Reviewer #2 (Public Review):

The short-term administration of reprogramming factors to partially reprogram cells has gained traction in recent years as a potential strategy to reverse aging in cells and organisms. Early studies used Yamanaka factors in transgenic mice to reverse aging phenotypes, but chemical cocktails could present a more feasible approach for in vivo delivery. In this study, Mitchell et al sought to determine the effects that short-term administration of chemical reprogramming cocktails have on biological age and function. To address this question, they treated young and old mouse fibroblasts with chemical reprogramming cocktails and performed transcriptome, proteome, metabolome, and DNA methylation profiling pre- and post-treatment. For each of these datasets, they identified changes associated with treatment, showing downregulation of some previously identified molecular signatures of aging in both young and old cells. From these data, the authors conclude that partial chemical reprogramming can rejuvenate both young and old fibroblasts.

The main strength of this study is the comprehensive profiling of cells pre- and post-treatment with the reprogramming cocktails, which will be a valuable resource for better understanding the molecular changes induced by chemical reprogramming. The authors highlighted consistent changes across the different datasets that are thought to be associated with aging phenotypes, showing reduction of age-associated signatures previously identified in various tissues. However, from the findings, it remains unclear which changes are functionally relevant in the specific fibroblast system being used. Specifically:

1) The 4 month and 20 month mouse fibroblasts are designated "young" vs "old" in this study. An important analysis that was not shown for each of the profiled modalities was a comparison of untreated young vs old fibroblasts to determine age-associated molecular changes in this specific model of aging. Then, rather than using aging signatures defined in other tissues, it would be more appropriate to determine whether the chemical cocktails reverted old fibroblasts to a younger state based on the age-associated changes identified in this comparison.<br /> 2) Across all datasets, it appears that the global profiles of young vs old mouse fibroblasts are fairly similar compared to treated fibroblasts, suggesting that the chemical cocktails are not reverting the fibroblasts to a younger state but instead driving them to a different cell state. Similarly, in most cases where specific age-related processes/genes are being compared across untreated and treated samples, no significant differences are observed between young and old fibroblasts.<br /> 3) Functional validation experiments to confirm that specific changes observed after partial reprogramming are indeed reducing biological age is limited.<br /> 4) Partial reprogramming appears to substantially reduce biological age of the young (4 month) fibroblasts based on the aging signatures used. It is unclear how this result should be interpreted.

Reviewer #1 (Public Review):

Summary:<br /> In this manuscript, Unckless and colleagues address the issue of the maintenance of genetic diversity of the gene diptericin A, which encodes an antimicrobial peptide in the model organism Drosophila melanogaster.

Strengths:<br /> The data indicate that flies homozygous for the dptA S69 allele are better protected against some bacteria. By contrast, male flies homozygous for the R69 allele better resist starvation than flies homozygous for the S69 allele.

Weaknesses:<br /> -I am surprised by the inconsistency between the data presented in Fig. 1A and Fig. S2A for the survival of male flies after infection with P. rettgeri. I am not convinced that the data presented support the claim that females have lower survival rates than males when infected with P. rettgeri (lines 176-182).

-The data in Fig. 2 do not seem to support the claim that female flies with either the dptA S69 or the R69 alleles have a longer lifespan than males (lines 211-215). A comment on the [delta] dpt line, which is one of the CRISPR edited lines, would be welcome.

-The data in Fig. 2B show that male flies with the dptA S69 or R69 alleles have the same lifespan when poly-associated with L. plantarum and A. tropicalis, which contradicts the claim of the authors (lines 256-260).

Reviewer #2 (Public Review):

Summary: In this study, the authors delve into the mechanisms responsible for the maintenance of two diptericin alleles within Drosophila populations. Diptericin is a significant antimicrobial peptide that plays a dual role in fly defense against systemic bacterial infections and in shaping the gut bacterial community, contributing to gut homeostasis.

Strengths: The study unquestionably demonstrates the distinct functions of these two diptericin alleles in responding to systemic infections caused by specific bacteria and in regulating gut homeostasis and fly physiology. Notably, these effects vary between male and female flies.

Weaknesses: Although the findings are highly intriguing and shed light on crucial mechanisms contributing to the preservation of both diptericin alleles in fly populations, a more comprehensive investigation is warranted to dissect the selection mechanisms at play, particularly concerning diptericin's roles in systemic infection and gut homeostasis. Unfortunately, the results from the association study conducted on wild-caught flies lack conclusive evidence.

Major Concerns:

Lines 120-134: The second hypothesis is not adequately defined or articulated. Please revise it to provide more clarity. Additionally, it should be explicitly stated that the first part of the first hypothesis (pathogen specificity), i.e., the superior survival of the S allele in Providencia infections compared to the R allele, has been previously investigated and supported by the results in the Unkless et al. 2016 paper. The current study aims to additionally investigate the opposite scenario: whether the R allele exhibits better survival in a different infection. Please consider revising to emphasize this point.

Figures and statistical analyses: It is essential to present the results of significant differences from the statistical analyses within Figures 1B, 2B, and 3. Additionally, please include detailed descriptions of the statistical analysis methods in the figure legends. Specify whether the error bars represent standard error or standard deviation, particularly in Figure 3, where assays were conducted with as few as 3 flies.

Lines 317-318 (as well as 320-328): The data related to P. rettgeri appear somewhat incomplete, and the authors acknowledge that bacterial load varies significantly, and this bacterium establishes poorly in the gut. These data may introduce more noise than clarity to the study. Please consider revising these sections by either providing more data, refining the presentation, or possibly removing them altogether.

Lines 335-387 and Figure 4: Although these results are intriguing and suggest interactions between functional diptericin and fly physiology, some mediated by the gut microbiome, they remain descriptive and do not significantly contribute to our understanding of the mechanism that maintains the diptericin alleles.

Lines 399-400: The contrast between this result and statement and the highly reproducible data presented in Figures 2-4 should be discussed.

Lines 422-429 and Figure 5D: The conclusion regarding an association between diptericin alleles and Morganellaceae bacteria is not clearly supported by Figure 5D and lacks statistical evidence.

Reviewer #3 (Public Review):

Summary:<br /> This paper investigates the evolutionary aspects around a single amino acid polymorphism in an immune peptide (the antimicrobial peptide Diptericin A) of Drosophila melanogaster. This polymorphism was shown in an earlier population genetic study to be under long-term balancing selection. Using flies with different AA at this immune peptide it was found that one allelic form provides better survival of systemic infections by a bacterial pathogen, but that the alternative allele provides its carriers a longer lifespan under certain conditions (depending on the microbiota). It is suggested that these contrasting fitness effects of the two alleles contribute to balance their long-term evolutionary fate.

Strengths:<br /> The approach taken and the results presented are interesting and show the way forward for studying such polymorphisms experimentally.

Weaknesses:<br /> 1. A clear demonstration (in one experiment) that the antagonistic effect of the two selection pressures isolated is not provided.

The study is overwhelming with many experiments and countless statistical tests. The overall conclusion of the many experiments and tests suggests that "dptS69 flies survive systemic infection better, while dptS69R flies survive some opportunistic gut infections better." (line 444-446). Given the number of results, different experiments, and hundreds of tests conducted, how can we make sure that the result is not just one of many possible combinations? I suggest experimentally testing this conclusion in one experiment (one may call this the "killer-experiment") with the relevant treatments being conducted at the same time, side by side, and the appropriate statistical test being conducted by a statistical test for a treatment x genotype interaction effect.

2. The implication that the two forms of selection acting on the immune peptide are maintained by balancing selection is not supported.

The picture presented about how balancing selection is working is rather simplistic and not convincing. In particular, it is not distinguished between fluctuating selection (FL) and balancing selection (BL). BL is the result of negative frequency-dependent selection. It may act within populations (e.g. Red Queen type processes, mating types) or between populations (local adaptation). FL is a process that is sometimes suggested to produce BL, but this is only the case when selection is negative frequency dependent. In most cases, FL does not lead to BL.

The presented study is introduced with a framework of BL, but the aspects investigated are all better described as FL (as the title says: "A suite of selective pressures ..."). The two models presented in the introduction (lines 62 to 69; two pathogens, cost of resistance) are both examples for FL, not for BL.

Finally, no evidence is presented that the different selection pressures suggested to select on the different allelic forms of the immune peptide are acting to produce a pattern of negative frequency dependence.

Reviewer #1 (Public Review):

Summary:<br /> This interesting study applies the PSMC model to a set of new genome sequences for migratory and nonmigratory thrushes and seeks to describe differences in the population size history among these groups. The authors create a set of summary statistics describing the PSMC traces - mean and standard deviation of Ne, plus a set of metrics describing the shape of the oldest Ne peak - and use these to compare across migratory and resident species (taking single samples sequenced here as representative of the species). The analyses are framed as supporting or refuting aspects of a biogeographic model describing colonization dynamics from tropical to temperate North and South America.

Strengths:<br /> At a technical level, the sequencing and analysis up through PSMC looks good and the paper is engaging and interesting to read as an introduction to some verbal biogeographic models of avian evolution in the Pleistocene. The core findings - higher and more variable Ne in migratory species - seem robust, and the biogeographic explanation is plausible.

Weaknesses:<br /> I did not find the analyses particularly persuasive in linking specific aspects of clade-level PSMC patterns causally to evolutionary driving forces. To their credit, the authors have anticipated my main criticism in the discussion. This is that variation in population size inferred by methods like PSMC is in "effective" terms, and the link between effective and census population size is a morass of bias introduced by population structure and selection so robustly connecting specific aspects of PSMC traces to causal evolutionary forces is somewhere between extremely difficult and impossible.

Population structure is the most obvious force that can generate large Ne changes mimicking the census-size-focused patterns the authors discuss. The authors argue in the discussion that since they focus on relatively deep time (>50kya at least, with most analyses focusing on the 5mya - 500kya range) population structure is "likely to become less important", and the resident species are usually more structured today (true) which might bias the findings against the observed higher Ne in migrants.

But is structure really unimportant in driving PSMC results at these specific timescales? There is no numerical analysis presented to support the claim in this paper. The biogeographic model of increased temperate-latitude land area supporting higher populations could yield high Ne via high census size, but shifts in population structure (for example, from one large panmictic population to a series of isolated refugial populations as a result of glaciation-linked climate changes) could plausibly create elevated and more variable Ne. Is it more land area and ecological release leading to a bigger and faster initial Ne bump, or is it changes in population connectivity over time at expanding range edges, or is the whole single-bump PSMC trace an artifact of the dataset size, or what? The authors have convinced me that the Ne history of migratory thrushes is on average very different from nonmigrant thrushes, but beyond that it's unclear what exactly we've learned here about the underlying process.

I generally agree with the authors that "at present there is no way to fully disentangle the effects of population structure and geographic space on our results". But given that, I think there are two options - either we can fully acknowledge that oversimplified demographic models like PSMC cannot be interpreted as supporting evidence of any particular mechanistic or biogeographic hypothesis and stop trying to use them to do that, or we have to do our best to understand specifically which models can be distinguished by the analyses we're employing.

Short of developing some novel theory deep in the PSMC model, I think readers would need to see simulations showing that the analyses employed in this paper are capable of supporting or refuting their biogeographic hypothesis before viewing them as strongly supporting a specific biogeographic model. Tools like msprime and stdpopsim can be used to simulate genome-scale data with fairly complex biogeographic models. Running simulations of a thrush-like population under different biogeographic scenarios and then using PSMC to differentiate those patterns would be a more convincing argument for the biogeographic aspects of this paper. The other benefit of this approach would be to nail down a specific quantitative version of the taxon cycles model referenced in the abstract, and it would allow the authors to better study and explain the motivation behind the specific summary statistics they develop for PSMC posthoc analysis.

Reviewer #2 (Public Review):

Summary:<br /> Winker and Delmore present a study on the demographic consequences of migratory versus resident behavior by contrasting the evolutionary history of lineages within the same songbird group (thrushes of the genus Catharus).

Strengths:<br /> I appreciate the test-of-hypothesis design of the study and the explicit formulation of three main expectations to test. The data analysis has been done with appropriate available tools.

Weaknesses:<br /> The current version of the paper, with the case study chosen, the results, and the relative discussion, is not satisfying enough to support or reject the hypotheses here considered.

The authors hypothesized that the wider realized breeding and ecological range characterising migrants versus resident lineages could be a major drive for increased effective population size and population expansion in migrants versus residents. I understand that this pattern (wider range in migrants) is a common characteristic across bird lineages and that it is viewed as a result of adapting to migration. A problem that I see in their dataset is that the breeding grounds range of the two groups are located in very different geographic areas (mainly South versus North America). The authors could have expanded their dataset to include species whose breeding grounds are from the two areas, regardless of their migratory behaviour, as a comparison to disentangle whether ecological differences of these two areas can affect the population sizes or growth rates.

As I understand from previous literature, the time-scale to population growth and estimates of effective population sizes considered in the present paper for the resident versus migratory clades seem to widely predate the times to speciation for the same lineages, which were reported in previous work of the same authors (Everson et al 2019) and others (Termignoni-Garcia et al 2022). This piece of information makes the calculation of species-specific population size changes difficult to interpret in the light of lineages' comparison. It is unclear what the authors consider to be lineage-specific in these estimates, as the clades were likely undergoing substantial admixture during the time predating full isolation.

Regarding the methodological difficulties in interpreting the impact of population structure on the estimates of effective population sizes with the PSMC approach, I would think that performing simulations to compare different scenarios of different degrees of structured populations would have helped substantially understand some of the outcomes.

Additionally, I have struggled to understand if migratory behaviour in birds is considered to be acquired to relieve species competition, or as a consequence of expanded range (i.e., birds expand their range but their feeding ground is kept where speciation occurred as to exploit a ground with higher quality and abundance of seasonal local resources).

The points raised above could be considered to improve the current version of the paper.

Reviewer #3 (Public Review):

Summary:<br /> This paper applies PSMC and genomic data to test interesting questions about how life history changes impact long-term population sizes.

Strengths:<br /> This is a creative use of PSMC to test explicit a priori hypotheses about season migration and Ne. The PSMC analyses seem well done and the authors acknowledge much of the complexity of interpretation in the discussion.

Weaknesses:<br /> The authors use an average generation time for all taxa, but the citations imply generation time is known for at least some of them. Are there differences in generation time associated with migration? I am not a bird biologist, but quick googling suggests maybe this is the case (https://doi.org/10.1111/1365-2656.13983). I think it important the authors address this, as differences in generation time I believe should affect estimates of Ne and growth.

The writing could be improved, both in the introduction for readers not familiar with the system and in the clarity and focus of the discussion.

Reviewer #1 (Public Review):

The manuscript has helped address a long-standing mystery in splicing regulation: whether splicing occurs co- or post-transcriptionally. Specifically, the authors (1) uniquely combined smFISH, expansion microscopy, and live cell imaging; (2) revealed the ordering and spatial distribution of splicing steps; and (3) discovered that nascent, not-yet-spliced transcripts move more slowly around the transcription site and undergo splicing as they move through the clouds. Based on the experimental results, the authors suggest that the observation of co-transcriptional splicing in previous literature could be due to the limitation of imaging resolution, meaning that the observed co-transcriptional splicing might actually be post-transcriptional splicing occurring in proximity to the transcription site. Overall, the work presented here clearly provides a comprehensive picture of splicing regulation.

Major points:<br /> 1. Linearity of expansion microscopy. For Figure 2B, it would be helpful to display the same sample before and after expansion, just like Supplementary Figure 3, but with a transcription site and "cloud". In the current version, the transcription site looks quite different in the not-expanded (more green dots on the left) and expanded image (more green dots on the top).

2. FISH dot colocalization. What is the colocalization rate of FISH dots in general under experimental conditions? In addition, in Figures 2C and 2G, why do some 3'exon dots not have co-localized 5'exon dots?

3. It would be helpful if the authors uploaded a few examples of live cell imaging movies.

4. It is recommended to double-check the text for errors.

Reviewer #2 (Public Review):

Allison Coté et al. investigated the ordering and spatial distribution of nascent transcripts in several cells using smFISH, expansion microscopy, and live-cell imaging. They find that pre-mRNA splicing occurs post-transcriptionally at the clouds around the transcription start site, termed the transcription site proximal zone. They show that pre-mRNA may undergo continuous splicing when they pass through the zone after transcription. These data suggest a unifying model for explaining previously reported co-transcriptional splicing events and provide a direction for further study of the nature of the slow-moving zone around the transcription start site.

This paper is well-written. The findings are very important, and the data supports the conclusions well. However, some aspects of the image and description need to be clarified and revised.

The authors describe Figure 4E and 4F results in the main text as that "we performed RNA FISH simultaneously with immunofluorescence for SC35, a component of speckles, and saw that this compartmentalized pre-mRNA did indeed appear near nuclear speckles both before (Supplementary Figure 6C) and after (Figure 4E) splicing inhibition." However, no SC35 staining is shown in the Figure 4E. A similar situation happened in describing Figure 4F.

Reviewer #1 (Public Review):

Summary:<br /> The authors use a combination of biochemistry and cryo-EM studies to explore a complex between the cap-binding complex and an RNA binding protein, ALYREF, that coordinates mRNA processing and export.

Strengths:<br /> The biochemistry and structural biology are supported by mutagenesis which tests the model in vitro. The structure provides new insight into how key events in RNA processing and export are likely to be coordinated.

Weaknesses:<br /> The authors provide biochemical studies to confirm the interactions that they identify; however, they do not perform any studies to test these models in cells or explore the consequences of mRNA export from the nucleus. In fact, several of the amino acids that they identified in ALYREF that are critical for the interaction, as determined by their own biochemical studies, are conserved in budding yeast Yra1 (residues E124/E128 are E/Q in budding yeast and residues Y135/V138/P139 are F/S/P), where the impact on poly(A) RNA export from the nucleus could be readily evaluated. The authors could at least mention this point as part of the implications and the need for future studies. No one seems to have yet targeted any of these conserved residues, so this would be a logical extension of the current work.

Specific suggestions:<br /> The authors could put their work in context by speculating how some of the amino acids that they identify as being critical for the interactions they identify could contribute to cancer. For example, they mention mutations of interacting residues in NCBP2 are associated with human cancers, pointing out that NCBP2 R105C amino acid substitution has been reported in colorectal cancer and the NCBP2 I110M mutation has been found in head and neck cancer. Do the authors speculate that these changes would decrease the interaction between NCBP2 and ALYREF and, if so, how would this contribute to cancer? They also mention that a K330N mutation in NCBP1 in human uterine corpus endometrial carcinoma, where Y135 on the α2 helix of mALYREF2 makes a hydrogen bond with K330 of NCBP1. How do they speculate loss of this interaction would contribute to cancer?

Reviewer #2 (Public Review):

Summary:<br /> In this manuscript, Bradley and his colleagues represented the cryo-EM structure of the nuclear cap-binding complex (CBC) in complex with an mRNA export factor, ALYREF, providing a structural basis for understanding CBC regulating gene expression.

Strengths:<br /> The authors successfully modeled the N-terminal region and the RRM domain of ALYREF (residues 1-183) within the CBC-ALYREF structure, which revealed that both the NCBP1 and NCBP2 subunits of the CBC interact with the RBM domain of ALYREF. Further mutagenesis and pull-down studies provided additional evidence to the observed CBC-ALYREF interface. Additionally, the authors engaged in a comprehensive discussion regarding other cellular complexes containing CBC and/or ALYREF components. They proposed potential models that elucidated coordinated events during mRNA maturation. This study provided good evidence to show how CBC effectively recruits mRNA export factor machinery, enhancing our understanding of CBC regulating gene expression during mRNA transcription, splicing, and export.

Weaknesses:<br /> No in vivo or in vitro functional data to validate and support the structural observations and the proposed models in this study. Cryo-EM data processing and structural representation need to be strengthened.

Reviewer #3 (Public Review):

Summary:<br /> The authors carried out structural and biochemical studies to investigate the multiple functions of CBC and ALYREF in RNA metabolism.

Strengths:<br /> For the structural study part, the authors successfully revealed how NCBP1 and NCBP2 subunits interact with mALYREF (residues 1-155). Their binding interface was then confirmed by biochemical assays (mutagenesis and pull-down assays) presented in this study.

Weaknesses:<br /> The authors did not provide functional data to support their proposed models. The authors should include more details regarding the workflow of their cryo-EM data processing in the figure.

Reviewer #1 (Public Review):

Summary:<br /> Kinase inhibitors represent a highly valuable class of drugs as evidenced by their continued clinical success. The target landscape of kinase targeting small molecules can be leveraged to alter multiple phenotypes with increasing complexity that broadly aligns with increasing target promiscuity. This 'tools and resources' contribution provides a starting point for researchers interested in aligning kinase inhibitor activity with cytokine/chemokine stimulated signal transduction networks.

Strengths:<br /> KinCytE is a forward-thinking database that yields hypothesis-generating options for researchers interested in pharmacologically modulating cytokine/chemokine signaling.

Weaknesses:<br /> As a 'tools and resources' contribution, the primary (potential) weakness will be the authors' willingness to update and improve the tool. KinCytE will require frequent updating to better inform users in terms of contextual cytokine/chemokine stimulated signaling and the target landscape of those agents that are included as options.

Reviewer #2 (Public Review):

Summary:<br /> In this manuscript, "KinCytE- a Kinase to Cytokine Explorer to Identify Molecular Regulators and Potential Therapeutic", the authors present a web resource, KinCytE, that lets researchers search for kinase inhibitors that have been shown to affect cytokine and chemokine release and signaling networks. I think it's a valuable resource that has a lot of potential and could be very useful in deciding on statistical analysis that might precede lab experiments.

Opportunities:<br /> With the release of the manuscript and the code base in place, I hope the authors continue to build upon the platform, perhaps by increasing the number of cell types that are probed (beyond macrophages). Additionally, when new drug-response data becomes available, perhaps it can be used to further validate the findings. Overall, I see this as a great project that can evolve.

Strengths:<br /> The site contains valuable content, and the structure is such that growing that content should be possible.

Weaknesses:<br /> Only based on macrophage experiments, would be nice to have other cell types investigated, but I'm sure that will be remedied with some time.

Reviewer #1 (Public Review):

Summary:

This work describes a new method for sequence-based remote homology detection. Such methods are essential for the annotation of uncharacterized proteins and for studies of protein evolution.

Strengths:

The main strength and novelty of the proposed approach lies in the idea of combining state-of-the-art sequence-based (HHpred and HMMER) and structure-based (Foldseek) homology detection methods with recent developments in the field of protein language models (the ESM2 model was used). The authors show that features extracted from high-dimensional, information-rich ESM2 sequence embeddings can be suitable for efficient use with the aforementioned tools.

The reduced features take the form of amino acid occurrence probability matrices estimated from ESM2 masked-token predictions, or structural descriptors predicted by a modified variant of the ESM2 model. However, we believe that these should not be called "embeddings" or "representations". This is because they don't come directly from any layer of these networks, but rather from their final predictions.

The benchmarks presented suggest that the approach improves sensitivity even at very low sequence identities <20%. The method is also expected to be faster because it does not require the computation of multiple sequence alignments (MSAs) for profile calculation or structure prediction.

Weaknesses:

The benchmarking of the method is very limited and lacks comparison with other methods. Without additional benchmarks, it is impossible to say whether the proposed approach really allows remote homology detection and how much improvement the discussed method brings over tools that are currently considered state-of-the-art.

Reviewer #2 (Public Review):

Summary:

The authors present a number of exploratory applications of current protein representations for remote homology search. They first fine-tune a language model to predict structural alphabets from sequence and demonstrate using these predicted structural alphabets for fast remote homology search both on their own and by building HMM profiles from them. They also demonstrate the use of residue-level language model amino acid predicted probabilities to build HMM profiles. These three implementations are compared to traditional profile-based remote homology search.

Strengths:

- Predicting structural alphabets from a sequence is novel and valuable, with another approach (ProstT5) also released in the same time frame further demonstrating its application for the remote homology search task.<br /> - Using these new representations in established and battle-tested workflows such as MMSeqs, HMMER, and HHBlits is a great way to allow researchers to have access to the state-of-the-art methods for their task.<br /> - Given the exponential growth of data in a number of protein resources, approaches that allow for the preparation of searchable datasets and enable fast search is of high relevance.

Weaknesses:

- The authors fine-tuned ESM-2 3B to predict 3Di sequences and presented the fine-tuned model ESM-2 3B 3Di with a claimed accuracy of 64% compared to a test set of 3Di sequences derived from AlphaFold2 predicted structures. However, the description of this test set is missing, and I would expect repeating some of the benchmarking efforts described in the Foldseek manuscript as this accuracy value is hard to interpret on its own.<br /> - Given the availability of predicted structure data in AFDB, I would expect to see a comparison between the searches of predicted 3Di sequences and the "true" 3Di sequences derived from these predicted structures. This comparison would substantiate the innovation claimed in the manuscript, demonstrating the potential of conducting new searches solely based on sequence data on a structural database.<br /> - The profile HMMs built from predicted 3Di appear to perform sub-optimally, and those from the ESM-2 3B predicted probabilities also don't seem to improve traditional HMM results significantly. The HHBlits results depicted in lines 5 and 6 in the figure are not discussed at all, and a comparison with traditional HHBlits is missing. With these results and presentation, the advantages of pLM profile-based searches are not clear, and more justification over traditional methods is needed.<br /> - Figure 3 and its associated text are hard to follow due to the abundance of colors and abbreviations used. One figure attempting to explain multiple distinct points adds to the confusion. Suggestion: Splitting the figure into two panels comparing (A) Foldseek-derived searches (lines 7-10) and (B) language-model derived searches (line 3-6) to traditional methods could enhance clarity. Different scatter markers could also help follow the plots more easily.<br /> - The justification for using Foldseek without amino acids (3Di-only mode) is not clear. Its utility should be described, or it should be omitted for clarity.<br /> - Figure 2 is not described, unclear what to read from it.

Reviewer #1 (Public Review):

Summary:<br /> There has been substantial prior work trying to understand the transcriptional control of proteasome expression as an adaptive response to proteasome inhibition. This field has been mired by fierce debates over the role of the protease Ddi2 in activating the transcription factor Nrf1/NFE2L1. As the authors of this manuscript point out, most of the previous research centers on the continuous treatment of cells with proteasome inhibitors rather than a brief pulse of inhibition that better models the situation when these drugs are used clinically. The authors find that the initial recovery of proteasome activity is independent of Ddi2 and involves a mechanism distinct from transcription. The authors intriguingly point to a model in which the assembly of proteasomes is regulated. If true, this would be a significant finding, but for now, this model remains more speculative.

Strengths:<br /> The pulsed treatment of proteasome inhibitors is a strength of this lab that few others use. It better mimics the clinical use of these inhibitors and allows for a more detailed analysis of the initial response to inhibition. The authors have used multiple different clones of Ddi2 knockouts and siRNA against Ddi2 to rule out the necessity of Ddi2 in the early production of proteasomes when cells are inhibited with proteasomes. establishing a thorough knockout approach while also avoiding compensatory mutations. These experiments are well controlled showing both the levels of Ddi2 upon knockout or knockdown and demonstration that cleavage of Nrf1, one of two known targets of Ddi2, is impaired. However, it should be noted that even in the knockout residual bands for Ddi2 remain. Since these HAP1 cells only have one copy of the Ddi2 gene, it is possible that this other band could be Ddi1, a very similar paralogue. If so the conclusions of Ddi2-like activity with Ddi1 must be tempered and rely more on the data with Nrf1 knockdowns.

This article sensitively monitors the recovery of proteasome function with the β5 activity assay and for the production of new proteasome transcripts by Q-PCR. This precision coupled with detailed analysis of the timing are strengths that pointed to a more rapid recovery than transcription alone.

Weaknesses:<br /> This paper's major weakness is the difficulty in establishing the authors' model that assembly is regulating this process. They do a convincing job demonstrating that activity recovers before transcription. The evidence that translation is not affected depends entirely on the polysome RNA profiling from two replicates. Clearer and orthogonal data would help establish this finding. The stability of subunits is interesting and important in its own right. However, the clustering of proteins is somewhat unusual. The authors include PSMB8, an immuno-proteasome subunit that is not regulated by Nrf1. The proteins highlighted in green are an unusual assortment of alternative activators (PSME1-3), a ubiquitin-binding protein (ADRM1), and proteasome chaperones (PSMG1-2). Similarly, the purple proteins are not just proteins in the 19S regulatory particle but also assembly chaperones. However, these labeling issues do not detract from the conclusions of this figure.

In short, the authors establish that Ddi2 is not necessary for the initial, non-transcriptional, recovery of proteasome activity after a pulse of proteasome inhibition.

It is not clear what clinical impact this work will have. Although it models the pulse of proteasome inhibition more perfectly, it only looks at a single pulse rather than multiple treatments. Thus, ruling Ddi2's importance out for clinical benefit may be premature. More significantly this work suggests that the assembly of proteasomes might be a regulated process worth substantial follow-up that will be interesting to follow.

Reviewer #2 (Public Review):

Summary:<br /> In this work, Ibtisam and Kisselev explore the role of DDI2 in proteasome function recovery after a clinically relevant pulse dosing using different proteasome inhibitors and their corresponding PK properties. The authors report that despite the lack of NRF1 activation by DDI2 there was no difference in recovery from pulsed proteasome inhibition observed in DDI2 KO cells as compared to WT controls suggesting that DDI2 is not required for recovery in this system. They further show that transcription of the proteasome subunits is initiated only after partial recovery of proteasome activity is already observed suggesting that non-transcriptional mechanisms might be also involved. The authors further show that translation inhibition blocked the recovery from proteasome inhibitors.

Strengths:<br /> Overall, it is very important and informative to use a pulse treatment type approach (mimicking the PK properties of the drugs) to explore the biology of PIs as used in this study. The authors also provide convincing data that DDI2 is not required for proteasome activity recovery post-PI pulse treatment in the systems they explored.

Weaknesses:<br /> Many of the other conclusions are not supported by the data in the current form of the manuscript and are too speculative and ignore the major findings in the field that can present alternative mechanisms. In particular, the authors discuss the "levels" of the proteasomes post-PI treatment without measuring the actual protein level of the individual subunits or the different assembled proteasome complexes.

Reviewer #3 (Public Review):

Summary:<br /> In their manuscript "Recovery of proteasome activity in cells pulse-treated with proteasome inhibitors is independent of DDI2", Ibtisam and Kisselev investigate proteasome recovery in HAP1 cells either WT or DDI2 KO upon inhibition of proteasome via bortezomib or carfilzomib. The authors argue that proteasome recovery is independent of DDI2 as it is independent of the novo proteasome subunit synthesis. They argue recovery is dependent on the assembly of already synthesized proteasome subunits.

Strengths:<br /> The findings are important as they provide insight into a transcriptionally-independent proteasome stress recovery that is likely applicable across distinct cellular subtypes. Comparable proteasome recovery early on (<12 hours) from proteasomal inhibition in DDI2 KO cell lines was already noted in other manuscripts, including Chen et al, suggesting that this phenomenon is applicable to other histotypes.

Weaknesses:<br /> Some of the conclusions are not adequately supported by the data and how generalizable these findings are is unclear. In particular, there is concern regarding the status of the ubiqutin-proteasome-system in the HAP1 cell line that was used for these studies. In a previously published model system, a dependency on DDI2 and NRF1 was clearly demonstrated and this pathway was critical for late (12-24 hours) proteasome recovery as well as cell viability. The model system used here (HAP1 cells) seems completely independent of DDI2 both for proteasome recovery and viability as curves are substantially overlapping. It would be important to assess how the baseline proteasome activity in HAP1 cells compare to other cell lines and model system as these cells may be largely independent of proteasome degradation and their synthetic load on the pathway very modest.

It would also be relevant to look at later time points of proteasome recovery as one would expect DDI2 to play a role later on in the recovery of proteasome. the authors may have missed that time point as cells do not appear to recover close to 100% proteasome activity by 24 hours not even when the smallest concentration of carfilzomib is used.

A critical experiment to look at de novo proteasome assembly was not carried out, leaving the data hypothetical.

Finally, the authors leverage HAP1 cells for their work and should be mindful of not generalizing findings or disputing other author's conclusions in the absence of adequate experiments to support their hypothesis.

Reviewer #3 (Public Review):

Youssef et al. have used a range of markers to identify cancer stem cells (CSCs) in patients with oral cancers. CSCs were identified in lab conditions and were often linked to the invasiveness of cancers. The authors found a combination of markers convincingly liked to known biology and found cells expressing them in the invading cancers.<br /> The major weakness of the paper is in the technical side. There isn't enough description as to how they discriminated between CSCs inside the tumour and those invading its surroundings. Similarly, the way the information is presented it is not clear why artificial intelligence was needed to enhance the accuracy of the method linking CSCs to cancer invasion (and ultimately deadly metastasis to other organs).

Reviewer #1 (Public Review):

This is a valuable study that convincingly demonstrates that quantification of EpCAM+/CD24+/Vimentin+ cells in the stroma of human oral cancers followed by machine learning algorithms can be used as a prognostic indicator of metastasis.

This manuscript explores the utility of detecting a population of EpCAM+/CD24+/Vimentin+ cells in the stroma of human oral cancers as a prognostic indicator of metastasis. This follows work from the group showing that these cells manifest EMT plasticity. The authors used standard analyses and then machine learning algorithms on a test cohort of 24 patients and then a validation cohort of 60. Overall the staining seems clean, and the presence of these cells does seem to be predictive in a cohort of oral cancer patients.

The authors have addressed previous comments, adding additional patients and streamlining the work to focus on one hypothesis.

An additional validation set would enhance the work.

The authors should include clinical data for all samples used.

Reviewer #2 (Public Review):

It is recommended to use a blind sample test to determine the specimen's status using the AI they developed.<br /> Where these markers promote tumorigenesis or metastasis if tested in vivo?<br /> The article would be very valuable in the future to promote using AI to predict disease status and facilitate cancer screening.<br /> Much more improvement is required for data validation and presentation.

Reviewer #1 (Public Review):

The authors aimed to understand whether the superficial, retinorecipient layers of the mouse superior colliculus (sSC) participate in figure-ground segregation and object recognition. To address this question, they use a combination of optogenetic perturbations of sSC and recordings. These data are consistent with SC being causally involved in object recognition. This would be useful information for the field and likely to be cited. However, I have several concerns regarding their conclusions.

A significant limitation of this study is methodological. The major novelty is the effect of optogenetic silencing, because the recordings are largely correlative, but the optogenetic silencing approach lacks appropriate controls for the effects of the optogenetic excitation light. The authors acknowledge that the optogenetic light is a potential confound, but attempt to address this by shielding the fiber to eliminate light leak and strobing a blue led in the arena. The former does not account for the effects of excitation light scattering intracerebrally--during optogenetic experiments, intracerebral scattering causes the eyes to light up--and for the latter, there is no way to compare the intensity or qualia of the externally strobed LED and the intracerebral light. The proper control would be a cohort of mice lacking channelrhodopsin expression in sSC. Regardless, it is essential to acknowledge this potential confound.

Relatedly, as the authors note, there are GABAergic projection neurons in sSC that may be driving these effects via gain of function. This is a significant concern that has limited the widespread adoption of this approach in sSC despite its popularity in studies in cortex. Indeed, one recently published study of behavioral functions of deep SC found that activating inhibitory neurons actually caused paradoxical behavioral effects consistent with gain of function in the targeted hemisphere, due to the effects of long-range inhibitory projections on the other SC hemisphere. Given the presence of inhibitory projections in sSC, it would be preferable to use an orthogonal method for silencing and at least to thoroughly acknowledge these concerns and cite these recent studies.

A minor point is that although activation of GABAergic neurons in sSC is expected to cause inhibition of neighboring neurons, I would expect channelrhodopsin-expressing GABAergic cells to show an increase in firing during optogenetic excitation. However, it seems that none of the cells plotted (assuming each point in Supplementary Fig 4D is a cell, which the legend does not specify) had such an increase. Do these extracellular recordings not detect inhibitory neurons well?

Finally, the relationship between these stimuli and objects is not entirely clear. The authors acknowledge this but it would be worthwhile to devote more attention to this point. In effect, as the authors note, the gray screen and sinuisoidal grating do not have any sharp edges on the screen, whereas each of the behaviorally relevant stimuli will create a sharp, step-like edge on the screen. Whether edge detection is truly object detection or simply a variant of more general visual detection is unclear.

Reviewer #2 (Public Review):

The goal of this study is to show that the superficial superior colliculus (sSC) of mouse signals figure-ground differences defined by contrast, orientation, and phase, and that these signals are necessary for the animal to detect such figure-ground differences. By inhibiting sSC while the animals perform a figure-ground detection task, the study shows that detection performance decreases when sSC activity is suppressed during the onset of the visual stimulus. The study then intends to show that sSC neurons exhibit surround suppression based on orientation differences, and that surround suppression is stronger when the animal detects the correct location of the figure on the background.

The major strength of this study is the use of a behavioural paradigm to test detection performance of figure-ground stimuli while manipulating neural activity in the sSC during different times after stimulus onset. This paradigm would show whether activity in the sSC is relevant for performing the task. Secondly, the study collected data to confirm previous findings: sSC neurons exhibit orientation specific surround suppression. Additionally, it is impressive that the authors were able to train mice to generalize their task performance across different stimulus categories (figure-ground differences in orientation and phase). This should be highlighted as it may inform future studies.

The study has, however, methodological and analytical weaknesses so that the stated conclusions are not supported by the presented results.

1) Optogenetic inhibition is not limited to sSC (even expression may not be limited)<br /> About 30% of inhibitory neurons in the sSC project to other areas, e.g. ventral LGN, parabigeminal nucleus and pretectum (Whyland et al, 2019, see ref in manuscript). This means that these areas receive direct inhibition when inhibitory sSC neurons are optogenetically stimulated. This fact is mentioned in the discussion but the consequences and implications for the results are ignored. This is a major flaw of the optogenetic experiments of this study. Additionally, no evidence is given that opsin expression was limited to the superficial layers (except for one histological slice), which the authors acknowledge in line 285. Deeper layers may have other inhibitory neurons with long-range projections.<br /> The finding that sSC neurons show no figure-ground modulation for phase while the optogenetic manipulation has behavioural effects may be an indication for other areas being affected by the optogenetic manipulation.

2) Could other behavioural variables explain the results?<br /> a) Are there any task events other than the visual stimuli that the mice could use to make their decisions? The authors state the use of a custom made lick spout but it is not clear how this spout works, i.e. how do mechanics of the spout deliver water to the right versus the left output and could the mouse perceive these mechanics?<br /> b) Could the different neural responses to figure versus ground shown in Fig 2I-J and Fig 3B be explained by behaviours varying between the trial types, e.g. by early lick movements (which are conceivable even if the spout is not present), eye movements or changes in pupil-linked arousal? A behavioural difference seems even more likely to occur between hit and error/miss trials (Fig 4). If these behaviours were not measured, the possibility of behavioural modulation should be discussed.

3) What is the behavioural strategy of the animals?<br /> Only licks beyond 200 ms after stimulus onset determine the choice of the animal because "mice made early random licks" from 0 to 200 ms. To better understand the behavioural strategies of the animals we need to see their behavioural data, i.e. left and right licks aligned to stimulus onset. It would be particularly interesting to see how number and latency of licks changes during optogenetic manipulation.

4) Data relating to misses should be included in analyses to provide a complete picture of behaviour and neural responses<br /> a) In the optogenetic manipulations, an increase in misses seems to dominate the decreased accuracy (please, explain when a response was counted as a miss). A separate analysis of miss trials may be more robust than of error trials and also offers a different interpretation of the data, namely that the mouse did not see the stimulus rather than perceiving the figure on the opposite side. However, if the mice reduced their lick rate in general during optogenetic stimulation, this begs the question whether their motor performance was affected by optogenetic manipulation. Can this possibility be excluded?<br /> b) Related to Fig 4, it would be equally interesting to see how FGM changes during misses. Do the changes support the observations for error trials?

