown of the [SR] model with fixed c_max remains observable with less extreme values of m and \nu (say, for \nu=7 and m=3 plus or minus 1 used in Fig. 3 in the manuscript).

So I still find the claim that " the phenomenon that leads to high diversity in the simulations of Siljestam and Rueffler depends on finely tuned parameter values" is not well substantiated.

Reviewer #2 (Public review):

Summary:

This study addresses the population genetic underpinnings of the extraordinary diversity of genes in the MHC, which is widespread among jawed vertebrates. This topic has been widely discussed and studied, and several hypotheses have been suggested to explain this diversity. One of them is based on the idea that heterozygote genotypes have an advantage over homozygotes. While this hypothesis lost early on support, a reason study claimed that there is good support for this idea. The current study highlights an important aspect that allows us to see results presented in the earlier published paper in a different light, changing strongly the conclusions of the earlier study, i.e., there is no support for a heterozygote advantage. This is a very important contribution to the field. Furthermore, this new study presents an alternative hypothesis to explain the maintenance of MHC diversity, which is based on the idea that gene duplications can create diversity without heterozygosity being important. This is an interesting idea, but not entirely new.

Strength:

(1) A careful re-evaluation of a published model, questioning a major assumption made by a previous study.

(2) A convincing reanalysis of a model that, in the light of the re-analysis-loses all support.

(3) A convincing suggestion for an alternative hypothesis.

Weakness:

(1) The title of the study is catchy, but it is explained only in the very end of the paper.

Reviewer #1 (Public review):

In this study, the authors set out to determine how two classes of kinase inhibitors, which stabilise a disease-relevant enzyme in either an active (Type I) or inactive state (Type II), influence its organisation and interactions with microtubule filaments in cells. Using the state-of-the-art in-cell structural imaging approaches, they examine how these compounds affect the formation of protein filaments and their association with microtubules, and succeed in defining the underlying structural basis for these differences.

A major strength of the work is the application of in-cell cryo-electron tomography combined with correlative imaging, which enables direct visualisation of protein organisation in a near-native cellular context. The data convincingly demonstrate that the Type I inhibitor compound stabilising the active state promotes extensive LRRK2 filament formation and microtubule bundling, whereas compounds stabilising the inactive state markedly reduce these interactions. The structural analysis further provides insight into how conformational states relate to filament organisation, including modelling of previously unresolved regions of the protein.

These findings are internally consistent and align well with prior biochemical and structural studies, many of which were performed by the same team.

There are, however, some limitations that should be noted. The experiments rely on overexpression of the I2020T mutant form of the LRRK2 protein, which is a rare variant, in a single cell type (293T cells), which may not fully reflect endogenous behaviour or wild-type LRRK2 in a physiological context. In addition, while the imaging data are compelling, the functional consequences of the observed filament formation and microtubule association remain unclear.

The study therefore provides strong descriptive and structural insight, but more limited evidence linking these observations to cellular or disease-relevant outcomes.

Overall, the authors largely achieve their aims, and the results support their central conclusion that different classes of kinase inhibitors have distinct effects on protein organisation in cells. The work represents an important advance in understanding how small molecules can reshape protein architecture in a cellular environment, with potential implications for therapeutic strategies. The methodological approach will also be of broad interest to the field, as it highlights the power of in-cell structural biology to study dynamic protein assemblies that are difficult to capture using traditional approaches.

Reviewer #2 (Public review):

Summary:

Mutations in Leucine-Rich Repeat Kinase 2 (LRRK2) are a major cause of Parkinson's disease. LRRK2 PD-related mutations all result in increased kinase activity. Therefore, LRRK2 has been the focus of the development of kinase inhibitors. So far, two classes of kinase inhibitors have been identified: type 1 LRRK2-specific inhibitors that stabilize LRRK2 in a closed active-like conformation and broad-range type 2 inhibitors that stabilize LRRK2 in an open inactive-like conformation. Basiashvili et al. used here in cell structural biology to study the effect of both type 1 and type 2 inhibitors on the localization and structural conformation of LRRK2-I2020T.

Strengths:

They showed that Type 1 and not Type 2 inhibitors induce LRRK2 filament/ on microtubules. Furthermore, they were able to build a structural map of full-length LRRK2 I2020T bound to a Type 1 inhibitor in a closed kinase confirmation. Together, this work thus confirms the data of previous studies that showed that LRRK2 Type 1 and 2 inhibitors differently affect filament formation.

Weaknesses:

All conclusions are fully supported by the provided data. However, as the authors indicated themselves, the physiological relevance of LRRK2 microtubule binding is questionable. Furthermore, although the authors used a full-length LRRK2 protein, like in previously published structures, the resolution of the N-terminal domains is rather poor. Therefore, it also remains unclear what we learn from this structure compared to the previously published structures.

Reviewer #3 (Public review):

Summary:

This paper describes new insights into the effects of type-I and type-II LRRK2 inhibitors on HEK293T cells that over-express GFP-labeled LRRK2-I2020T. Using correlative light microscopy and cryo-electron tomography, a type-I inhibitor leads to the extensive decoration of microtubules with LRRK2, which is not seen for a type-II inhibitor. Subtomogram averaging reveals that LRRK2 binds to the microtubules in a closed-kinase conformation, with density for the N-terminal arms.

Strengths:

The paper is well written; the CLEM and cryo-ET appear to be done to a high standard. Consequently, I have only minor comments.

Weaknesses:

The resolution of the subtomogram averages is somewhat limited, but the authors have adequately limited the number of degrees of freedom in the fitting of their atomic models by only allowing rigid-body transformations of separate parts of LRRK2.

The authors should include FSC curves between the rigid-body fitted atomic models and the various sub-tomogram average maps.