The ability to segment cells from images enables unbiased and high-throughput phenotyping for biological studies. I was excited to come across this preprint on Segment Anything for Microscopy, which builds upon the promising Segment Anything Model developed by a team at Facebook. Your model particularly excels in expanding the utility of the Segment Anything Model to cellular images and their associated biological features.

Having tried Segment Anything for Microscopy, I'd like to offer some comments and questions:

1. The software was straightforward to install, and I commend the clarity of the instructions provided on the Github repository. I was up and running within 30 minutes, which is excellent.

2. I was impressed with the automatic segmentation feature in 2D mode, which successfully segmented an algal cell in my test image without additional training.

3. For tracking mode, however, I encountered some difficulties when testing an image stack of an algal cell swimming in a microchamber. I allotted 30 minutes for this test, expecting this to be sufficient based on my experience with similar tools. The algorithm seemed to struggle with tracking the cell when it moved significantly between frames. Could you include a section in the documentation that describes how to adjust tracking parameters to account for different velocities of cell movement? This would be a useful addition for users like me who deal with fast-moving cells.

4. I couldn't find any documentation regarding batch processing of images. Is this feature available, or do you have plans to implement it?

Thank you for your contribution to the field. I look forward to future updates and improvements to Segment Anything for Microscopy. I used ChatGPT to revise an initial draft of my comments for clarity and accurate word choice, but I verify that all of the text accurately reflects my review of the software.

Galo Garcia, Scientist at Arcadia Science

The new dye to label acidic organelles appears incredibly useful. The high photostability and low toxicity of the dye make it a useful tool for cell biology research. I have a few questions.

1. Where is the dye available for scientists to use?
2. Figure 5 shows that the new dye is less toxic than other dyes. Could the authors speculate on why the dye is non-toxic compared to other fluorescent dyes?
3. Could the authors label the rows of images so readers can immediately know which dyes are being used without having to peruse the legend?

The authors have successfully developed a computational pipeline to automatically score nictation, a specific motility behavior in nematodes, and demonstrated its utility with data, such as the detection of an increase in nictation after nematode exposure to G. mellonella. To enhance the manuscript's clarity and the utility of the work, I propose the following suggestions:

1. Please consider linking the Github page (https://github.com/TemmermanLab/nictation-tracking-and-scoring) directly in the manuscript to allow easier access to the code for readers.

2. Additional information in the Github readme to assist users would be beneficial. More explicit instructions on how to use the computational pipeline, as well as improved visibility of key documents like the 'manual_scoring_instructions.docx', would enhance user navigation.

3. To provide better comprehension of the nictation behavior, consider including a visual representation or graphic. This addition would help readers, like myself, who still find the concept of nictation somewhat unclear.

I used ChatGPT to help craft the language in this feedback, but verify that the content is accurate.

-Galo

The authors have made significant contributions by developing a segmentation-free machine learning pipeline, ImmuNet, which efficiently identifies and phenotypes immune cells across diverse human tissues. The ability to bypass computational cell segmentation, a challenging task in many instances, underscores the profound utility of this technique.

However, while the potential application of ImmuNet beyond the domain of immunology and human studies is intriguing, a comprehensive understanding of the technique's limitations is paramount for its broader applicability. In this context, the authors could consider addressing the following points:

1. Marker Specificity: ImmuNet seems to heavily rely on well-defined markers, along with antibodies that can reproducibly and specifically detect these molecules. Could the authors elucidate any potential limitations or challenges this reliance might present, particularly when expanding the use of ImmuNet beyond its current scope?

2. Novel Cell Type Detection: The manuscript illustrates ImmuNet's efficacy in identifying well-characterized cell types. However, could the technique also shed light on cells that remain undetected with the current samples studied? Would it be possible to use ImmuNet to potentially identify novel cell types? Could the authors discuss any future directions or enhancements to ImmuNet's pipeline that might allow for such advancements?

These discussions could add to the depth of the current study, paving the way for a broader understanding and application of ImmuNet across different fields.

I used ChatGPT to help craft the language in this feedback, but verify that the content is accurate. -Galo

The MedAGI tools is interesting, and it looks very useful! Were the tests (figures 2-4) performed with images from the training set, or were the images independent from the training sets?

This text in figure 3 is small, making it difficult to read.

It would be useful to have a scale bar in the image so the reader can assess the size of the objects. It would also be useful to have labels denoting the taxonomy of the samples.