5) Statistical tests do not support the conclusions, are missing or inadequate<br /> a) In Fig 1E, accuracy is significantly affected at only 1-2 time points in each task, specifically either the 1st and 3rd or the 2nd time point. How do the authors interpret these results? If inhibition starting at the 2nd time point has no significant effects, why would it be significant when inhibition starts later (at the 3rd time)? Furthermore, given that all other starting points of laser stimulation have no significant effects, there is no reason to trust the latency of inhibition effects based on mostly insignificant data points. This analysis in its current form should be removed, including a comparison of latencies between tasks, which was not tested for significance. It may be more meaningful to analyse accuracy for each animal separately. This may reduce variability.<br /> b) Analyses regarding the difference in neural response to figure and ground (Fig 2I-J, Fig 3B, Fig 4B, Fig 5C) would be more convincing and informative if the differences were analysed on the level of single neurons in response to the same orientation within their RF (or at the location where the figure is presented, for edge-RF neurons). A histogram of these differences would show how many neurons are affected and how large the effect is in single neurons.<br /> c) All statistical tests performed across neurons should account for dependencies due to simultaneous recordings (dependency on session) and due to recordings in the same animal (dependency on animal). This can be done in most cases by using linear mixed-effects models.<br /> d) There was no significant difference between model weights (Fig 3D), so the statement in line 210 (RF-edge neurons had higher weights) should be removed.<br /> e) Fig 4B compares FGM during correct and error trials. This comparison has to be performed with the same set of neurons in correct and error trials (not the case for orientation). Again, the most compelling and informative comparison would be on the level of single neurons: response difference between figure and ground (same visual features at figure position) during hits versus errors.<br /> f) There is no evidence that FGM for phase was different between hit and error trials as stated in line 234.<br /> g) It is not clear why and how the mixed linear effects model was used pooling data across tasks (Fig 4C and Fig 5D). Different neurons were recorded for each task, so the sample points (neurons) are not affected by both task effects (orientation and phase). Each task should be analysed separately.<br /> h) Bonferroni correction in Fig 1E should correct multiple comparisons across time points, not across tasks (see Table 1).<br /> i) What is the reason to perform some tests one-tailed, others two-tailed?

6) The results relating to "multisensory neurons" are ambiguous regarding their interpretation (if significant at all) and seem unrelated to the goal of the study. It is particularly likely that behaviours like licking or other movements cause the response differences between figure and ground.

7) What depth were neurons recorded from (Fig 3 and 4)?

Reviewer #3 (Public Review):

The authors used optogenetic manipulations and electrophysiology recordings to study a causal role and the coding of superficial part of the mouse Superior Colliculus (SCs) during figure detection tasks. Authors previously reported that figure-ground perception relies on V1 activity (Kirchberger et al. 2021) and pointed out that silencing of V1 reduced the accuracy of the mice but still the performance was above the chance level. Therefore, visual information necessary in this task, could be processed via alternative pathways. In this study, authors investigated specifically SCs and used similar approach and analysis as in Kirchberger et al. 2021. Optogenetic silencing of the activity of visual neurons in SCs impaired the accuracy in all 3 versions of the figure detection task: contrast, orientation, and phase. Electrophysiology recordings revealed that SCs neurons are figure-ground modulated, but only by contrast- and orientation-based figures. They show SCs visually responsive neurons reflect behavioral performance in orientation-based figure task. The authors conclusion is that SCs is involved in figure detection task.

Overall, this study provides evidence that mouse SCs is involved in a figure detection task, and codes for task-related events. Authors heroically compared results between 3 different versions of the figure-based detection task. The logic of the study flows through the manuscript and authors prepared a detailed description of methods. However, my main concern is with 1) the amount of data used to make the key arguments, and 2) the interpretation of results. The key findings of this study (figure-ground modulations in SCs) could be a result of the visual cortical feedback in SCs during the task, or pupil diameter changes. Unfortunately, the authors did not rule out these possibilities.

Still, this study can be relevant to a general neuroscience audience, and results could be more convincing if the authors could clarify:

1) Optogenetic inactivation<br /> - The impact of laser stimulation on neural activity is not satisfactory (Supplementary Figure 1). The method seems to be insufficient to fully salience neurons. Electrophysiology control recordings of inactivation are performed in anesthetized mice, which is not a fair estimation of the effect in awake state. Therefore, it rises a major question how effective the inactivation is during the task?<br /> - Could authors provide more details if laser stimulation has an effect only on visual, or all sampled units? How many of units were recorded, and how many show positive and negative laser modulation? How local the inactivation effect is? Where was the silicon probe placed in relation to AAV expression and optical fiber position?

2) Number of sessions and units<br /> - The inactivation effect on behavior (Figure 1E) during phase-task has a significantly larger effect at 66ms after stimulus onset. How can authors explain this? Could this result be biased by one animal/session, or low number of trials for this condition? There is no information about number of trials, or sessions from individual animals. Adding a single example of animal's performance, and sessions for individual mice could clarify results in Figure 1.

- Figure 2H shows an example of neuron with an effect in the figure detection task based on phase difference, but Figure 2I/J (population response) shows there is no effect. Overall, the conclusion is that SCs neurons are not modulated by a phase-defined object. It seems that number of mice and hence units are smaller in phase-detection task comparing to two other tasks. How many of single units are modulated in each version of the task? How big is the FGM effect on single neuron response (could authors provide values in spikes/s)?

- One task is dropped from analysis which it is one of the main points of the paper: to compare responses across different versions of the figure detection task in SCs. But Figures 3-5 only focuses on two tasks, because there is not enough of data for figure-based contrast task.

3) Figure-ground modulation in SCs<br /> - How is neural activity correlated with pupil size, movement (eg. whisking, or face), or jaw movement (preparation to lick)? Can activity of FGM neurons in SCs be explained by these behavioral variables?<br /> - Could authors describe in more detail how they measure a pupil position and diameter, by showing raw data, pupil size aligned to task events?<br /> - How does pupil diameter change between tasks? Small pupil changes can affect responses of visual neurons, and this could be an explanation of FGM effect in SCs. Can authors rule out this possibility, by for example showing pupil size and changes in position at stimulus onset in different tasks?<br /> - Authors in discussion mentioned that the modulation of V1 could be transferred to SCs through the direct projection. Moreover, animals perform above chance in both inactivation experiments (V1 and SC), which could be also an effect of geniculate projections to HVAs (eg. Sincich et al. 2004). Could authors discuss different possibilities?

4) Interpretation of multisensory neurons is not clear. In Figure 5B, there is an example of neuron with two peaks of response. Authors speculate about the activity (pre-motor) but there is lack of clear measurement showing "multisensory" response of these neurons. Could these responses be related to the movement of the lick spout towards the mouth of the mouse (500 ms after the presentation of the stimulus)? Moreover, the number of "multisensory" units is very low (5 units, and 8 units).

Joint Public Review:

The assembly of the apical cytoskeleton of epithelial cells, i.e. the terminal web and microvilli (MV), requires precise control of actin dynamics and non-muscle myosin II (NM M2) contractility. Previous work from the Bretscher lab (Zaman et al, 2021) revealed a connection between ERM protein (ezrin) phosphorylation by LOK/SLK kinases and NM M2 activity and showed that ezrin negatively regulates RhoA. Here the authors now identify the missing link between ezrin and RhoA activity - the GAP ARHGAP18. Binding of ARHGAP18 to the ezrin FERM domain localizes its activity to the site of MV formation, maintaining optimal levels of active RhoA turn on the ezrin kinases LOK/SLK and prevents NM M2 activity (via reduced ROCK activity) within the growing MV. The results here establish that an ARHGAP18-ezrin interaction serves to tightly localize RhoA activity, promoting optimized signalling for MV formation.

The results from several complementary approaches strongly support the identification of ARHGAP18 as a critical component of a negative feedback loop that relies on interaction with ezrin for highly localized control of RhoA-GTP levels. The work is thoughtful and systematic. The results now bring into focus an elegant mechanism for controlling the formation of microvilli that relies on formation of a complex of key players - ezrin that is required for microvilli formation, LOK/SLK kinases that opens and activates ezrin at the membrane and ARHGAP18 that downregulates RhoA, the GTPase that activates LOK/SLK and NM M2.<br /> The findings also suggest interesting possibilities for a similar mode of control in the building of related cellular protrusions, i.e. filopodia and stereocilia.

There are a few questions remaining about the results. One concerns the strength of the ARHGAP18-ezrin FERM domain interaction. Also, the authors propose that activation of non-muscle Myo2 activation accounts for increased apical stiffness and that myosin filaments are present within microvilli in cells lacking ARHGAP. The distribution of the NM 2B heavy chain versus the pMLC seems at odds with the first proposition and the localization results don't quite seem to support the author's conclusion about the relocalization of NM 2B within MV. These are straightforward issues that the author should be able to clarify or address.

Reviewer #1 (Public Review):

Summary:<br /> The paper is an attempt to explain a geographic paradox between infection prevalence and antimalarial resistance emergence. The authors developed a compartmental model that importantly contains antigenic strain diversity and in turn antigen-specific immunity. They find a negative correlation between parasite prevalence and the frequency of resistance emergence and validate this result using empirical data on chloroquine-resistance. Overall, the authors conclude that strain diversity is a key player in explaining observed patterns of resistance evolution across different geographic regions.

The authors pose and address the following specific questions:

1. Does strain diversity modulate the equilibrium resistance frequency given different transmission intensities?<br /> 2. Does strain diversity modulate the equilibrium resistance frequency and its changes following drug withdrawal?<br /> 3. Does the model explain biogeographic patterns of drug resistance evolution?

Strengths:<br /> The model built by the authors is novel. As emphasized in the manuscript, many factors (e.g., drug usage, vectorial capacity, population immunity) have been explored in models attempting to explain resistance emergence, but strain diversity (and strain-specific immunity) has not been explicitly included and thus explored. This is an interesting oversight in previous models, given the vast antigenic diversity of Plasmodium falciparum (the most common human malaria parasite) and its potential to "drive key differences in epidemiological features".

The model also accounts for multiple infections, which is a key feature of malarial infections, with individuals often infected with either multiple Plasmodium species or multiple strains of the same species. Accounting for multiple infections is critical when considering resistance emergence, as with multiple infections there is within-host competition which will mediate the fitness of resistant genotypes. Overall, the model is an interesting combination of a classic epidemiological model (e.g., SIR) and a population genetics model.

In terms of major model innovations, the model also directly links selection pressure via drug administration with local transmission dynamics. This is accomplished by the interaction between strain-specific immunity, generalized immunity, and host immune response.

Weaknesses:<br /> In several places, the explanation of the results (i.e., why are we seeing this result?) is underdeveloped. For example, under the section "Response to drug policy change", it is stated that (according to the model) low diversity scenarios show the least decline in resistant genotype frequency after drug withdrawal; however, this result emerges mechanistically. Without an explicit connection to the workings of the model, it can be difficult to gauge whether the result(s) seen are specific to the model itself or likely to be more generalizable.

The authors emphasize several model limitations, including the specification of resistance by a single locus (thus not addressing the importance of recombination should resistance be specified by more than one locus); the assumption that parasites are independently and randomly distributed among hosts (contrary to empirical evidence); and the assumption of a random association between the resistant genotype and antigenic diversity. However, each of these limitations is addressed in the discussion.

Did the authors achieve their goals? Did the results support their conclusion?

Returning to the questions posed by the authors:

1. Does strain diversity modulate the equilibrium resistance frequency given different transmission intensities? Yes. The authors demonstrate a negative relationship between prevalence/strain diversity and resistance frequency (Figure 2).

2. Does strain diversity modulate the equilibrium resistance frequency and its changes following drug withdrawal? Yes. The authors find that, under resistance invasion and some level of drug treatment, resistance frequency decreased with the number of strains (Figure 4). The authors also find that lower strain diversity results in a slower decline in resistant genotypes after drug withdrawal and higher equilibrium resistance frequency (Figure 6).

3. Does the model explain biogeographic patterns of drug resistance evolution? Yes. The authors find that their full model (which includes strain-specific immunity) produces the empirically observed negative relationship between resistance and prevalence/strain diversity, while a model only incorporating generalised immunity does not (Figure 8).

Utility of work to others and relevance within and beyond the field?<br /> This work is important because antimalarial drug resistance has been an ongoing issue of concern for much of the 20th century and now 21st century. Further, this resistance emergence is not equitably distributed across biogeographic regions, with South America and Southeast Asia experiencing much of the burden of this resistance emergence. Not only can widespread resistant strains be traced back to these two relatively low-transmission regions, but these strains remain at high frequency even after drug treatment ceases.

Reviewer #2 (Public Review):

Summary:<br /> The evolution of resistance to antimalarial drugs follows a seemingly counterintuitive pattern, in which resistant strains typically originate in regions where malaria prevalence is relatively low. Previous investigations have suggested that frequent exposures in high-prevalence regions produce high levels of partial immunity in the host population, leading to subclinical infections that go untreated. These subclinical infections serve as refuges for sensitive strains, maintaining them in the population. Prior investigations have supported this hypothesis; however, many of them excluded important dynamics, and the results cannot be generalized. The authors have taken a novel approach using a deterministic model that includes both general and adaptive immunity. They find that high levels of population immunity produce refuges, maintaining the sensitive strains and allowing them to outcompete resistant strains. While general population immunity contributed, adaptive immunity is key to reproducing empirical patterns. These results are robust across a range of fitness costs, treatment rates, and resistance efficacies. They demonstrate that future investigations cannot overlook adaptive immunity and antigenic diversity.

Strengths:<br /> Overall, this is a very nice paper that makes a significant contribution to the field. It is well-framed within the body of literature and achieves its goal of providing a generalizable, unifying explanation for otherwise disparate investigations. As such, this work will likely serve as a foundation for future investigations. The approach is elegant and rigorous, with results that are supported across a broad range of parameters.

Weaknesses:<br /> Although the title states that the authors describe resistance invasion, they do not support or even explore this claim. As they state in the discussion (line 351), this work predicts the equilibrium state and doesn't address temporal patterns. While refuges in partially immune hosts may maintain resistance in a population, they do not account for the patterns of resistance spread, such as the rapid spread of chloroquine resistance in Africa once it was introduced from Asia.

As the authors state in the discussion, the evolution of compensatory mutations that negate the cost of resistance is possible, and in vitro experiments have found evidence of such. It appears that their results are dependent on there being a cost, but the lower range of the cost parameter space was not explored.

The use of a deterministic, compartmental model may be a structural weakness. This means that selection alone guides the fixation of new mutations on a semi-homogenous adaptive landscape. In reality, there are two severe bottlenecks in the transmission cycle of Plasmodium spp., introducing a substantial force of stochasticity via genetic drift. The well-mixed nature of this type of model is also likely to have affected the results. In reality, within-host selection is highly heterogeneous, strains are not found with equal frequency either in the population or within hosts, and there will be some linkage between the strain and a resistance mutation, at least at first. Of course, there is no recourse for that at this stage, but it is something that should be considered in future investigations.

The authors mention the observation that patterns of resistance in high-prevalence Papua New Guinea seem to be more similar to Southeast Asia, perhaps because of the low strain diversity in Papua New Guinea. However, they do not investigate that parameter space here. If they did and were able to replicate that observation, not only would that strengthen this work, it could profoundly shape research to come.

Reviewer #1 (Public Review):

Summary<br /> This work contains 3 sections. The first section describes how protein domains with SQ motifs can increase the abundance of a lacZ reporter in yeast. The authors call this phenomenon autonomous protein expression-enhancing activity, and this finding is well supported. The authors show evidence that this increase in protein abundance and enzymatic activity is not due to changes in plasmid copy number or mRNA abundance, and that this phenomenon is not affected by mutants in translational quality control. It was not completely clear whether the increased protein abundance is due to increased translation or to increased protein stability.

In section 2, the authors performed mutagenesis of three N-terminal domains to study how protein sequence changes protein stability and enzymatic activity of the fusions. These data are very interesting, but this section needs more interpretation. It is not clear if the effect is due to the number of S/T/Q/N amino acids or due to the number of phosphorylation sites.

In section 3, the authors undertake an extensive computational analysis of amino acid runs in 27 species. Many aspects of this section are fascinating to an expert reader. They identify regions with poly-X tracks. These data were not normalized correctly: I think that a null expectation for how often poly-X track occur should be built for each species based on the underlying prevalence of amino acids in that species. As a result, I believe that the claim is not well supported by the data.

Strengths<br /> This work is about an interesting topic and contains stimulating bioinformatics analysis. The first two sections, where the authors investigate how S/T/Q/N abundance modulates protein expression level, is well supported by the data. The bioinformatics analysis of Q abundance in ciliate proteomes is fascinating. There are some ciliates that have repurposed stop codons to code for Q. The authors find that in these proteomes, Q-runs are greatly expanded. They offer interesting speculations on how this expansion might impact protein function.

Weakness<br /> At this time, the manuscript is disorganized and difficult to read. An expert in the field, who will not be distracted by the disorganization, will find some very interesting results included. In particular, the order of the introduction does not match the rest of the paper.

In the first and second sections, where the authors investigate how S/T/Q/N abundance modulates protein expression levels, it is unclear if the effect is due to the number of phosphorylation sites or the number of S/T/Q/N residues. The authors also do not discuss if the N-end rule for protein stability applies to the lacZ reporter or the fusion proteins.

The most interesting part of the paper is an exploration of S/T/Q/N-rich regions and other repetitive AA runs in 27 proteomes, particularly ciliates. However, this analysis is missing a critical control that makes it nearly impossible to evaluate the importance of the findings. The authors find the abundance of different amino acid runs in various proteomes. They also report the background abundance of each amino acid. They do not use this background abundance to normalize the runs of amino acids to create a null expectation from each proteome. For example, it has been clear for some time (Ruff, 2017; Ruff et al., 2016) that Drosophila contains a very high background of Q's in the proteome and it is necessary to control for this background abundance when finding runs of Q's. The authors could easily address this problem with the data and analysis they have already collected. However, at this time, without this normalization, I am hesitant to trust the lists of proteins with long runs of amino acid and the ensuing GO enrichment analysis.

Ruff KM. 2017. Washington University in St.<br /> Ruff KM, Holehouse AS, Richardson MGO, Pappu RV. 2016. Proteomic and Biophysical Analysis of Polar Tracts. Biophys J 110:556a.

Reviewer #2 (Public Review):

Summary:<br /> This study seeks to understand the connection between protein sequence and function in disordered regions enriched in polar amino acids (specifically Q, N, S and T). While the authors suggest that specific motifs facilitate protein-enhancing activities, their findings are correlative, and the evidence is incomplete. Similarly, the authors propose that the re-assignment of stop codons to glutamine-encoding codons underlies the greater user of glutamine in a subset of ciliates, but again, the conclusions here are, at best, correlative. The authors perform extensive bioinformatic analysis, with detailed (albeit somewhat ad hoc) discussion on a number of proteins. Overall, the results presented here are interesting, but are unable to exclude competing hypotheses.

Strengths:<br /> Following up on previous work, the authors wish to uncover a mechanism associated with poly-Q and SCD motifs explaining proposed protein expression-enhancing activities. They note that these motifs often occur IDRs and hypothesize that structural plasticity could be capitalized upon as a mechanism of diversification in evolution. To investigate this further, they employ bioinformatics to investigate the sequence features of proteomes of 27 eukaryotes. They deepen their sequence space exploration uncovering sub-phylum-specific features associated with species in which a stop-codon substitution has occurred. The authors propose this stop-codon substitution underlies an expansion of ploy-Q repeats and increased glutamine distribution.

Weaknesses:<br /> The preprint provides extensive, detailed, and entirely unnecessary background information throughout, hampering reading and making it difficult to understand the ideas being proposed.<br /> The introduction provides a large amount of detailed background that appears entirely irrelevant for the paper. Many places detailed discussions on specific proteins that are likely of interest to the authors occur, yet without context, this does not enhance the paper for the reader.

The paper uses many unnecessary, new, or redefined acronyms which makes reading difficult. As examples: (1) Prion forming domains (PFDs). Do the authors mean prion-like domains (PLDs), an established term with an empirical definition from the PLAAC algorithm? If yes, they should say this. If not, they must define what a prion-forming domain is formally. (2) SCD is already an acronym in the IDP field (meaning sequence charge decoration) - the authors should avoid this as their chosen acronym for Serine(S) / threonine (T)-glutamine (Q) cluster domains. Moreover, do we really need another acronym here (we do not). (3) Protein expression-enhancing (PEE) - just say expression-enhancing, there is no need for an acronym here.

The results suggest autonomous protein expression-enhancing activities of regions of multiple proteins containing Q-rich and SCD motifs. Their definition of expression-enhancing activities is vague and the evidence they provide to support the claim is weak. While their previous work may support their claim with more evidence, it should be explained in more detail. The assay they choose is a fusion reporter measuring beta-galactosidase activity and tracking expression levels. Given the presented data they have shown that they can drive the expression of their reporters and that beta gal remains active, in addition to the increase in expression of fusion reporter during the stress response. They have not detailed what their control and mock treatment is, which makes complete understanding of their experimental approach difficult. Furthermore, their nuclear localization signal on the tag could be influencing the degradation kinetics or sequestering the reporter, leading to its accumulation and the appearance of enhanced expression. Their evidence refuting ubiquitin-mediated degradation does not have a convincing control.

Based on the experimental results, the authors then go on to perform bioinformatic analysis of SCD proteins and polyX proteins. Unfortunately, there is no clear hypothesis for what is being tested; there is a vague sense of investigating polyX/SCD regions, but I did not find the connection between the first and section compelling (especially given polar-rich regions have been shown to engage in many different functions). As such, this bioinformatic analysis largely presents as many lists of percentages without any meaningful interpretation. The bioinformatics analysis lacks any kind of rigorous statistical tests, making it difficult to evaluate the conclusions drawn.

The methods section is severely lacking. Specifically, many of the methods require the reader to read many other papers. While referencing prior work is of course, important, the authors should ensure the methods in this paper provide the details needed to allow a reader to evaluate the work being presented. As it stands, this is not the case.

Overall, my major concern with this work is that the authors make two central claims in this paper (as per the Discussion).

The authors claim that Q-rich motifs enhance protein expression. The implication here is that Q-rich motif IDRs are special, but this is not tested. As such, they cannot exclude the competing hypothesis ("N-terminal disordered regions enhance expression"). The authors also do not explore the possibility that this effect is in part/entirely driven by mRNA-level effects (see Verma Na Comms 2019). As such, while these observations are interesting, they feel preliminary and, in my opinion, cannot be used to draw hard conclusions on how N-terminal IDR sequence features influence protein expression. This does not mean the authors are necessarily wrong, but from the data presented here, I do not believe strong conclusions can be drawn.

That re-assignment of stop codons to Q increases proteome-wide Q usage. I was unable to understand what result led the authors to this conclusion. My reading of the results is that a subset of ciliates has re-assigned UAA and UAG from the stop codon to Q. Those ciliates have more polyQ-containing proteins. However, they also have more polyN-containing proteins and proteins enriched in S/T-Q clusters. Surely if this were a stop-codon-dependent effect, we'd ONLY see an enhancement in Q-richness, not a corresponding enhancement in all polar-rich IDR frequencies? It seems the better working hypothesis is that free-floating climate proteomes are enriched in polar amino acids compared to sessile ciliates. Regardless, the absence of any kind of statistical analysis makes it hard to draw strong conclusions here.

Reviewer #3 (Public Review):

Summary:<br /> The paper "Unveiling the signaling network of FLT3-ITD AML improves drug sensitivity prediction" reports the combination of prior knowledge signaling networks, multiparametric cell-based data on the activation status of 14 crucial proteins emblematic of the cell state downstream of FLT3 obtained under a variety of perturbation conditions and Boolean logic modeling, to gain mechanistic insight into drug resistance in acute myeloid leukemia patients carrying the internal tandem duplication in the FLT3 receptor tyrosine kinase and predict drug combinations that may reverse pharmacorresistant phenotypes. Interestingly, the utility of the approach was validated in vitro, and also using mutational and expression data from 14 patients with FLT3-ITD positive acute myeloid leukemia to generate patient-specific Boolean models.

Strengths:<br /> The model predictions were positively validated in vitro: it was predicted that the combined inhibition of JNK and FLT3, may reverse resistance to tyrosine kinase inhibitors, which was confirmed in an appropriate FLT3 cell model by comparing the effects on apoptosis and proliferation of a JNK inhibitor and midostaurin vs. midostaurin alone.

Whereas the study does have some complexity, readability is enhanced by the inclusion of a section that summarizes the study design, plus a summary figure. Availability of data as supplementary material is also a high point.

Weaknesses:<br /> Some aspects of the methodology are not properly described (for instance, no methodological description has been provided regarding the clustering procedure that led to Figs. 2C and 2D).

It is not clear in the manuscript whether the patients gave their consent to the use of their data in this study, or the approval from an ethical committee. These are very important points that should be made explicit in the main text of the paper.

The authors claim that some of the predictions of their models were later confirmed in the follow-up of some of the 14 patients, but it is not crystal clear whether the models helped the physicians to make any decisions on tailored therapeutic interventions, or if this has been just a retrospective exercise and the predictions of the models coincide with (some of) the clinical observations in a rather limited group of patients. Since the paper presents this as additional validation of the models' ability to guide personalized treatment decisions, it would be very important to clarify this point and expand the presentation of the results (comparison of observations vs. model predictions).

Reviewer #1 (Public Review):

The authors deploy a combination of their own previously developed computational methods and databases (SIGNOR and CellNOptR) to model the FLT3 signaling landscape in AML and identify synergistic drug combinations that may overcome the resistance AML cells harboring ITD mutations in the TKI domain of FLT3 to FLT3 inhibitors. I did not closely evaluate the details of these computational models since they are outside of my area of expertise and have been previously published. The manuscript has significant issues with data interpretation and clarity, as detailed below, which, in my view, call into question the main conclusions of the paper.

The authors train the model by including perturbation data where TKI-resistant and TKI-sensitive cells are treated with various inhibitors and the activity (i.e. phosphorylation levels) of the key downstream nodes are evaluated. Specifically, in the Results section (p. 6) they state "TKIs sensitive and resistant cells were subjected to 16 experimental conditions, including TNFa and IGF1 stimulation, the presence or absence of the FLT3 inhibitor, midostaurin, and in combination with six small-molecule inhibitors targeting crucial kinases in our PKN (p38, JNK, PI3K, mTOR, MEK1/2 and GSK3)". I would appreciate more details on which specific inhibitors and concentrations were used for this experiment. More importantly, I was very puzzled by the fact that this training dataset appears to contain, among other conditions, the combination of midostaurin with JNK inhibition, i.e. the very combination of drugs that the authors later present as being predicted by their model to have a synergistic effect. Unless my interpretation of this is incorrect, it appears to be a "self-fulfilling prophecy", i.e. an inappropriate use of the same data in training and verification/test datasets.

My most significant criticism is that the proof-of-principle experiment evaluating the combination effects of midostaurin and SP600125 in FLT3-ITD-TKD cell line model does not appear to show any synergism, in my view. The authors' interpretation of the data is that the addition of SP600125 to midostaurin rescues midostaurin resistance and results in increased apoptosis and decreased viability of the midostaurin-resistant cells. Indeed, they write on p.9: "Strikingly, the combined treatment of JNK inhibitor (SP600125) and midostaurin (PKC412) significantly increased the percentage of FLT3ITD-TKD cells in apoptosis (Fig. 4D). Consistently, in these experimental conditions, we observed a significant reduction of proliferating FLT3ITD- TKD cells versus cells treated with midostaurin alone (Fig. 4E)." However, looking at Figs 4D and 4E, it appears that the effects of the midostaurin/SP600125 combination are virtually identical to SP600125 alone, and midostaurin provides no additional benefit. No p-values are provided to compare midostaurin+SP600125 to SP600125 alone but there seems to be no appreciable difference between the two by eye. In addition, the evaluation of synergism (versus additive effects) requires the use of specialized mathematical models (see for example Duarte and Vale, 2022). That said, I do not appreciate even an additive effect of midostaurin combined with SP600125 in the data presented.

In my view, there are significant issues with clarity and detail throughout the manuscript. For example, additional details and improved clarity are needed, in my view, with respect to the design and readouts of the signaling perturbation experiments (Methods, p. 15 and Fig 2B legend). For example, the Fig 2B legend states: "Schematic representation of the experimental design: FLT3 ITD-JMD and FLT3 ITD-JMD cells were cultured in starvation medium (w/o FBS) overnight and treated with selected kinase inhibitors for 90 minutes and IGF1 and TNFa for 10 minutes. Control cells are starved and treated with PKC412 for 90 minutes, while "untreated" cells are treated with IGF1 100ng/ml and TNFa 10ng/ml with PKC412 for 90 minutes.", which does not make sense to me. The "untreated" cells appear to be treated with more agents than the control cells. The logic behind cytokine stimulation is not adequately explained and it is not entirely clear to me whether the cytokines were used alone or in combination. Fig 2B is quite confusing overall, and it is not clear to me what the horizontal axis (i.e. columns of "experimental conditions", as opposed to "treatments") represents. The Method section states "Key cell signaling players were analyzed through the X-Map Luminex technology: we measured the analytes included in the MILLIPLEX assays" but the identities of the evaluated proteins are not given in the Methods. At the same time, the Results section states "TKIs sensitive and resistant cells were subjected to 16 experimental conditions" but these conditions do not appear to be listed (except in Supplementary data; and Fig 2B lists 9 conditions, not 16). In my subjective view, the manuscript would benefit from a clearer explanation and depiction of the experimental details and inhibitors used in the main text of the paper, as opposed to various Supplemental files/figures. The lack of clarity on what exactly were the experimental conditions makes the interpretation of Fig 2 very challenging. In the same vein, in the PCA analysis (Fig 2C) there seems to be no reference to the cytokine stimulation status while the authors claim that PC2 stratifies cells according to IGF1 vs TNFalpha. There are numerous other examples of incomplete or confusing legends and descriptions which, in my view, need to be addressed to make the paper more accessible.

I am not sure that I see significant value in the patient-specific logic models because they are not supported by empirical evidence. Treating primary cells from AML patients with relevant drug combinations would be a feasible and convincing way to validate the computational models and evaluate their potential benefit in the clinical setting.

Reviewer #2 (Public Review):

Summary:<br /> This manuscript by Latini et al describes a methodology to develop Boolean-based predictive logic models that can be applied to uncover altered protein/signalling networks in cancer cells and discover potential new therapeutic targets. As a proof-of-concept, they have implemented their strategy on a hematopoietic cell line engineered to express one of two types of FLT3 internal tandem mutations (FLT3-ITD) found in patients, FLT3-ITD-TKD (which are less sensitive to tyrosine kinase inhibitors/TKIs) and FLT3-ITD-JMD (which are more sensitive to TKIs).

Strengths:<br /> This useful work could potentially represent a step forward towards personalised targeted therapy, by describing a methodology using Boolean-based predictive logic models to uncover altered protein/signalling networks within cancer cells. However, the weaknesses highlighted below severely limit the extent of any conclusions that can be drawn from the results.

Weaknesses:<br /> While the highly theoretical approach proposed by the authors is interesting, the potential relevance of their overall conclusions is severely undermined by a lack of validation of their predicted results in real-world data. Their predictive logic models are built upon a set of poorly-explained initial conditions, drawn from data generated in vitro from an engineered cell line, and no attempt was made to validate the predictions in independent settings. This is compounded by a lack of sufficient experimental detail or clear explanations at different steps. These concerns considerably temper one's enthusiasm about the conclusions that could be drawn from the manuscript. Some specific concerns include:

1. It remains unclear how robust the logic models are, or conversely, how affected they might be by specific initial conditions or priors that are chosen. The authors fail to explain the rationale underlying their input conditions at various points. For example:<br /> - at the start of the manuscript, they assert that they begin with a pre-PKN that contains "76 nodes and 193 edges", though this is then ostensibly refined with additional new edges (as outlined in Fig 2A). However, why these edges were added, nor model performance comparisons against the basal model are presented, precluding an evaluation of whether this model is better.

- At a later step (relevant to Fig S4 and Fig 3), they develop separate PKNs, for each of the mutation models, that contain "206 [or] 208 nodes" and "756 [or] 782 edges", without explaining how these seemingly arbitrary initial conditions were arrived at. Their relation to the original parameters in the previous model is also not investigated, raising concerns about model over-fitting and calling into question the general applicability of their proposed approach. The authors need to provide a clearer explanation of the logic underlying some of these initial parameter selections, and also investigate the biological/functional overlap between these sets of genes (nodes).

2. There is concern about the underlying experimental data underpinning the models that were generated, further compounded by the lack of a clear explanation of the logic. For example, data concerning the status of signalling changes as a result of perturbation appears to be generated from multiplex LUMINEX assays using phosphorylation-specific antibodies against just 14 "sentinel" proteins. However, very little detail is provided about the rationale underlying how these 14 were chosen to be "sentinels" (and why not just 13, or 15, or any other number, for that effect?). How reliable are the antibodies used to query the phosphorylation status? What are the signal thresholds and linear ranges for these assays, and how would these impact the performance/reliability of the logic models that are generated from them?

In addition, there are publicly available quantitative proteomics datasets from FLT3-mutant cell lines and primary samples treated with TKIs. At the very least, these should have been used by the authors to independently validate their models, selection of initial parameters, and signal performance of their antibody-based assays, to name a few unvalidated, yet critical, parameters.

3. There is an overwhelming reliance on theoretical predictions without taking advantage of real-world validation of their findings. For example, the authors identified a set of primary AML samples with relevant mutations (Fig 5) that could potentially have provided a valuable experimental validation platform for their predictions of effective drug combination. Yet, they have performed Boolean simulations of the predicted effects, a perplexing instance of adding theoretical predictions on top of a theoretical prediction!

Additionally, there are datasets of drug sensitivity on primary AML samples where mutational data is also known (for example, from the BEAT-AML consortia), that could be queried for independent validation of the authors' models.

4. There are additional examples of insufficient experimental detail that preclude a fuller appreciation of the relevance of the work. For example, it is alluded that RNA-sequencing was performed on a subset of patients, but the entire methodological section detailing the RNA-seq amounts to just 3 lines! It is unclear which samples were selected for sequencing nor where the data has been deposited (or might be available for the community - there are resources for restricted/controlled access to deidentified genomics/transcriptomics data).

Similarly, in the "combinatory treatment inference" methods, it states "...we computed the steady state of each cell line best model....." and "Then we inferred the activity of "apoptosis" and "proliferation" phenotypes", without explaining the details of how these were done. The outcomes of these methods are directly relevant to Fig 4, but with such sparse methodological detail, it is difficult to independently assess the validity of the presented data.

Overall, the theoretical nature of the work is hampered by real-world validation, and insufficient methodological details limit a fuller appreciation of the overall relevance of this work.

Joint Public Review:

Lujan et al make a significant contribution to the field by elucidating the essential role of TGN46 in cargo sorting and soluble protein secretion. TGN46 is a prominent TGN protein that cycles to the plasma membrane and it has been used as a TGN marker for many years, but its function has been a fundamental mystery.

In parallel, it remains unclear how most secreted proteins are targeted from the Golgi to the cell surface. These molecules do not contain conserved sequence motifs or post-translation modifications such as lysosomal hydrolases. Cargo receptors for these secreted proteins have remained elusive.

Therefore, these investigations are likely to have a significant influence on the field.

To gain an insight into the molecular role of TGN46 in sorting, they systematically test the impact of the luminal, transmembrane, and cytosolic domains. Importantly and against the current thinking, they demonstrate that the luminal domain of TGN facilitates sorting. Interestingly, neither the cytosolic nor the length of the transmembrane domain of TGN46 plays a role in cargo export. The effects of TGN46 depletion are specific as membrane-associated VSVG remains unaffected.

Interestingly, TGN46 luminal domain also plays an important role in the intracellular and intra-Golgi localization of TGN46, and it contains a positive signal for Golgi export in CARTS. Rigorous, well-performed data support the experimental evidence.

A speculative part of the manuscript, with some accompanying experimental data, proposes that the luminal domain of TGN46 forms biomolecular condensates that help to capture cargo proteins for export.

One important point to discuss is that the effects of TGN46 KO are partial, suggesting that TGN46 stimulates the Golgi export of PAUF but is not essential for this process. The incomplete block is apparent in Fig 1 and in Fig 5D.

Reviewer #1 (Public Review):

The manuscript by Lin et al describes a wide biophysical survey of the molecular mechanisms underlying full length BTK regulation. This is a continuation of this lab's excellent work on deciphering the myriad levels of regulation of BTKs downstream of their activation by plasma membrane localised receptors.

The manuscript uses a synergy of cryo EM, HDX-MS and mutational analysis to delve into the role of the how the accessory domains modify the activity of the kinase domain. The manuscript essentially has three main novel insights into BTK regulation.

1. Cryo EM and SAXS shows that the PHTH region is dynamic compared to the conserved Src module.<br /> 2. A 2nd generation tethered PH-kinase construct crystal of BTK reveals a unique orientation of the PH domain relative to the kinase domain, that is different from previous structures.<br /> 3. A new structure of the kinase domain dimer shows how trans-phosphorylation can be achieved.

Excitingly these structural work allow for the generation of a model of how BTK can act as a strict coincidence sensor for both activated BCR complex as well as PIP3 before it obtains full activity. To my eye the most exciting result of this work is describing how the PH domain can inhibit activity once the SH3/SH2 domain is disengaged, allowing for an additional level of regulatory control.

I have very few experimental concerns as the methods and figures are well described and clear. As the authors are potentially saying that the previously solved PH domain-kinase interface is but one of many possible inhibitory conformations that can be adapted.

Reviewer #2 (Public Review):

In this study, multiple biophysical techniques were employed to investigate the activation mechanism of BTK, a multi-domain non-receptor protein kinase. Previous studies have elucidated the inhibitory effects of the SH3 and SH2 domains on the kinase and the potential activation mechanism involving the membrane-bound PIP3 inducing transient dimerization of the PH-TH domain, which binds to lipids.

The primary focus of the present study was on three new constructs: a full-length BTK construct, a construct where the PH-TH domain is connected to the kinase domain, and a construct featuring a kinase domain with a phosphomimetic at the autophosphorylation site Y551. The authors aimed to provide new insights into the autoinhibition and allosteric control of BTK.

The study reports that SAXS analysis of the full-length BTK protein construct, along with cryoEM visualization of the PH-TH domain, supports a model in which the N-terminal PH-TH domain exists in a conformational ensemble surrounding a compact/autoinhibited SH3-SH2-kinase core. This finding is interesting because it contradicts previous models proposing that each globular domain is tightly packed within the core.

Furthermore, the authors present a model for an inhibitory interaction between the N-lobe of the kinase and the PH-TH domain. This model is based on a study using a tethered complex with a longer tether than a previously reported construct where the PH-TH domain was tightly attached to the kinase domain (ref 5). The authors argue that the new structure is relevant. However, this assertion requires further explanation and discussion, particularly considering that the functional assays used to assess the impact of mutating residues within the PH-TH/kinase domain contradict the results of the previous study (ref 5).

Additionally, the study presents the structure of the kinase domain with swapped activation loops in a dimeric form, representing a previously unseen structure along the trans-phosphorylation pathway. This structure holds potential relevance. To better understand its significance, employing a structure/function approach like the one described for the PH-TH/kinase domain interface would be beneficial.

Overall, this study contributes to our understanding of the activation mechanism of BTK and sheds light on the autoinhibition and allosteric control of this protein kinase. It presents new structural insights and proposes novel models that challenge previous understandings.