It's useful to have a deep learning method for taxonomic classification of species. However, for the method to be broadly useful across the scientific community the specific methods need to be accessible. Do you have a Github repository where you share the code for this work so that other scientists can try this method on their own biological samples?

The development of these new genetically-encoded ATP biosensors is impressive! The targeting of the sensor to different parts of the cell enables studies of cellular energy expenditure in different regions or compartments of the cell. I have a few questions. 1. Have you considered making a ciliary ATP biosensor? You could fuse a ciliary targeting sequence to your sensor. I think the cilia community would be interested in this tool. 2. How well do you think this tool would work in other organisms, such as nematodes, algae, or ciliates? 3. How difficult would it be to develop a similar sensor for GTP?

Great figure! It clearly shows the utility of the ATP sensor for studying energy expenditure locally in the cell.

It would be useful to the reader to have a legend describing the different traces directly in the figure, so the reader can understand the experiments even without reading the text. For example, you could have small boxes that are black or cyan with text right besides that says "Control ( DMSO)" or "ATP depletion (2-DG)". Readers will appreciate clear and easy-to-interpret figures!

u-Unwrap3D is a useful new computational to map 3D biological surfaces onto 2D for further analysis. The software is an exciting development, and it's awesome that the code has been made available on Github for use by a broader community of scientists. The ability to correlate signals from specific proteins (Septins) with particular cell surface curvatures is impressive. I don't have any feedback about the actual tool, except to say that I want to try it out! However, the results presented in the manuscript can be simplified in a way that helps the reader understand the utility of u-Unwrap3D. In the figures, some of utility of this new and exciting tool is buried among a lot of distracting detail. For example, the interesting Septin data is not immediately clear from studying Figure 4 without a detailed reading of the accompanying text. Could the authors come up with a way to more obviously connect the results in Figure 4B-4F to the mapping visualized in Figure 4A? Sometimes showing less can be more constructive for helping the reader understand the content.

It's awesome to identify the specific target of a kinase inhibitor! Such a clever experiment!

The kinase inhibitor screen described here is useful to identify kinases that coordinate cell proliferation in choanoflagellates. This chemical biology approach would also be incredibly useful to identify kinases involved in cell proliferation in other protists. The use of the ActivX probe in the context of a competitive inhibition assay is a clever approach to identify a specific target of a kinase inhibitor. A few questions for the authors:

1. How did you decide to focus your attention on kinases, given the vast diversity of enzymes in cell biology?
2. Related to question 1, have you considered similar screens with GTPase inhibitors or with other specific enzyme inhibitors?
3. Why did you choose to screen for cell proliferation versus other phenotypes?
4. Have you screened for kinase inhibitors that disrupt rosette formation?

I imagine that this technique will enable lots of researchers to perform similar chemical screens in other emerging research organisms.

I think you mean "pier".

Uranyl acetate acronym is undefined.

The correlative light and electron microscopy data in this work is absolutely amazing! I'm completely blown away by the isotropic and featureful volumetric segmentation! I wish I had more substantive and constructive feedback to provide, but I'm just impressed with the high the quality of the imaging data. I very much enjoyed looking through the data in the manuscript.

I have one major comment. I couldn't find the data on EMPIAR. I guess it hasn't been released publicly yet?

Besides that one comment I just have some minor, mainly editorial and stylistic, suggestions.

1. Watch out for acronyms. Make sure to define them so the reader can quickly understand what they are reading or looking at. For example, 2p-branding is not defined in the Figure 2 legend. I suggest sticking to either the 2p-branding or the NIR branding designation. They are used interchangeably in the text.

2. I suggest placing the scale bar in images in the first panel, instead of the last panel. See Figure 3. The reader will look at the figure from left to right, not right to left.

3. It would be helpful to the reader to label the different features that are shown in supplementary video 2.

4. Could you show a 3D rendering of all of the features shown in supplementary video 2? Currently individual components are rendered separately, but it would be useful to the reader to see the relative positions of the cellular components.