Reviewer #3 (Public Review):

Yin-wei Lin et al set out to visualize the inactive conformation of full length Bruton's Tyrosine Kinase (BTK), a molecule that has evaded high resolution structural studies in its full length form to this date. An open question in the field is how the Pleckstrin Homology-Tec Homology (PHTH) domain inhibits BTK activity, with multiple competing models in the field. The authors used a complimentary set of biophysical techniques combined with well thought out stabilizing mutations to obtain structural insights into BTK regulation in its full length form. They were able to crystallize the full length construct of BTK but unfortunately the PHTH was not resolved yielding the structure similar to previously obtained in the field. The investigation of the same construct by SAXS yielded an elongated structural model, consistent with previous SAXS studies. Using cryo-EM the authors obtained a low resolution model for the FL BTK with a loosely connected density assigned to the dynamic PHTH around the compact SH2-SH3-Kinase Domain (KD) core. To gain further molecular insights into PHTH-KD interactions the authors followed a previously reported strategy and generated a fusion of PHTH-KD with a longer linker, yielding a crystal structure with a novel PHTH-KD interface which they tested in biochemical assays. Lastly, Yin-wei Lin et al crystallized the BTK KD in a novel partially active state in a "face to face" dimer with kinases exchanging the activation loops, although partially disordered, being theoretically perfectly positioned for trans phosphorylation. Overall this presents a valiant effort to gain molecular insights into what clearly is a dynamic regulatory motif on BTK and is a valuable addition to the field.

I think the authors addressed all the comments that I had during the initial round of review. The only thing I can think of that would strengthen the paper is to add a supplemental figure/table with the results of unbiased SITUS fitting rather than just saying that it is close to manual fitting. Additionally, SITUS outputs not just one best solution but all the top fits and having a significant difference in cross correlation between the best fit and second best fit is usually indicative of true fit. As the authors already ran SITUS and colores they have this data and I think having a sup table with cross correlations for the top 3 fits for each of their maps would make their EM fitting more convincing and not hard to do.

Lastly, it seems like both the authors and I agree that the cryoEM reconstructions do not correspond to the reported resolutions by the FSC. This point in no way changes any of the conclusions of the paper, however, I can't help but feel guilty that some student who is not in the field will look at these EM maps in the future and think that this is how 7A reconstructions should look like. If the authors, maybe somewhere in the methods could add a sentence indicating that the FSC curves may be overly optimistic and that there are no secondary structure features present which would be expected at these resolutions, that would be great.

Reviewer #1 (Public Review):

Summary:<br /> This study is valuable in that it may lead to the discovery of future OA markers, etc., in that changes in glycan metabolism in chondrocytes are involved in the initiation of cartilage degeneration and early OA via hypertrophic differentiation of chondrocytes. However, more robust results would be obtained by analyzing the mechanisms and pathways by which changes in glycosylation lead to cartilage degeneration.

Strengths:<br /> This study is important because it indicates that glycan metabolism may be associated with pre-OA and may lead to the elucidation of the cause and diagnosis of pre-OA.

Weaknesses:<br /> More robust results would be obtained by analyzing the mechanism by which cartilage degeneration induced by changes in glycometabolism occurs.

Reviewer #2 (Public Review):

Summary:<br /> This paper consists of mostly descriptive data, judged from alpha-mannosidase-treated samples, in which they found an increase in core fucose, a product of Fut 8.

Strengths:<br /> This paper is interesting in the clinical field, but unfortunately, the data is mostly descriptive and does not have a significant impact on the scientific community in general.

Weaknesses:<br /> If core fucose is increased, at least the target glycan molecules of core fucose should be evaluated. They also found an increase in NO, suggesting that inflammatory processes also play an important role in OA in addition to glycan changes.<br /> It has already been reported that core fucose is decreased by administration of alpha-mannosidase inhibitors. Therefore, it is expected that alpha-mannosidase administration increases core fucose.

Reviewer #3 (Public Review):

Summary:<br /> In the manuscript "Articular cartilage corefucosylation regulates tissue resilience in osteoarthritis", the authors investigate the glycan structural changes in the context of pre-OA conditions. By mainly conducting animal experiments and glycomic analysis, this study clarified the molecular mechanism of N-glycan core fucosylation and Fut8 expression in the extracellular matrix resilience and unrecoverable cartilage degeneration. Lastly, a comprehensive glycan analysis of human OA cartilage verified the hypothesis.

Strengths:<br /> Generally, this manuscript is well structured with rigorous logic and clear language. This study is valuable and important in the early diagnosis of OA patients in the clinic, which is a great challenge nowadays.

Weaknesses:<br /> I recommend minor revisions:

1. I would suggest the authors prepare an illustrative scheme for the whole study, to explain the complex mechanism and also to summarize the results.

2. Including but not limited to Figures 2A-C, Figures 3A and C, Figure 4B, and Figures 5A and D. The texts in the above images are too small to read, I would suggest the authors remake these images.

3. The paper is generally readable, but the language could be polished a bit. Several writing errors should be realized during the careful check.

4. As several species and OA models were conducted in this study, it would be better if the authors could note the reason behind their choice for it.

Reviewer #1 (Public Review):

Summary:<br /> This paper described the dynamics of the nuclear substructure called PML Nucleolar Association (PNA) in response to DNA damage on ribosomal DNA (rDNA) repeats. The authors showed that the PNA with rDNA repeats is induced by the inhibition of topoisomerases and RNA polymerase I and that the PNA formation is modulated by RAD51, thus homologous recombination. Artificially induced DNA double-strand breaks (DSBs) in rDNA repeats stimulate the formation of PNA with DSB markers. This DSB-triggered PNA formation is regulated by DSB repair pathways.

Strengths:<br /> This paper illustrates a unique DNA damage-induced sub-nuclear structure containing the PML body, which is specifically associated with the nucleolus. Moreover, the dynamics of this PML Nucleolar Association (PNA) require topoisomerases and RNA polymerase I and are modulated by RAD51-mediated homologous recombination and non-homologous end-joining. This study provides a unique regulation of DSB repair at rDNA repeats associated with the unique-membrane-less subnuclear structure.

Weaknesses:<br /> Although the PNA formation on rDNA repeat is nicely shown by cytological analysis, the biological significance of PNA in DSB repair is not fully addressed.

Reviewer #2 (Public Review):

In this manuscript, the authors aim to study the PML-nucleoli association (PNAs) by different genotoxic stress and to determine the underlying molecular mechanisms.

First, from a diverse set of genotoxic stress conditions (topoisomerases, RNA Pol I, rRNA processing, and DNA replication stress), the authors have found that the inhibition of topoisomerases and RNA Polymerase I has the highest PNA formation associated with p53 stabilization, gamma-H2AX, and PAF49 segregation. It was further demonstrated that Rad51-mediated HR pathway but not NHEJ pathway is associated with the PNA formation. Immuno-FISH assays show that doxorubicin induces DSBs (53BP1 foci) in rDNA and PNA interactions with rDNA/DJ regions. Furthermore, endonuclease I-Ppol induced DSB at a defined location in rDNA and led to PNAs.

Most claims by the authors are supported by the data provided. However, below weaknesses/concerns may need to be addressed to improve the quality of the study.

1) Top2B toxin doxorubicin had the highest degree of elevating PNAs; however, Top2B-knockdown had almost no noticeable effects on PNAs. How to reconcile the different phenotypes targeting Top2B?

2) To test the role of Rad51 and DNA-PKcs in the PNA formation, Rad51 inhibitor B02 and DNA-PKcs inhibitor NU-7441 were chosen to use in the study. To further exclude the possible off-target of B02 and NU-7441, siRNA-mediated knockdown of Rad51 and DNA-PKcs would be an appropriate complementary approach to the pharmaceutical inhibitor approach.

3) Several previous studies have shown the activation of the nucleolar ATM-mediated DNA damage response pathway by I-Ppol-induced DSBs in rDNA. What is the role of nucleolar ATM in the regulation of PNAs?

Reviewer #3 (Public Review):

Summary:<br /> Hornofova et al examined interactions between the nucleolus and promyelocytic leukemia nuclear bodies (PML-NBs) termed PML-nucleolar associations (PNAs). PNAs are found in a minor subset of cells, exist within distinct morphological subcategories, and are induced by cellular stressors including genotoxic damage. A systematic pharmacological investigation identified that compounds that inhibit RNA Polymerase 1 (RNAPI) and/or topoisomerase 1 or 2A caused the greatest proportion of cells with PNA. A specific RAD51 inhibitor (R02) impacted the number of cells exhibiting PNAs and PNA morphology. Genetic double-strand break (DSB) induction within the rDNA locus also induced PNA structures that were more prevalent when non-homologous end joining (NHEJ) was inhibited.

Strengths:<br /> PNA are morphologically distinct and readily visualized. The imaging data are high quality, and rDNA is amenable to studying nuclear dynamics. Specific induction of rDNA damage is a strong addition to the non-specific pharmacological damage characterized early in the manuscript. These data nicely demonstrate that rDNA double-strand breaks undermine PNA formation. Figure 1 is a comprehensive examination and presents a compelling argument that RNAPI and/or TOP1, TOP2A inhibition promote PNA structures.

Weaknesses:<br /> The data are limited to fixed fluorescent microscopy of structures present in a minority of cells. Data are occasionally qualitative and/or based upon interpretation of dynamic events extrapolated from fixed imaging. This study would benefit from live imaging that captures PNA dynamics.

Cell cycle and cell division are not considered. Double-strand break repair is cell cycle dependent, and most experiments occur over days of treatment and recovery. It is unclear if the cultures are proliferating, or which cell cycle phase the cells are in at the time of analysis. It is also unclear if PNAs are repeatedly dissociating and reforming each cell division.

The relationship of PNA morphologies (bowl, funnel, balloon, and PML-NDS) also remains unclear. It is possible that PNAs mature/progress through the distinct morphologies, and that morphological presentation is a readout of repair or damage in the rDNA locus. However, this is not formally addressed.

An I-Ppol targeted sequence within the rDNA locus suggests 3D structural rearrangement following damage. An orthogonal approach measuring rDNA 3D architecture would benefit comprehension. Following I-Ppol induction, it is possible that cells arrest in a G1 state. This may explain why targeting NHEJ has a greater impact on the number of 53BP1 foci and should be investigated.

Conclusions: PNAs are a phenomenon of biological significance and understanding that significance is of value. More work is required to advance knowledge in this area. The authors may wish to examine the literature on APBs (Alt-associated PML-NBs), which are similar structures where telomeres associate with PML-NBs in a specific subset of cancers. It is possible that APBs and PNAs share similar biology, and prior efforts on APBs may help guide future PNA studies.

Reviewer #1 (Public Review):

In this study, Chen et al. used super-resolution microscopy on T47D cells to investigate the cell surface distribution of hGHR and hPRLR in steady-state and in response to ligand stimulation. The initial findings of this study suggest both PRL and GH stimulation lead to a decrease in GH receptors but an increase in the PRLR on the cell surface. A subset of both receptors co-localize in close proximity and may form heteromers. Moreover, the study revealed that the box 1 region in GHR plays an essential role in the regulation of its interaction with the PRLR, and the box 1 region in the PRLR is involved in the PRL-induced downregulation of the GHR. The most innovative aspect of this study is the super-resolution microscopy methodology that permits the analysis of proteins on the level of single molecules, and other notable advances are the generation of T47D cells that lack the PRLR and GHR. The questions after reading this manuscript are what novel insights have been gained that significantly go beyond what was already known about the interaction of these receptors and, more importantly, what are the physiological implications of these findings? The proposed significance of the results in the last paragraph of the Discussion section is speculative since none of the receptor interactions have been investigated in TNBC cell lines. Moreover, no physiological experiments were conducted using the PRLR and GH knockout T47D cells to provide biological relevance for the receptor heteromers. The proposed role of JAK2 in the cell surface distribution and association of both receptors as stated in the title was only derived from the analysis of box 1 domain receptor mutants. A knockout of JAK2 was not conducted to assess heteromer formation.

There are additional points that require the authors' attention:

1. Except for some investigation of γ2A-JAK2 cells, most of the experiments in this study were conducted on a single breast cancer cell line. In terms of rigor and reproducibility, this is somewhat borderline. The CRISPR/Cas9 mutant T47D cells were not used for rescue experiments with the corresponding full-length receptors and the box1 mutants. A missed opportunity is the lack of an investigation correlating the number of receptors with physiological changes upon ligand stimulation (e.g., cellular clustering, proliferation, downstream signaling strength).

2. An obvious shortcoming of the study that was not discussed seems to be that the main methodology used in this study (super-resolution microscopy) does not distinguish the presence of various isoforms of the PRLR on the cell surface. Is it possible that the ligand stimulation changes the ratio between different isoforms? Which isoforms besides the long form may be involved in heteromer formation, presumably all that can bind JAK2?

3. Changes in the ligand-inducible activation of JAK2 and STAT5 were not investigated in the T47D knockout models for the PRL and GHR. It is also a missed opportunity to use super-resolution microscopy as a validation tool for the knockouts on the single cell level and how it might affect the distribution of the corresponding other receptor that is still expressed.

4. Why does the binding of PRL not cause a similar decrease (internalization and downregulation) of the PRLR, and instead, an increase in cell surface localization? This seems to be contrary to previous observations in MCF-7 cells (J Biol Chem. 2005 October 7; 280(40): 33909-33916).

5. Some figures and illustrations are of poor quality and were put together without paying attention to detail. For example, in Fig 5A, the GHR was cut off, possibly to omit other nonspecific bands, the WB images look 'washed out'. 5B, 5D: the labels are not in one line over the bars, and what is the point of showing all individual data points when the bar graphs with all annotations and SD lines are disappearing? As done for the y2A cells, the illustrations in 5B-5E should indicate what cell lines were used. No loading controls in Fig 5F, is there any protein in the first lane? No loading controls in Fig 6B and 6H.

6. The proximity ligation method was not described in the M&M section of the manuscript.

Reviewer #2 (Public Review):

Summary:<br /> Chen Chen et al. investigated the interaction between GHR and PRLR at the cell surface using STORM-type super-resolution microscopy, proximity ligation assay, and mutagenesis. They found that GH and PRL change the surface expression of GHR and PRLR. Upon stimulation, the hGHR cluster size significantly increases in a transient manner, whereas changes in hPRLR occur more slowly. In their previous publication, the authors found that hGHR and hPRLR co-immunoprecipitate in the absence of ligands. Based on that finding and the observations here, the authors examined colocalization of hGHR and hPRLR in clusters with proximity ligation assays and found that the receptors form complexes on the surface of T47D cells, and that these complexes respond differently to the ligands. Remarkably, the experiments in cells lacking either hGHR or hPRLR showed that PRLR is necessary for the reduction of surface hGHR induced by PRL. Studies with truncation or deletion of hPRLR mutants, suggest the box 1 region in hPRLR plays a critical role in stabilizing the hGHR-hPRLR complexes. This region contains the JAK2 binding site, and the authors show that binding of JAK2 to hGHR is also required for hPRLR-mediated regulation of hGHR surface expression. Cytokine receptors have very important broad-ranging roles in regulating cells and physiological roles. Therefore, the new findings described here will significantly expand our understanding of the structure-function relationship that drives a core signalling mechanism in cell biology.

Strengths:<br /> I particularly appreciate that the authors used different angles to examine the mechanism of GHR-PRLR interaction and that they also checked the conclusions with CRISPR/Cas9 technology and with a cellular reconstitution system.

Weaknesses:<br /> I could not fully evaluate some of the data, mainly because several details on acquisition and analysis are lacking. It would be useful to know what the background signal was in dSTORM and how the authors distinguished the specific signal from unspecific background fluorescence, which can be quite prominent in these experiments. Typically, one would evaluate the signal coming from antibodies randomly bound to a substrate around the cells to determine the switching properties of the dyes in their buffer and the average number of localisations representing one antibody. This would help evaluate if GHR or PRLR appeared as monomers or multimers in the plasma membrane before stimulation, which is currently a matter of debate. It would also provide better support for the model proposed in Figure 8. Since many of the findings in this work come from the evaluation of localisation clusters, an image showing actual localisations would help support the main conclusions. I believe that the dSTORM images in Figures 1 and 2 are density maps, although this was not explicitly stated. Alexa 568 and Alexa 647 typically give a very different number of localisations, and this is also dependent on the concentration of BME. Did the authors take that into account when interpreting the results and creating the model in Figures 2 and 8? I believe that including this information is important as findings in this paper heavily rely on the number of localisations detected under different conditions. Including information on proximity labelling and CRISPR/Cas9 in the methods section would help with the reproducibility of these findings by other groups.

Reviewer #3 (Public Review):

Summary:<br /> The authors are interested in the relative importance of PRL versus GH and their interactive signaling in breast cancer. After examining GHR-PRLR interactions in response to ligands, they suggest that a reduction in cell surface GHR in response to PRL may be a mechanism whereby PRL can sometimes be protective against breast cancer.

Strengths:<br /> The strengths of the study include the interesting question being addressed and the application of multiple complementary techniques, including dSTORM, which is technically very challenging, especially when using double labeling. Thus, dSTORM is used to show co-clustering of GHR and PRLR, and, in response to PRL, rapid internalization of GHR and increased cell surface PRLR. Proximity ligation assays demonstrate that some GHR and PRLR are within 40 nm (≈ 4 plasma membranes) of each other and that upon ligand stimulation, they move apart. Intact receptor knockin and knockout approaches and receptor constructs without the Jak2 binding domain demonstrate a) a requirement for the PRLR for there to be PRL-driven internalization of GHR, and b) that Jak2-PRLR interactions are necessary for the stability of the GHR-PRLR colocalizations.

Weaknesses:<br /> The manuscript suffers from a lack of detail, which in places makes it difficult to evaluate the data and would make it very difficult for the results to be replicated by others. In addition, the manuscript would very much benefit from a full discussion of the limitations of the study. For example, the manuscript is written as if there is only one form of the PRLR while the anti-PRLR antibody used for dSTORM would also recognize the intermediate form and short forms 1a and 1b on the T47D cells. Given the very different roles of these other PRLR forms in breast cancer (Dufau, Vonderhaar, Clevenger, Walker and other labs), this limitation should at the very least be discussed. Similarly, the manuscript is written as if Jak2 essentially only signals through STAT5 but Jak2 is involved in multiple other signaling pathways from the multiple PRLRs, including the long form. Also, while there are papers suggesting that PRL can be protective in breast cancer, the majority of publications in this area find that PRL promotes breast cancer. How then would the authors interpret the effect of PRL on GHR in light of all those non-protective results?

Reviewer #1 (Public Review):

Summary:<br /> The authors started by stimulating the PBMCs in bulk, then encapsulated single cells in droplets to monitor the secreted cytokines in each droplet for the next 4 hours. The secreted cytokines are bound by fluorescently labeled detection antibodies. At the same time, the cytokines can be captured by the capture antibodies that are immobilized to the magnetic beads. Under the magnetic field, the magnetic beads will line up in the middle of the droplet along with bound fluorescent antibodies. This effectively enriches the fluorescent antibody to the middle of the droplet, making it a higher fluorescent signal compared to the background signal that is in the rest of the droplet. They can parallel the measurement of three cytokines in each droplet.

Strengths:<br /> Observed heterogeneous cytokine secretion dynamics, which they have reported in their previous paper as well.

Weaknesses:<br /> Since they used PBMCs, without other assays to confirm the cell subtypes, I am not sure if any of the heterogeneity they detected in 6 cytokine secretion would be able to relate back to biology. In addition, the two panels were measured on separate cells, I am not sure it is meaningful to make any comparisons of the two panels as they are on different cells.

Reviewer #2 (Public Review):

Summary:<br /> In their manuscript titled "Stimulation-induced cytokine polyfunctionality as a dynamic concept," the authors investigate the dynamic nature of polyfunctional cytokine responses to established stimulants. The authors use their previously published single-cell encapsulation droplet-microfluidic platform to analyse the response of peripheral blood mononuclear cells (PBMCs) to different stimulants and measure the secretion dynamics of individual cytokines. This assay shows that polyfunctionality in cytokine responses is a complex but short-lived phenomenon that decreases with prolonged stimulation times. The study finds that polyfunctional cells predominantly display elevated cytokine concentrations with similar secretion patterns but higher secretion levels compared to their monocytokine-secreting counterparts. The method is promising to analyse the correlation between the secretion dynamics of different cytokines in primary samples and heterogeneous cell populations.

Strengths:<br /> This method provides single-cell-resolved and dynamic cytokine concentration information, which might be used to identify "fingerprints" of secretion patterns for selected cytokines. When extending the available data to more than one donor, this might be the basis for a diagnostic tool. The combination of established droplet microfluidics with an epi-fluorescence microscope-based readout makes it convincing that the method is transferable to other labs. Specifically, the dynamic analysis of cytokine concentrations is interesting, and the differences or similarities in secretion timepoints might be missed with end-point methods. The authors convincingly show that they detect up to three different cytokines in single cells.

Weaknesses:<br /> The conclusions of the study are based on samples from a single donor, which makes the conclusions on secretion patterns difficult to interpret. The choice of cytokines is explained, but the justification of the groupings of the antibodies into the two panels is missing. It would further be helpful to discuss how the single cell incubation might affect the sectration dynamics vs. the influence of co-culture of all cell types during the 24 h activation. The authors compare average secretion rates and levels. However, the right panel in Fig. 6 looks like there might be two different populations of mono- or polyfuntional cells that have two secretion rates. As the authors have single-cell data, I would find the separation into these populations more meaningful than comparing the mean values. In line with this comment, comparing the mean values for these cytokines instead of the mean of the populations with distinct seretion properties might actually show stronger differences than the authors report here. Is the plateau of the cytokine concentration caused by the fluorescence signal saturating the camera, saturation of the magnetic beads, exhaustion of the fluorescent antibodies, or constant cytokine concentrations? The high number of non-CSCs and the limited number of droplets decrease the statistical power of the method. The authors discuss their choice to use PBMCs and not solely T cells, but this aspect is missing in the discussion.

Joint Public Review:

The manuscript by Budinska et al investigated that morphological heterogeneity may have an impact on gene-expression profiles and conventional molecular signatures applied to bulk CRC tissues. The authors conducted whole transcriptome microarrray profiling data from macro-dissected morphotype-specific tumor regions, bulk tumor and surrounding normal and stromal tissues to support their claims. The paper is interesting as it provides a putative morphological approach through which clinicians might improve the performance of molecular signatures and consequently predict the clinical response of patients with better accuracy. In the updated version of the manuscript, the authors have improved the manuscript and addressed several unsolved concerns such as patient selection and tumor area selection to justify their claims. The findings of the manuscript may have potential to be translated into the clinic of CRC.

Reviewer #1 (Public Review):

Ps observed 24 objects and were asked which afforded particular actions (14 action types). Affordances for each object were represented by a 14-item vector, values reflecting the percentage of Ps who agreed on a particular action being afforded by the object. An affordance similarity matrix was generated which reflected similarity in affordances between pairs of objects. Two clusters emerged, reflecting correlations between affordance ratings in objects smaller than body size and larger than body size. These clusters did not correlate themselves. There was a trough in similarity ratings between objects ~105 cm and ~130 cm, arguably reflecting the body size boundary. The authors subsequently provide some evidence that this clear demarcation is not simply an incidental reflection of body size, but likely causally related. This evidence comes in the flavour of requiring Ps to imagine themselves as small as a cat or as large as an elephant and showing a predicted shift in the affordance boundary. The manuscript further demonstrates that ChatGPT (theoretically interesting because it's trained on language alone without sensorimotor information; trained now on words rather than images) showed a similar boundary.

The authors also conducted a small MRI study task where Ps decided whether a probe action was affordable (graspable?) and created a congruency factor according to the answer (yes/no). There was an effect of congruency in the posterior fusiform and superior parietal lobule for objects within body size range, but not outside. No effects in LOC or M1.

The major strength of this manuscript in my opinion is the methodological novelty. I felt the correlation matrices were a clever method for demonstrating these demarcations, the imagination manipulation was also exciting, and the ChatGPT analysis provided excellent food for thought. These findings are important for our understanding of the interactions between action and perception, and hence for researchers from a range of domains of cognitive neuroscience.

The major elements that limit conclusions and I'd recommend to be addressed in a revision include justification of the 80% of Ps removed for the imagination analysis, and consideration that an MRI study with 12 P in this context can really only provide pilot data. I'd also encourage the authors to consider theoretically how else this study could really have turned out and therefore the nature of the theoretical progress.

Specifics:<br /> 1. The main behavioural work appears well-powered (>500 Ps). This sample reduces to 100 for the imagination study, after removing Ps whose imagined heights fell within the human range (100-200 cm). Why 100-200 cm? 100 cm is pretty short for an adult. Removing 80% of data feels like conclusions from the imagination study should be made with caution.

2. There are only 12 Ps in the MRI study, which I think should mean the null effects are not interpreted. I would not interpret these data as demonstrating a difference between SPL and LOC/M1, but rather that some analyses happened to fall over the significance threshold and others did not.

3. I found the MRI ROI selection and definition a little arbitrary and not really justified, which rendered me even more cautious of the results. Why these particular sensory and motor regions? Why M1 and not PMC or SMA? Why SPL and not other parietal regions? Relatedly, ROIs were defined by thresholding pF and LOC at "around 70%" and SPL and M1 "around 80%", and it is unclear how and why these (different) thresholds were determined.

4. Discussion and theoretical implications. The authors discuss that the MRI results are consistent with the idea we only represent affordances within body size range. But the interpretation of the behavioural correlation matrices was that there was this similarity also for objects larger than body size, but forming a distinct cluster. I therefore found the interpretation of the MRI data inconsistent with the behavioural findings.

5. In the discussion, the authors outline how this work is consistent with the idea that conceptual and linguistic knowledge is grounded in sensorimotor systems. But then reference Barsalou. My understanding of Barsalou is the proposition of a connectionist architecture for conceptual representation. I did not think sensorimotor representation was privileged, but rather that all information communicates with all other to constitute a concept.

6. More generally, I believe that the impact and implications of this study would be clearer for the reader if the authors could properly entertain an alternative concerning how objects may be represented. Of course, the authors were going to demonstrate that objects more similar in size afforded more similar actions. It was impossible that Ps would ever have responded that aeroplanes afford grasping and balls afford sitting, for instance. What do the authors now believe about object representation that they did not believe before they conducted the study? Which accounts of object representation are now less likely?

Reviewer #2 (Public Review):

Summary<br /> In this work, the authors seek to test a version of an old idea, which is that our perception of the world and our understanding of the objects in it are deeply influenced by the nature of our bodies and the kinds of behaviours and actions that those objects afford. The studies presented here muster three kinds of evidence for a discontinuity in the encoding of objects, with a mental "border" between objects roughly of human body scale or smaller, which tend to relate to similar kinds of actions that are yet distinct from the kinds of actions implied by human-or-larger scale objects. This is demonstrated through observers' judgments of the kinds of actions different objects afford; through similar questioning of AI large-language models (LLMs); and through a neuroimaging study examining how brain regions implicated in object understanding make distinctions between kinds of objects at human and larger-than-human scales.

Strengths <br /> The authors address questions of longstanding interest in the cognitive neurosciences -- namely how we encode and interact with the many diverse kinds of objects we see and use in daily life. A key strength of the work lies in the application of multiple approaches, as noted in the summary. Examining the correlations among kinds of objects, with respect to their suitability for different action kinds, is novel, as are the complementary tests of judgments made by LLMs.

Weaknesses <br /> A limitation of the tests of LLMs may be that it is not always known what kinds of training material was used to build these models, leading to a possible "black box" problem. Further, presuming that those models are largely trained on previous human-written material, it may not necessarily be theoretically telling that the "judgments" of these models about action-object pairs show human-like discontinuities. Indeed, verbal descriptions of actions are very likely to mainly refer to typical human behaviour, and so the finding that these models demonstrate an affordance discontinuity may simply reflect those statistics, rather than evidence that affordance boundaries can arise independently even without "organism-environment interactions" as the authors claim here.

The authors include a clever manipulation in which participants are asked to judge action-object pairs, having first adopted the imagined size of either a cat or an elephant, showing that the discontinuity in similarity judgments effectively moved to a new boundary closer to the imagined scale than the veridical human scale. The dynamic nature of the discontinuity suggests a different interpretation of the authors' main findings. It may be that action affordance is not a dimension that stably characterises the long-term representation of object kinds, as suggested by the authors' interpretation of their brain findings, for example. Rather these may be computed more dynamically, "on the fly" in response to direct questions (as here) or perhaps during actual action behaviours with objects in the real world.

Reviewer #3 (Public Review):

Summary:<br /> Feng et al. test the hypothesis that human body size constrains the perception of object affordances, whereby only objects that are smaller than the body size will be perceived as useful and manipulable parts of the environment, whereas larger objects will be perceived as "less interesting components."

To test this idea, the study employs a multi-method approach consisting of three parts:

In the first part, human observers classify a set of 24 objects that vary systematically in size (e.g., ball, piano, airplane) based on 14 different affordances (e.g., sit, throw, grasp). Based on the average agreement of ratings across participants, the authors compute the similarity of affordance profiles between all object pairs. They report evidence for two homogenous object clusters that are separated based on their size with the boundary between clusters roughly coinciding with the average human body size. In follow-up experiments, the authors show that this boundary is larger/smaller in separate groups of participants who are instructed to imagine themselves as an elephant/cat.

In the second part, the authors ask different large language models (LLMs) to provide ratings for the same set of objects and affordances and conduct equivalent analyses on the obtained data. Some, but not all, of the models produce patterns of ratings that appear to show similar boundary effects, though less pronounced and at a different boundary size than in humans.

In the third part, the authors conduct an fMRI experiment. Human observers are presented with four different objects of different sizes and asked if these objects afford a small set of specific actions. Affordances are either congruent or incongruent with objects. Contrasting brain activity on incongruent trials against brain activity on congruent trials yields significant effects in regions within the ventral and dorsal visual stream, but only for small objects and not for large objects.

The authors interpret their findings as support for their hypothesis that human body size constrains object perception. They further conclude that this effect is cognitively penetrable, and only partly relies on sensorimotor interaction with the environment (and partly on linguistic abilities).

Strengths:<br /> The authors examine an interesting and relevant question and articulate a plausible (though somewhat underspecified) hypothesis that certainly seems worth testing. Providing more detailed insights into how object affordances shape perception would be highly desirable. Their method of analyzing similarity ratings between sets of objects seems useful and the multi-method approach is quite original and interesting.

Weaknesses:<br /> The study presents several shortcomings that clearly weaken the link between the obtained evidence and the drawn conclusions. Below I outline my concerns in no particular order:

1) Even after several readings, it is not entirely clear to me what the authors are proposing and to what extent the conducted work actually speaks to this. In the introduction, the authors write that they seek to test if body size serves not merely as a reference for object manipulation but also "plays a pivotal role in shaping the representation of objects." This motivation seems rather vague motivation and it is not clear to me how it could be falsified.<br /> Similarly, in the discussion, the authors write that large objects do not receive "proper affordance representation," and are "not the range of objects with which the animal is intrinsically inclined to interact, but probably considered a less interesting component of the environment." This statement seems similarly vague and completely beyond the collected data, which did not assess object discriminability or motivational values.<br /> Overall, the lack of theoretical precision makes it difficult to judge the appropriateness of the approaches and the persuasiveness of the obtained results. This is partly due to the fact that the authors do not spell out all of their theoretical assumptions in the introduction but insert new "speculations" to motivate the corresponding parts of the results section. I would strongly suggest clarifying the theoretical rationale and explaining in more detail how the chosen experiments allow them to test falsifiable predictions.

2) The authors used only a very small set of objects and affordances in their study and they do not describe in sufficient detail how these stimuli were selected. This renders the results rather exploratory and clearly limits their potential to discover general principles of human perception. Much larger sets of objects and affordances and explicit data-driven approaches for their selection would provide a far more convincing approach and allow the authors to rule out that their results are just a consequence of the selected set of objects and actions.

3) Relatedly, the authors could be more thorough in ruling out potential alternative explanations. Object size likely correlates with other variables that could shape human similarity judgments and the estimated boundary is quite broad (depending on the method, either between 80 and 150 cm or between 105 to 130 cm). More precise estimates of the boundary and more rigorous tests of alternative explanations would add a lot to strengthen the authors' interpretation.

4) Even though the division of the set of objects into two homogenous clusters appears defensible, based on visual inspection of the results, the authors should consider using more formal analysis to justify their interpretation of the data. A variety of metrics exist for cluster analysis (e.g., variation of information, silhouette values) and solutions are typically justified by convergent evidence across different metrics. I would recommend the authors consider using a more formal approach to their cluster definition using some of those metrics.

5) While I appreciate the manipulation of imagined body size, as a way to solidify the link between body size and affordance perception, I find it unfortunate that this is implemented in a between-subjects design, as this clearly leaves open the possibility of pre-existing differences between groups. I certainly disagree with the authors' statement that their findings suggest "a causal link between body size and affordance perception."

6) The use of LLMs in the current study is not clearly motivated and I find it hard to understand what exactly the authors are trying to test through their inclusion. As noted above, I think that the authors should discuss the putative roles of conceptual knowledge, language, and sensorimotor experience already in the introduction to avoid ambiguity about the derived predictions and the chosen methodology. As it currently stands, I find it hard to discern how the presence of perceptual boundaries in LLMs could constitute evidence for affordance-based perception.

7) Along the same lines, the fMRI study also provides very limited evidence to support the authors' claims. The use of congruency effects as a way of probing affordance perception is not well motivated. What exactly can we infer from the fact a region may be more active when an object is paired with an activity that the object doesn't afford? The claim that "only the affordances of objects within the range of body size were represented in the brain" certainly seems far beyond the data.

Importantly (related to my comments under 2) above), the very small set of objects and affordances in this experiment heavily complicates any conclusions about object size being the crucial variable determining the occurrence of congruency effects.

I would also suggest providing a more comprehensive illustration of the results (including the effects of CONGRUENCY, OBJECT SIZE, and their interaction at the whole-brain level).

Overall, I consider the main conclusions of the paper to be far beyond the reported data. Articulating a clearer theoretical framework with more specific hypotheses as well as conducting more principled analyses on more comprehensive data sets could help the authors obtain stronger tests of their ideas.

Reviewer #1 (Public Review):

Summary:

Sex differences in the liver gene expression and function have previously been proposed to be caused by sex differences in the pattern growth hormone (GH) secretion by the pituitary, which are established by the effects of testicular hormones that act on the hypothalamus perinatally to masculinize control of pituitary GH secretion beginning at puberty and for the rest of the animal's life. The Waxman lab has previously implicated GH control of STAT5 as a critical event leading to a masculine pattern of gene expression. The present study separates male-biased regulatory sites associated with the male-biased genes into different classes based on their responsiveness to the cyclic male pattern of STAT5 activity, and investigates DNAse hypersensitivity sites (DHS) of different classes showing cyclic sex-bias or not. It further reports on the binding of transcription factors to STAT5-sensitive DHS, and involvement of specific histone marks at these sites. The study argues that STAT5 is the proximate factor regulating chromatin accessibility in about 1/3 of male-biased DHS that are sexually differentiated by GH secretion. The authors propose the pulsatile GH secretion as a novel proximate mechanism of regulating chromatin accessibility to cause sex differences.

Strengths:

The study offers new insight into the effects of hypophysectomy and injection of GH on different classes of sex-biased genes in mouse liver. The results support the general conclusion of the authors. Cyclic secretion of other hormones (for example, estrous secretion of estrogens and progesterone) are well known to cause sex differences in multiple organs in rodents, and it will be interesting to assess if these cyclic secretions induce similar changes in chromatin accessibility causing female tissue gene expression to differ from that of males.

Weaknesses:

The authors argue for two major mechanisms controlling sexual bias in liver gene expression, and analyze in depth one of these mechanisms. The focus is on the group of DHS (about 1/3 of all male-biased DHS) in which the sex bias is controlled by cyclic secretion of growth hormone (GH) in males, compared to static and low growth hormone in adult females. The sex difference in pituitary secretion of GH is induced by permanent effects of androgens acting on the hypothalamus perinatally. The manuscript study would be improved by further discussion of the mechanistic relationship between this class of sex-biased DHS and the other 2/3 of liver DHS that also show male-biased accessibility but whose chromatin does not respond directly to GH-stimulated STAT5. Previous studies, including those in the Waxman lab (PMIDs: 26959237, 18974276, 35396276) suggest castration of males or gonadectomy of both sexes eliminates most sex differences in mRNA expression in mouse liver, and/or that androgens such as DHT or testosterone administered in adulthood potentially reverses the effects of gonadectomy and/or masculinizes liver gene expression. It is not clear from the present discussion whether the GH/STAT5 cyclic effects to masculinize chromatin status require the presence of androgens in adulthood to masculinize pituitary GH secretion. Are there analyses of the present (or past) data that might provide evidence about a dual role for GH and androgen acting on the same genes? For example, are sex-biased DHS bound by androgen-dependent factors or show other signs of androgen sensitivity? Are histone marks associated with DHS regulated by androgens? Moreover, it would help if the authors indicate whether they believe that the "constitutive" static sex differences in the larger 2/3 set of male-biased DHS are the result of "constitutive" (but variable) action of testicular androgens in adulthood. Although the present study is nicely focused on the GH pulse-sensitive DHS, is there mechanistic overlap in sex-biasing mechanisms with the larger static class of sex-biased liver DHS?

Reviewer #2 (Public Review):

Summary:

The present work addresses the mechanisms linking the sex-dependent temporal GH secretion patterns to the robust sex differences in chromatin accessibility and transcription factor binding that ultimately regulate sexually dimorphic liver gene expression. Using DNAseq analysis genomic sites hypersensitive to cleavage by DNase I, DNase hypersensitive sites [DHS] were studied in hepatocytes from male and female mice. DHS in the genome corresponds to accessible chromatin regions and encompasses key regulatory elements, including enhancers, promoters, insulators, and silencers, often flanked by specific histone modifications, and all of these players were described in different settings of GH action. Importantly, the dynamics of sex-dependent and independent chromatin accessibility linked to STAT5 binding were evaluated. For that purpose, hepatic samples from mice were divided into STAT high and STAT low binding by EMSA screening. With this information changes in DHS related to STAT binding were calculated in both sexes, giving an approximation of chromatin opening in response to STAT5, or alternatively to hypophsectomy, or a single GH pulse. More the 800 male-biased DHS (from a total of more than 70000 DHS) regions were identified in the STAT5 high groups, implying that the binding of a plasma GH pulse activates STAT5, and evokes a dynamic cycle of male liver chromatin opening and closing at sites that comprised 31% of all male-biased DHS. This proves that the pulsatility of plasma GH stimulation confers significant male bias in chromatin accessibility, and STAT5 binding at a fraction of the genomic sites linked to sex-biased liver gene expression and liver disease. As a proof of concept, authors show that a single physiological replacement dose or pulse of GH given to hypophysectomized mice recapitulate, within 30 min, the pulsatile re-opening of chromatin seen in pituitary-intact male mouse liver.

In another male-biased DHS set (69% of male-biased DHS), chromatin accessibility was static, that is unchanged across the peaks and valleys of GH-induced liver STAT5 activity and mapped to a set of target genes and processes distinct though sometimes overlapping those of the dynamic male-biased DHS.

In view of these distinct dynamic and static DHS in males, authors evaluated key epigenetic features distinguishing the dynamic STAT5-driven mechanism of chromatin opening from that of static male-biased DHS, which are constitutively open in the male liver but closed in the female liver. The analysis of histone marks enriched at each class of sex-biased DHS indicated exquisite differences in the epigenetic mechanisms that mediate sex-specific gene repression in each sex. For example, H3K27me3 and H3K9me3, two widely used repressive histone marks, are used in a unique way in each sex to enforce sex differences in chromatin states at sex-biased DHS.

Finally, the work recapitulates and explains the classifications of sex dimorphic genes made in previous works. Sex-biased and pituitary hormone-dependent DHS act as regulatory elements with a positive enhancer potential, to induce or maintain gene expression in the intact liver by sustaining an open chromatin in the case of class I male-biased DHS and class I male-biased genes in the male liver. Contrariwise DHS may participate in the inhibition of gene expression by maintaining a closed chromatin state, as in the case of class II male-biased DHS and class II female-biased genes in male liver.<br /> These results as a whole present a complex mechanism by which GH regulates the sexual dimorphism of liver genes in order to cope with the metabolic needs of each sex. In a complete story, the information on chromatin accessibility, histone modification, and transcription factor binding was integrated to elucidate the complex patterns of transcriptional regulation, which is sexually dimorphic in the liver.

Strengths:

The work presents a novel insight into the fundamental underlying epigenetic mechanisms of sex-biased gene regulation.

Results are supported by numerous Tables, and Supplementary Tables with the raw data, which present the advantage that they may be reanalyzed in the future to prove new hypotheses.

Weaknesses:

It is a complicated work to analyze, even though the main messages are clearly conveyed.

Joint Public Review:

The manuscript by Mitra and coworkers analyses the functional role of Orai in the excitability of central dopaminergic neurons in Drosophila. The authors show that a dominant-negative mutant of Orai (OraiE180A) significantly alters the gene expression profile of flight-promoting dopaminergic neurons (fpDANs). Among them, OraiE180A attenuates the expression of Set2 and enhances that of E(z) shifting the level of epigenetic signatures that modulate gene expression. The present results also demonstrate that Set2 expression via Orai involves the transcription factor Trl. The Orai-Trl-Set2 pathway modulates the expression of VGCC, which, in turn, are involved in dopamine release. The topic investigated is interesting and timely and the study is carefully performed and technically sound.

The reviewers appreciate the authors' efforts to revise the manuscript in order to address many of their concerns. Nevertheless, there remain a few important issues:

1) The main issue relates to Set2, and how STIM1 expression rescues Set2-dependent functions in Set2 KO flies. If Set2 is downstream of STIM1, how would STIM1 over-expression rescue a Set2-dependent effect?

2) There is still no characterization of SOCE in fpDANs from flies expressing native Orai or the dominant negative OraiE180A mutant.

3) The revised version does not include an analysis of the STIM:Orai stoichiometry, which has been demonstrated to be essential for SOCE.

Reviewer #1 (Public Review):

Hyperactivation of mTOR signaling causes epilepsy. It has long been assumed that this occurs through overactivation of mTORC1, since treatment with the mTORC1 inhibitor rapamycin suppresses seizures in multiple animal models. However, the recent finding that genetic inhibition of mTORC1 via Raptor deletion did not stop seizures while inhibition of mTORC2 did, challenged this view (Chen et al, Nat Med, 2019). In the present study, the authors tested whether mTORC1 or mTORC2 inhibition alone was sufficient to block the disease phenotypes in a model of somatic Pten loss-of-function (a negative regulator of mTOR). They found that inactivation of either mTORC1 or mTORC2 alone normalized brain pathology but did not prevent seizures, whereas dual inactivation of mTORC1 and mTORC2 prevented seizures. As the functions of mTORC1 versus mTORC2 in epilepsy remain unclear, this study provides important insight into the roles of mTORC1 and mTORC2 in epilepsy caused by Pten loss and adds to the emerging body of evidence supporting a role for both complexes in the disease development.

Strengths:<br /> The animal models and the experimental design employed in this study allow for a direct comparison between the effects of mTORC1, mTORC2, and mTORC1/mTORC2 inactivation (i.e., same animal background, same strategy and timing of gene inactivation, same brain region, etc.). Additionally, the conclusions on brain epileptic activity are supported by analysis of multiple EEG parameters, including seizure frequencies, sharp wave discharges, interictal spiking, and total power analyses.

Weaknesses:<br /> The sample size of the study is small and does not allow for the assessment of whether mTORC1 or mTORC2 inactivation reduces seizure frequency or incidence. This is a limitation of the study.

The authors describe that they inactivated mTORC1 and mTORC2 in a new model of somatic Pten loss-of-function in the cortex. This is slightly misleading since Cre expression was found both in the cortex and the underlying hippocampus, as shown in Figure 1. Throughout the manuscript, they provide supporting histological data from the cortex. However, since Pten loss-of-function in the hippocampus can lead to hippocampal overgrowth and seizures, data showing the impact of the genetic rescue in the hippocampus would further strengthen the claim that neither mTORC1 nor mTORC2 inactivation prevents seizures.

Some of the methods for the EEG seizure analysis are unclear. The authors describe that for control and Pten-Raptor-Rictor LOF animals, all 10-second epochs in which signal amplitude exceeded 400 μV at two time-points at least 1 second apart were manually reviewed, whereas, for the Pten LOF, Pten-Raptor LOF, and Pten-Rictor LOF animals, at least 100 of the highest-amplitude traces were manually reviewed. Does this mean that not all flagged epochs were reviewed? This could potentially lead to missed seizures. Additionally, the inclusion of how many consecutive hours were recorded among the ~150 hours of recording per animal would help readers with the interpretation of the data.

Finally, it is surprising that mTORC2 inactivation completely rescued cortical thickness since such pathological phenotypes are thought to be conserved down the mTORC1 pathway. Additional comments on these findings in the Discussion would be interesting and useful to the readers.

Reviewer #2 (Public Review):

Summary:<br /> The study by Cullen et al presents intriguing data regarding the contribution of mTOR complex 1 (mTORC1) versus mTORC2 or both in Pten-null-induced macrocephaly and epileptiform activity. The role of mTORC2 in mTORopathies, and in particular Pten loss-off-function (LOF)-induced pathology and seizures, is understudied and controversial. In addition, recent data provided evidence against the role of mTORC1 in PtenLOF-induced seizures. To address these controversies and the contribution of these mTOR complexes in PtenLOF-induced pathology and seizures, the authors injected a AAV9-Cre into the cortex of conditional single, double, and triple transgenic mice at postnatal day 0 to remove Pten, Pten+Raptor or Rictor, and Pten+raptor+rictor. Raptor and Rictor are essentially binding partners of mTORC1 and mTORC2, respectively. One major finding is that despite preventing mild macrocephaly and increased cell size, Raptor knockout (KO, decreased mTORC1 activity) did not prevent the occurrence of seizures and the rate of SWD event, and aggravated seizure duration. Similarly, Rictor KO (decreased mTORC2 activity) partially prevented mild macrocephaly and increased cell size but did not prevent the occurrence of seizures and did not affect seizure duration. However, Rictor KO reduced the rate of SWD events. Finally, the pathology and seizure/SWD activity were fully prevented in the double KO. These data suggest the contribution of both increased mTORC1 and mTORC2 in the pathology and epileptic activity of Pten LOF mice, emphasizing the importance of blocking both complexes for seizure treatment. Whether these data apply to other mTORopathies due to Tsc1, Tsc2, mTOR, AKT or other gene variants remains to be examined.

Strengths:<br /> The strengths are as follows: 1) they address an important and controversial question that has clinical application, 2) the study uses a reliable and relatively easy method to KO specific genes in cortical neurons, based on AAV9 injections in pups. 2) they perform careful video-EEG analyses correlated with some aspects of cellular pathology.

Weaknesses:<br /> The study has nevertheless a few weaknesses: 1) the conclusions are perhaps a bit overstated. The data do not show that increased mTORC1 or mTORC2 are sufficient to cause epilepsy. However the data clearly show that both increased mTORC1 and mTORC2 activity contribute to the pathology and seizure activity and as such are necessary for seizures to occur. 2) the data related to the EEG would benefit from having more mice. Adding more mice would have helped determine whether there was a decrease in seizure activity with the Rictor or Raptor KO. 3) it would have been interesting to examine the impact of mTORC2 and mTORC1 overexpression related to point #1 above.

Reviewer #3 (Public Review):

Summary: This study investigated the role of mTORC1 and 2 in a mouse model of developmental epilepsy which simulates epilepsy in cortical malformations. Given activation of genes such as PTEN activates TORC1, and this is considered to be excessive in cortical malformations, the authors asked whether inactivating mTORC1 and 2 would ameliorate the seizures and malformation in the mouse model. The work is highly significant because a new mouse model is used where Raptor and Rictor, which regulate mTORC1 and 2 respectively, were inactivated in one hemisphere of the cortex. The work is also significant because the deletion of both Raptor and Rictor improved the epilepsy and malformation. In the mouse model, the seizures were generalized or there were spike-wave discharges (SWD). They also examined the interictal EEG. The malformation was manifested by increased cortical thickness and soma size.

Strengths: The presentation and writing are strong. The quality of data is strong. The data support the conclusions for the most part. The results are significant: Generalized seizures and SWDs were reduced when both Torc1 and 2 were inactivated but not when one was inactivated.

Weaknesses: One of the limitations is that it is not clear whether the area of cortex where Raptor or Rictor were affected was the same in each animal. Also, it is not clear which cortical cells were measured for soma size. Another limitation is that the hippocampus was affected as well as the cortex. One does not know the role of cortex vs. hippocampus. Any discussion about that would be good to add. It would also be useful to know if Raptor and Rictor are in glia, blood vessels, etc.

Reviewer #1 (Public Review):

In "Resting-state alterations in behavioral variant frontotemporal dementia are related to the distribution of monoamine and GABA neurotransmitter systems" by Hahn et al, the authors investigate the association between structural and functional alterations in bvFTD and neurotransmitter systems. The authors take this a step further and also relate functional activation reductions in bvFTD to mRNA expression levels of neurotransmitter systems, and clinical/behavioural measures of the bvFTD subjects. The authors find significant associations between fALFF bvFTD maps and serotonin, dopamine, noradrenaline, and GABAa receptors/transporters, demonstrating a link between specific neurotransmitter systems and functional alterations in bvFTD. They successfully achieve their aim of finding neurotransmitter systems that may subserve functional changes in bvFTD. This is strengthened by the finding that receptor-fALFF correspondence is correlated with performance on cognitive tests across individuals. This multimodal approach is important for informing clinical interventions in bvFTD and the authors nicely demonstrate a link between functional changes in bvFTD, receptor systems, and cognition. In my opinion, the primary weakness of the study is that the effects are small, although I wonder whether this is related to the fact that some of the neurotransmitter receptor maps have small sample size and low sensitivity in the cortex.

Reviewer #2 (Public Review):

The aim of this study was to relate functional alterations in patients with bvFTD to neurotransmitter maps provided by the JuSpace toolbox in order to better understand the underlying pathological mechanisms of this disease.

A strength of the study is the novelty of this aim. Some weaknesses are the different fMRI parameters of patients belonging to each centre and a better explanation of some methodological choices as well a better description of the JuSpace toolbox.

The authors have achieved their aims and the results seem to support some conclusions, although the results should be interpreted in light of a potential lack of proper control for multiple comparisons.

This work will increase the use of approaches that relate brain abnormalities to neurotransmitters and transcriptomics.

There is an increasing trend to assess the correspondence between neuroimaging alterations and detailed information of neurotransmitters across the brain. This work represents this trend and adds to an increasing body of work doing the same with transcriptomics.

Reviewer #3 (Public Review):

This manuscript analyzed resting state functional MRI metrics related to behavioral variant frontotemporal dementia (bvFTD) for associations with patterns of neurotransmitter system receptor distribution, patterns of neurotransmitter-related gene expression, and profiles of performance on neuropsychological test battery items.

The overarching goal of the work was to assess whether these analyses point to selective vulnerability of some neurotransmitter systems in the symptomatology of bvFTD. The manuscript reports that reductions in fMRI measures of local brain functional activity in bvFTD followed the distribution of specific neurotransmitter systems. No similar findings were identified for MRI-based gray matter volume measurements.

Strengths of the manuscript include its leveraging of publicly available tools for large-scale regional brain mRNA profiles and neurotransmitter receptor distributions. An additional positive step for the literature involves further development of the concept that biomarkers of disruptions to specific functionally-connected networks may guide specific treatment strategies (as a corollary to this work, related to neurotransmitter system disruption) in neurodegenerative disease.

A weakness of the manuscript is that it is not able to directly address the main literature gap described in the Introduction -- namely, whether there is specific vulnerability of certain neuronal types versus other in bvFTD, or whether broader network/region-based neurodegeneration is the driver (and happens to include some selective neurotransmitter-related disruptions). In other words, if "A" is a biomarker of bvFTD, "A" has a partial correlation with "B", and the "AB" correlation has a partial correlation with "C", it seems too far a leap to conclude that "B" (in this case, profiles/distributions of neurotransmitter systems) is the central figure in the cascade.

Joint Public Review:

The authors clearly state the current mystery surrounding transcriptional regulation of ACE2-expression, and how SARS-CoV-2 infection might impact this regulation. Several medications have been identified impacting the gene expression of ACE2, such as colchicine. However, the mechanism behind this regulation of ACE2 gene expression is currently unknown, yet worth investigating. Indeed, getting to know the mechanism behind the transcriptional regulation of ACE2 might lead to development of therapies targeting this expression in order to attenuate COVID-19 severity.<br /> In order to achieve insight in the regulation of ACE2 expression by SARS-CoV-2, the authors used a luciferase reporter based assay to investigate a range of signaling pathways. The authors found that ACE2 expression is upregulated by SARS-CoV-2 infection via activation of transcription factor Sp1 and inhibition of HNF4α through the PI3K/AKT pathway. This led to the discovery that inhibition of Sp1 using mithramycin A reduces SARS-CoV-2 infection in vitro and in an animal model.

Strengths<br /> - The authors used an elegant design for their investigation. Based on a broad luciferase based assay, and keeping in mind the opposite effects of SARS-CoV-2 infection and colchicine administration on the expression of ACE2, they identified transcription factors as potential candidates for regulating ACE2 expression.<br /> - Throughout the several experiments performed, the antagonizing effects of SARS-CoV-2 infection and colchicine on the identified transcription factors (Sp1 and HNF4α) are consistent and therefore strengthen the conclusions.

Weaknesses<br /> - For the in vitro work, only one cell line is used in this article: HPAEpiC cells, an immortalized human cell line derived from alveolar epithelial type II cells. This limits the generalizability of the results obtained in this study, as SARS-CoV-2 is known to infect several kinds of cells.<br /> - From the results of two separate experiments (colchicine leading to reduced ACE2-expression in HPAEpiC cells & colchicine leading to reduced SARS-CoV-2 replication in HPAEpiC cells), the authors infer that inhibition of ACE2 expression by colchicine suppresses SARS-CoV-2 infection. However, their experiments do not explicitly prove this hypothesis and do not give weight to the importance of this reduced ACE2 expression in the colchicine antiviral effect they observed, as other mechanisms may play a (bigger) role in producing this effect.<br /> - The authors refer to colchicine as a drug leading to mortality benefit when used as treatment for COVID-19 (line 101-105). However, whether colchicine is beneficial in COVID-19 is unclear. For instance, the randomized controlled trial by the RECOVERY Collaborative Group (Lancet Respir Med 2021), which included more than 11,000 patients, did not find benefit from colchicine in patients admitted to hospital with COVID-19. The authors refer to the review of Drosos et al to infer benefit of colchicine in COVID-19, however this review ignores the numerous trials contradicting this (as also stated in a letter from Finsterer in response to this review). The meta-analysis by Elshafei to which the authors refer was published before the largest RCT by the RECOVERY Group was published.<br /> - The authors did not let a pathologist blinded to the infection/treatment state of the animals score the samples obtained in the animal experiments, which could have introduced bias in these results.

These results add to the existing knowledge that the characteristics of ACE2 (its functionality and abundance) in the respiratory tract are pivotal to understand infection by SARS-CoV-2. The author conclusions are supported by the results. The identification of the two transcription factors influenced by SARS-CoV-2 infection is valuable, but needs further research to assess whether their effect on ACE2 expression is also seen in other cell types than the one assessed by the authors. More in-depth research will have to follow to assess if and how targeting the identified transcription factors could ultimately benefit patients with COVID-19.

Reviewer #2 (Public Review):

Prior results established that Lepr, Calcr, and Cck neurons are non-overlapping neuronal populations in the NTS that individually suppress food intake when activated. This paper examines the consequences of activating or inhibiting two or three of these populations simultaneously. Activating two or three populations inhibits food intake a body weight more than each individually. Activation of Lepr and/or Calcr neurons is not aversive based on the conditioned taste aversion test, whereas activating all three is aversive by this test, indicating that aversion due to Cck neurons activation is dominant. Vertical sleeve gastrectomy (VSG) causes weight loss, but inhibiting each of these neurons individual or all three of them does not prevent weight loss. Overall, this paper provides a solid set of results but does not provide mechanistic insight into any of the phenomena examined.

Reviewer #1 (Public Review):

The authors provide compelling evidence that the activation of distinct populations of NTS neurons provides stronger decreases in eating/body weight when co-activated. Avoidance is not necessarily linked to the extent of the effects but seems to depend on specific neurons which when activated, not only reduce eating but also induce avoidance reactions. The results of this study provide strong data promoting multi-targeted approaches to reduce eating and body weight in obesity. Interestingly, none of the pathways identified is necessary for the weight-reducing effect of vertical sleeve gastrectomy. Future studies will hopefully shed light on the type of neurotransmitters released by these distinct populations of NTS neurons.

Reviewer #2 (Public Review):

Summary:<br /> In this study, Wilmot et al., ran a series of experiments to describe a dopaminergic projection from LC to dHPC, and its functional role in trace fear conditioning (TFC). Using fiber photometry in LC, they show convincingly that the activity of LC TH neurons is increased to both cues and footshock, and that this increases with acquisition or TFC, and decreases during extinction of this association. Projections from LC to dHPC show a similar pattern of activity, and dopamine release (measured by the fluorescent sensor GRAB-DA) is also comparable to calcium activity from LC. While the authors do show that activity at the dopamine D1R/D5R is necessary for TFC, a direct test of the necessity of dopamine release from LC during TFC is not shown.

Strengths:<br /> • The authors clearly and effectively show that the LC-dHPC projection is activated by an aversive outcome (i.e. shock), and that activity in this pathway changes in response to learning about a neutral cue that predicts this shock (i.e. TFC). Furthermore, they show that increased dopamine release in dHPC can be observed if LC is chemogenetically activated. A critical role for dopamine receptors (but not β- and ⍺-adrenergic receptors) in TFC was demonstrated, and intra-dHPC injection of a D1R/D5R antagonist blocks this learning. Finally, dopamine release (measured by GRAB-DA) in dHPC was shown to also occur during trace fear conditioning.

• The authors have conclusively shown that activity at the dopamine receptors in the dPHC during trace fear conditioning is of the same pattern as calcium activity recorded both in LC cell bodies, but more importantly in the axonal projections from LC to dHPC. This is very good evidence that this pathway is recruited during TFC.

Weaknesses:<br /> • The claim that dopamine release in dHPC is caused by LC neurons is not directly tested. Unfortunately, the most critical experiment for the claims that dopamine release comes from LC during conditioning is not tested. A lack of dopamine signal in dHPC caused by inhibition of LC during TFC would show this. It is indeed an interesting observation that chemoegenetic activation of LC causes dopamine release in the dHPC. However, in the absence of concurrent VTA inhibition or lesion, it remains a possibility that the dopamine release is mediated through indirect actions on other dopamine-expressing neurons. The authors do a good job of arguing against this interpretation in the discussion, and the literature seems appropriate for this. However, the title is still an overstatement of the data presented in this study.

• The primary alternative interpretations of the phasic activation experiment are whether only stimulation to the cue events (both on and off), or whether only stimulation to the shock. Thus this experiment would benefit from additional data showing either a no shock control, to show that enhanced activity of the LC to the tone is not inherently aversive, or manipulations to the tone but not to the shock.

• Specificity of the GRAB-NE and GRAB-DA sensors should be either justified through additional experiments testing the alternative antagonist (i.e. GRAB-NE CNO+eticloprode / GRAB-DA CNO+yohimbine) or additional citations that have tested this already. It is critical for the claims of the paper to show that these sensors are specific to dopamine or norepinephrine.

• The role of dopamine in prediction error was tested through a series of conditions whereby the shock was presented either signaled (i.e. predicted), or not. However, another way that prediction error is signaled is through the absence of an expected outcome. Admittedly it might not be possible to observe a decrease in dopamine signaling with this methodology.

• The difference between Fig. 6E and 6H needs to be clarified. What is shown in Fig. 6E is that the response to the shock decreases through experience (i.e. by the 10th trial). However in Fig 6H, there is no difference between signaled and signaled shock, but this is during conditioning, and not after learning (based on my understanding of the methods, line 482).

• Unless I missed it, at no point in the manuscript is the number of subjects described. Please add the n per experiment within each section describing each experiment in the methods (Behavioral procedures). Some more details in the photometry statistical analysis would be helpful. For example, what is the n per group for every data set that is presented? How many trials per analysis?

Reviewer #1 (Public Review):

Summary:<br /> The authors investigate the role of the noradrenergic nucleus Locus Coeruleus (LC) in hippocampally-dependent learning and memory processes. The two stated aims of these experiments are to distinguish between 'tonic and phasic' activity and release in LC neurons and to determine the relative contribution of noradrenaline and dopamine, released from LC terminals, during learning. To address these questions, the investigators used a trace conditioning protocol (a behavior that is well established to be dependent on the hippocampus), coupled with a genetically based toolbox of sensors allowing measurements and manipulation of cell-type specific populations of neurons.

This includes photometric imaging of neuronal activity within the LC through Calcium signaling (Fig 1B), and in the hippocampal target site (Fig 3F), photostimulation of monoamine-containing neurons in the LC Fig 4B), measuring of extracellular dopamine and noradrenergic in the hippocampus with fluorescent sensors (GRABs) (Fig 5B). The study was complemented by a pharmacological approach to demonstrate that dopamine and not noradrenaline were essential for learning this task.

Results show that the calcium signal in the LC increased in response to tone or footshock in an intensity-dependent manner (Fig 1C,D,E F). LC responses can be conditioned and conditioned responses are of higher amplitude than the responses to the to-be-conditioned stimulus (Fig 2D). These results replicate sparse data gleaned over the past four decades using single and multiple-unit electrophysiological recording in LC in rats and monkeys. Calcium imaging LC axonal projections in the hippocampus showed a small but significant increase in response to tone onset and offset and to shock during conditioning.

Gain of function experiments show that enhancing a weak tone stimulus by phasic activation of LC through photostimulation during conditioning, facilitated subsequent memory performance (Fig 4D).

Fluorescent sensors demonstrated the release of both Noradrenaline and Dopamine in the hippocampus in response to activation of LC.

Using conventional pharmacology the essential role of dopamine was confirmed in the learning of this trace conditioning task, corroborating previous reports of hippocampal dopamine involvement in spatial learning.

Strengths:<br /> The experiments confirm many of the results of the past four decades from unit recordings from the LC in behaving rats and monkeys. The available data are sparse, due to the difficulty of recording from this tiny pontine nucleus; the reports emanate from only a few laboratories. Given the large amount of theorizing based on sparse data, it is important that the observations concerning the environmental contingencies driving the activity of LC be corroborated.

That dopamine is released from LC terminals in the forebrain has been known for 20 years (Devoto 2004), but this was largely ignored until recently when a few laboratories demonstrated the functional importance of this projection in hippocampal-dependent learning. The present corroboration should lend further credence and promote further studies of the factors governing this release of dopamine from LC terminals, into specific forebrain regions.

Weaknesses:<br /> --One criticism the authors have made of previous studies was that they have not distinguished between 'tonic' and 'phasic' LC activity and could not demonstrate 'time-locked phasic firing'. This has not been achieved in the present report, as an examination of Fig 1 C,D and 2 C,D shows. Previous reports in rats and monkeys, using unit recording in rats and monkeys clearly show that the latency of LC 'phasic' responses to salient or behaviorally relevant stimuli are in the range of tens of milliseconds, with a very short duration, often followed by a long-lasting inhibition. This kind of temporal precision concerning the phasic response cannot be gleaned from the time scale shown in the Figures (assuming the time scale is in seconds). We can discern a long-lasting increase in tonic firing level for the more salient stimuli (Fig 1C) (although the authors state in the discussion that "we did not observe obvious changes in tonic LC-HPC activity). This calcium imaging methodology as used in the present experiments can give us a general idea of the temporal relation of LC response to the stimulus, but apparently does not afford the millisecond resolution necessary to capture a phasic response, at least as the data are presented in the Figures.

--Much of the data presented here can be regarded as 'proof of concept' i.e. demonstrating that Photometric imaging of calcium signalling yields similar results concerning LC responses to salient or behaviorally relevant stimuli as has been previously reported using electrophysiological unit recording. The role of dopamine as the principal player in hippocampal-dependent learning also corroborates previous reports.

-- No attempt was made to address the important current question of the modular organisation of Locus Coeruleus, although the authors recognize the importance of this question and propose future experiments using their methodology to record simultaneously in several LC projection sites.

Reviewer #3 (Public Review):

Summary:<br /> The manuscript examines an important question, namely how the brain associates events spaced in time. It uses a variety of neural methods including fiber photometry as well as area-specific and pathway-silencing methods with the exquisite dissociation of norepinephrine and dopamine. The data show that neurons in the locus coeruleus (LC) respond to auditory cue onset, offset, and shock. These responses are stronger if the cue is paired with shock in a trace procedure. Optogenetic stimulation similar to the neural response captured by fiber photometry enhances associative learning. LC terminals in the dorsal hippocampus also showed phasic responses during fear conditioning and drove dopamine and norepinephrine responses. Pharmacological methods revealed that dopamine and not norepinephrine is critical for fear learning.

Strengths:<br /> The examination of the neural signal to different tone intensities, different shock intensities, repeated tone presentation (habituation), and conditioning, offers an unprecedented account of the neural signal to non-associative and associative processes. This kind of deconstruction of the elements of conditioning offers a strong account of how the brain processes the stimuli used and their interaction during learning.

Excellent use of data acquired with fiber photometry in the optogenetic interrogation study.

The use of pharmacology to disentangle dopamine and norepinephrine was excellent.

Weaknesses:<br /> While the optogenetic study was lovely, a control using the same stimulation but delivered at different time points would have been a good addition to show how critical the neural signal at tone onset, tone offset, and shock is.

Justification for the focus on D1 receptors was lacking.

The manuscript provides convincing evidence that the neural signal is not an error-correcting one by including a predicted (by a tone) and unpredicted shock. One possibility is that perhaps the unpredicted shock could be predicted by the context. Some clarification on the behavioural procedures would help understand if indeed the unsignaled shock could be predicted by the context or not.

Reviewer #3 (Public Review):

Summary:<br /> The authors set out to characterize the anatomical connectivity profile and the functional responses of chandelier cells (ChCs) in the mouse primary visual cortex. Using retrograde rabies tracing, optogenetics, and in vitro electrophysiology, they found that the primary source of input to ChCs are local layer 5 pyramidal cells, as well as long-range thalamic and cortical connections. ChCs provided input to local layer 2/3 pyramidal neurons, but did not receive reciprocal connections.

With two-photon calcium imaging recordings during passive viewing of drifting gratings, the authors showed that ChCs exhibit weakly selective visual responses, high correlations within their own population, and strong responses during periods of arousal (assessed by locomotion and pupil size). These results were replicated and extended in experiments with natural images and prediction of receptive field structure using a convolutional neural network.

Furthermore, the authors employed a learned visuomotor task in a virtual corridor to show that ChCs exhibit strong responses to mismatches between visual flow and locomotion, locomotion-related activation (similar to what was shown above), and visually-evoked suppression. They also showed the existence of two clusters of pyramidal neurons with functionally different responses - a cluster with "classically visual" responses and a cluster with locomotion- and mismatch-driven responses (the latter more correlated with ChCs). Comparing naive and trained mice, the authors found that visual responses of ChCs are suppressed following task learning, accompanied by a shortening of the axon initial segment (AIS) of pyramidal cells and an increase in the proportion of AIS contacted by ChCs. However, additional controls would be required to identify which component(s) of the experimental paradigm led to the functional and anatomical changes observed.

Finally, using a chemogenetic inactivation of ChCs, the authors propose weak connectivity to pyramidal cells (due to small effects in pyramidal cell activity). However, these results are not unequivocally supported, as the baseline activity of ChCs before inactivation is considerably lower, suggesting a potentially confounding homeostatic plasticity mechanism might already be operating.

Strengths:<br /> The authors bring a comprehensive, state-of-the-art methodology to bear, including rabies tracing, in vivo two-photon calcium imaging, in vitro electrophysiology, optogenetics and chemogenetics, and deep neural networks. Their analyses and statistical tests are sound and for the most part, support their claims. Their results are in line with previous findings and extend them to the primary visual cortex.

Weaknesses:<br /> - Some of the results (e.g. arousal-related responses) are not entirely surprising given that similar results exist in other cortical areas.

- Control analyses regarding locomotion patterns before and after learning the task (Figure 5), and additional control experiments to identify whether functional and anatomical changes following task learning were due to learning, repeated visual exposure, exposure to reward, or visuomotor experience would strengthen the claims made.

- The strength of the results of the chemogenetics experiment is impacted by the lower baseline activity of ChCs that express the KORD receptor. At present, it is not possible to exclude the presence of homeostatic plasticity in the network *before* the inactivation takes place.

Reviewer #1 (Public Review):

Overall, the experiments are well-designed and the results of the study are exciting. We have one major concern, as well as a few minor comments that are detailed in the following.

Major:<br /> 1. The authors suggest that "Visuomotor experience induces functional and structural plasticity of chandelier cells". One puzzling thing here, however, is that mice constantly experience visuomotor coupling throughout life which is not different from experience in the virtual tunnel. Why do the authors think that the coupled experience in the VR induces stronger experience-dependent changes than the coupled experience in the home cage? Could this be a time-dependent effect (e.g. arousal levels could systematically decrease with the number of head-fixed VR sessions)? The control experiment here would be to have a group of mice that experience similar visual flow without coupling between movement and visual flow feedback. Either change would be experience-dependent of course, but having the "visuomotor experience dependent" in the title might be a bit strong given the lack of control for that. We would suggest changing the pitch of the manuscript to one of the conclusions the authors can make cleanly (e.g. Figure 4).

Minor:<br /> 2. "ChCs shape the communication hierarchy of cortical networks providing visual and contextual information." We are not sure what this means.

3. "respond to locomotion and visuomotor mismatch, indicating arousal-related activity" This is not clear. We think we understand what the authors mean but would suggest rephrasing.

4. 'based on morphological properties revealed that 87% (287/329) of labeled neurons were ChCs" Please specify the morphological properties used for the classification somewhere in the methods.

5. We may have missed this - in the patch clamp experiment (Fig.1 H-K), please add information about how many mice/slices these experiments were performed in.

6. "These findings suggest that the rabies-labeled L1-4 neurons providing monosynaptic input to ChCs are predominantly inhibitory neurons". We are not sure this conclusion is warranted given the sparse set of neurons labelled and the low number of cells recorded in the paired patch experiment. We would suggest properly testing (e.g. stain for GABA on the rabies data) or rephrasing.

7. Figure 2E. A direct comparison of dF/F across different cell types can be subject to a problematic interpretation. The transfer function from spikes to calcium can be different from cell type to cell type. Additionally, the two cell populations have been marked with different constructs (despite the fact that it's the same GECI) further reducing the reliability of dF/F comparisons. We would recommend using a different representation here that does not rely on a direct comparison of dF/F responses (e.g. like the "response strength" used in Figure 3B). Assuming calcium dynamics are different in ChCs and PyCs - this similarity in calcium response is likely a coincidence.

8. If ChCs are more strongly driven by locomotion and arousal, then it's a bit counterintuitive that at the beginning of the visual corridor when locomotion speed consistently increases, the activity of ChCs consistently decreases. This does not appear to be driven by suppression by visual stimuli as it is present also in the first and last 20cm of the tunnel where there are no visual stimuli. How do the authors explain this?

9. The authors mention that "ChC responses underwent sensory-evoked plasticity during the repeated visual exposure, even though the visual stimuli were different from those encountered during training in the virtual tunnel". How would this work? And would this mean all visual responses are reduced? What is special about the visual experience in the virtual tunnel? It does not inherently differ from visual experience in the home cage, given that the test stimuli (full field gratings) are different from both.

10. Just as a point to consider for future experiments: For the open-loop control experiments, the visual flow is constant (20cm/s) - ideally, this would be a replay of the running speed the mouse previously generated to match statistics.

11. We would recommend specifying the parameters used for neuropil correction in the methods section.

12. If we understand correctly, the F0 used for the dF/F calculation is different from that used for division. Why is this?

13. Authors compare neuronal responses using "baseline-corrected average". Please specify the parameters of the baseline correction (i.e. what is used as baseline here).

Reviewer #2 (Public Review):

Summary:<br /> Seignette et al. investigated the potential roles of axo-axonic (chandelier) cells (ChCs) in a sensory system, namely visual processing. As introduced by the authors, the axo-axonic cell type has remained (and still is) somehow mysterious in its function. Seignette and colleagues leveraged the development of a transgenic mouse line selective for ChC, and applied a very wide range of techniques: transsynaptic rabies tracing, optogenetic input activation, in vitro electrophysiology, 2-photon recording in vivo, behavior and chemogenetic manipulations, to precisely determine the contribution of ChCs to the primary visual cortex network.

The main findings are 1) the identification of synaptic inputs to ChC, with a majority of local, deep layer principal neurons (PN), 2) the demonstration that ChC is strongly and synchronously activated by visual stimuli with low specificity in naive animals, 3) the recruitment of ChC by arousal/visuomotor mismatch, 4) the induction of functional and structural plasticity at the ChC-PN module, and, 5) the weak disinhibition of PNs induced by ChCs silencing. All these findings are strongly supported by experimental data and thoroughly compared to available evidence.

Strengths:<br /> This article reports an impressive range of very demanding experiments, which were well executed and analyzed, and are presented in a very clear and balanced manner. Moreover, the manuscript is well-written throughout, making it appealing to future readers. It has also been a pleasure to review this article.

In sum, this is an impressive study and an excellent manuscript, that presents no major flaws.

Notably, this study is one of the first studies to report on the activities and potential roles of axo-axonic cells in an active, integrated brain process, beyond locomotion as reported and published in V1. This type of research was much awaited in the fields of interneuron and vision research.

Weaknesses:<br /> There are no fundamental weaknesses; the latter mainly concern the presentation of the main results.

The main weakness may be that the different sections appear somehow disconnected conceptually.

Additionally, some parts deserve a more in-depth clarification/simplification of concepts and analytic methods for scientists outside the subfield of V1 research. Indeed, this paper will be of key interest to researchers of various backgrounds.

Reviewer #2 (Public Review):

In the revised manuscript, the authors aim to investigate brain-wide activation patterns following administration of the anesthetics ketamine and isoflurane, and conduct comparative analysis of these patterns to understand shared and distinct mechanisms of these two anesthetics. To this end, they perform Fos immunohistochemistry in perfused brain sections to label active nuclei, use a custom pipeline to register images to the ABA framework and quantify Fos+ nuclei, and perform multiple complementary analyses to compare activation patterns across groups. This is an interesting line of research and a tour de force in brain-wide Fos quantification.

I appreciate many of the changes that were made in the revised manuscript, including FDR correction and transparency in showing their results with and without transformation. However, several key issues described in our first review have not been addressed.

1-Aside from issues with their data transformation (see below), (a) I think they have some interesting Fos counts data in Figures 4B and 5B that indicate shared and distinct activation patterns after KET vs. ISO based anesthesia. These data are far closer to the raw data than PC analyses and need to be described and analyzed in the first figures long before figures with the more abstracted PC analyses. In other words, you need to show the concrete raw data before describing the highly transformed and abstracted PC analyses. (b) This gets to the main point that when selecting brain areas for follow up analyses, these should be chosen based on the concrete Fos counts data, not the highly transformed and abstracted PC analyses.

2-Now, the choice of data transformation for Fos counts is the most significant problem. First, the authors show in the response letter that not using this transformation (region density/brain density) leads to no clustering. However, they also showed the region-densities without transformation (which we appreciate) and it looks like overall Fos levels in the control group Home (ISO) are a magnitude (~10-fold) higher than those in the control group Saline (KET) across all regions shown. This large difference seems unlikely to be due to a biologically driven effect and seems more likely to be due to a technical issue, such as differences in staining or imaging between experiments. Was the Homecage-ISO experiment or at least the Fos labeling and imaging performed at the same time as for the Saline-Ketamine experiment? Please state the answer to this question in the Results section one way or the other.

3-Second, they need to deal with this large difference in overall staining or imaging for these two (Home/ISO and Saline/KET) experiments more directly; their current normalization choice does not really account for the large overall differences in mean values and variability in Fos counts (e.g. due to labeling and imaging differences).

3a-I think one option (not perfect but I think better than the current normalization choice) could be z-scoring each treatment to its respective control. They can analyze these z-scored data first, and then in later figures show PC analyses of these data and assess whether the two treatments separate on PC1/2. And if they don't separate, then they don't separate, and you have to go with these results.

3b-Alternatively, they need to figure out the overall intensity distributions from the different runs (if that the main reason of markedly different counts) and adjust their thresholds for Fos-positive cell detection based on this. I would expect that the saline and HC groups should have similar levels of activation, so they could use these as the 'control' group to determine a Fos-positive intensity threshold that gets applied to the corresponding 'treatment' group.

3c- If neither 3a nor 3b is an option then they need to show the outcomes of their analysis when using the untransformed data in the main figures (the untransformed data plots in their responses to reviewer are currently not in the main or supplementary figs) and discuss these as well.

Reviewer #1 (Public Review):

Overall, the manuscript has been improved by addressing some of the concerns, however, I am still very confused about the data analysis due to the use of data transformation (relative %fos), the fact that some graphs only show regions that are significant and the interpretation of the PCA analysis which I find inappropriate. Moreover, many answers in the rebuttal did not make it to the final manuscript and are not discussed and limitations raised by the reviewers are not discussed either.

1a. The addition of the EEG/EMG is useful, however, this information is not discussed. For instance, there are differences in EEG/EMG between the two groups (only Ket significantly increased delta/theta power, and only ISO decreased EMG power). These results should be discussed as well as the limitation of not having physiological measures of anesthesia to control for the anesthesia depth.<br /> 1b. The possibility that the differences in fos observed may be due to the doses used should be discussed.<br /> 1c. The possibility that the differences in fos observed may be due kinetic of anesthetic used should be discussed.

2b. I am confused because Fig 2C seems to show significant decrease in %fos in the hypothalamus, midbrain and cerebellum after KET, while the author responded that " in our analysis, we did not detect regions with significant downregulation when comparing anesthetized mice with controls." Moreover the new figure in the rebuttal in response to reviewer 2 suggests that Ket increases Fos in almost every single region (green vs blue) which is not the conclusion of the paper.

3. There are still critical misinterpretations of the PCA analysis. For instance, it is mentioned that "KET is associated with the activation of cortical regions (as evidenced by positive PC1 coefficients in MOB, AON, MO, ACA, and ORB) and the inhibition of subcortical areas (indicated by negative coefficients) " as well as "KET displays cortical activation and subcortical inhibition, whereas ISO shows a contrasting preference, activating the cerebral nucleus (CNU) and the hypothalamus while inhibiting cortical areas. To reduce inter-individual variability." These interpretations are in complete contradiction with the answer 2b above that there was no region that had decreased Fos by either anesthetic.