5. Could you speculate on what cellular components are being visualized by the green autofluorescence?

The authors found that the ant N. fulva expresses a lower abundance of cuticular hydrocarbon compounds compared to other ants, such as S. invicta. Half of the worker ants of N. fulva do not express the cuticular compound 2-tridecanone. The authors hypothesize that the lack of 2-tridecanone in half of the population enables the species to form supercolonies. In this model, lower levels of cuticular hydrocarbons lead to reduced discrimination of nestmates, enabling a higher ant density in the colony. The authors also hypothesize that there is a tradeoff to having lower cuticular hydrocarbons. The ants with lower hydrocarbons can achieve higher population densities but are more susceptible to desiccation. If this model is true, the N.fulva ants that do not express 2-tridecanone will die sooner from desiccation than the N.fulva ants that express the compound. Have the authors compared desiccation survival in the N.fulva ants that express 2-tridecanone, relative to ants of the same species that do not express the compound?

If the authors coat ants with 2-tridecanone, do the ants show higher survival in the desiccation assay?

Comment: Figure S2 contains useful information about the distribution of the amount of CHCs produced by worker ants. It is clear from the graph that there are many N.fulva ants that express low levels of CHC. This information is best shown in the main set of figures, as opposed to alongside accessory data in the supplement.

The authors developed an assay to measure the efficacy of molecules that protect against environmental stress. They measured the ability of specific disaccharides and proteins to preserve the function of Human Blood Clotting Factor VIII in a clotting assay after repeated cycles of desiccation. As expected sucrose and trehalose stabilize FVIII after repeated cycles of desiccation (Figure 2). Full length CAHS D, derived from a tardigrade, does not protect the function of FVIII (Fig 3). However, the linker region alone of CAHS D protects FVIII even at low concentrations (Fig 3). They find that other intrinsically disordered proteins have a mixed effect on FVIII protection. LEA1 protects FVIII from desiccation but Hero9 does not (Fig 4). They go on to measure the protection of FVIII under thermal stress. They have an interesting result whereby the CAHS D with a 2x linker protects FVIII from thermal stress (Fig 6) whereas the linker region alone of CAHSD had the most striking protection of FVIII under desiccation. I have some questions and suggestions for the authors.

Questions: 1. Could you speculate about the biophysical/biochemical mechanism by which the different CAHS D constructs confer desiccation or heat resistance? 2. Is it surprising that the construct that does not form a gel (Linker) is the one that confers the best desiccation resistance? 3. Is there a biophysical or biochemical explanation for how a gel-forming protein might confer heat resistance but not desiccation resistance? 4. If you compare the primary sequences or the domain structures of CAHS D, Hero9, and LEA1 are there any interesting similarities or differences that might explain the results you've obtained?

Comments: 1. Are you using vector graphics in the figures? It is very hard to read much of the text in the figures. This often occurs when using images for line art instead of vector graphics. 2. Figure 1 is not necessary or helpful. It would be more helpful to the reader to have a diagram depicting the actual assay being performed in the subsequent figures. 3. It would be helpful to know how many times each experiment was repeated. This could be reported in the figure legends. 4. It would also be helpful to readers to have a graphical summary of the results in a final figure that summarizes the protective effects of the various molecules tested.

To interpret the Raman spectra, as well as the positional differences in the spectra along the filaments, it would be helpful to the reader to see images of the filaments. How do the spectra relate to the images of the filaments?

Where is the data that supports this claim that one of the vegetative cells differentiated into a heterocyst?

Where is the data that supports this claim that one of the vegetative cells differentiated into a heterocyst?

To interpret the Raman spectra, as well as the positional differences in the spectra along the filaments, it would be helpful to the reader to see images of the filaments. How do the spectra relate to the images of the filaments?

The correlative light and electron microscopy data in this work is absolutely amazing! I'm completely blown away by the isotropic and featureful volumetric segmentation! I wish I had more substantive and constructive feedback to provide, but I'm just impressed with the high the quality of the imaging data. I very much enjoyed looking through the data in the manuscript.

I have one major comment. I couldn't find the data on EMPIAR. I guess it hasn't been released publicly yet?

Besides that one comment I just have some minor, mainly editorial and stylistic, suggestions.

1. Watch out for acronyms. Make sure to define them so the reader can quickly understand what they are reading or looking at. For example, 2p-branding is not defined in the Figure 2 legend. I suggest sticking to either the 2p-branding or the NIR branding designation. They are used interchangeably in the text.

2. I suggest placing the scale bar in images in the first panel, instead of the last panel. See Figure 3. The reader will look at the figure from left to right, not right to left.