4. I still do not understand the rationale for the use of that metric. The use of a % of total Fos makes the data for each region dependent on the data of the other regions which wrongly leads to the conclusion that some regions are inhibited while they are not when looking at the raw data. Moreover, the interdependence of the variable (relative density) may affect the covariance structure which the PCA relies upon. Why not using the PCA on the logarithm of the raw data or on a relative density compared to the control group on a region-per-region basis instead of the whole brain?

Fig. 2B: it's unclear to me why the regions are connected by a line. Such representation is normally used for time series/within-subject series. What is the rationale for the order of the regions and the use of the line? The line connecting randomly organized regions is meaningless and confusing.

Fig 6A. the correlation matrices are difficult to interpret because of the low resolution and arbitrary order of brain regions. I recommend using hierarchical clustering and/or a combination of hierarchical clustering and anatomical organization (e.g. PMID: 31937658). While it is difficult to add the name of the regions on the graph I recommend providing supplementary figures with large high-resolution figures with the name of each brain region so the reader can actually identify the correlation between specific brain regions and the whole brain,

Rationale for Metric Choice: Note that I do not dispute the choice of the log which is appropriate, it is the choice of using the relative density that I am questioning.

5. I am still having difficulties understanding Fig. 3.<br /> Panel A: The lack of identification for the dots in panel A makes it impossible to understand which regions are relevant.<br /> Panel B: what is the metric that the up/down arrow summarizes? Fos density? Relative density? PC1/2?<br /> Panel C: it's unclear to me why the regions are connected by a line. Such representation is normally used for time series/within-subject series. What is the rationale for the order of the regions?

Reviewer #3 (Public Review):

The present study presents a comprehensive exploration of the distinct impacts of Isoflurane and Ketamine on c-Fos expression throughout the brain. To understand the varying responses across individual brain regions to each anesthetic, the researchers employ principal component analysis (PCA) and c-Fos-based functional network analysis. The methodology employed in this research is both methodical and expansive. Notably, the utilization of a custom software package to align and analyze brain images for c-Fos positive cells stands out as an impressive addition to their approach. This innovative technique enables effective quantification of neural activity and enhances our understanding of how anesthetic drugs influence brain networks as a whole.

The primary novelty of this paper lies in the comparative analysis of two anesthetics, Ketamine and Isoflurane, and their respective impacts on brain-wide c-Fos expression. The study reveals the distinct pathways through which these anesthetics induce loss of consciousness. Ketamine primarily influences the cerebral cortex, while Isoflurane targets subcortical brain regions. This finding highlights the differing mechanisms of action employed by these two anesthetics-a top-down approach for Ketamine and a bottom-up mechanism for Isoflurane. Furthermore, this study uncovers commonly activated brain regions under both anesthetics, advancing our knowledge about the mechanisms underlying general anesthesia.

Reviewer #3 (Public Review):

Summary:<br /> The study conducted by Ouasti et al. is an elegant investigation of fission yeast CAF-1, employing a diverse array of technologies to dissect its functions and their interdependence. These functions play a critical role in specifying interactions vital for DNA replication, heterochromatin maintenance, and DNA damage repair, and their dynamics involve multiple interactions. The authors have extensively utilized various in vitro and in vivo tools to validate their model and emphasize the dynamic nature of this complex.

Strengths:<br /> Their work is supported by robust experimental data from multiple techniques, including NMR and SAXS, which validate their molecular model. They conducted in vitro interactions using EMSA and isothermal microcalorimetry, in vitro histone deposition using Xenopus high-speed egg extract, and systematically generated and tested various genetic mutants for functionality in in vivo assays. They successfully delineated domain-specific functions using in vitro assays and could validate their roles to large extent using genetic mutants. One significant revelation from this study is the unfolded nature of the acidic domain, observed to fold when binding to histones. Additionally, the authors also elucidated the role of the long KER helix in mediating DNA binding and enhancing the association of CAF-1 with PCNA. The paper effectively addresses its primary objective and is strong.

Weaknesses:<br /> A few relatively minor unresolved aspects persist, which, if clarified or experimentally addressed by the authors, could further bolster the study.

1. The precise function of the WHD domain remains elusive. Its deletion does not result in DNA damage accumulation or defects in heterochromatin maintenance. This raises questions about the biological significance of this domain and whether it is dispensable. While in vitro assays revealed defects in chromatin assembly using this mutant (Figure 5), confirming these phenotypes through in vivo assays would provide additional assurance that the lack of function is not simply due to the in vitro system lacking PTMs or other regulatory factors.

2. The observation of increased Pcf2-gfp foci in pcf1-ED* cells, particularly in mono-nucleated (G2-phase) and bi-nucleated cells with septum marks (S-phase), might suggest the presence of replication stress. This could imply incomplete replication in specific regions, leading to the persistence of Caf1-ED*-PCNA factories throughout the cell cycle. To further confirm this, detecting accumulated single-stranded DNA (ssDNA) regions outside of S-phase using RPA as an ssDNA marker could be informative.

3. Moreover, considering the authors' strong assertion of histone binding defects in ED* through in vitro assays (Figure 2d and S2a), these claims could be further substantiated, especially considering that some degree of histone deposition might still persist in vivo in the ED* mutant (Figure 7d, viable though growth defective double ED*+hip1D mutants). For example, the approach, akin to the one employed in Fig. 6a (FLAG-IPs of various Pcf1-FLAG-tagged mutants), could also enable a comparison of the association of different mutants with histones and PCNA, providing a more thorough validation of their findings.

4. It would be valuable for the authors to speculate on the necessity of having disordered regions in CAF1. Specifically, exploring the overall distribution of these domains within disordered/unfolded structures could provide insightful perspectives. Additionally, it's intriguing to note that the significant disparities observed among mutants (ED*, PIP*, and KER*) in in vitro assays seem to become more generic in vivo, except for the indispensability of the WHD-domain. Could these disordered regions potentially play a crucial role in the phase separation of replication factories? Considering these questions could offer valuable insights into the underlying mechanisms at play.

Reviewer #1 (Public Review):

Summary:<br /> This paper makes important contributions to the structural analysis of the DNA replication-linked nucleosome assembly machine termed Chromatin Assembly Factor-1 (CAF-1). The authors focus on the interplay of domains that bind DNA, histones, and replication clamp protein PCNA.

Strengths:<br /> The authors analyze soluble complexes containing full-length versions of all three fission yeast CAF-1 subunits, an important accomplishment given that many previous structural and biophysical studies have focused on truncated complexes. New data here supports previous experiments indicating that the KER domain is a long alpha helix that binds DNA. Via NMR, the authors discover structural changes at the histone binding site, defined here with high resolution. Most strikingly, the experiments here show that for the S. pombe CAF-1 complex, the WHD domain at the C-terminus of the large subunit lacks DNA binding activity observed in the human and budding yeast homologs, indicating a surprising divergence in the evolution of this complex. Together, these are important contributions to the understanding of how the CAF-1 complex works.

Weaknesses:<br /> 1. There are some aspects of the experimentation that are incompletely described:

In the SEC data (Fig. S1C) it appears that Pcf1 in the absence of other proteins forms three major peaks. Two are labeled as "1a" (eluting at ~8 mL) and "1b" (~10-11 mL). It appears that Pcf1 alone or in complex with either or both of the other two subunits forms two different high molecular weight complexes (e.g. 4a/4b, 5a/5b, 6a/6b). There is also a third peak in the analysis of Pcf1 alone, which isn't named here, eluting at ~14 mL, overlapping the peaks labeled 2a, 4c, and 5c.

The text describing these different macromolecular complexes seems incomplete (p. 3, lines 32-33): "When isolated, both Pcf2 and Pcf3 are monomeric while Pcf1 forms large soluble oligomers". Which of the three Pcf1-alone peaks are oligomers, and how do we know? What is the third peak? The gel analysis across these chromatograms should be shown.

More importantly, was a particular SEC peak of the three-subunit CAF-1 complex (i.e. 4a or 4b) characterized in the further experimentation, or were the data obtained from the input material prior to the separation of the different peaks? If the latter, how might this have affected the results? Do the forms inter-convert spontaneously?

2. Given the strong structural predication about the roles of residues L359 and F380 (Fig. 2f), these should be mutated to determine effects on histone binding.

3. Could it be that the apparent lack of histone deposition by the delta-WHD mutant complex occurs because this mutant complex is unstable when added to the Xenopus extract?

Reviewer #2 (Public Review):

Summary:<br /> The authors describe the structure-functional relationship of domains in S. pombe CAF-1, which promotes DNA replication-coupled deposition of histone H3-H4 dimer. The authors nicely showed that the ED domain with an intrinsically disordered structure binds to histone H3-H4, that the KER domain binds to DNA, and that, in addition to a PIP box, the KER domain also contributes to the PCNA binding. The ED and KER domains as well as the WHD domain are essential for nucleosome assembly in vitro. The ED, KER domains, and the PIP box are important for the maintenance of heterochromatin.

Strengths:<br /> The combination of structural analysis using NMR and Alphafold2 modeling with biophysical and biochemical analysis provided strong evidence on the role of the different domain structures of the large subunit of SpCAF-1, spPCF-1 in the binding to histone H3-H4, DNA as well as PCNA. The conclusion was further supported by genetic analysis of the various pcf1 mutants. The large amounts of data provided in the paper support the authors' conclusion very well.

Reviewer #3 (Public Review):

Light energy drives photosynthesis. However, excessive light can damage (i.e., photo-damage) and thus inactivate the photosynthetic process. A major target site of photo-damage is photosystem II (PSII). In particular, one component of PSII, the reaction center protein, D1, is very suspectable to photo-damage, however, this protein is maintained efficiently by an elaborate multi-step PSII-D1 turnover/repair cycle. Two proteases, FtsH and Deg, are known to contribute to this process, respectively, by efficient degradation of photo-damaged D1 protein processively and endoproteolytically. In this manuscript, Kato et al., propose an additional step (an early step) in the D1 degradation/repair pathway. They propose that "Tryptophan oxidation" at the N-terminus of D1 may be one of the key oxidations in the PSII repair, leading to processive degradation of D1 by FtsH. Both, their data and arguments are very compelling.

The D1 protein repair/degradation pathway in its simplest form can be defined essentially by five steps: (1) migration of damaged PSII core complex to the stroma thylakoid, (2) partial PSII disassembly of the PSII core monomer, (3) access of protease degrading damaged D1, (4) concomitant D1 synthesis, and (5) reassembly of PSII into grana thylakoid. An enormous amount of work has already been done to define and characterize these various steps. Kato et al., in this manuscript, are proposing a very early yet novel critical step in D1 protein turnover in which Tryptophan(Trp) oxidation in PSII core proteins influences D1 degradation mediated by FtsH.

Using a variety of approaches, such as mass-spectrometry (Table 1), site-directed mutagenesis (Figures 2-4), D1 degradation assays (Figures 3, and 4), and simulation modeling (Figure 5), Kato et al., provide both strong evidence and reasonable arguments that an N-terminal Trp oxidation may be likely to be a 'key' oxidative post-translational modification (OPTM) that is involved in triggering D1 degradation and thus activating the PSII repair pathway. Consequently, from their accumulated data, the authors propose a scenario in which the unraveling of the N-terminal of the D1 protein facilitated by Trp oxidation plays a critical 'recognition' role in alerting the plant that the D1 protein is photo-damaged and thus to kick start the processive degradation pathway initiated possibly by FtsH. Coincidently, Forsman and Eaton-Rye (Biochemistry 2021, 60, 1, 53-63), while working with the thermophilic cyanobacterium, Thermosynechococcus vulcanus, showed that when the N-terminal DE-loop of the D1 protein is photo-damaged a disruption of the interaction between the PsbT subunit and D1 occurs which may serve as a signal for PSII to undergo repair following photodamage. While the activation of the processive degradation pathways in Chlamydomonas versus Thermosynechococcus vulcanus have significant mechanistic differences, it's interesting to note and speculate that the stability of the N-terminal of their respective D1 proteins seems to play a critical role in 'signaling' the PSII repair system to be activated and initiate repair. But it's complicated. For instance, significant Trp oxidation also occurs on the lumen side of other PSII subunits which may also play a significant role in activating the repair processes as well. Indeed, Kato et al.,( Photosynthesis Research volume 126, pages 409-416 (2015)) proposed a two-step model whereby the primary event is disruption of a Mn-cluster in PSII on the lumen side. A secondary event is damage to D1 caused by energy that is absorbed by chlorophyll. But models adapt, change, and get updated. And the data provided by Kato et al., in this manuscript, gives us a unique glimpse/snapshot into the importance of the stability of the N-terminal during photo-damage and its role in D1-turnover. For instance, the author's use site-directed mutagenesis of Trp residues undergoing OPTM in the D1 protein coupled with their D1 degradation assays (Figure 3 and 4), provides evidence that Trp oxidation (in particular the oxidation of Trp14) in coordination with FtsH results in the degradation of D1 protein. Indeed, their D1 degradation assays coupled with the use of a ftsh mutant provide further significant support that Trp14 oxidation and FtsH activity are strongly linked. But for FstH to degrade D1 protein it needs to gain access to photo-damaged D1. FtsH access to D1 is achieved by having CP43 partially dissociate from the PSII complex. Hence, the authors also addressed the possibility that Trp oxidation may also play a role in CP43 disassembly from the PSII complex thereby giving FtsH access to D1. Using a site-directed mutagenesis approach, they showed that Trp oxidation in CP43 appeared to have little impact on the PSII repair (Supplemental Figure S6). This result shows that D1-Trp14 oxidation appears to be playing a role in D1 turnover that occurs after CP43 disassembly from the PSII complex. Alternatively, the authors cannot exclude the possibility that D1-Trp14 oxidation in some way facilitates CP43 dissociation. Further investigation is needed on this point. However, D1-Trp14 oxidation is causing an internal disruption of the D1 protein possibly at the N-terminus of the protein. Consequently, the role of Trp14 oxidation in disrupting the stability of the N-terminal domain of the D1 protein was analyzed computationally. Using a molecular dynamics approach (Figure 5), the authors attempted to create a mechanistic model to explain why when D1 protein Trp14 undergoes oxidation the N-terminal domain of D1protein becomes unraveled. Specifically, the authors propose that the interaction between D1 protein Trp14 with PsbI Ser25 becomes disrupted upon oxidation of Trp14. Consequently, the authors concluded from their molecular dynamics simulation analysis that " the increased fluctuation of the first α-helix of D1 would give a chance to recognize the photo-damaged D1 by FtsH protease". Hence, the author's experimental and computational approaches employed here develop a compelling early-stage repair model that integrates 1) Trp14 oxidation, 2) FtsH activation and 3) D1- turnover being initiated at its N-terminal domain. However, a word of caution should be emphasized here. This model is just a snapshot of the very early stages of the D1 protein turnover process. The data presented here gives us just a small glimpse into the unique relationship between Trp oxidation of the D1 protein which may trigger significant N-terminal structural changes of the D1 protein that both signals and provides an opportunity for FstH to begin protease digestion of the D1 protein. However, the authors go to great lengths in their discussion section to not overstate solely the role of Trp14 oxidation in the complicated process of D1 turnover. The authors certainly recognize that there are a lot of moving parts involved in D1 turnover. And while Trp14 oxidation is the major focus of this paper, the authors show in Supplemental Fig S4 the structural positions of various additional oxidized Trp residues in the Thermosynecoccocus vulcans PSII core proteins. Indeed, this figure shows that the majority of oxidized Trps are located on the luminal side of PSII complex clustered around the oxygen-evolving complex. So, while oxidized Trp14 may be involved in the early stages of D1 turnover certainly oxidized Trps on the lumen side are also more than likely playing a role in D1 turnover as well. To untangle this complex process will require additional research.

Nevertheless, identifying and characterizing the role of oxidative modification of tryptophan (Trp) residues, in particular, Trp14, in the PSII core provides another critical step in an already intricate multi-step process of D1 protein turnover during photo-damage.

Reviewer #1 (Public Review):

This manuscript tried to answer a long-standing question in an important research topic. I read it with great interest. The quality of the science is high, and the text is clearly written. The conclusion is exciting. However, I feel that the phenotype of the transgenic line may be explained by an alternative idea. At least, the results should be more carefully discussed.

Specific comments:

1) Stability or activity (Fv/Fm) was not affected in PSII with the W14F mutation in D1. If W14F really represents the status of PSII with oxidized D1, what is the reason for the degradation of almost normal D1?

2) To focus on the PSII in which W14 is oxidized, this research depends on the W14F mutant lines. It is critical how exactly the W-to-F substitution mimics the oxidized W. The authors tried to show it in Figure 5. Because of the technical difficulty, it may be unfair to request more evidence. But the paper would be more convincing with the results directly monitoring the oxidized D1 to be recognized by FtsH.

3) Figure 3. If the F14 mimics the oxidized W14 and is sensed by FtsH, I would expect the degradation of D1 even under the growth light. The actual result suggests that W14F mutation partially modifies the structure of D1 under high light and this structural modification of D1 is sensed by FtsH. Namely, high light may induce another event which is recognized by FtsH. The W14F is just an enhancer.

Reviewer #2 (Public Review):

In their manuscript, Kato et al investigate a key aspect of membrane protein quality control in plant photosynthesis. They study the turnover of plant photosystem II (PSII), a hetero-oligomeric membrane protein complex that undertakes the crucial light-driven water oxidation reaction in photosynthesis. The formidable water oxidation reaction makes PSII prone to photooxidative damage. PSII repair cycle is a protein repair pathway that replaces the photodamaged reaction center protein D1 with a new copy. The manuscript addresses an important question in PSII repair cycle - how is the damaged D1 protein recognized and selectively degraded by the membrane-bound ATP-dependent zinc metalloprotease FtsH in a processive manner? The authors show that oxidative post-translational modification (OPTM) of the D1 N-terminus is likely critical for the proper recognition and degradation of the damaged D1 by FtsH. Authors use a wide range of approaches and techniques to test their hypothesis that the singlet oxygen (1O2)-mediated oxidation of tryptophan 14 (W14) residue of D1 to N-formylkynurenine (NFK) facilitates the selective degradation of damaged D1. Overall, the authors propose an interesting new hypothesis for D1 degradation and their hypothesis is supported by most of the experimental data provided. The study certainly addresses an elusive aspect of PSII turnover and the data provided go some way in explaining the light-induced D1 turnover. However, some of the data are correlative and do not provide mechanistic insight. A rigorous demonstration of OPTM as a marker for D1 degradation is yet to be made in my opinion. Some strengths and weaknesses of the study are summarized below:

Strengths:

1. In support of their hypothesis, the authors find that FtsH mutants of Arabidopsis have increased OPTM, especially the formation of NFK at multiple Trp residues of D1 including the W14; a site-directed mutation of W14 to phenylalanine (W14F), mimicking NFK, results in accelerated D1 degradation in Chlamydomonas; accelerated D1 degradation of W14F mutant is mitigated in an ftsH1 mutant background of Chlamydomonas; and that the W14F mutation augmented the interaction between FtsH and the D1 substrate.

2. Authors raise an intriguing possibility that the OPTM disrupts the hydrogen bonding between W14 residue of D1 and the serine 25 (S25) of PsbI. According to the authors, this leads to an increased fluctuation of the D1 N-terminal tail, and as a consequence, recognition and binding of the photodamaged D1 by the protease. This is an interesting hypothesis and the authors provide some molecular dynamics simulation data in support of this. If this hypothesis is further supported, it represents a significant advancement.

3. The interdisciplinary experimental approach is certainly a strength of the study. The authors have successfully combined mass spectrometric analysis with several biochemical assays and molecular dynamics simulation. These, together with the generation of transplastomic algal cell lines, have enabled a clear test of the role of Trp oxidation in selective D1 degradation.

4. Trp oxidative modification as a degradation signal has precedent in chloroplasts. The authors cite the case of 1O2 sensor protein EXECUTER 1 (EX1), whose degradation by FtsH2, the same protease that degrades D1, requires prior oxidation of a Trp residue. The earlier observation of an attenuated degradation of a truncated D1 protein lacking the N-terminal tail is also consistent with authors' suggestion of the importance of the D1 N-terminus recognition by FtsH. It is also noteworthy that in light of the current study, D1 phosphorylation is unlikely to be a marker for degradation as posited by earlier studies.

Weaknesses:

1. The study lacks some data that would have made the conclusions more rigorous and convincing. It is unclear why the level of Trp oxidation was not analyzed in the Chlamydomonas ftsH 1-1 mutant as done for the var 2 mutant. Increased oxidation of W14 OPTM in Chlamydomonas ftsH 1-1 is a key prediction of the hypothesis. It is also unclear to me what is the rationale for showing D1-FtsH interaction data only for the double mutant but not for the single mutant (W14F). Why is the FtsH pulldown of D2 not statistically significant (p value = {less than or equal to}0.1). Wouldn't one expect FtsH pulls down the RC47 complex containing D1, D2, and RC47. Probing the RC47 level would have been useful in settling this. A key proposition of the authors' is that the hydrogen bonding between D1 W14 and S25 of PsbI is disrupted by the oxidative modification of W14. Can this hypothesis be further tested by replacing the S25 of PsbI with Ala, for example?

2. Although most of the work described is in vivo analysis, which is desirable, some in vitro degradation assays would have strengthened the conclusions. An in vitro degradation assay using the recombinant FtsH and a synthetic peptide encompassing D1 N-terminus with and without OPTM will test the enhanced D1 degradation that the authors predict. This will also help to discern the possibility that whether CP43 detachment alone is sufficient for D1 degradation as suggested for cyanobacteria.

3. The rationale for analyzing a single oxidative modification (W14) as a D1 degradation signal is unclear. D1 N-terminus is modified at multiple sites. Please see Mckenzie and Puthiyaveetil, bioRxiv May 04 2023. Also, why is modification by only 1O2 considered while superoxide and hydroxide radicals can equally damage D1?

4. The D1 degradation assay seems not repeatable for the W14F mutant. High light minus CAM results in Fig. 3 shows a statistically significant decrease in D1 levels for W14F at multiple time points but the same assay in Fig. 4a does not produce a statistically significant decrease at 90 min of incubation. Why is this? Accelerated D1 degradation in the Phe mutant under high light is key evidence that the authors cite in support of their hypothesis.

5. The description of results at times is not nuanced enough, for e.g. lines 116-117 state "The oxidation levels in Trp-14 and Trp-314 increased 1.8-fold and 1.4-fold in var2 compared to the wild type, respectively (Fig. 1c)" while an inspection of the figure reveals that modification at W314 is significant only for NFK and not for KYN and OIA. Likewise, the authors write that CP43 mutant W353F has no growth phenotype under high light but Figure S6 reveals otherwise. The slow growth of this mutant is in line with the earlier observation made by Anderson et al., 2002. In lines 162-163, the authors talk about unchanged electron transport in some site-directed mutants and cite Fig. 2c but this figure only shows chl fluorescence trace and nothing else.

6. The authors rightly discuss an alternate hypothesis that the simple disassembly of the monomeric core into RC47 and CP43 alone may be sufficient for selective D1 degradation as in cyanobacteria. This hypothesis cannot yet be ruled out completely given the lack of some in vitro degradation data as mentioned in point 2. Oxidative protein modification indeed drives the disassembly of the monomeric core (Mckenzie and Puthiyaveetil, bioRxiv May 04 2023).

Reviewer #2 (Public Review):

Summary:<br /> This work tests the hypothesis that water coordination in WNK kinases is linked to allosteric control of activity. It is proposed that dimeric WNK is inactive and bound to some conserved water molecules, and that monomerization/activation involves departure of these waters. New data here include a crystal structure of monomeric WNK1 which shows missing waters compared to the dimeric structure, in support of the hypothesis. Mutant proteins of a different isozyme (WNK3) designed to disrupt water coordination were produced, and activity and quaternary structure were measured. The results with WNK3 do not clearly support or refute the hypothesis as there is no systematic correlation between mutations designed to disrupt water coordination and activity or quaternary structure.

Strengths:<br /> The most interesting result presented here is that P1 crystals of WNK1 convert to P21 in the presence of PEG400 and still diffract (rather than being destroyed as the crystal contacts change, as one would expect). All of the assays for activity and osmolyte sensing are carried out well.

Weaknesses:<br /> The rationale for using WNK3 for the mutagenesis study is that it is more sensitive to osmotic pressure than WNK1. I think that WNK1 would have been a better platform because of the direct correlation to the structural work leading to the hypothesis being tested. All of the crystallographic work is WNK1; it is not logical to jump to WNK3 without other practical considerations.

Osmolyte sensing was tested by measuring ATP consumption as a function of PEG400 (Figure 6). Data for the subset of mutants analyzed by this assay showed increasing activity. It is not clear why the same collection of mutant proteins analyzed in the experiments of Figure 5 was not also measured for osmolyte sensing in Figure 6.

The last set of data presented uses light scattering to test whether the WNK3 mutant proteins exhibit quaternary structural changes consistent with the monomer/dimer hypothesis. If they did, one would expect a higher degree of monomer for those that are activated by mutation, and a lower amount of monomer (like wt) for those that are not. Instead, one of the mutant proteins that showed the most chloride inhibition (Y346F) had a quaternary structure similar to the wt protein, and others have similar monomer/dimer mixtures but distinct chloride inhibition profiles (K307A and M301A). I don't see how the light scattering data contribute to this story other than to refute the hypothesis by showing a lack of correlation between quaternary structure, water binding, and activity. This is another reason why the disconnect between WNK1 and WNK3 could be a problem. All of the detailed structural work with WNK1 must be assumed with WNK3; perhaps the light scattering data are contradicting this assumption?

Reviewer #1 (Public Review):

Summary:<br /> This manuscript addresses the regulation of the osmosensing protein kinases, WNK1 and WNK3. Prior work by the authors has shown that these enzymes are activated by PEG400 or ethylene glycol and inhibited by chloride ion, and that activation is associated with a conformational transition from dimer to monomer. In X-ray structures of the WNK1/SA inactive dimer, a water-mediated hydrogen bond network was observed between the catalytic loop (CL) and the activation loop (AL), named CWN1. This led to the proposal that bound water may be part of the osmosensing mechanism.

The current study carries this work further, by applying PEG400 to Xtals of dimeric WNK1/SA. This results in a change in kinase conformation and space group, along with 4-9 fewer waters in CWN1 and the complete disappearance of another water cluster (CWN2) located at the dimer interface. Six conserved residues lining the CWN1 pocket in WNK3 are mutated to determine effects on activity and inhibition by chloride ion (measured by AL autophosphorylation) and monomer-dimer interconversion (light scattering).

The results show that two mutants (E314Q/A in WNK3) at a site central to the water cluster result in increased kinase activity (autophosphorylation), and increased SLS, interpreted as aggregation. Three sites (D279A, Y346F, M301A) inhibit kinase activity with varying effects on oligomerization - Y346A and M301A retain monomer-dimer ratios similar to WT while D279N promotes aggregation. K236A and K307A show activity and monomer:dimer ratios similar to WT. Selected mutants (E314Q, D279N, Y346F) and WT appear to retain osmosensitivity with comparable activation by PEG400.

The study concludes that osmolytes may activate the kinase by removing waters from the CWN1 and CWN2 clusters, suggesting that waters might be considered allosteric ligands that promote the inactive structure of WNKs. The differing effects of mutations may be ascribed to disruption of the water networks as well as inhibitory perturbations at the active site.

Strengths:<br /> This study presents a novel and unique function for bound water, and its potential role to explain osmosensory regulation. The mechanism is innovative and the new structures and mutational data presented by the work will be useful for further investigations of the mechanisms that enable cells to respond to osmotic pressure.

Weaknesses:<br /> Given that all mutants tested showed the same degree of activation by PEG400, it seemed possible that PEG400 might be an allosteric activator of WNK1/3 through direct binding interactions. Perhaps PEG400 eliminates CWN1/2 waters by inducing conformational changes so that water loss is an effect not a cause of activation. To address this it would be helpful to comment on whether new electron densities appeared in the X-ray structure of WNK1/SA/PEG400 that might reflect PEG400 interactions with chains A or B. It would also be helpful to discuss any experiments that might have been done in previous work to examine the direct binding of glycerol and other osmolytes to WNKs.

The study would benefit from a deeper discussion about how to reconcile the different effects of mutations. For example, wouldn't most or all of the mutations be expected to disrupt the water network, and relieve the proposed autoinhibition? This seemed especially true for some of the residues, like Y420(Y346), D353(D279), and K310(K236), which based on Fig 3 appeared to interact with waters that were removed by PEG400.

Alternatively, perhaps the waters in CWN2 are more important for maintaining the autoinhibited structure. This possibility would be useful to discuss, and perhaps comment on what may be known about the energetic contributions of bound water towards stabilizing dimers.

It would also be useful to comment on why aggregation of E319Q/A shouldn't inhibit kinase activity instead of activating it.

The X-ray work was done entirely with WNK1 while the mutational work was done entirely with WNK3. Therefore, a simple explanation for the disconnect between structure and mutations might be that WNK1 and WNK3 differ enough that predictions from the structure of one are not applicable to mutations of the other. It would be helpful to describe past work comparing the structure and regulation of WNK1 and WNK3 that support the assumption of their interchangeability.

Reviewer #2 (Public Review):

Summary:

The manuscript's main claim is that the absence of H2-O, a component of the MHC II presentation pathway, promotes regulatory T cell development and function.

Unfortunately, the submitted material is not sufficient for proper evaluation of the manuscript, both in terms of the significance of the findings and the strength of the supporting evidence.

Major issues include:

- the scRNAseq (shown in Fig. 5) is too rudimentary to allow any conclusion. Statements in the text (eg "Principle Component Analysis (PCA) of the normalized scRNA-seq data identified 11 distinct CD4 T cell clusters", line 166) suggest that additional expertise should be leveraged for these analyses.

- Most flow cytometry data (Figs. 1 and 2) shows marginal (at best) differences on y-axis truncated bar graphs, with no original data plot, gating strategies, etc., severely challenging conclusions drawn from this data.

Reviewer #1 (Public Review):

The non-classical MHCII-like protein H2-M is essential for the loading of peptides on MHCII. The discovery that DM was partnered with a second MHCII-like protein, H2-O, which squelched or modified its activity was confounding. It was immediately speculated that H2-O was likely diminished self-peptide presentation. This led to the hypothesis that H2-O was involved in preventing unwanted CD4 T cell activation, thereby making autoimmunity less likely. 25 years of analysis of H2-O deficient mice have, indeed, shown that the self-peptide repertoire in the absence of H2-O is modestly altered. Demonstrating that autoimmunity results from this altered peptide repertoire has been decidedly less convincing. Old mice are reported to have increased serum anti-nuclear antibody titers, but mice prone to type 1 diabetes (T1D) and systemic lupus erythematosus (SLE) were not impacted by the loss of H2-O (Lee et al, 2021). Induction of the multiple sclerosis-like disease, EAE, in mice, was also shown to not be impacted by Lee et al 2021, although in a previous paper (Welsh et al 2020), the authors of this current manuscript suggest otherwise. Unfortunately, these discrepancies are not acknowledged by the authors, and the papers are, for the most part, not referenced.

In addition to antigen-presenting cells, H2-O is also found in MHCII-expressing medullary epithelial cells, suggesting it might play a role in T-cell selection. Direct data to support this idea, however, has, at most, shown a minimal impact. In this manuscript, the authors follow up on their previous paper (Welsh et al, 2020) to further evaluate changes to T cell development. The conclusions are that H2-O impacts Treg development and changes the frequency and homeostasis of CD4 T cells. Although these would be interesting results, the data analysis is flawed, the presentation is incomplete, and the conclusions are exaggerated.

T-cell development analysis shown in Figs. 1 and 2 use the discovery from the Hogquist lab (Breed et all 2019) that thymocytes destined for clonal deletion can be differentiated from those still "auditioning" for selection by FACS for expression of cleaved caspase 3. Detection relies on complex FACS analysis that requires the exclusion of multiple populations, followed by accurate gating on CD5+TCRb+ cells (see Hogquist Fig. 1A). The authors apparently neglected to use the essential gating steps, but rather only used CD4 and CCR7 expression (Fig. 1A). This deviation from the Hogquist approach makes interpretation of Figs 1 and 2 meaningless. Even if this is an oversight in the description of the experiments, key conclusions are drawn from minimal changes to CD69 expression. CD69 is expressed as a continuum in the thymus (a "shoulder") making gating somewhat subjective and prone to variation from experiment to experiment. At the minimum, FACS data should be shown to indicate how these changes were measured, plus variations from mouse to mouse should be plotted, with statistics. FACS data needs to be shown to define how the complex semi-mature, M1, and M2 populations were defined (see Hogquist Fig. 2) from which key conclusions are drawn.

To make the data more robust, 1) cell numbers must be included for all experiments;

2) rather than normalizing results to "the average H2-O WT levels", the actual data should be included;

3) figures should be more completely labeled/described;

4) FACS gating strategies should be clearly laid out (again, see Hogquist for examples). Furthermore, efforts must be made to explain why results are so different from analyses of H2-O deficient mice that have been published by many other groups. For example, the reported "dramatic increase in the proportion of CD3+CD4+ T cells" is not consistent with previous reports starting with Lars Karlsson's initial report (Liljedahl et al 1998). Extensive spontaneous activation of CD4 T cells has also not been reported in other papers that have studied these mice. Again, the paper is not placed in the context of the long, very thorough analysis of both the H2-O deficient mice and the study of H2-O/DO and H2-M/DM in general.

Reviewer #1 (Public Review):

Summary:<br /> Glaser et al present ExA-SPIM, a light-sheet microscope platform with large volumetric coverage (Field of view 85mm^2, working distance 35mm), designed to image expanded mouse brains in their entirety. The authors also present an expansion method optimized for whole mouse brains and an acquisition software suite. The microscope is employed in imaging an expanded mouse brain, the macaque motor cortex, and human brain slices of white matter.

This is impressive work and represents a leap over existing light-sheet microscopes. As an example, it offers a fivefold higher resolution than mesoSPIM (https://mesospim.org/), a popular platform for imaging large cleared samples. Thus while this work is rooted in optical engineering, it manifests a huge step forward and has the potential to become an important tool in the neurosciences.

Strengths:<br /> -ExA-SPIM features an exceptional combination of field of view, working distance, resolution, and throughput.

-An expanded mouse brain can be acquired with only 15 tiles, lowering the burden on computational stitching. That the brain does not need to be mechanically sectioned is also seen as an important capability.

-The image data is compelling, and tracing of neurons has been performed. This demonstrates the potential of the microscope platform.

Weaknesses:<br /> -There is a general question about the scaling laws of lenses, and expansion microscopy, which in my opinion remained unanswered: In the context of whole brain imaging, a larger expansion factor requires a microscope system with larger volumetric coverage, which in turn will have lower resolution (Figure 1B). So what is optimal? Could one alternatively image a cleared (non-expanded) brain with a high-resolution ASLM system (Chakraborty, Tonmoy, Nature Methods 2019, potentially upgraded with custom objectives) and get a similar effective resolution as the authors get with expansion? This is not meant to diminish the achievement, but it was unclear if the gains in resolution from the expansion factor are traded off by the scaling laws of current optical systems.

-It was unclear if 300 nm lateral and 800 nm axial resolution is enough for many questions in neuroscience. Segmenting spines, distinguishing pre- and postsynaptic densities, or tracing densely labeled neurons might be challenging. A discussion about the necessary resolution levels in neuroscience would be appreciated.

-Would it be possible to characterize the aberrations that might be still present after whole brain expansion? One approach could be to image small fluorescent nanospheres behind the expanded brain and recover the pupil function via phase retrieval. But even full width half maximum (FWHM) measurements of the nanospheres' images would give some idea of the magnitude of the aberrations.

Reviewer #2 (Public Review):

Summary:<br /> In this manuscript, Glaser et al. describe a new selective plane illumination microscope designed to image a large field of view that is optimized for expanded and cleared tissue samples. For the most part, the microscope design follows a standard formula that is common among many systems (e.g. Keller PJ et al Science 2008, Pitrone PG et al. Nature Methods 2013, Dean KM et al. Biophys J 2015, and Voigt FF et al. Nature Methods 2019). The primary conceptual and technical novelty is to use a detection objective from the metrology industry that has a large field of view and a large area camera. The authors characterize the system resolution, field curvature, and chromatic focal shift by measuring fluorescent beads in a hydrogel and then show example images of expanded samples from mouse, macaque, and human brain tissue.

Strengths:<br /> I commend the authors for making all of the documentation, models, and acquisition software openly accessible and believe that this will help assist others who would like to replicate the instrument. I anticipate that the protocols for imaging large expanded tissues (such as an entire mouse brain) will also be useful to the community.

Weaknesses:<br /> The characterization of the instrument needs to be improved to validate the claims. If the manuscript claims that the instrument allows for robust automated neuronal tracing, then this should be included in the data.

Reviewer #1 (Public Review):

Summary:<br /> This publication applies 3D super-resolution STORM imaging to understanding the role of developmental neural activity in the clustering of retinal inputs to the mouse dorsal lateral geniculate nucleus (dLGN). The authors argue that retinal ganglion cell (RGC) synaptic boutons start forming clusters early in postnatal development (P2). They then argue that these clusters contribute to eye-specific segregation of retinal inputs by activity-dependent stabilization of nearby boutons from the same eye. The data provided is N=3 animals for each condition of P2, P4, and P8 animals in wild-type mice and in mice where early patterns of structured retinal activity are blocked.

Strengths:<br /> The 3D storm imaging of pre and postsynaptic elements provides convincing high-resolution localization of synapses.

The experimental design of comparing ipsilateral and contralateral RGC axon boutons in a region of the dLGN that is known to become contralateral is elegant. The design makes it possible to relate fixed time point structural data to a known outcome of activity-dependent remodeling.

Weaknesses:<br /> Based on previous literature, it is known that synapse density, synapse clustering, and synaptic specificity increase during postnatal development. Previous work has also shown that both the changes in synaptic clustering and synaptic specificity are affected by retinal activity. The data and analysis provided by the authors add little unambiguous evidence that advances this understanding.

General problem 1: Most of the statistical analysis is limited to ANOVA comparison of axons from the contralateral and ipsilateral retina in the contralateral dLGN. The hypothesis that ipsilateral and contralateral axons would be statistically identical in the contralateral dLGN is not a plausible hypothesis so rejecting the hypothesis with P < X does not advance the authors' arguments beyond what was already known.

General problem 2: Most of the interpretation of data is qualitative. While error bars are provided, these error bars are not used to draw conclusions. Given the small sample size (N=3), there is a large degree of uncertainty regarding the magnitude of changes (synapse size, number, specificity). The authors base their conclusions on the averages of these values when the likely degree of uncertainty could allow for the opposite interpretation.

General problem 3: Two of the four results sections depend on using the frequency of single active zone vGlut2 clusters near multiple active zone vGlut2 as a proxy for synaptic stabilization of the single active zone vGlut2 clusters by the multiple active zone vGlut2 clusters. The authors argue that the increased frequency of same-eye single active zone clusters relative to opposite-eye single active zone clusters means that multiple active zone vGlut2 clusters are selectively stabilizing single active zone clusters. There are other plausible explanations for this observation that are not eliminated. An increased frequency of nearby single active zone clusters would also occur if RGC axons form more than one synapse in the dLGN. Eye-specific segregation is, by definition, a relative increase in the frequency of nearby boutons from the same eye. The authors were, therefore, guaranteed to observe a non-random relationship between boutons from the same eye. The authors do compare their measures to a random model, but I could not find a description of the model. I would expect that the model would need to account for RGC arbor size, arbor structure, bouton number, and segregation independent of multi-active-zone vGlut2 clusters. The most common randomization for the type of analysis described here, a shift in the positions of single-active zone boutons, would not be adequate.

In discussing the claimed cluster-induced stabilization of nearby boutons, the authors state that the specificity increases with age due to activity-dependent refinement. Their quantification does not support an increase in specificity with age. In fact, the high degree of clustering "specificity" they observe at P2 argues for the trivial same axon explanation.

Analysis of specific claims:

Result Section 1

Most of the figures show mean, error bars, and asterisks, but not the three data points from which these statistics are derived. Large changes in variance from condition to condition suggest that displaying the data points would provide more useful information.

Claim 1: Contralateral density increases more than ipsilateral in the contralateral region over the course of development. This claim is supported by the qualitative comparison of means and error bars in Figure 2D. The argument could be made quantitative by providing a confidence interval for synapse density increase for dominant and non-dominant synapse density. A confidence interval could then be generated for the difference in this change between the two groups. Currently, the most striking effect is a big difference in variance between P4 and P8 for dominant eye complex synapses. Given that N=3, I assume there is one extreme outlier here.

Claim 2: The fraction of multiple-active zone vGlut2 clusters increases with age. This claim is weakly supported by a qualitative reading of panel 1E. The error bars overlap so it is difficult to know what the range of possible increases could be. In the text, the authors report mean differences without confidence intervals (or any other statistics). The reported results should, therefore, be interpreted as a description of their three mice and not as evidence about mice in general.

Figure S1. Panel A makes the point that the study could not be done without STORM by comparing the STORM images to "Conventional" images. The images are over-saturated low-resolution images. A reasonable comparison would be to a high-quality quality confocal image acquired with a high NA objective (~1.4) and low laser power (PSF ~ 0.2 x 0.2 x 0.6 um) that was acquired over the same amount of time it takes to acquire a STORM volume.

Result section 2.

Claim 1: The ipsi/contra (in contra LGN) difference in VGluT2 cluster volume increases with development. While there are many p-values listed, the main point is not directly quantified. A reasonable way to quantify the relative increase in volume could be in the form: the non-dominant volumes were 75%-95%(?) of the dominant volume at P2 and 60%-80% (?) at P8. The difference in change was -5 to 15%(?).

Claim 2: Complex synapses (vGlut2 clusters with multiple active zones) represent clusters of simple synapses and not single large boutons with multiple active zones. The authors argue that because vGlut2 cluster volume scales roughly linearly with active zone number, the vGlut2 clusters are composed of multiple boutons each containing a single active zone. Their analysis does not rule out the (known to be true) possibility that RGC bouton sizes are much larger in boutons with multiple active zones. The correlation of volume and active zone number, by itself, does not resolve the issue. A good argument for multiple boutons might be that the variance is smallest in clusters with 4 active zones (looks like it in the plot) since they would be the average of four active zones to vesicle pool ratios. It is very likely that the multi-active zone vGlut2 clusters represent some clustering and some multi-synaptic boutons. The reference cited by the authors as evidence for the presence of single active zone boutons in young tissue does not rule out the existence of multiple active zone boutons.

Several arguments are made that depend on the interpretation of "not statistically significant" (n.s.) meaning that "two groups are the same" instead of "we don't know if they are different". This interpretation is incorrect and materially impacts the conclusions.

Several arguments are made that interpret statistical significance for one group and a lack of statistical significance for another group meaning that the effect was bigger in the first group. This interpretation is incorrect and materially impacts the conclusions.

Result Section 3.

Claim 1: Complex synapses stabilize simple synapses. There are alternative explanations (mentioned above) for the observed clustering that negate the conclusions. 1) Boutons from the same axon tend to be found near one another. 2) Any form of eye-specific segregation would produce non-random associations in the analysis as performed. The authors compare each observation to a random model, but I cannot determine from the text if the model adequately accounts for alternative explanations.

The authors claim that specificity increases over time. Figure 3b (middle) shows that the number of synapses near complex synapses might increase with time (needs confidence interval for effect size), but does not show that specificity (original relative to randomized) increases with time. The fact that nearby simple synapse density is always (P2) very different from random suggests a primarily non-activity-dependent explanation. The simplest explanation is that same-side boutons could be from the same axon whereas different-side axons could not be.

Claim 2: vGlut2 clusters more than 1.5 um away from multi-active zone vGlut2 clusters are not statistically significantly different in size than vGlut2 clusters within 1.5 um of multi-active zone vGlut2 clusters. Therefore "activity-dependent synapse stabilization mechanisms do not impact simple synapse vesicle pool size". The specific measure of 1.5 um from multi-active zone vGlut2 clusters does not represent all possible synapse stabilization mechanisms.

Result Section 4.

Claim: The proximity of complex synapses with nearby simple synapses to other complex synapses with nearby simple synapses from the same eye is used to argue that activity is responsible for all this clustering.

It is difficult to derive anything from the quantification besides 'not-random'. That is a problem because we already know that axons from the left and right eye segregate during the period being studied. All the measures in Section 4 are influenced by eye-specific segregation. Given this known bias, demonstrating a non-random relationship (P<br /> The results can be stated as: If you are a contralateral complex synapse, contralateral complex synapses that are also close to contralateral simple synapses will, on average, be slightly closer to you than contralateral complex synapses that are not close to contralateral ipsilateral synapses. That would be true if there is any eye-specific segregation (which there is).

It is an overinterpretation of the data to claim that the lack of a clear correlation between vGlut2 cluster volume and distance to vGlut2 clusters with multiple active zones provides support for the claim that "presynaptic protein organization is not influenced by mechanisms governing synaptic clustering".

Reviewer #2 (Public Review):

Summary:<br /> In this manuscript, Zhang and Speer examine changes in the spatial organization of synaptic proteins during eye-specific segregation, a developmental period when axons from the two eyes initially mingle and gradually segregate into eye-specific regions of the dorsal lateral geniculate. The authors use STORM microscopy and immunostain presynaptic (VGluT2, Bassoon) and postsynaptic (Homer) proteins to identify synaptic release sites. Activity-dependent changes in this spatial organization are identified by comparing the β2KO mice to WT mice. They describe two types of presynaptic organization based on Bassoon clustering, the complex and the simple synapse. By analyzing the relative densities and distances between these proteins over age, the authors conclude that the complex synapses promote the clustering of simple synapses nearby to form the future mature glomerular synaptic structure.

Strengths:<br /> The data presented is of good quality and provides an unprecedented view at high resolution of the presynaptic components of the retinogeniculate synapse during active developmental remodeling. This approach offers an advance to the previous mouse EM studies of this synapse because of the CTB label allows identification of the eye from which the presynaptic terminal arises. Using this approach, the authors find that simple synapses cluster close to complex synapses over age, that complex synapse density increases with age.

Weaknesses:<br /> From these data, the authors conclude that the complex synapse serves to "promote clustering of like-eye synapses and prohibit synapse clustering from the opposite eye". However, the authors show no causal data to support these ideas. There are a number of issues that the authors should consider:

1. Clustering of retinal synapses is in part due to the fact that retinal inputs synapse on the proximal dendrites. With increased synaptogenesis, there will be increased density of retinal terminals that are closely localized. And with development, perhaps simple synapses mature into complex synapses. Simple synapses may also represent ones that are in the process of being eliminated as previously described by Campbell and Shatz, JNeurosci 1992 (consider citing). Can the authors distinguish these scenarios from the ones that they conclude?

2. The argument that "complex" synapses are the aggregate of "simple" synapses (Fig 2, S2) is not convincing.

3. The authors use of the β2KO mice to assess changes in the organization of synaptic proteins in retinal terminals that have disrupted retinal waves. However, β2-nAChRs are also expressed in the dLGN and other areas of the brain and glutamatergic synapse development has been reported in the CNS independent of the disruption in retinal waves. This issue should be considered when interpreting the total reduced retinal synapse density in the dLGN of the mutant.

4. Outside of a total synapse density difference between WT and β2KO mice, the changes in the spatial organization of synaptic proteins over development do not seem that different. In fact % simple synapses near complex synapses from the non-dominant eye in the mutant is not that different from WT at P8 (Fig 3C), an age when eye-specific segregation is very different between the genotypes. Can the authors explain this discrepancy?

5. The authors use nomenclature that has been previously used and associated with other aspects of retinogeniculate properties. For example, the phrases "simple" and "complex" synapses have been used to describe single boutons or aggregates of boutons from numerous retinal axons, whereas in this manuscript the phrases are used to describe vesicle clusters/release sites with no knowledge of whether they are from single or multiple boutons. Likewise, the use of the word "glomerulus" has been used in the context of the retinogeniculate synapse to refer to a specific pattern of bouton aggregates that involves inhibitory and neuromodulatory inputs. It is not clear how the release sites described by the authors fit in this picture. Finally the use of the word "punishment" is associated with a body of literature regarding the immune system and retinogeniculate refinement-which is not addressed in this study. This double use of the phrases can lead to confusion in the field and should be clarified by clear definitions of how they are used in the current study.

Reviewer #3 (Public Review):

Summary:<br /> This manuscript is a follow-up to a recent study of synaptic development based on a powerful data set that combines anterograde labeling, immunofluorescence labeling of synaptic proteins, and STORM imaging (Cell Reports 2023). Specifically, they use anti-Vglut2 label to determine the size of the presynaptic structure (which they describe as the vesicle pool size), anti-Bassoon to label a number of active zones, and anti-Homer to identify postsynaptic densities. In their previous study, they compared the detailed synaptic structure across the development of synapses made with contra-projecting vs ipsi-projecting RGCs and compared this developmental profile with a mouse model with reduced retinal waves. In this study, they produce a new analysis on the same data set in which they classify synapses into "complex" vs. "simple" and assess the number and spacing of these synapses. From these measurements, they make conclusions regarding the processes that lead to synapse competition/stabilization.

Strengths:<br /> This is a fantastic data set for describing the structural details of synapse development in a part of the brain undergoing activity-dependent synaptic rearrangements. The fact that they can differentiate eye of origin is also a plus.

Weaknesses:<br /> The lack of details provided for the classification scheme as well as the interpretation of small effect sizes limit the interpretations that can be made based on these findings.

1. The criteria to classify synapses as simple vs. complex is critical for all of the analysis in this study. Therefore this criteria for classification should be much more explicit and tested for robustness. As stated in the methods, it is based on the number of active zones which are designated by the number of Bassoon clusters associated with a Vglut2 cluster (line 697). A second part of the criteria is the size of the presynaptic terminal as assayed by "greater Vglut2 signal" (line 116). So how are these thresholds determined? For Bassoon clusters, is one voxel sufficient? Two? If it's one, how often do they see a Bassoon positive voxel with no Vglut2 cluster and therefore may represent "noise"? There is no distribution of Bassoon volumes that is provided that might be the basis for selecting this number of sites. Unfortunately, the images are not helpful. For example, does P8 WT in Figure 1B have 7 or 2? According to Figure 2C, it appears the numbers are closer to 2-4.

The Vglut volume measurements also do not seem to provide a clear criterion. Figure 2 shows that the distributions of Vglut2 cluster volumes for complex and for simple synapses are significantly overlapping.

The authors need to clarify the quantitative approach used for this classification strategy and test how sensitive the results of the study are to how robust this strategy is

2. Effect sizes are quite small and all comparisons are made on medians of distributions. This leads to an n=3 biological replicates for all comparisons. Hence this small n may lead to significant results based on ANOVAS/t-tests, but the statistical power of these effects is quite weak. To accurately represent the variance in their data, the authors should show all three data points for each category (with a SD error bar when possible). They should also include the number of synapses in each category (e.g. the numerators in Figure 1D and the denominators for Figure 1E). For other figures, there are additional statistical questions described below.

3. The authors need to add a caveat regarding their classification of synapses as "complex" vs. "simple" since this is a terminology that already exists in the field and it is not clear that these STORM images are measuring the same thing. For example, in EM studies, "complex" refers to multiple RGCs converging on the same single postsynaptic site. The authors here acknowledge that they cannot assign different AZs to different RGCs so this comparison is an assumption. In Figure 2 they argue this is a good assumption based on the finding that the Vglut column/active zone is constant and therefore each represents a single RGC. However, the authors should acknowledge that they are actually seeing quite different percentages than those in EM studies. For example, in Monavarfeshani et al, eLife 2018, there were no complex synapses found at P8. (Note this study also found many more complex vs. simple synapses in the adult - 70% vs. the 20% found in the current study - but this difference could be a developmental effect). In the future, the authors may want to take another data set in the adult dLGN to make a direct comparison based on numbers and see if their classification method for complex/simple maps onto the one that currently exists in the literature.

4. Figure 3 assays the relative distribution of simple vs. complex synapses. They found that a larger percentage of simple synapses were within 1.5 microns of complex synapses than you would expect by chance for both ipsi and contra projecting RGCs, and hence conclude that complex synapses are sites of synaptic clustering. In contrast, there was no clustering of ipsi-simple to contra-complex synapses and vice versa. The authors also argue that this clustering decreases between P4 and P8 for ipsi projecting RGCs.

This analysis needs much more rigor before any conclusions can be drawn. First, the authors need to justify the 1.5-micron criteria for clustering and how robust their results are to variations in this distance. Second, these age effects need to be tested for statistical significance with an ANOVA (all the stats presented are pairwise comparisons to means expected by random distributions at each age). Finally, the authors should consider what n's to use here - is it still grouped by biological replicate? Why not use individual synapses across mice? If they do biological replicates, then they should again show error bars for each data point in their biological replicates. And they should include the number of synapses that went into these measurements in the caption.

5. Line 211-212 - the authors conclude that the absence of clustered ipsi-simple synapses indicates a failure to stabilize (Figure 3). Yet, the link between this measurement and synapse stabilization is not clear. In particular, the conclusion that "isolated" synapses are the ones that will be eliminated seems to be countered by their finding in Figure 3D/E which shows that there is no difference in vesicle pool volume between near and far synapses. If isolated synapses are indeed the ones that fail to stabilize by P8, wouldn't you expect them to be weaker/have fewer vesicles? Also, it's hard to tell if there is an age-dependent effect since the data presented in Figures 3D/E are merged across ages.

Reviewer #1 (Public Review):

Summary:<br /> The work of Muller and colleagues concerns the question of where we place our feet when passing uneven terrain, in particular how we trade-off path length against the steepness of each single step. The authors find that paths are chosen that are consistently less steep and deviate from the straight line more than an average random path, suggesting that participants indeed trade-off steepness for path length. They show that this might be related to biomechanical properties, specifically the leg length of the walkers. In addition, they show using a neural network model that participants could choose the footholds based on their sensory (visual) information about depth.

Strengths:<br /> The work is a natural continuation of some of the researchers' earlier work that related the immediately following steps to gaze [17]. Methodologically, the work is very impressive and presents a further step forward towards understanding real-world locomotion and its interaction with sampling visual information. While some of the results may seem somewhat trivial in hindsight (as always in this kind of study), I still think this is a very important approach to understanding locomotion in the wild better.

Weaknesses:<br /> The manuscript as it stands has several issues with the reporting of the results and the statistics. In particular, it is hard to assess the inter-individual variability, as some of the data are aggregated across individuals, while in other cases only central tendencies (means or medians) are reported without providing measures of variability; this is critical, in particular as N=9 is a rather small sample size. It would also be helpful to see the actual data for some of the information merely described in the text (e.g., the dependence of \Delta H on path length). When reporting statistical analyses, test statistics and degrees of freedom should be given (or other variants that unambiguously describe the analysis). The CNN analysis chosen to link the step data to visual sampling (gaze and depth features) should be motivated more clearly, and it should describe how training and test sets were generated and separated for this analysis. There are also some parts of figures, where it is unclear what is shown or where units are missing. The details are listed in the private review section, as I believe that all of these issues can be fixed in principle without additional experiments.

Reviewer #2 (Public Review):

Summary:<br /> This manuscript examines how humans walk over uneven terrain using vision to decide where to step. There is a huge lack of evidence about this because the vast majority of locomotion studies have focused on steady, well-controlled conditions, and not on decisions made in the real world. The author team has already made great advances in this topic, but there has been no practical way to map 3D terrain features in naturalistic environments. They have now developed a way to integrate such measurements along with gaze and step tracking, which allows quantitative evaluation of the proposed trade-offs between stepping vertically onto vs. stepping around obstacles, along with how far people look to decide where to step.

Strengths:<br /> 1. I am impressed by the overarching outlook of the researchers. They seek to understand human decision-making in real-world locomotion tasks, a topic of obvious relevance to the human condition but not often examined in research. The field has been biased toward well-controlled studies, which have scientific advantages but also serious limitations. A well-controlled study may eliminate human decisions and favor steady or periodic motions in laboratory conditions that facilitate reliable and repeatable data collection. The present study discards all of these usually-favorable factors for rather uncontrolled conditions, yet still finds a way to explore real-world behaviors in a quantitative manner. It is an ambitious and forward-thinking approach, used to tackle an ecologically relevant question.

2. There are serious technical challenges to a study of this kind. It is true that there are existing solutions for motion tracking, eye tracking, and most recently, 3D terrain mapping. However most of the solutions do not have turn-key simplicity and require significant technical expertise. To integrate multiple such solutions together is even more challenging. The authors are to be commended on the technical integration here.

3. In the absence of prior studies on this issue, it was necessary to invent new analysis methods to go with the new experimental measures. This is non-trivial and places an added burden on the authors to communicate the new methods. It's harder to be at the forefront in the choice of topic, technical experimental techniques, and analysis methods all at once.

Weaknesses:<br /> 1. I am predisposed to agree with all of the major conclusions, which seem reasonable and likely to be correct. Ignoring that bias, I was confused by much of the analysis. There is an argument that the chosen paths were not random, based on a comparison of probability distributions that I could not understand. There are plots described as "turn probability vs. X" where the axes are unlabeled and the data range above 1. I hope the authors can provide a clearer description to support the findings. This manuscript stands to be cited well as THE evidence for looking ahead to plan steps, but that is only meaningful if others can understand (and ultimately replicate) the evidence.

2. I wish a bit more and simpler data could be provided. It is great that step parameter distributions are shown, but I am left wondering how this compares to level walking. The distributions also seem to use absolute values for slope and direction, for understandable reasons, but that also probably skews the actual distribution. Presumably, there should be (and is) a peak at zero slope and zero direction, but absolute values mean that non-zero steps may appear approximately doubled in frequency, compared to separate positive and negative. I would hope to see actual distributions, which moreover are likely not independent and probably have a covariance structure. The covariance might help with the argument that steps are not random, and might even be an easy way to suggest the trade-off between turning and stepping vertically. This is not to disregard the present use of absolute values but to suggest some basic summary of the data before taking that step.

3. Along these same lines, the manuscript could do more to enable others to digest and go further with the approach, and to facilitate interpretability of results. I like the use of a neural network to demonstrate the predictiveness of stepping, but aside from above-chance probability, what else can inform us about what visual data drives that? Similarly, the step distributions and height-turn trade-off curves are somewhat opaque and do not make it easy to envision further efforts by others, for example, people who want to model locomotion. For that, clearer (and perhaps) simpler measures would be helpful.

I am absolutely in support of this manuscript and expect it to have a high impact. I do feel that it could benefit from clarification of the analysis and how it supports the conclusions.

Reviewer #3 (Public Review):

Summary:<br /> The systematic way in which path selection is parametrically investigated is the main contribution.

Strengths:<br /> The authors have developed an impressive workflow to study gait and gaze in natural terrain.

Weaknesses:<br /> 1. The training and validation data of the CNN are not explained fully making it unclear if the data tells us anything about the visual features used to guide steering.

It is not clear how or on what data the network was trained (training vs. validation vs. un-peeked test data), and justification of the choices made. There is no discussion of possible overfitting. The network could be learning just e.g. specific rock arrangements. If the network is overfitting the "features" it uses could be very artefactual, pixel-level patterns and not the kinds of "features" the human reader immediately has in mind.

2. The use of descriptive terminology should be made systematic.

Specifically, the following terms are used without giving a single, clear definition for them: path, step, step location, foot plant, foothold, future foothold, foot location, future foot location, foot position.

I think some terms are being used interchangeably. I would really highly recommend a diagrammatic cartoon sketch, showing the definitions of all these terms in a single figure, and then sticking to them in the main text.

3. More coverage of different interpretations / less interpretation in the abstract/introduction would be prudent

The authors discuss the path selection very much on the basis of energetic costs and gait stability. At least mention should be given to other plausible parameters the participants might be optimizing (or that indeed they may be just satisficing).

That is, it is taken as "given" that energetic cost is the major driver of path selection in your task, and that the relevant perception relies on internal models. Neither of these is a priori obvious nor is it as far as I can tell shown by the data (optimizing other variables, satisficing behavior, or online "direct perception" cannot be ruled out).

Reviewer #1 (Public Review):

Summary:<br /> The authors aim to consider the effects of phonotactics on the effectiveness of memory reactivation during sleep. They have created artificial words that are either typical or atypical and showed that reactivation improves memory for the latter but not the former.

Strengths:<br /> This is an interesting design and a creative way of manipulating memory strength and typicality. In addition, the spectral analysis on both the wakefulness data and the sleep data is well done. The article is clearly written and provides a relevant and comprehensive of the literature and of how the results contribute to it.

Weaknesses:<br /> 1. Unlike most research involving artificial language or language in general, the task engaged in this manuscript did not require (or test) learning of meaning or translation. Instead, the artificial words were arbitrarily categorised and memory was tested for that categorisation. This somewhat limits the interpretation of the results as they pertain to language science, and qualifies comparisons with other language-related sleep studies that the manuscript builds on.

2. The details of the behavioural task are hard to understand as described in the manuscript. Specifically, I wasn't able to understand when words were to be responded to with the left or right button. What were the instructions? Were half of the words randomly paired with left and half with right and then half of each rewarded and half unrewarded? Or was the task to know if a word was rewarded or not and right/left responses reflected the participants' guesses as to the reward (yes/no)? Please explain this fully in the methods, but also briefly in the caption to Figure 1 (e.g., panel C) and in the Results section.

3. Relatedly, it is unclear how reward or lack thereof would translate cleanly into a categorisation of hits/misses/correct rejections/false alarms, as explained in the text and shown in Figure 1D. If the item was of the non-rewarded class and the participant got it correct, they avoided loss. Why would that be considered a correct rejection, as the text suggests? It is no less of a hit than the rewarded-correct, it's just the trial was set up in a way that limits gains. This seems to mix together signal detection nomenclature (in which reward is uniform and there are two options, one of which is correct and one isn't) and loss-aversion types of studies (in which reward is different for two types of stimuli, but for each type you can have H/M/CR/FA separably). Again, it might all stem from me not understanding the task, but at the very least this required extended explanations. Once the authors address this, they should also update Fig 1D. This complexity makes the results relatively hard to interpret and the merit of the manuscript hard to access. Unless there are strong hypotheses about reward's impact on memory (which, as far as I can see, are not at the core of the paper), there should be no difference in the manner in which the currently labelled "hits" and "CR" are deemed - both are correct memories. Treating them differently may have implications on the d', which is the main memory measure in the paper, and possibly on measures of decision bias that are used as well.

4. The study starts off with a sample size of N=39 but excludes 17 participants for some crucial analyses. This is a high number, and it's not entirely clear from the text whether exclusion criteria were pre-registered or decided upon before looking at the data. Having said that, some criteria seem very reasonable (e.g., excluding participants who were not fully exposed to words during sleep). It would still be helpful to see that the trend remains when including all participants who had sufficient exposure during sleep. Also, please carefully mention for each analysis what the N was.

5. Relatedly, the final N is low for a between-subjects study (N=11 per group). This is adequately mentioned as a limitation, but since it does qualify the results, it seemed important to mention it in the public review.

6. The linguistic statistics used for establishing the artificial words are all based on American English, and are therefore in misalignment with the spoken language of the participants (which was German). The authors should address this limitation and discuss possible differences between the languages. Also, if the authors checked whether participants were fluent in English they should report these results and possibly consider them in their analyses. In all fairness, the behavioural effects presented in Figure 2A are convincing, providing a valuable manipulation test.

7. With regard to the higher probability of nested spindles for the high- vs low-PP cueing conditions, the authors should try and explore whether what the results show is a general increase for spindles altogether (as has been reported in the past to be correlated with TMR benefit and sleep more generally) or a specific increase in nested spindles (with no significant change in the absolute numbers of post-cue spindles). In both cases, the results would be interesting, but differentiating the two is necessary in order to make the claim that nesting is what increased rather than spindle density altogether, regardless of the SW phase.

Reviewer #2 (Public Review):

Summary:<br /> The work by Klaassen & Rasch investigates the influence of word learning difficulty on sleep-associated consolidation and reactivation. They elicited reactivation during sleep by applying targeted memory reactivation (TMR) and manipulated word learning difficulty by creating words more similar (easy) or more dissimilar (difficult) to our language. In one group of participants, they applied TMR of easy words and in another group of participants, they applied TMR of difficult words (between-subjects design). They showed that TMR leads to higher memory benefits in the easy compared to the difficult word group. On a neural level, they showed an increase in spindle power (in the up-state of an evoked response) when easy words were presented during sleep.

Strengths:<br /> The authors investigate a research question relevant to the field, that is, which experiences are actually consolidated during sleep. To address this question, they developed an innovative task and manipulated difficulty in an elegant way.

Overall, the paper is clearly structured, and results and methods are described in an understandable way. The analysis approach is solid.

Weaknesses:<br /> 1.Sample size<br /> For a between-subjects design, the sample size is too small (N = 22). The main finding (also found in the title "Difficulty in artificial word learning impacts targeted memory reactivation") is based on an independent samples t-test with 11 participants/group.

The authors explicitly mention the small sample size and the between-subjects design as a limitation in their discussion. Nevertheless, making meaningful inferences based on studies with such a small sample size is difficult, if not impossible.

2.Choice of task<br /> Even though the task itself is innovative, there would have been tasks better suited to address the research question. The main disadvantage the task and the operationalisation of memory performance (d') have is that single-trial performance cannot be calculated. Consequently, choosing individual items for TMR is not possible.

Additionally, TMR of low vs. high difficulty is conducted between subjects (and independently of pre-sleep memory performance) which is a consequence of the task design.

The motivation for why this task has been used is missing in the paper.

Reviewer #3 (Public Review):

Summary:<br /> In this study, the authors investigated the effects of targeted memory reactivation (TMR) during sleep on memory retention for artificial words with varying levels of phonotactical similarity to real words. The authors report that the high phonotactic probability (PP) words showed a more pronounced EEG alpha decrease during encoding and were more easily learned than the low PP words. Following TMR during sleep, participants who had been cued with the high PP TMR, remembered those words better than 0, whilst no such difference was found in the other conditions. Accordingly, the authors report higher EEG spindle band power during slow-wave up-states for the high PP as compared to low PP TMR trials. Overall, the authors conclude that artificial words that are easier to learn, benefit more from TMR than those which are difficult to learn.

Strengths:<br /> 1. The authors have carefully designed the artificial stimuli to investigate the effectiveness of TMR on words that are easy to learn and difficult to learn due to their levels of similarity with prior word-sound knowledge. Their approach of varying the level of phonotactic probability enables them to have better control over phonotactical familiarity than in a natural language and are thus able to disentangle which properties of word learning contribute to TMR success.

2. The use of EEG during wakeful encoding and sleep TMR sheds new light on the neural correlates of high PP vs. low PP both during wakeful encoding and cue-induced retrieval during sleep.

Weaknesses:<br /> 1. The present analyses are based on a small sample and comparisons between participants. Considering that the TMR benefits are based on changes in memory categorization between participants, it could be argued that the individuals in the high PP group were more susceptible to TMR than those in the low PP group for reasons other than the phonotactic probabilities of the stimuli (e.g., these individuals might be more attentive to sounds in the environment during sleep). While the authors acknowledge the small sample size and between-subjects comparison as a limitation, a discussion of an alternative interpretation of the data is missing.

2. While the one-tailed comparison between the high PP condition and 0 is significant, the ANOVA comparing the four conditions (between subjects: cued/non-cued, within-subjects: high/low PP) does not show a significant effect. With a non-significant interaction, I would consider it statistically inappropriate to conduct post-hoc tests comparing the conditions against each other. Furthermore, it is unclear whether the p-values reported for the t-tests have been corrected for multiple comparisons. Thus, these findings should be interpreted with caution.

3. With the assumption that the artificial words in the study have different levels of phonotactic similarity to prior word-sound knowledge, it was surprising to find that the phonotactic probabilities were calculated based on an American English lexicon whilst the participants were German speakers. While it may be the case that the between-language lexicons overlap, it would be reassuring to see some evidence of this, as the level of phonotactic probability is a key manipulation in the study.

4. Another manipulation in the study is that participants learn whether the words are linked to a monetary reward or not, however, the rationale for this manipulation is unclear. For instance, it is unclear whether the authors expect the reward to interact with the TMR effects.

Reviewer #1 (Public Review):

Summary:

Flavonoids are abundant in plant-based foods. They have been widely recognized for their health-promoting properties. There is increasing evidence that the effects of dietary flavonoids depend on their metabolism by gut bacteria, which can enhance, reduce or otherwise alter the flavonoids' bioactivities. On the other hand, little is known regarding the enzymes and species that can utilize flavonoids as metabolic substrates.

In the current manuscript, the authors analyzed the possibility to predict the degradation of flavonoids that we take up with our food by gut bacteria. In contrast to plants, bacteria do not contain obvious degradation enzymes.

Strengths:

To predict such enzymes with a broad substrate specificity (enzyme promiscuity) the authors optimized/modified a bioinformatic tool to predict whether a gut bacterial enzyme could catalyze a flavonoid reaction based on the chemical reaction similarity of the enzyme's native reaction and known flavonoid reactions in plants.<br /> They predicted such enzyme activities in genomes of bacteria that had been shown to occur in the human gut. Then, they cultivated selected bacteria with the predicted enzymatic activities and in fact showed, that they can degrade parts of these flavonoids. Together with the bioinformatic and mass spectrometry they identified a metabolization pathway of the flavonoid tilianin that spanned multiple species, i.e., Bifidobacterium longum subsp. animalis, Blautia coccoides, and Flavonifractor plautii. Lastly, the authors showed that tilianin metabolites exhibit protective effects against H2O2 through reactive oxygen species scavenging activity and thus, improve viability of a neuronal cell line, while the parent compound, tilianin, was ineffective. This protective effect might be due to gut microbiota-dependent physiological effects of dietary flavonoids.

Weaknesses:

1) To confirm the bioinformatic-based predictions the authors used in vitro culture experiments and LC-MS experiments. Although these in vitro experiments clearly add value to the bioinformatic prediction, they fall short of providing firm evidence for the predictions because they do not show whether the predicted enzymes really catalyze the predicted reactions. In theory, there could be other enzymes not identified bioinformatically that catalyze the reactions.

2) It is not clear how the authors selected the bacterial species. Did they analyze meta genome sequences or hundreds of genomes of gut bacteria? Did they analyze bacteria isolated from the gut or rather type strains? What about other bacterial species in the gut? Do they also encode relevant enzymes? If yes, how many do? This needs to be clarified.

3) The reported data on E. coli is difficult to understand. Has E. coli a different degradation pathway leading to the observed disappearance of tilianins?

Reviewer #2 (Public Review):

The manuscript deals with an interesting topic in metabolism: the so-called underground metabolism enabled by enzymes with broad substrate specificity. This is mainly relevant in secondary metabolisms. The authors deal, in particular, with the conversion of flavonoids, which have health-promoting effects. They present an algorithm for predicting the moonlight activities of enzymes, which must be given as inputs. Moreover, the authors performed experiments on the antioxidant activities of the flavonoids under study.

My focus was on the bioinformatics part. Overall, the bioinformatics part is not a major scientific achievement in my eyes, or it is too poorly described to see its merits. There may be difficulties understanding the presented algorithm.

Comments:

The prediction algorithm should be explained much better. Although the manuscript is quite long, it does not describe the approaches sufficiently well. It is quite hard to read.

As far as I can see, the method was only tested with a small sample of different flavonoid substances.

Major comments<br /> (1) I see the following contradiction. Line 18/19: "As flavonoids are not natural substrates of gut bacterial enzymes" and lines 76/77: "commensal gut microorganisms do not have specialized enzymes that utilize flavonoids as their native substrates" versus lines 72-74: "flavonoids ..., which makes them available to be metabolized". How can they be metabolized given what is said in the first two phrases?<br /> (2) It should be explained better what is meant by "reaction class" (e.g. in lines 97 and 99). Is this the same as the EC number (in the Enzyme Catalogue)? The term "reaction class" is indeed used in the KEGG database. On the webpage<br /> https://www.genome.jp/brite/br08204<br /> it seems indeed as if the terms "reaction class" and EC number are somehow equivalent. However, the term "RClass RC00392" in line 557 of the manuscript points to a difference in meaning.<br /> (3) The prediction algorithm should be explained much better. For example, in the Figure showing the workflow, it is shown that an EC number should be given as input. However, if we search for enzymes which could potentially degrade a given flavonoid, we may not know any suitable EC number. Line 122: "To match a given enzyme with its non-native polyphenolic substrates..." However, where can we take the enzyme name/EC number from? Moreover, given that it is assumed that the reaction is performed by underground metabolism, should the enzyme given as input come from another organism, for example, a plant?<br /> (4) Lines 521-523: Our prediction tool can take either a single enzyme in the form of Enzyme Commission (EC) number (e.g. "ec:2.1.1.75"), or a KEGG organism-identifier (e.g. "cpv") or a consortium, a list of different organism-identifiers, as input." I do not understand the wording "or a consortium". According to the Figure showing the workflow, it should read "and a consortium".<br /> (5) In the Materials and Methods section, the KEGG PATHWAY database is mentioned. This comes somewhat out of the blue. What is the connection to the "reaction class" concept in KEGG? Or is the PATHWAY database only used for extracting the negative controls?<br /> (6) Line 142,143. "Our analysis shows that RClass-based similarity can predict the correct reactions for known flavonoid-metabolizing enzymes". How do the authors know that the results are correct? If it is easy to check, then I assume the test whether a given enzyme is able to catalyze reactions with flavonoids can be done manually in KEGG, so that a computer algorithm is unnecessary.<br /> (7) Elaborating on the previous point - I have the impression that the algorithm is a rather simple search routine for finding reactions in the KEGG database that match certain criteria. This might be a helpful tool to save time in comparison to doing the search manually. However, at least the bioinformatics part of the paper is not a major scientific achievement as far as I can see.<br /> (8) It is not sufficiently clear whether the prediction algorithm only works for the example shown in the top figure (tilianin, acacetin etc), which would be quite a restricted application, or for many or even all flavonoids. In line 565, the authors say: "our tabulated 312 unique flavonoids", while in the upper part of the MS, e.g. in lines 26 and 109, only the pathway starting from tilianin is mentioned.<br /> (9) In which programming language was the algorithm implemented?<br /> (10) The connection between the theoretical and experimental parts of the paper is not fully clear. Some of the experiments serve to test the predictions, which is fine. The experiments on free radicals, however, seem to be somewhat unrelated.

Reviewer #1 (Public Review):

Summary:<br /> In this highly ambitious paper, Breen and Deffner used a multi-pronged approach to generate novel insights on how differences between male and female birds in their learning strategies might relate to patterns of invasion and spread into new geographic and urban areas.

The empirical results, drawn from data available in online archives, showed that while males and females are similar in their initial efficiency of learning a standard color-food association (e.g., color X = food; color Y = no food) scenario when the associations are switched (now, color Y = food, X= no food), males are more efficient than females at adjusting to the new situation (i.e., faster at 'reversal learning'). Clearly, if animals live in an unstable world, where associations between cues (e.g., color) and what is good versus bad might change unpredictably, it is important to be good at reversal learning. In these grackles, males tend to disperse into new areas before females. It is thus fascinating that males appear to be better than females at reversal learning. Importantly, to gain a better understanding of underlying learning mechanisms, the authors use a Bayesian learning model to assess the relative role of two mechanisms (each governed by a single parameter) that might contribute to differences in learning. They find that what they term 'risk sensitive' learning is the key to explaining the differences in reversal learning. Males tend to exhibit higher risk sensitivity which explains their faster reversal learning. The authors then tested the validity of their empirical results by running agent-based simulations where 10,000 computer-simulated 'birds' were asked to make feeding choices using the learning parameters estimated from real birds. Perhaps not surprisingly, the computer birds exhibited learning patterns that were strikingly similar to the real birds. Finally, the authors ran evolutionary algorithms that simulate evolution by natural selection where the key traits that can evolve are the two learning parameters. They find that under conditions that might be common in urban environments, high-risk sensitivity is indeed favored.

Strengths:<br /> The paper addresses a critically important issue in the modern world. Clearly, some organisms (some species, some individuals) are adjusting well and thriving in the modern, human-altered world, while others are doing poorly. Understanding how organisms cope with human-induced environmental change, and why some are particularly good at adjusting to change is thus an important question.

The comparison of male versus female reversal learning across three populations that differ in years since they were first invaded by grackles is one of few, perhaps the first in any species, to address this important issue experimentally.

Using a combination of experimental results, statistical simulations, and evolutionary modeling is a powerful method for elucidating novel insights.

Weaknesses:<br /> The match between the broader conceptual background involving range expansion, urbanization, and sex-biased dispersal and learning, and the actual comparison of three urban populations along a range expansion gradient was somewhat confusing. The fact that three populations were compared along a range expansion gradient implies an expectation that they might differ because they are at very different points in a range expansion. Indeed, the predicted differences between males and females are largely couched in terms of population differences based on their 'location' along the range-expansion gradient. However, the fact that they are all urban areas suggests that one might not expect the populations to differ. In addition, the evolutionary model suggests that all animals, male or female, living in urban environments (that the authors suggest are stable but unpredictable) should exhibit high-risk sensitivity. Given that all grackles, male and female, in all populations, are both living in urban environments and likely come from an urban background, should males and females differ in their learning behavior? Clarification would be useful.

Reinforcement learning mechanisms:<br /> Although the authors' title, abstract, and conclusions emphasize the importance of variation in 'risk sensitivity', most readers in this field will very possibly misunderstand what this means biologically. Both the authors' use of the term 'risk sensitivity' and their statistical methods for measuring this concept have potential problems.

First, most behavioral ecologists think of risk as predation risk which is not considered in this paper. Secondarily, some might think of risk as uncertainty. Here, as discussed in more detail below, the 'risk sensitivity' parameter basically influences how strongly an option's attractiveness affects the animal's choice of that option. They say that this is in line with foraging theory (Stephens and Krebs 2019) where sensitivity means seeking higher expected payoffs based on prior experience. To me, this sounds like 'reward sensitivity', but not what most think of as 'risk sensitivity'. This problem can be easily fixed by changing the name of the term.

In addition, however, the parameter does not measure sensitivity to rewards per se - rewards are not in equation 2. As noted above, instead, equation 2 addresses the sensitivity of choice to the attraction score which can be sensitive to rewards, though in complex ways depending on the updating parameter. Second, equations 1 and 2 involve one specific assumption about how sensitivity to rewards vs. to attraction influences the probability of choosing an option. In essence, the authors split the translation from rewards to behavioral choices into 2 steps. Step 1 is how strongly rewards influence an option's attractiveness and step 2 is how strongly attractiveness influences the actual choice to use that option. The equation for step 1 is linear whereas the equation for step 2 has an exponential component. Whether a relationship is linear or exponential can clearly have a major effect on how parameter values influence outcomes. Is there a justification for the form of these equations? The analyses suggest that the exponential component provides a better explanation than the linear component for the difference between males and females in the sequence of choices made by birds, but translating that to the concepts of information updating versus reward sensitivity is unclear. As noted above, the authors' equation for reward sensitivity does not actually include rewards explicitly, but instead only responds to rewards if the rewards influence attraction scores. The more strongly recent rewards drive an update of attraction scores, the more strongly they also influence food choices. While this is intuitively reasonable, I am skeptical about the authors' biological/cognitive conclusions that are couched in terms of words (updating rate and risk sensitivity) that readers will likely interpret as concepts that, in my view, do not actually concur with what the models and analyses address.