3. It would be helpful to the reader to label the different features that are shown in supplementary video 2.

4. Could you show a 3D rendering of all of the features shown in supplementary video 2? Currently individual components are rendered separately, but it would be useful to the reader to see the relative positions of the cellular components.

5. Could you speculate on what cellular components are being visualized by the green autofluorescence?

Uranyl acetate acronym is undefined.

I think you mean "pier".

The authors developed an assay to measure the efficacy of molecules that protect against environmental stress. They measured the ability of specific disaccharides and proteins to preserve the function of Human Blood Clotting Factor VIII in a clotting assay after repeated cycles of desiccation. As expected sucrose and trehalose stabilize FVIII after repeated cycles of desiccation (Figure 2). Full length CAHS D, derived from a tardigrade, does not protect the function of FVIII (Fig 3). However, the linker region alone of CAHS D protects FVIII even at low concentrations (Fig 3). They find that other intrinsically disordered proteins have a mixed effect on FVIII protection. LEA1 protects FVIII from desiccation but Hero9 does not (Fig 4). They go on to measure the protection of FVIII under thermal stress. They have an interesting result whereby the CAHS D with a 2x linker protects FVIII from thermal stress (Fig 6) whereas the linker region alone of CAHSD had the most striking protection of FVIII under desiccation. I have some questions and suggestions for the authors.

Questions: 1. Could you speculate about the biophysical/biochemical mechanism by which the different CAHS D constructs confer desiccation or heat resistance? 2. Is it surprising that the construct that does not form a gel (Linker) is the one that confers the best desiccation resistance? 3. Is there a biophysical or biochemical explanation for how a gel-forming protein might confer heat resistance but not desiccation resistance? 4. If you compare the primary sequences or the domain structures of CAHS D, Hero9, and LEA1 are there any interesting similarities or differences that might explain the results you've obtained?

Comments: 1. Are you using vector graphics in the figures? It is very hard to read much of the text in the figures. This often occurs when using images for line art instead of vector graphics. 2. Figure 1 is not necessary or helpful. It would be more helpful to the reader to have a diagram depicting the actual assay being performed in the subsequent figures. 3. It would be helpful to know how many times each experiment was repeated. This could be reported in the figure legends. 4. It would also be helpful to readers to have a graphical summary of the results in a final figure that summarizes the protective effects of the various molecules tested.

The authors found that the ant N. fulva expresses a lower abundance of cuticular hydrocarbon compounds compared to other ants, such as S. invicta. Half of the worker ants of N. fulva do not express the cuticular compound 2-tridecanone. The authors hypothesize that the lack of 2-tridecanone in half of the population enables the species to form supercolonies. In this model, lower levels of cuticular hydrocarbons lead to reduced discrimination of nestmates, enabling a higher ant density in the colony. The authors also hypothesize that there is a tradeoff to having lower cuticular hydrocarbons. The ants with lower hydrocarbons can achieve higher population densities but are more susceptible to desiccation. If this model is true, the N.fulva ants that do not express 2-tridecanone will die sooner from desiccation than the N.fulva ants that express the compound. Have the authors compared desiccation survival in the N.fulva ants that express 2-tridecanone, relative to ants of the same species that do not express the compound?

If the authors coat ants with 2-tridecanone, do the ants show higher survival in the desiccation assay?

Comment: Figure S2 contains useful information about the distribution of the amount of CHCs produced by worker ants. It is clear from the graph that there are many N.fulva ants that express low levels of CHC. This information is best shown in the main set of figures, as opposed to alongside accessory data in the supplement.

The kinase inhibitor screen described here is useful to identify kinases that coordinate cell proliferation in choanoflagellates. This chemical biology approach would also be incredibly useful to identify kinases involved in cell proliferation in other protists. The use of the ActivX probe in the context of a competitive inhibition assay is a clever approach to identify a specific target of a kinase inhibitor. A few questions for the authors:

1. How did you decide to focus your attention on kinases, given the vast diversity of enzymes in cell biology?
2. Related to question 1, have you considered similar screens with GTPase inhibitors or with other specific enzyme inhibitors?
3. Why did you choose to screen for cell proliferation versus other phenotypes?
4. Have you screened for kinase inhibitors that disrupt rosette formation?

I imagine that this technique will enable lots of researchers to perform similar chemical screens in other emerging research organisms.

It's awesome to identify the specific target of a kinase inhibitor! Such a clever experiment!