To emphasize, while the authors imply that their analyses separate the updating rate from 'risk sensitivity', both the 'updating parameter' and the 'risk sensitivity' parameter influence both the strength of updating and the sensitivity to reward payoffs in the sense of altering the tendency to prefer an option based on recent experience with payoffs. As noted in the previous paragraph, the main difference between the two parameters is whether they relate to behaviour linearly versus with an exponential component.

Overall, while the statistical analyses based on equations (1) and (2) seem to have identified something interesting about two steps underlying learning patterns, to maximize the valuable conceptual impact that these analyses have for the field, more thinking is required to better understand the biological meaning of how these two parameters relate to observed behaviours, and the 'risk sensitivity' parameter needs to be re-named.

Agent-based simulations:<br /> The authors estimated two learning parameters based on the behaviour of real birds, and then ran simulations to see whether computer 'birds' that base their choices on those learning parameters return behaviours that, on average, mirror the behaviour of the real birds. This exercise is clearly circular. In old-style, statistical terms, I suppose this means that the R-square of the statistical model is good. A more insightful use of the simulations would be to identify situations where the simulation does not do as well in mirroring behaviour that it is designed to mirror.

Reviewer #2 (Public Review):

Summary:<br /> The study is titled "Leading an urban invasion: risk-sensitive learning is a winning strategy", and consists of three different parts. First, the authors analyse data on initial and reversal learning in Grackles confronted with a foraging task, derived from three populations labeled as "core", "middle" and "edge" in relation to the invasion front. The suggested difference between study populations does not surface, but the authors do find moderate support for a difference between male and female individuals. Secondly, the authors confirm that the proposed mechanism can actually generate patterns such as those observed in the Grackle data. In the third part, the authors present an evolutionary model, in which they show that learning strategies as observed in male Grackles do evolve in what they regard as conditions present in urban environments.

Strengths:<br /> The manuscript's strength is that it combines real learning data collected across different populations of the Great-tailed grackle (Quiscalus mexicanus) with theoretical approaches to better understand the processes with which grackles learn and how such learning processes might be advantageous during range expansion. Furthermore, the authors also take sex into account revealing that males, the dispersing sex, show moderately better reversal learning through higher reward-payoff sensitivity. I also find it refreshing to see that the authors took the time to preregister their study to improve transparency, especially regarding data analysis.

Weaknesses:<br /> One major weakness of this manuscript is the fact that the authors are working with quite low sample sizes when we look at the different populations of edge (11 males & 8 females), middle (4 males & 4 females), and core (17 males & 5 females) expansion range. Although I think that when all populations are pooled together, the sample size is sufficient to answer the questions regarding sex differences in learning performance and which learning processes might be used by grackles but insufficient when taking the different populations into account.

Another weakness of this manuscript is that it does not set up the background well in the introduction. Firstly, are grackles urban dwellers in their natural range and expand by colonising urban habitats because they are adapted to it? The introduction also fails to mention why urban habitats are special and why we expect them to be more challenging for animals to inhabit. If we consider that one of their main questions is related to how learning processes might help individuals deal with a challenging urban habitat, then this should be properly introduced.

Also, the authors provide a single example of how learning can differ between populations from more urban and more natural habitats. The authors also label the urban dwellers as the invaders, which might be the case for grackles but is not necessarily true for other species, such as the Indian rock agama in the example which are native to the area of study. Also, the authors need to be aware that only male lizards were tested in this study. I suggest being a bit more clear about what has been found across different studies looking at: (1) differences across individuals from invasive and native populations of invasive species and (2) differences across individuals from natural and urban populations.

Finally, the introduction is very much written with regard to the interaction between learning and dispersal, i.e. the 'invasion front' theme. The authors lay out four predictions, the most important of which is No. 4: "Such sex-mediated differences in learning to be more pronounced in grackles living at the edge, rather than the intermediate and/or core region of their range." The authors, however, never return to this prediction, at least not in a transparent way that clearly pronounces this pattern not being found. The model looking at the evolution of risk-sensitive learning in urban environments is based on the assumption that urban and natural environments "differ along two key ecological axes: environmental stability 𝑢 (How often does optimal behaviour change?) and environmental stochasticity 𝑠 (How often does optimal behaviour fail to pay off?). Urban environments are generally characterised as both stable (lower 𝑢) and stochastic (higher 𝑠)". Even though it is generally assumed that urban environments differ from natural environments the authors' assumption is just one way of looking at the differences which have generally not been confirmed and are highly debated. Additionally, it is not clear how this result relates to the rest of the paper: The three populations are distinguished according to their relation to the invasion front, not with respect to a gradient of urbanization, and further do not show a meaningful difference in learning behaviour possibly due to low sample sizes as mentioned above.

In conclusion, the manuscript was well written and for the most part easy to follow. The format of having the results before the methods makes it a bit harder to follow because the reader is not fully aware of the methods at the time the results are presented. It would, therefore, be important to more clearly delineate the different parts and purposes. Is this article about the interaction between urban invasion, dispersal, and learning? Or about the correct identification of learning mechanisms? Or about how learning mechanisms evolve in urban and natural environments? Maybe this article can harbor all three, but the borders need to be clear. The authors need to be transparent about what has and especially what has not been found, and be careful to not overstate their case.

Reviewer #1 (Public Review):

There are a number of outstanding questions concerning how cohesin turnover on DNA is controlled by various accessory factors and how such turnover is controlled by post-translational modification. In this paper, Nasmyth et al. perform a series of AlphaFold structure predictions that aim to address several of these outstanding questions. Their structure predictions suggest that the release factor WAPL forms a ternary complex with PDS5 and SA/SCC3. This ternary complex appears to be able to bind the N-terminal end of SCC1, suggesting how formation of such a complex could stabilize an open state of the cohesin ring. Additional calculations suggest how the Eco/ESCO acetyltransferases and Sororin engage the SMC3 head domain presumably to protect against WAPL-mediated release.

This work thus demonstrates the power of AF prediction methods and how they can lead to a number of interesting and testable hypotheses that can transform our understanding of cohesin regulation. These findings require orthogonal experimental validation, but authors argue convincingly that such validation should not be a pre-requisite to publication.

In their revised version, the authors did not systematically include model confidence scores, and it therefore remains difficult for the reader to evaluate the reliability of the models obtained. The authors correctly point out that such metrics are available on figshare. It is therefore possible to obtain such information. The caveat is that it remains to the user to identify and extract the relevant information. While they claim that they have labeled N- and C-termini in their figures, no such labeling can be seen in the revised version. Addition of such labels, at least for some of the figures, would help the user to navigate the models.

The authors have now updated figure legends to indicate which protein is referred to by the chain labels shown in PAE plots.

It is exciting to see AF-multimer predictions being applied to cohesin. As some of the reported interactions are not universally conserved and some involve relatively small interfaces the possibility arises that these interfaces show poor or borderline confidence scores. As some of these interfaces map to mutants that have previously been obtained by hypothesis-free genetic screens and mutational analyses, they appear nevertheless valid. Thus, an important point to make is that even interfaces that show modest confidence scores may turn out to be valid while others may be not.

Reviewer #2 (Public Review):

The ATPase protein machine cohesin shapes the genome by loop extrusion and holds sister chromatids together by topological entrapment. When executing these functions, cohesin is tightly regulated by multiple cofactors, such as Scc2/Nipbl, Pds5, Wapl, and Eco1/Esco1/2, and it undergoes dynamic conformational changes with ATP binding and hydrolysis. The mechanisms by which cohesin extrudes DNA loops and medicates siter-chromatid cohesion are still not understood. A major reason for the lack of understanding of cohesin dynamics and regulation is the failure to capture the structures of intact cohesin in different nucleotide-bound states and in complex with various regulators. So far only the ATP state cohesin bound to NIPBL and DNA have been experimentally determined.

In this manuscript, Nasmyth et al. made use of the powerful protein structure prediction tool, AlphaFold2 (AF), to predict the models of tens of cohesin subcomplexes from different species. The results provide important insight into how the Smc3-Scc1 DNA exiting gate is opened, how Pds5 and Wapl maintain the opened gate, how Pds5 and Scc3/SA recruit different cofactors, how Eco1 and Sororin antagonize Wapl, and how Scc2/Nipbl interacts with Scc3/SA. The models are for the most part consistent with published mutations in these proteins that affect cohesin's functions in vitro and in vivo and raise testable hypotheses of cohesin dynamics and regulation. This study also serves as an example of how to use AF to build models of protein complexes that involve the docking of flexible regions to globular domains.

Joint Public Review:

The study as a concept is well designed, although there is still one issue I see in the methodology.

I still have concerns with their attempts to combine the different scales of data. While the use of point data is great, it limits the sample size, and they have included the district to country level data to try and increase the sample size. The problem is that although they try to get an overall estimate at the district/state/country by taking 10 random sample points, which could be a method to get an estimate for the district/state/country. It would be a suitable method if the primates were evenly distributed across the district/state/country. The reality is that the primates are not evenly distributed across the district/state/country therefore the random point sampling is not a reasonable method to get an estimate of the environmental variables in relation to the macaques. For example if you had a mountainous country and you took 10 random points to estimate altitude, you would end up with a large number, but if all the animals of interest lived on the coast, your average altitude is meaningless in relation to the animals of interest as they are all living at low altitude. The fact that the model relies less on highly variable components and places more reliance on less variable components, is really not relevant as the district/state/country measurements have no real meaning in relation to the distribution of masques.

A simple possible way forward could be to run the model without the district/state/country samples and see what the outcome is. If the outcome is similar then the random point method may be viable (but if it gives the same outcome as ignoring those samples then you don't need the district/state/country samples). If you get a totally different outcome then it should raise concerns about using the district/state/country samples.

This paper is a really nice piece of work and is a valuable contribution but the district/state/country sample issue really needs to be addressed.

Reviewer #1 (Public Review):

Summary:<br /> Ciliary rootlet is a structure associated with the ciliary basal body (centriole) with beautiful striation observed by electron microscopy. It has been known for more than a century, but its function and protein arrangement are still unknown. This work reconstructed the near-atomic resolution 3D structure of the rootlet using cryo-electron tomography, discovered a number of interesting filamentous structures inside, and built a molecular model of the rootlet.

Strengths:<br /> The authors exploited the currently possible ability of cryo-ET and used it appropriately to describe the 3D structure of the rootlet. They carefully conducted subtomogram averaging and classification, which enabled an unprecedented detailed view of this structure. The dual use of (nearly) intact rootlets from cilia and extracted (demembraned) rootlets enabled them to describe with confidence how D1/D2/A bands form periodic structures and cross with longitudinal filaments, which are likely coiled-coil.

Weaknesses:<br /> Some more clarifications are needed. This reviewer believes that the authors can address them.

Reviewer #2 (Public Review):

Summary:<br /> This work performs structural analysis on isolated or purified rootlets.

Strengths:<br /> To date, most studies of this cellular assembly have been from fluorescence microscopy, conventional TEM methods, or through biochemical analysis of constituents. It is clearly a challenging target for structural analysis due to its complexity and heterogeneity. The authors combine observations from cryo-electron tomograms, automated segmentations, subtomogram averaging, and previous data from the literature to present an overall model of how the rootlet is organised.

Their model will serve as a jumping-off point for future studies, and as such it is something of considerable value and interest.

Weaknesses:<br /> It is speculative but is presented as such, and is well-reasoned, plausible, and thorough.

Reviewer #3 (Public Review):

Summary:<br /> The study offers a compelling molecular model for the organization of rootlets, a critical organelle that links cilia to the basal body. Striations have been observed in rootlets, but their assembly, composition, and function remain unknown. While previous research has explored rootlet structure and organization, this study delivers an unprecedented level of resolution, valuable to the centrosome and cilia field. The authors isolated rootlets from mice's eyes. They apply EM to partially purified rootlets (first negative stain, then cryoET). From these micrographs, they observed striations along the membranes along the rootlet but no regular spacing was observed.

The thickness of the sample and membranes prevented good contrast in the tomograms. Thus they further purified the rootlets using detergent, which allowed them to obtain cryoET micrographs of the rootlets with greater details. The tomograms were segmented and further processed to improve the features of the rootlet structures. From their analysis, they described 3 regular cross-striations and amorphous densities, which are connected perpendicularly to filaments along the length of the rootlets. They propose that various proteins provide the striations and rootletin forms parallel coiled coils that run along the rootlet. Overall their data provide a detailed model for the molecular organization of the rootlet.

The major strength is that this high-quality study uses state-of-the-art cryo-electron tomography, sub-tomogram averaging, and image analysis to provide a model of the molecular organization of rootlets. The micrographs are exceptional, with excellent contrast and details, which also implies the sample preparation was well optimized to provide excellent samples for cryo-ET. The manuscript is also clear and accessible.

To further validate their model, it would have been useful to identify some components in the EM maps through complementary approaches (mass spectrometry, mutants disrupting certain features, CLEM). Some potential candidates are mentioned in the discussion.

This research marks a significant step forward in our understanding of rootlets' molecular organization.

Reviewer #1 (Public Review):

The authors set out to define the molecular basis for LP as the origin of BRCA1-deficient breast cancers. They showed that LPs have the highest level of replicative stress, and hypothesise that this may account for their tendency to transform. They went on to identify ELF3 as a candidate driver of LP transformation and showed that ELF3 expression is up-regulated in response to replicative stress as well as BRCA1 deficiency. They went on to show that ELF3 inactivation led to a higher level of DNA damage, which may result from compromised replicative stress responses.

While the manuscript supports the interesting idea wherein ELF3 may fuel LP cell transformation, it remains obscure how ELF3 promotes cell tolerance to DNA damage. Interestingly the authors proposed that ELF3 suppresses excessive genomic instability, but in my opinion, I do not see any evidence that supports this claim. In fact, one might think that genomic instability is key to cell transformation.

Reviewer #2 (Public Review):

Summary:<br /> The manuscript focuses on a persistent question of why germline mutations in BRCA1 which impair homology-directed repair of DNA double-strand breaks predispose to primarily breast and ovarian cancers but not other tissues. The authors propose that replication stress is elevated in the luminal progenitor (LP) cells and apply the gene signature from Dreyer et al as a measure of replication stress in populations of cells selected by FACS previously (published by Lim et al.) and suggest an enrichment of replication stress among the LP cells. This is followed by single-cell RNA seq data from a small number of breast tissues from a small number of BRCA1 mutation carriers but the pathogenic variants are not listed. The authors perform an elegant analysis of the effects of BRCA1 knockdown in MCF10A cells, but these cells are not considered a model of LP cells.

Overall, the manuscript suffers from significant gaps and leaps in logic among the datasets used. The connection to luminal progenitor cells is not adequately established because the models used are not representative of this population of cells. Therefore, the central hypothesis is not sufficiently justified.

Strengths:<br /> The inducible knockdown of BRCA1 provided compelling data pointing to an upregulation of ELF3 in this setting as well as a small number of other genes. It would be useful to discuss the other genes for completeness and explain the logic for focusing on ELF3. Nonetheless, the connection with ELF 3 is reasonable. The authors provide significant data showing a role for ELF3 in breast epithelial cells and its role in cell survival.

Weaknesses:<br /> The initial observations in primary breast cells have small sample sizes. The mutations in BRCA1 seem to be presumed to be all the same, but we know that pathogenic variants differ among individuals and range from missense mutations affecting interactions with one critical partner to large-scale truncations of the protein.

The figure legends are missing critical details that make it difficult for the reader to evaluate the data. The data support the notion that ELF3 may participate in relieving replication stress, but does not appear to be limited to LP cells as proposed in the hypothesis.

Reviewer #1 (Public Review):

Summary:<br /> The authors analyzed 102 human embryos in order to address outstanding questions about human lower spinal development and secondary neural tube formation. Through whole embryo imaging and histologic analysis, they provide exceptional quantification of the timing of posterior neuropore closure, rate of lower spinal somite formation, and formation and regression of the human "tail." Their analysis also provides convincing qualitative evidence of the cellular and molecular mechanisms at play during lower spinal development by identifying the presence of caspase-dependent programmed cell death and the dynamic expression of FGF8/WNT3A within the elongating embryo. Interestingly, they identify multiple polarized lumens within the site of secondary neural tube formation and add a solid argument for the mode of formation of this structure; however, in its current state, the evidence for a conclusive morphogenetic mechanism remains elusive. Finally, the authors provide a substantial review of the existing publications related to human lower spinal development, creating an excellent reference and demonstrating the importance of continuing to utilize each of these precious samples for furthering our understanding of human development.

Strengths:<br /> This manuscript provides an excellent window into the key morphogenetic events of human caudal neural tube formation. Figures 1 and 2 provide beautiful images and quantification of the developmental events, enabling comparison to models that are currently in use, including model organisms and the developing spinal organoid field. The characterization of somite development and later regression is particularly important.

Next, the authors addressed current questions regarding the molecular pathways present during the elongation of the embryo and later regression of the tail structure. The in situ hybridization experiments in Figures 5 and 6 demonstrate important evidence for a maintained neuromesodermal progenitor pool of stem cells that promote axial elongation. Additionally, the identification of caspase-dependent cell death within the human tail provides an explanation for the mechanism of this regression, especially given the notable lack of presence of any gross necrosis.

Finally, as mentioned above, the non-trivial collection and review of the existing human secondary neural tube and body formation literature is an important tool and organizes and synthesizes ~ 100 years of observations from precious human samples.

Weaknesses:<br /> While there are no glaringly incorrect claims from the authors, several of the conclusions could benefit from a form of quantification to support their observations:

1) The identification of the proximal to distal degeneration of the tailgut within the human tail is difficult to distinguish with the current images present in Figure 3. A picture within a picture of the area containing the tail gut could be provided to prominently demonstrate the cellular architecture. Additionally, quantification of the localization of apoptosis would strongly support this observation, as well as provide a visualization of the tail's regression overall. For example, a graph plotting the number of apoptotic cells versus the rostral to caudal locations of the transverse sections while accounting for the CS stage of each analyzed embryo could be created; this could even be further broken down by region of tail, for example, tailgut, ventral ectodermal ridge, somite, etc.

2) The identification of the mode of formation of the secondary neural tube is probably the most interesting question to be addressed, however, Figure 7's evidence is not completely satisfying in its current form. While I agree that it is unlikely that multiple polarization foci form within the most caudal part of the tail and coalesce more rostrally, I am equally unsure that a single polarization would form rostrally and then split and re-coalesce as it moves caudally, as is currently depicted by 7B.

Multiple groups have recently shown the influence of geometric confinement on neuroectoderm and its ability to polarize and form a singular central lumen (Karzbrun 2021, Knight 2018), or the inverse situation of a lack of confinement resulting in the presence of multiple lumens. The tapering of the diameter of the tail and its shared perimeter and curvature with the polarization bears a striking resemblance to this controlled confinement. An interesting quantification to depict would include the number of lumens versus the transverse section diameter and CS stage to see if there is any correlation between embryo size and the number of multiple polarizations. Anecdotally, the fusion of multiple polarizations/lumens tends to occur often in these human organoid-type platforms, while splitting to multiple lumens as the tissues mature does not. Other supplements to Figure 7 could include 3D renderings of lumens of interest as depicted in Catala 2021, especially if it demonstrates the re-coalescence as seen in 7B.

The non-pathologic presence of multiple polarizations in human tails compared to the rodent pathogenic counterpart is interesting given that rodents obviously maintain this appendage while it is lost in humans.

3) Of potential interest is the process of junctional neurulation describing the mechanistic joining of the primary and secondary neural tube, which has recently been explored in chick embryos and demonstrated to have relevance to human disease (Dady 2014, Eibach 2017, Kim 2021). While it is clear this paper's goal does not center on the relationship between primary and secondary neurulation, such a mechanism may be relevant to the authors' interpretation of their observations of lumen coalescence. I wonder if the embryos studied provide any evidence to support junctional neurulation.

Reviewer #2 (Public Review):

Summary:<br /> This study utilizes a large series of neurulation human embryos to address several questions about the similarities and differences between human neurulation and model systems such as the chicken and rodent.

Strengths:<br /> The number of specimens utilized for the analysis provides robustness to the findings.

Weaknesses:<br /> It is not clear how the gestational age of the specimens was determined or how that can be known with certainty. There is no information given in the methods on this. With this in mind, bunching the samples at 2-day intervals in Figure 1J will lead to inaccuracies in assessing the rate of somite formation. This is pointed out as a major difference between specimens and organoids in the abstract but a similar result in the results section. The data supporting either of these statements is not convincing.

Whenever possible, give the numbers of specimens that had the described findings. For example, in Figure 2C - how many embryos were examined with the massive rounded end at CS13? Apoptosis in Figures 3 and 4?

For Figure 2I-K, it would be informative to superimpose the individual data points on the box plots distinguishing males from females, as in Figure 1I.

Is it possible to quantitate apoptosis and proliferation data?

The Tunel staining in Figure 3 is difficult to make out.

Additional improvements to the presentation of figures, writing, and quantization of results are suggested.

Reviewer #2 (Public Review):

Joshi et al. investigated the use of dantrolene, an RyR stabilizing drug, in improving contractile function and slowing pathological progression of pressure-overload heart failure. In a guinea pig model, they found that dantrolene treatment reduced cytosolic Ca2+ levels, improved contractility, reduced the incidence of arrhythmias, reduced fibrosis, and slowed the progression of heart failure. Importantly, delaying treatment until 3 weeks after aortic banding (when heart failure was already established) also resulted in improvements in function and decreased arrhythmogenesis. While some of the mechanistic details remain to be worked out, the data suggest that improving intracellular Ca2+ handling can break the vicious cycle of sympathetic activation, ROS production, and further deterioration of cardiac function.

The functional ECG and echo data are convincing, and very clearly demonstrate the positive effects of dantrolene in heart failure. This is important because dantrolene is already FDA-approved to treat malignant hyperthermia and muscle spasms, so repurposing this drug as a heart failure therapeutic might have a straightforward path to clinical implementation. This also highlights the non-specific nature of dantrolene to interact with RyR1, and therefore, potential side effects. However, this does not detract from the main proof-of-concept demonstrated here.

The guinea pig model employed here is also a strength, as the guinea pig has intracellular Ca2+ handling and ionic currents that are much more similar to human (vs. a murine model, for example).

One weakness is the exclusion of female animals from the study. The authors report more heterogeneity in the progression of HF in the female guinea pig model, however it will be very important to determine effects of dantrolene in the female heart, as there are considerable known sex differences in intracellular Ca2+ handling and contractility. Therefore, it is possible that dantrolene could have sex-dependent effects.

Reviewer #1 (Public Review):

The current study tests the hypothesis that inhibition of ryanodine receptor 2 (RyR2) in failing arrhythmogenic hearts reduces sarcoplasmic Ca leak, ventricular arrhythmias and improves contractile function. A guinea pig model of nonischemic heart failure (HF) was used and randomized to receive dantrolene (DS) or placebo in early or chronic HF. The authors show that DS treatment prevented ventricular arrhythmias and sudden cardiac death by decreasing dispersion of repolarization. The authors conclude that inhibition of RyR2 hyperactivity with DS mitigates the vicious cycle of sarcoplasmic Ca leak-induced increases in diastolic Ca and reactive oxygen species-mediated RyR2 oxidation. Moreover, the consequent increase in sarcoplasmic Ca2+ load improves contractile function.

In general, the study is well designed and the findings are likely to be of interest to the field.

Reviewer #1 (Public Review):

Summary:<br /> Leanza et al. investigated the regulation of Wnt signaling factors in the bone tissue obtained from individuals with or without type 2 diabetes. They showed that typical canonical Wnt ligands and downstream factors (Wnt10b, LEF1) are down-regulated, while Wnt5a and sclerostin mRNA are unregulated in diabetic bone tissue. Further, Wnt5a and sclerostin associated with the content of AGEs and SOST mRNA levels also correlated with glycemic control and disease duration.

Strengths:<br /> - A strength of the study is the investigation of Wnt signaling in bone tissue from humans with type 2 diabetes. Most studies measure only serum levels of Wnt inhibitors, but this study takes it further and looks into bone specifically.<br /> - The measurement of AGEs and its correlation to the Wnt signaling molecules is interesting and important. The correlation of sclerostin and Wnt5a with AGEs and disease duration suggests that inhibited Wnt signaling is paralleled by higher AGE levels and potentially weaker bone.<br /> - The methodology in terms of obtaining the bone samples and the rigorous evaluation of RNA integrity is great and provides a solid basis for further analyses.

Weaknesses:<br /> - A weakness may include the rather limited number of samples. Especially for some sub-analyses (e.g. RNA analyses), only a subset of samples was used.<br /> - How was the sample size determined? It seems like more samples might have been necessary to obtain significant results for methods with a higher standard deviation (e.g. histomorphometry).<br /> - Why is the number of samples different for the mRNA measurements? In most cases, there were 9, but in some 8 and in some 10?

Overall, this study validates findings from the group that reported similar findings in 2020. This validates their methodology and shows that alterations in Wnt signaling are reproducible in human bone tissue.

Reviewer #2 (Public Review):

Summary:<br /> This study reports the levels of expression of selected genes implicated in Wnt signaling in trabecular bone from femur heads obtained after surgery from post-menopausal women with (15 women) or without (21 women) type 2 diabetes. They found higher expression levels of SOST and WNT5A, and lower expression levels of LEF-1 and WNT10B in tissues from subjects with T2D, correlating with glycemia and advanced glycation products. No significant differences in bone density were observed. Overall, this is a cross-sectional, observational study measuring a limited set of genes found to vary with glycemia in postmenopausal women undergoing hip surgery.

Strengths:<br /> The study demonstrates the feasibility of measuring gene expression in post-surgical trabecular bone samples, and finds differences associated with glycemia despite a relatively small number of subjects. It can form the basis for further research on the causes and consequences of changes in elements of the WNT signaling pathway in bone biology and disease.

Weaknesses:<br /> The small number of targeted genes does not provide a comprehensive view of the transcriptional landscape within which the effects are observed. The gene expression changes are not associated with cellular or physiological properties of the tissue, raising questions about the biological significance of the observations.

Reviewer #3 (Public Review):

Summary:<br /> The manuscript by Leanza and colleagues explores the regulation of Wnt signaling and its association with advanced glycation end products (AGEs) accumulation in postmenopausal women with type 2 diabetes (T2D). The paper provides valuable insights into the potential mechanisms underlying bone fragility in individuals with T2D. Overall, the manuscript is well-structured, and the methodology is sound. I would suggest some minor revisions to improve clarity.

Strengths:<br /> The study addresses an important and clinically relevant question concerning the mechanisms underlying bone fragility in postmenopausal women with T2D.

The study's methodology appears sound, and the inclusion of postmenopausal women with and without T2D undergoing hip arthroplasty adds to the clinical relevance of the findings. Additionally, measuring gene expression and AGEs in bone samples provides direct insights into the study's objectives.

The manuscript presents data clearly, and the results are well-organized.

Weaknesses:<br /> Title. The title could be more specific to better reflect the content of the study. Also, the abstract should concisely summarize the study's main findings, providing some figures.

Introduction: the introduction would benefit from the addition of a clearer, more focused statement of the research questions or hypotheses guiding this study.

Methods: more information is needed on the hystomorphometry analysis. Surgical samples from 8 T2D and 9 non-diabetic subjects were used for histomorphometry analysis. How did these subjects compare with the other subjects in the T2D and control groups? Were they representative? How were they selected?

Reviewer #1 (Public Review):

In the study described in the manuscript, the authors identified Mecp2, a methyl-CpG binding protein, as a key regulator involved in the transcriptional shift during the exit of quiescent cells into the cell cycle. Their data show that Mecp2 levels were remarkably reduced during the priming/initiation stage of partial hepatectomy-induced liver regeneration and that altered Mecp2 expression affected the quiescence exit. Additionally, the authors identified Nedd4 E3 ligase that is required for the downregulation of Mecp2 during quiescence exit. This is an interesting study with well-presented data that supports the authors' conclusions regarding the role of Mecp2 in transcription regulation during the G0/G1 transition. However, the significance of the study is limited by a lack of mechanistic insights into the function of Mecp2 in the process. This weakness can be addressed by identifying the signaling pathway(s) that trigger Mecp2 degradation during the quiescence exit.

Reviewer #2 (Public Review):

In the manuscript by Yang et al titled "Mecp2 fine-tunes quiescent exit by targeting nuclear receptors", the authors found that Mecp, a well-known protein because of its crucial role in neurological disorders, has a cell cycle-dependent ability to negatively regulate quiescent exit by transcriptional activation of metabolic genes while repressing proliferation-related genes. Conceptually, this is an interesting study with very well-executed experiments and controls.

Since the mutation of MeCP2 was identified as the cause of Rett syndrome, the previous reports have been focused on the exhaustive biochemical and functional characterization of this protein. In this study, the authors show that MeCP2 expression is cell-cycle related, and acute reduction of Mecp2 is essential for efficient quiescence exit in cells. They also identified a novel E3 ligase Nedd4 contributes to Mecp2 degradation during G0 exit. These findings are the first description of MeCP2 protein expression during the cell cycle. The variation in MeCP2 levels at different stages of the cell cycle phases should be taken into consideration when examining MeCP2-related disordered disease.

Reviewer #1 (Public Review):

The manuscript focused on roles of a key fatty-acid synthesis enzyme, acetyl-coA-carboxylase 1 (ACC1), in the metabolism, gene regulation and homeostasis of invariant natural killer T (NKT_ cells and impact on these T cells' roles during asthma pathogenesis. The authors presented data showing that the acetyl-coA-carboxylase 1 enzyme regulates the expression of PPARg then the function of NKT cells including the secretion of Th2-type cytokines to impact on asthma pathogenesis. The results are clearcut and data were logically presented.

Reviewer #2 (Public Review):

In this study the authors sought to investigate how the metabolic state of iNKT cells impacts their potential pathological role in allergic asthma. The authors used two mouse models, OVA and HDM-induced asthma, and assessed genes in glycolysis, TCA, B-oxidation and FAS. They found that acetyl-coA-carboxylase 1 (ACC1) was highly expressed by lung iNKT cells and that ACC1 deficient mice failed to develop OVA-induced and HDM-induced asthma. Importantly, when they performed bone marrow chimera studies, when mice that lacked iNKT cells were given ACC1 deficient iNKT cells, the mice did not develop asthma, in contrast to mice given wildtype NKT cells. In addition, these observed effects were specific to NKT cells, not classic CD4 T cells. Mechanistically, iNKT cell that lack AAC1 had decreased expression of fatty acid-binding proteins (FABPs) and peroxisome proliferator-activated receptor (PPAR)γ, but increased glycolytic capacity and increased cell death. Moreover, the authors were able to reverse the phenotype with the addition of a PPARg agonist. When the authors examined iNKT cells in patient samples, they observed higher levels of ACC1 and PPARG levels, compared to healthy donors and non-allergic-asthma patients.

Reviewer #1 (Public Review):

Summary:<br /> The authors developed a deep learning method called H3-OPT, which combines the strength of AF2 and PLM to reach better prediction accuracy of antibody CDR-H3 loops than AF2 and IgFold. These improvements will have an impact on antibody structure prediction and design.

Strengths:<br /> The training data are carefully selected and clustered, the network design is simple and effective.

The improvements include smaller average Ca RMSD, backbone RMSD, side chain RMSD, more accurate surface residues and/or SASA, and more accurate H3 loop-antigen contacts.

The performance is validated from multiple angles.

Weaknesses:<br /> There are very limited prediction-then-validation cases, basically just one case.

Reviewer #2 (Public Review):

This work provides a new tool (H3-Opt) for the prediction of antibody and nanobody structures, based on the combination of AlphaFold2 and a pre-trained protein language model, with a focus on predicting the challenging CDR-H3 loops with enhanced accuracy than previously developed approaches. This task is of high value for the development of new therapeutic antibodies. The paper provides an external validation consisting of 131 sequences, with further analysis of the results by segregating the test sets into three subsets of varying difficulty and comparison with other available methods. Furthermore, the approach was validated by comparing three experimentally solved 3D structures of anti-VEGF nanobodies with the H3-Opt predictions

Strengths:<br /> The experimental design to train and validate the new approach has been clearly described, including the dataset compilation and its representative sampling into training, validation and test sets, and structure preparation. The results of the in silico validation are quite convincing and support the authors' conclusions.

The datasets used to train and validate the tool and the code are made available by the authors, which ensures transparency and reproducibility, and allows future benchmarking exercises with incoming new tools.

Compared to AlphaFold2, the authors' optimization seems to produce better results for the most challenging subsets of the test set.

Weaknesses:<br /> The scope of the binding affinity prediction using molecular dynamics is not that clearly justified in the paper.

Some parts of the manuscript should be clarified, particularly the ones that relate to the experimental validation of the predictions made by the reported method. It is not absolutely clear whether the experimental validation is truly a prospective validation. Since the methodological aspects of the experimental determination are not provided here, it seems that this may not be the case. This is a key aspect of the manuscript that should be described more clearly.

Some Figures would benefit from a more clear presentation.

Reviewer #3 (Public Review):

Summary:<br /> The manuscript introduces a new computational framework for choosing 'the best method' according to the case for getting the best possible structural prediction for the CDR-H3 loop. The authors show their strategy improves on average the accuracy of the predictions on datasets of increasing difficulty in comparison to several state-of-the-art methods. They also show the benefits of improving the structural predictions of the CDR-H3 in the evaluation of different properties that may be relevant for drug discovery and therapeutic design.

Strengths:<br /> The authors introduce a novel framework, which can be easily adapted and improved. The authors use a well-defined dataset to test their new method. A modest average accuracy gain is obtained in comparison to other state-of-the art methods for the same task while avoiding testing different prediction approaches.

Weaknesses:<br /> The accuracy gain is mainly ascribed to easy cases, while the accuracy and precision for moderate to challenging cases are comparable to other PLM methods (see Fig. 4b and Extended Data Fig. 2). That raises the question: how likely is it to be in a moderate or challenging scenario? For example, it is not clear whether the comparison to the solved X-ray structures of anti-VEGF nanobodies represents an easy or challenging case for H3-OPT. The mutant nanobodies seem not to provide any further validation as the single mutations are very far away from the CDR-H3 loop and they do not disrupt the structure in any way. Indeed, RMSD values follow the same trend in H3-OPT and IgFold predictions (Fig. 4c). A more challenging test and interesting application could be solving the structure of a designed or mutated CDR-H3 loop.

The proposed method lacks a confidence score or a warning to help guide the users in moderate to challenging cases.

The fact that AF2 outperforms H3-OPT in some particular cases (e.g. Fig. 2c and Extended Data Fig. 3) raises the question: is there still room for improvements? It is not clear how sensible is H3-OPT to the defined parameters. In the same line, bench-marking against other available prediction algorithms, such as OmegaFold, could shed light on the actual accuracy limit.

Reviewer #1 (Public Review):

Mice and humans have two Cylicin genes (X-linked Cylicin 1 and the autosomal Cylicin 2) that encode cytoskeletal proteins. Cylicins are localized in the acrosomal region of round spermatids, yet they resemble a calyx component within the perinuclear theca of mature sperm nuclei. The function of Cylicins during this developmental stage of spermiogenesis (tail formation and head elongation/shaping) was not known. In this study, using CRISPR/Cas genome editing, the authors generated Cylc1-and Cylc2-knockout mouse lines to study the loss-of-function of each Cylicin or all together.

The major strengths of the study are the rigorous and comparative phenotypic analyses of all the combinatorial genotypes from the cross between the two mouse lines (Cylc1-/y, Cylc2-/-, Cylc1-/y Cylc2+/- and Cylc1-/y Cylc2-/-) at the levels of male fertility, cellular, and subcellular levels to support the conclusion of the study. While spermatogenesis appeared undisturbed, with germ cells of all types detected in the testis, low sperm counts in epididymis were observed. Mice were subfertile or infertile in a dose-dependent manner where fewer functional alleles had more severe phenotypes; the loss of Cylc2 was less tolerated than the loss of Cylc1. Thus, loss of Cylc1, and to an even greater extent, loss of Cylc2, leads to sperm structure anomalies and decreased sperm motility. Particularly, the sperm head and sperm head-neck region are affected, with calyx not forming in the absence of Cylicins, the acrosomal region being attached more loosely, and the sperm head itself appearing structurally rounder and shorter. Furthermore, manchette, which disassembles during spermiogenesis, persists in mature sperm of mice missing Cylc2. It is interesting that the study identifies a human male that has mutations in both CYLC1 and CYLC2 genes and suffers from infertility, with similar motility and sperm structure defects compared to the mouse models. CYLC1 in the sperm from the infertile patient sperm is absent, providing evidence that in both rodents and primates, Cylicins are essential for male fertility. Evolutionary analysis of two genes adds an interesting point. The authors show that the reason for the loss of Cylc2 being more severe is due to the higher conservation of Cylc2 compared to Cylc1 in rodents and primates.

Overall, the work highlights the relevance and importance of Cylicins in male infertility and advances our understanding of perinuclear theca formation during spermiogenesis.

Reviewer #2 (Public Review):

The work presented in this manuscript focuses on the role of Cylicins in spermiogenesis and the consequences of their absence on infertility. The manuscript is presented in two parts: the first part studies the absence of Cylicins from KO mouse models and shows in mice that both isoforms of Cylicins are necessary for normal spermiogenesis. The evaluation of double heterozygotes is particularly useful for the second part which looks at the presence of mutations in these genes in a cohort of infertile men. A patient with two hemizygous/heterozygous mutations in the CYLC1 and 2 genes, respectively, was identified for the first time and the results obtained with the KO models support the hypothesis of the pathogenicity of the mutations.

In general, the experiments are perfectly performed and the results are clear. Numerous techniques in the state of the art in male reproduction are used to obtain high-quality phenotyping of the mouse models.

The discovery of two concomitant mutations in an infertile patient is very interesting and the work carried out on mice allows supporting that an absence of CYLC1 and a heterozygous mutation of CYLC2 could lead to a phenotype of complete infertility. However, as the mutation on CYLC2 is not identified as pathogenic, the pathogenicity of this mutation remains in question (the authors note this point in the discussion). It would be interesting to see if the mutated amino acid is conserved between different species. In mice, the authors have shown the importance of these proteins on the morphology of the acrosome. What about in humans?

Reviewer #3 (Public Review):

The authors tried to study the role of the cylicin gene in sperm formation and male fertility. They used the Crispr/cas 9 to knockout two mouse cylicin genes, cylicin 1 and cylicin 2. They used comprehensive methods to phenotype the mouse models and discovered that the two genes, particularly cylicin 2 are essential for sperm calyx formation. They further compared the evolution of the two genes. Finally, they identified mutations of the genes in a patient. The major strengths are the high quality of data presented, and the conclusion is supported by their findings from the animal models and patients. The major weakness is that the study is rather descriptive without molecular mechanism studies, limiting its impact on the field.

Joint Public Review:

In this manuscript, Karl et al. explore mechanisms underlying the activation of the receptor tyrosine kinase FGFR1 and stimulation of intracellular signaling pathways in response to FGF4, FGF8, or FGF9 binding to the extracellular domain of FGFR1. The manuscript demonstrates that FGF4, FGF8, and FGF9 exhibit distinct binding modes towards FGFRs. It is also proposed that FGF8 exhibits "biased ligand" characteristics that is manifested via binding and activation FGFR1 mediated by unproven and speculative "structural differences in the FGF-FGFR1 dimers, which impact the interactions of the FGFR1 trans membrane helices, leading to differential recruitment and activation of the downstream signaling adapter FRS2".

Reviewer #1 (Public Review):

Summary:<br /> The authors use insights into the dynamics of the PKA kinase domain, obtained by NMR experiments, to inform MD simulations that generate an energy landscape of PKA kinase domain conformational dynamics.

Strengths:<br /> The authors integrate strong experimental data through the use of state-of-the-art MD studies and derive detailed insights into allosteric communication in PKA kinase. Comparison of wt kinase with a mutant (F100A) shows clear differences in the allosteric regulation of the two proteins. These differences can be rationalized by NMR and MD results.

Weaknesses:<br /> The very detailed insights gained by the authors into allosteric regulation require very specialized techniques in this study. This poses a challenge to communicate the methods, the results, and the meaning of the results to a broader audience. In some places, the authors overcome this challenge better than in others.

Reviewer #2 (Public Review):

Summary:<br /> In this study, Olivieri & Wang et.al. probe the role of the conserved alphaC-beta4 loop in the allosteric regulation of the PKA catalytic subunit. The authors employ a combination of NMR-restrained molecular dynamics simulations and mutational analysis to uncover the conformational transitions between distinct excited states and identify a pivotal role for the alphaC-beta4 loop in facilitating these conformational transitions. These studies support previous models proposing the alphaC-beta4 loop as a critical element in kinase conformational regulation. Overall, this is a timely and fitting study.

Strengths:<br /> 1. Exciting application of NMR and MD to explore hidden conformation states of kinases.<br /> 2. Novel mechanistic insights into the role of the alphaC-beta4 loop in PKA.

Weaknesses:<br /> 1. While the alphaC-beta4 loop is a conserved feature of protein kinases, the residues within this loop vary across various kinase families and groups, enabling group and family-specific control of activity through cis and trans acting elements. F102 in PKA interacts with co-conserved residues in the C-tail, which has been proposed to function as a cis regulatory element. The authors should elaborate on the conformational changes in the C-tail, particularly in the arginine that packs against F102, in the results and discussion. This would further extend the impact and scope of the manuscript, which is currently confined to PKA.<br /> 2. The MD data and conformational states would be a valuable resource for the community and should be shared via some open-source repositories.<br /> 3. The authors state that ES1 and ES2 states are novel and not observed in previous crystal structures. The authors should quantify this through comparisons with PKA inactive states and with other AGC kinases.<br /> 4. Based on the results, can the authors speculate on the impact of oncogenic mutations in the alphaC-beta4 loop mutations in PKA?

Reviewer #3 (Public Review):

Summary:<br /> Combining several MD simulation techniques (NMR-constrained replica-exchange metadynamics, Markov State Model, and unbiased MD) the authors identified the aC-beta4 loop of PKA kinase as a switch crucially involved in PKA nucleotide/substrate binding cooperatively. They identified a previously unreported excited conformational state of PKA (ES2), this switch controls and characterized ES2 energetics with respect to the ground state. Based on translating the simulations into chemical shits and NMR characterizing of PKA WT and an aC-beta4 mutant, the author made a convincing case in arguing that the simulation-suggested excited state is indeed an excited state observed by NMR, thus giving the excited state conformational details.

Strengths:<br /> This work incorporates extensive simulation works, new NMR data, and in vitro biochemical analysis. It stands out in its comprehensiveness, and I think it made a great case.

Weaknesses:<br /> The manuscript is somewhat difficult to read even for kinase experts, and even harder for the layman. The difficulty partially arises from mixing technical description of the simulations with structural interpretation of the results, which is more intuitive, and partially arises from the assumption that readers are familiar with kinase architecture and its key elements (the aC helix, the APE motif etc).

Reviewer #2 (Public Review):

The authors sought to define the molecular structure of autoinhibited Kinesin-1, which is the major kinesin providing plus-end directed transport on microtubules. The paper reports a structural model of full-length kinesin-1 which builds on the known folded conformation of kinesin-1 and describes its autoinhibitory mechanism using cryo-EM, alphafold structural predictions, cross-linking, and mass spectrometry. The authors study the conformation of dimeric Kinesin Heavy Chain (KHC) and tetrameric KHC bound to the Kinesin Light Chains (KLCs), where KLC stabilizes the autoinhibited conformation. The combination of these various approaches leads to an integrated molecular model of autoinhibited Kinesin-1. Until now, there was some debate over the role of the small coiled-coil 3 (a and b) and where the hinge region of Kinesin-1. The authors resolve this question and present data indicating the hinge is between cc3a and cc3b.

In some places the absence of crosslinks is reported as a lack of interaction, however, it could also be that there are no residues that can be crosslinked in this region. Some crosslinks also are too long to satisfy the model, so it is possible, while most crosslinks occur when Kinesin-1 is inhibited, that a small number of crosslinks arise from when Kinesin-1 adopts another conformation. The structural data are supported by single-molecule motility assays with various mutants of Kinesin-1, which greatly help characterising the domains functionally.

Overall there are some interesting novel data on the autoinhibitory mechanism of Kinesin-1, with well performed and analyzed data with KLC and TRAP. The topic and paper will be of interest to many.

Reviewer #1 (Public Review):

Using a combination of structural biology methods, this report aims to describe the auto-inhibited architecture of kinesin 1 either as homodimers or hetero-tetramers. Hence, the multiple contacts between the protein domains and their folding pattern are addressed using cross-linking mass spectrometry (XL-MS), negative stain electron microscopy and Alpha Fold-based structure prediction. Based on the existing literature, the key domains and amino acids responsible for kinesin-1 inhibited state were not clearly deciphered. The synergetic use of different methods now seems to describe in detail the molecular cues that could induce kinesin-1 refolding and opening. Multiple interactions between the different domains seem to induce the folded conformation.

The combination of methodologies is an efficient way to unravel details that could not be addressed previously. The paper is well written. The methods for generating the electron microscopy data and its relevance and quality, for instance, are much better described after revision. In addition, the conclusions are now more convincing because similar investigations are carried out for all isoforms (KIF5B and FIF5C) in parallel.

This article raises the potential strength and power of deep learning structure prediction methods combined simultaneously with other structural biology methods to answer specific questions. In the present context, this study will certainly be helpful in revealing and understanding the activation mechanism of kinesin motor proteins.

Reviewer #2 (Public Review):

Summary:<br /> In eukaryotes, sterols are crucial for signaling and regulating membrane fluidity, however, the mechanism governing cholesterol production and transport across the cell membrane in bacteria remains enigmatic. The manuscript by Zhai et al. sheds light on this topic by uncovering three potential cholesterol transport proteins. Through comprehensive bioinformatics analysis, the authors identified three genes bstA, bstB, and bstC encoding proteins which share homology with transporters, periplasmic binding proteins, and periplasmic components superfamily, respectively. Furthermore, the authors confirmed the specific interaction between these three proteins and C-4 methylated sterols and determined the structures of BstB and BstC. Combining these structural insights with molecular dynamics simulation, they postulated several plausible substrate binding sites within each protein.

Strengths:<br /> The authors have identified 3 proteins that seem likely to be involved in sterol transport between the inner and outer membrane. The structures are of high quality, and the sterol binding experiments support a role for these proteins in sterol transport.

Weaknesses:<br /> While the author's model is very plausible, direct evidence for a role of BstABC in transport, or that the 3 proteins function together in a single pathway, is limited.

Reviewer #1 (Public Review):

Summary<br /> This article by Zhai et al, investigates sterol transport in bacteria. Synthesis of sterols is rare in bacteria but occurs in some, such as M capsulatus where the sterols are found primarily in the outer membrane. In a previous paper the authors discovered an operon consisting of five genes, with two of these genes encoding demethylases involved in sterol demethylation. In this manuscript, the authors set out to investigate the functions of the other three genes in the operon. Interestingly, through a bioinformatic analysis, they show that they are an inner membrane transporter of the RND family, a periplasmic binding protein, and an outer membrane-associated protein, all potentially involved with lipid transport, so providing a means of transporting the lipids to the outer membrane. These proteins are then extensively investigated through lipid pulldowns, binding analysis on all three, and X-ray crystallography and docking of the latter two.

Strengths<br /> The lipid pulldowns and associated MST binding analysis are convincing, clearly showing that sterols are able to bind to these proteins. The structures of BstB and BstC are high resolution with excellent maps that allow docking studies to be carried out. These structures are distinct from sterol-binding proteins in eukaryotes.

Weaknesses<br /> While the docking and molecular dynamics studies are consistent with the binding of sterols to BstB and BstC, this is not backed up particularly well. The MST results of mutants in the binding pocket of BstB have relatively little effect, and while I agree with the authors this may be because of the extensive hydrophobic interactions that the ligand makes with the protein, it is difficult to make any firm conclusions about binding.

The authors also discuss the possibility of a secondary binding site in BstB based on a slight cavity in domain B next to a flexible loop. This is not backed up in any way and seems unlikely.

Reviewer #3 (Public Review):

Summary:<br /> The work in this manuscript builds on prior efforts by this team to understand how sterols are biosynthesized and utilized in bacteria. The study reports a new function for three genes encoded near sterol biosynthesis enzymes, suggesting the resulting proteins function as a sterol transport system. Biochemical and structural characterization of the two soluble components of the pathway establishes that both proteins can bind sterols, with a preference for 4-methylated derivatives. High-resolution x-ray structures of the apoproteins reveal hydrophobic cavities of the appropriate size to accommodate these substrates. Docking and molecular dynamics simulations confirm this observation and provide specific insights into residues involved in substrate binding.

Strengths:<br /> The manuscript is comprehensive and well-written. The annotation of a new function in a set of proteins related to bacterial sterol usage is exciting and likely to enable further study of this phenomenon - which is currently not well understood. The work also has implications for improving our understanding of lipid usage in general among bacterial organisms.

Weaknesses:<br /> The authors might consider moving some of the bioinformatics figures to the main text, given how much space is devoted to this topic in the results section.

Reviewer #1 (Public Review):

Chen and colleagues investigated ZC3H11A as a potential cause of high myopia (HM) in humans through the analysis of exome sequencing in 1,015 adolescents and experiments involving Zc3h11a knock-out mice. The authors showed four possibly pathogenic missense variants in four adolescents with HM. After that, the authors presented the phenotypic features of Zc3h11a knock-out mice, the result of RNA-sequencing, and a comparison of mRNA and protein levels of the functional candidates between wild-type and Zc3h11a knock-out mice. Based on their observations, the authors concluded that ZC3H11A protein contributes to the early onset of myopia.

The strengths of this manuscript include: (1) successful identification of characteristic ophthalmic phenotypes in Zc3h11a knock-out mice, (2) demonstration of biological features related to myopia, such as PI3K-AKT and NF-kB pathways, and (3) inclusion of supporting human genetic data in individuals with HM. On the other hand, the weaknesses of this paper appear to be: (1) the lack of robust evidence from their genomic analysis, and (2) insufficient evidence to support phenotypic similarity between humans with ZC3H11A mutations and Zc3h11a knock-out mice. Given that the biological mechanisms of high myopia are not fully understood, the identification of a novel gene is valuable. As described in the manuscript, it is worth noting that the previous study using myopic mouse model has implicated the role of ZC3H11A in the etiology of myopia (Fan et al. Plos Genet 2012).

Specific comments:<br /> 1. I am concerned about the certainty of similarity in phenotypes between individuals with ZC3H11A mutation and Zc3h11a knock-out mice. A crucial point would be that there are no statistical differences in axial lengths (ALs) between wild-type and Zc3h11a knock-out mice at 8W and 10W, even though ALs in the individuals with ZC3H11A mutation were long. I would also like to note that the phenotypic information of these individuals is not available in the manuscript, although the authors indicated the suppressed b-wave amplitude in Zc3h11a knock-out mice. Considering that the authors described that "Detailed ophthalmic examinations were performed (lines: 321-323)", the detailed clinical features of these individuals should be included in the manuscript.

2. The term "pathogenic variant" should be used cautiously. Please clarify the pathogenicity of the reported variants in accordance with the ACMG guideline.

3. The genetic analysis does not fully support the claim that ZC3H11A is causative for HM. While the authors showed the rare allele frequencies and high CADD scores (> 20) of the identified variants, these were insufficient to establish causality. A helpful way to assess the causality would be performing a segregation analysis. An alternative approach is to show significant association by performing a gene-level association test. Assessing the pathogenicity of the variants using various prediction software, such as SIFT, PolyPhen2, and REVEL may also provide additional supportive evidence.

4. As shown in Figure 2, significant differences in refraction were observed from 4 weeks to 10 weeks. Nevertheless, no differences were observed in AL, anterior/vitreous chamber depth, and lens depth. The author should experimentally clarify what factors contribute to the observed difference in refraction.

5. The gene names should be italicized throughout the manuscript.

6. Table 1: providing chromosomal positions and rs numbers (if available) would be helpful for readers.

7. Figure 5b, c, and d: the results of pathway analysis and GO enrichment analysis are difficult to interpret due to the small font size. It would be preferable to present these results in tables. Moreover, the authors should set a significant threshold in the enrichment analyses.

Reviewer #2 (Public Review):

Summary:<br /> Chong Chen and colleagues reported that mutations were identified in the ZC3H11A gene in four adolescents from 1015 high myopia subjects in their myopia cohort. They further generated Zc3h11a knockout mice utilizing the CRISPR/Cas9 technology. They analyzed the heterozygotes knockout mice compared to control littermates and found refractive error changes, electrophysiological differences, and retinal inflammation-related gene expression differences. They concluded that ZC3H11A may play a role in the early onset of myopia by regulating inflammatory responses.

Strengths:<br /> Data were shown from both clinical cohort and animal models.

Weaknesses:<br /> Their findings are interesting and important, however; they need to resolve several points to make the current conclusion.

1. They described the ZC3H11A gene as a pathogenic variant for high myopia. It should be classified as pathogenic according to the guidelines of the American College of Medical Genetics and Genomics (Richards et al., Genet Med 17(5):405-24, 2015). The modes of inheritance for the families need to be shown. They also described identifying the gene as a "new" candidate. It should be checked in databases such as gnomAD and ClinVar, and any previous publications and be declared as a novel variant.

2. The phenotypes of the heterozygote mice are weak overall. The het mice showed mild to moderate myopic refractive shifts from 4 to 10 weeks of age. However, this cannot be explained by other ocular biometrics such as anterior chamber depth or lens thickness. Some differences are found between het and WT littermates in axial length and vitreous chamber depth but disappear after 8 weeks old. Furthermore, the early differences are not enough to explain the refractive error changes. They mentioned that they did not use homozygotes because of the embryonic lethality. I would strongly suggest employing conditional knockout systems to analyze homozygotes. This will also be able to identify the causative tissues/cells because they assume bipolar cells are functional. The cells in the retinal pigment epithelium and choroid are also important to contribute to myopia development.

3. Their hypothesis regarding inflammatory gene changes and myopic development is not logical. Are the inflammatory responses evoked from bipolar cells? Did the mice show an accumulation of inflammatory cells in the inner retina? Visible retinal inflammation is not generally seen in either early-onset or high-myopia human subjects. Can this be seen in the actual subjects in the cohort? To me, this is difficult to adapt the retina-to-sclera signaling they mentioned in the discussion so far. Egr-1 may be examined as described.

Reviewer #3 (Public Review):

Chen et al have identified a new candidate gene for high myopia, ZC3H11A, and using a knock-out mouse model, have attempted to validate it as a myopia gene and explain a potential mechanism. They identified 4 heterozygous missense variants in highly myopic teenagers. These variants are in conserved regions of the protein, but the authors provide no evidence that these specific variants affect protein function. They then created a knock-out mouse. Heterozygotes show myopia at all ages examined but increased axial length only at very early ages. Unfortunately, the authors do not address this point or examine corneal structure in these animals. They show that the mice have decreased B-wave amplitude on electroretinogram (a sign of retinal dysfunction associated with bipolar cells), and decreased expression of a bipolar cell marker, PKC. They do not address, however, whether there are fewer bipolar cells, or simply decreased expression of the marker protein. On electron microscopy, there are morphologic differences in the outer nuclear layer (where bipolar, amacrine, and horizontal cell bodies reside). Transcriptome analysis identified over 700 differentially expressed genes. The authors chose to focus on the PI3K-AKT and NF-B signaling pathways and show changes in the expression of genes and proteins in those pathways, including PI3K, AKT, IB, NF-B, TGF-1, MMP-2, and IL-6, although there is very high variability between animals. They propose that myopia may develop in these animals either as a result of visual abnormality (decreased bipolar cell function in the retina) or by alteration of NF-B signaling. These data provide an interesting new candidate variant for the development of high myopia, and provide additional data that MMP2 and IL6 have a role in myopia development, but do not support the claim of the title that myopia is caused by an inflammatory reaction.

Reviewer #3 (Public Review):

Summary:<br /> In this study, the authors set out to address the question of how the SNARE protein Syntaxin 17 senses autophagosome maturation by being recruited to autophagosomal membranes only once autophagosome formation and sealing is complete. The authors discover that the C-terminal region of Syntaxin 17 is essential for its sensing mechanism that involves two transmembrane domains and a positively charged region. The authors discover that the lipid PI4P is highly enriched in mature autophagosomes and that electrostatic interaction with Syntaxin 17's positively charged region with PI4P drives recruitment specifically to mature autophagosomes. The temporal basis for PI4P enrichment and Syntaxin 17 recruitment to ensure that unsealed autophagosomes do not fuse with lysosomes is a very interesting and important discovery. Overall, the data are clear and convincing, with the study providing important mechanistic insights that will be of broad interest to the autophagy field, and also to cell biologists interested in phosphoinositide lipid biology. The author's discovery also provides an opportunity for future research in which Syntaxin 17's c-terminal region could be used to target factors of interest to mature autophagosomes.

Strengths:<br /> The study combines clear and convincing cell biology data with in vitro approaches to show how Syntaxin 17 is recruited to mature autophagosomes. The authors take a methodical approach to narrow down the critical regions within Syntaxin 17 required for recruitment and use a variety of biosensors to show that PI4P is enriched on mature autophagosomes.

Weaknesses:<br /> There are no major weaknesses, overall the work is highly convincing. It would have been beneficial if the authors could have shown whether altering PI4P levels would affect Syntaxin 17 recruitment. However, this is understandably a challenging experiment to undertake and the authors outlined their various attempts to tackle this question. In addition, clear statements within the figure legends on the number of independent experimental repeats that were conducted for experiments that were quantitated are not currently present in the manuscript.

Reviewer #1 (Public Review):

In this manuscript, the authors report a molecular mechanism for recruiting syntaixn 17 (Syn17) to the closed autophagosomes through the charge interaction between enriched PI4P and the C-terminal region of Syn17. How to precisely control the location and conformation of proteins is critical for maintaining autophagic flux. Particularly, the recruitment of Syn17 to autophagosomes remains unclear. In this paper, the author describes a simple lipid-protein interaction model beyond previous studies focusing on protein-protein interactions. This represents conceptual advances.

Reviewer #2 (Public Review):

Summary:<br /> Syntaxin17 (STX17) is a SNARE protein that is recruited to mature (i.e., closed) autophagosomes, but not to immature (i.e., unclosed) ones, and mediates the autophagosome-lysosome fusion. How STX17 recognizes the mature autophagosome is an unresolved interesting question in the autophagy field. Shinoda and colleagues set out to answer this question by focusing on the C-terminal domain of STX17 and found that PI4P is a strong candidate that causes the STX17 recruitment to the autophasome.

Strengths:<br /> The main findings are: 1) Rich positive charges in the C-terminal domain of STX17 are sufficient for the recruitment to the mature autophagosome; 2) Fluorescence charge sensors of different strengths suggest that autophagic membranes have negative charges and the charge increases as they mature; 3) Among a battery of fluorescence biosensors, only PI4P-binding biosensors distribute to the mature autophagosome; 4) STX17 bound to isolated autophagosomes is released by treatment with Sac1 phosphatase; 5) By dynamic molecular simulation, STX17 TM is shown to be inserted to a membrane containing PI4P but not to a membrane without it. These results indicate that PI4P is a strong candidate that STX17 binds to in the autophagosome.

Weaknesses:<br /> • It was not answered whether PI4P is crucial for the STX17 recruitment in cells because manipulation of the PI4P content in autophagic membranes was not successful for unknown reasons.<br /> • The molecular simulation study did not show whether PI4P is necessary for the STX17 TM insertion or whether other negatively charged lipids can play a similar role.<br /> • The question that the authors posed in the beginning, i.e., why is STX17 recruited to the mature (closed) autophagosome but not to immature autophagic membranes, was not answered. The authors speculate that the seemingly gradual increase of negative charges in autophagic membranes is caused by an increase in PI4P. However, this was not supported by the PI4P fluorescence biosensor experiment that showed their distribution to the mature autophagosome only. Here, there are at least two possibilities: 1) The increase of negative charges in immature autophagic membranes is derived from PI4P. However the fluorescence biosensors do not bind there for some reason; for example, they are not sensitive enough to recognize PI4P until it reaches a certain level, or simply, their binding does not occur in a quantitative manner. 2) The negative charge in immature membranes is not derived from PI4P, and PI4P is generated abundantly only after autophagosomes are closed. In either case, it is not easy to explain why STX17 is recruited to the mature autophagosome only. For the first scenario, it is not clear how the PI4P synthesis is regulated so that it reaches a sufficient level only after the membrane closure. In the second case, the mechanism that produces PI4P only after the autophagosome closure needs to be elucidated (so, in this case, the question of the temporal regulation issue remains the same).

Reviewer #2 (Public Review):

Summary:

Recent advances in single-cell profiling of gene expression (RNA) permit the analysis of specialized cell types, an approach that has great value in the nervous system which is characterized by prodigious neuronal diversity. The novel data in this study focus primarily on genetic profiling to compare autonomic neurons from ganglia associated with the cranial parasympathetic outflow (sphenopalatine (also known as pteropalatine), the thoraco-lumbar sympathetic outflow (stellate, coeliac) and the sacral parasympathetic outflow (pelvic). Using statistical methods to reduce the dimensionality of the data and map gene expression, the authors provide interesting evidence that cranial parasympathetic and sacral sympathetic ganglia differ from each other and from sympathetic ganglia (Figures 1, S1 - S4). The authors interpret the mapping analysis as evidence that the cranial and sacral outflows differ so calling them both parasympathetic is unjustified. Based on anatomical localization of markers (Figure 2 ) (mainly transcription factors) the authors show a similarity between the sympathetic and pelvic ganglion. In Figure 3 they present evidence that some pelvic ganglionic neurons are dually innervated by sympathetic preganglionic neurons and sacral preganglionic neurons. These observations are interpreted to mean that the pelvic ganglion is not parasympathetic, but rather a modified sympathetic ganglion - hence the title of the manuscript.

Strengths:<br /> The extensive use of single-cell profiling in this work is both interesting and exciting. Although still in its early stages, it holds promise for a deepened understanding of autonomic development and function. As noted in the introduction, this study extends previous work by Professor Brunet and his associates.

Weaknesses:<br /> This work further documents differences between the cranial and sacral parasympathetic outflows that have been known since the time of Langley - 100 years ago. The approach taken by Brunet et al. has focused on late neonatal and early postnatal development, a time when autonomic function is still maturing. In addition, the sphenopalatine and other cranial ganglia develop from placodes and the neural crest, while sympathetic and sacral ganglia develop from the neural crest alone. How then do genetic programs specifying brainstem and spinal development differ and how can this account for kinship that Brunet documents between spinal and sacral ganglia? One feature that seems to set the pelvic ganglion apart is the mixture of 'sympathetic' and 'parasympthetic' ganglion cells and the convergence of preganglionic sympathetic and parasympathetic synapses on individual ganglion cells (Figure 3). This unusual organization has been reported before using microelectrode recordings (see Crowcroft and Szurszewski, J Physiol (1971) and Janig and McLachlan, Physiol Rev (1987)). Anatomical evidence of convergence in the pelvic ganglion has been reported by Keast, Neuroscience (1995). It should also be noted that the anatomy of the pelvic ganglion in male rodents is unique. Unlike other species where the ganglion forms a distributed plexus of mini-ganglia, in male rodents the ganglion coalesces into one structure that is easier to find and study. Interestingly the image in Figure 3A appears to show a clustering of Chat-positive and Th-positive neurons. Does this result from the developmental fusion of mini ganglia having distinct sympathetic and parasympathetic origins? In addition, Brunet et al dismiss the cholinergic and noradrenergic phenotypes as a basis for defining parasympathetic and parasympathetic neurons. However, see the bottom of Figure S4 and further counterarguments in Horn (Clin Auton Res (2018)). What then about neuropeptides, whose expression pattern is incompatible with the revised nomenclature proposed by Brunet et al.? Figure 1B indicates that VIP is expressed by sacral and cranial ganglion cells, but not thoracolumbar ganglion cells. The authors do not mention neuropeptide Y (NPY). The immunocytochemistry literature indicates that NPY is expressed by a large subpopulation of sympathetic neurons but never by sacral or cranial parasympathetic neurons.

Reviewer #1 (Public Review):

In recent years, these investigators have been engaged in a debate regarding the classification of the sacral parasympathetic system as "sympathetic" rather than "parasympathetic," based on shared developmental ontogeny of spinal preganglionic neurons. In this current study, these investigators conducted single-cell RNAseq analyses of four groups of autonomic neurons: paravertebral sympathetic neurons (stellate and lumbar train ganglia), prevertebral sympathetic neurons (coeliac-mesenteric ganglia), rostral parasympathetic ganglia (sphenopalatine ganglia), and the caudal pelvic ganglia (containing traditionally recognized sacral "parasympathetic cholinergic neurons," which the investigators sought to challenge in terms of nomenclature). The authors argued that the pelvic ganglionic neurons shared the expression of more genes with sympathetic ganglia, as opposed to parasympathetic ganglia. Additionally, the pelvic neurons did not express a set of genes observed in the rostral parasympathetic sphenopalatine ganglia. Based on these findings, they claimed that the sacral autonomic system should be considered sympathetic rather than parasympathetic. However, these arguments face significant challenges.

Firstly, among the P1-4 clusters of pelvic neurons, the P3 cluster predominantly represents noradrenergic sympathetic neurons, known to be present in pelvic ganglia. These neurons share gene expression patterns typically found in sympathetic neurons and lack the key cholinergic features identified in the P1, P2, and P4 clusters. Consistently, the P3 cluster of neurons is located close to sympathetic neuron clusters on the map, echoing the conventional understanding that the pelvic ganglia are mixed, containing both sympathetic and parasympathetic neurons.

Secondly, as mentioned above, the P1, P2, and P4 clusters are cholinergic neurons, expressing ChAT (and VIP). The authors claimed that these neurons shared a large set of genes expressed in sympathetic neurons (class I genes shown in Figure 1B). A closer look at the expression showed that some genes are expressed at higher levels in sympathetic neurons and in P2 cluster neurons, but much weaker in P1, P2, and P4 neurons, such as Islet1 and GATA2, and the opposite is true for SST. Another set of genes is expressed weakly across clusters, like HoxC6, HoxD4, GM30648, SHISA9, and TBX20. Since the pelvic ganglia are in a caudal body part, it is not surprising to have genes expressed in pelvic ganglia, but not in rostral sphenopalatine ganglia, and vice versa (to have genes expressed in sphenopalatine ganglia, but not in pelvic ganglia), according to well recognized rostro-caudal body patterning, such as nested expression of hox genes.

Thirdly, noradrenergic sympathetic neurons and cholinergic neurons, by virtue of expressing different neurotransmitters, could have distinct roles. It is true that some cholinergic neurons reside in the sympathetic train ganglia as well, such as those innervating the sweat gland and some vascular systems; in this sense, the pelvic ganglia share some features with sympathetic ganglia, except that the pelvic ganglia contain a much higher percentage of cholinergic neurons compared with sympathetic ganglia. It is much simpler and easier to divide the autonomic nervous system into sympathetic neurons that release noradrenaline versus parasympathetic neurons that release acetylcholine, and these two systems often act in antagonistic manners, though in some cases, these two systems can work synergistically. It also does not matter whether or not pelvic cholinergic neurons could receive inputs from thoracic-lumbar preganglionic neurons (PGNs), not just sacral PGNs; such occurrence only represents a minor revision of the anatomy. In fact, it makes much more sense to call those cholinergic neurons located in the sympathetic chain ganglia parasympathetic. Thus, from the functionality point of view, it is not justified to claim that "pelvic organs receive no parasympathetic innervation".

Reviewer #2 (Public Review):

In this study, the authors aimed to evaluate the contribution of brain-age indices in capturing variance in cognitive decline and proposed an alternative index, brain-cognition, for consideration.

The study employs suitable methods and data to address the research questions, and the methods and results sections are generally clear and easy to follow.

Comments on revised submission:

I appreciate the authors' efforts in significantly improving the paper, including some considerable changes, from the original submission. While not all reviewer points were tackled, the majority of them were adequately addressed. These include additional analyses, more clarity in the methods and a much richer and nuanced discussion. While recognising the merits of the revised paper, I have a few additional comments.

Perhaps it would help the reader to note that it might be expected for brain-cognition to account for a significantly larger variance (11%) in fluid cognition, in contrast to brain-age. This stems from the fact that the authors specifically trained brain-cognition to predict fluid cognition, the very variable under consideration. In line with this, the authors later recommend that researchers considering the use of brain-age should evaluate its utility using a regression approach. The latter involves including a brain index (e.g. brain-cognition) previously trained to predict the regression's target variable (e.g. fluid cognition) alongside a brain-age index (e.g., corrected brain-age gap). If the target-trained brain index outperforms the brain-age metric, it suggests that relying solely on brain-age might not be the optimal choice. Although not necessarily the case, is it surprising for the target-trained brain index to demonstrate better performance than brain-age? This harks back to the broader point raised in the initial review: while brain-age may prove useful (though sometimes with modest effect sizes) across diverse outcomes as a generally applicable metric, a brain index tailored for predicting a specific outcome, such as brain-cognition in this case, might capture a considerably larger share of variance in that specific context but could lack broader applicability. The latter aspect needs to be empirically assessed.

Furthermore, the discussion pertaining to training brain-age models on healthy populations for subsequent testing on individuals with neurological or psychological disorders seems somewhat one-sided within the broader debate. This one-sidedness might potentially confuse readers. It is worth noting that the choice to employ healthy participants in the training model is likely deliberate, serving as a norm against which atypical populations are compared. To provide a more comprehensive understanding, referencing Tim Hans's counterargument to Bashyam's perspective could offer a more complete view (https://academic.oup.com/brain/article/144/3/e31/6214475?login=false).

Overall, this paper makes a significant contribution to the field of brain-age and related brain indices and their utility.

Reviewer #1 (Public Review):

In this paper, the authors evaluate the utility of brain-age-derived metrics for predicting cognitive decline by performing a 'commonality' analysis in a downstream regression that enables the different contribution of different predictors to be assessed. The main conclusion is that brain-age-derived metrics do not explain much additional variation in cognition over and above what is already explained by age. The authors propose to use a regression model trained to predict cognition ("brain-cognition") as an alternative suited to applications of cognitive decline. While this is less accurate overall than brain age, it explains more unique variance in the downstream regression.

Comments on revised version:

I thank the authors for addressing many of my concerns with this revision. However, I do not feel they have addressed them all. In particular I think the authors could do more to address the concern I raised about the instability of the regression coefficients and about providing enough detail to determine that the stacked regression models do not overfit.

In considering my responses to the authors revision, I also must say that I agree with Reviewer 3 about the limitations of the brain age and brain cognition methods conceptually. In particular that the regression model used to predict fluid cognition will by construction explain more variance in cognition than a brain age model that is trained to predict age. To be fair, these conceptual problems are more widespread than this paper alone, so I do not believe the authors should be penalised for that. However, I would recommend to make these concerns more explicit in the manuscript.

Reviewer #3 (Public Review):

The main question of this article is as follows: "To what extent does having information on brain-age improve our ability to capture declines in fluid cognition beyond knowing a person's chronological age?" This question is worthwhile, considering that there is considerable confusion in the field about the nature of brain-age.

Comments on revised version:

Thank you to the authors for addressing so many of my concerns with this revision. There are a few points that I feel still need addressing/clarifying related to 1) calculating brain cognition, 2) the inevitability of their results, and 3) their continued recommendation to use brain-age metrics.

Reviewer #2 (Public Review):

Summary:<br /> The manuscript by Howard et al reports the development of high-affinity WDR5-interaction site inhibitors (WINi) that engage the protein to block the arginine-dependent engagement with its partners. Treatment of MLL-rearranged leukemia cells with high-affinity WINi (C16) decreases the expression of genes encoding most ribosomal proteins and other proteins required for translation. Notably, although these targets are enriched for WDR5-ChIP-seq peaks, such peaks are not universally present in the target genes. High concordance was found between the alterations in gene expression due to C16 treatment and the changes resulting from treatment with an earlier, lower affinity WINi (C6). Besides protein synthesis, genes involved in DNA replication or MYC responses are downregulated, while p53 targets and apoptosis genes are upregulated. Ribosome profiling reveals a global decrease in translational efficiency due to WINi with overall ribosome occupancies of mRNAs ~50% of control samples. The magnitude of the decrements of translation for most individual mRNAs exceeds the respective changes in mRNA levels genome-wide. From these results and other considerations, the authors hypothesize that WINi results in ribosome depletion. Quantitative mass spec documents the decrement in ribosomal proteins following WINi treatment along with increases in p53 targets and proteins involved in apoptosis occurring over 3 days. Notably, RPL22L1 is essentially completely lost upon WINi treatment. The investigators next conduct a CRISPR screen to find moderators and cooperators with WINi. They identify components of p53 and DNA repair pathways as mediators of WINi-inflicted cell death (so gRNAs against these genes permit cell survival). Next, WINi are tested in combination with a variety of other agents to explore synergistic killing to improve their expected therapeutic efficacy. The authors document the loss of the p53 antagonist MDM4 (in combination with splicing alterations of RPL22L1), an observation that supports the notion that WINi killing is p53-mediated.

Strengths:<br /> This is a scientifically very strong and well-written manuscript that applies a variety of state-of-the art molecular approaches to interrogate the role of the WDR5 interaction site and WINi. They reveal that the effects of WINi seem to be focused on the overall synthesis of protein components of the translation apparatus, especially ribosomal proteins-even those that do not bind WDR5 by ChIP (a question left unanswered is how much the WDR5-less genes are nevertheless WINi targeted). They convincingly show that disruption of the synthesis of these proteins is accompanied by DNA damage inferred by H2AX-activation, activation of the p53-pathway, and apoptosis. Pathways of possible WINi resistance and synergies with other anti-neoplastic approaches are explored. These experiments are all well-executed and strongly invite more extensive pre-clinical and translational studies of WINi in animal studies. The studies also may anticipate the use of WINi as probes of nucleolar function and ribosome synthesis though this was not really explored in the current manuscript.

Weaknesses:<br /> A mild deficiency in the current manuscript is the absence of cell biological methods to complement the molecular biological and biochemical approaches so ably employed. Some microscopic observations and confirmation of nucleolar dysfunction and DNA damage would be reassuring.

Reviewer #1 (Public Review):

Building on previous work from the Tansey lab, here Howard et al. characterize transcriptional and translational changes upon WIN site inhibition of WDR5 in MLL-rearranged cancer cells. They first analyze whether C16, a newer generation compound, has the same cellular effects as C6, an early generation compound. Both compounds reduce the expression of WDR5-bound RPGs in addition to the unbound RPG RPL22L1. They then investigate differential translation by ribo-seq and observe that WIN site inhibition reduces the translational RPGs and other proteins related to biomass accumulation (spliceosome, proteasome, mitochondrial ribosome). Interestingly, this reduction adds to the transcriptional changes and is not limited to RPGs whose promoters are bound by WDR5. Quantitative proteomics at two-time points confirmed the downregulation of RPGs. Interestingly, the overall effects are modest, but RPL22LA is strongly affected. Unexpectedly, most differentially abundant proteins seem to be upregulated 24 h after C6 (see below). A genetic screen showed that loss of p53 rescues the effect of C6 and C16 and helped the authors to identify pathways that can be targeted by compounds together with WIN site inhibitors in a synergistic way. Finally, the authors elucidated the underlying mechanisms and analyzed the functional relevance of the RPL22, RPL22L1, p53, and MDM4 axis.

While this work is not conceptually new, it is an important extension of the observations of Aho et al. The results are clearly described and, in my view, very meaningful overall.

Major points:<br /> 1. The authors make statements about the globality/selectivity of the responses in RNA-seq, ribo-seq, and quantitative proteomics. However, as far as I can see, none of these analyses have spike-in controls. I recommend either repeating the experiments with a spike-in control or carefully measuring transcription and translation rates upon WIN site inhibition and normalizing the omics experiments with this factor.

2. Why are the majority of proteins upregulated in the proteomics experiment after 24 h in C6 (if really true after normalization with general protein amount per cell)? This is surprising and needs further explanation.

3. The description of the two CRISPR screens (GECKO and targeted) is a bit confusing. Do I understand correctly that in the GECKO screen, the treated cells are not compared with non-treated cells of the same time point, but with a time point 0? If so, this screen is not very meaningful and perhaps should be omitted. Also, it is unclear to me what the advantages of the targeted screen are since the targets were not covered with more sgRNAs (data contradictory: 4 or 10 sgRNAs per target?) than in Gecko. Also, genome-wide screens are feasible in culture for multiple conditions. Overall, I find the presentation of the screening results not favorable.

4. Can Re-expression of RPL22 rescue the growth arrest of C6?.

Joint Public Review:

The authors explored previously developed pan-resolution x-ray tomographic imaging pipelines for quantitative analysis of thousands of blood cells within 4 and 5 dpf zebrafish. By performing automatic segmentation of individual cells within the zebrafish embryo, the authors tried to demonstrate the applicability of x-ray tomography to quantitative analysis of cell phenotypes at the tissue level. The combination of random forest classification and automatic segmentation based on cell pose is promising, especially considering the open access and the general applicability of these tools. However, the key features claimed by the authors, that is, visualisation of all blood cells in the embryo and quantitative analysis of blood cell phenotypes, were not sufficiently supported by the presented data. Additionally, I see limitations in applicability to other cell types, as mentioned by authors as well, and similar analysis on other organisms due to differences in cell size, packing, and tissue background.

When supported by additional data, the manuscript has the potential to be a useful pipeline for cell phenotype analysis and an impactful method for the zebrafish community and beyond.

Major points:<br /> 1. The authors report that pan-resolution x-ray tomography enables visualisation of blood cells in the whole zebrafish embryo. These observations are based on a comparative analysis of EM data and histology with x-ray tomography. Not EM, nor histology shows the distribution of all blood cells (or comparable volume) as in x-ray tomography. At this point, it would be important to supplement the work with the 3D distribution of blood cells visualized by complementary methods, for example, light-sheet microscopy. Such data can be compared to the cells visualized by x-ray tomography like in Figure 6 in terms of cell numbers and distribution throughout the organs. Without such comparative analysis, it is unclear whether X-ray tomography visualizes all blood cells in the organism.

2. Some critical information is missing for the optimisation of automatic segmentation. For example, how was the manual segmentation performed? For example, how cells of 3 pixels in diameter were segmented (Figure 8)? On how many cells? Taking that the F1 score is often biologically not meaningful, see Lena Maier-Hein, Bjoern Menze, et al. it would be important to make careful evaluation of segmentation results. For example, in Figure 2 it would be important to add the histogram of volume distribution in these datasets not just one mean value. The same type of histogram would be important to add to Figure 5 and compare these results to Figure 2.

3. For the comparison of blood cell shape between different samples, there is a lack of statistics and validation. How many embryos per condition were used? Considering that blood cells should be possible to obtain from zebrafish embryos. It would be important to see something like FACs data on blood cells from the same type of specimens. Would the size distribution obtained by FACs be comparable to X-ray tomography data? Without validation by other methods and statistically meaningful analysis, the results from x-ray tomography are simply not substantiated.

Minor points:<br /> 1. Please put some details on the parameters and usage of Cellpose.

2. The claim in the Discussion on 'was able to show differences between data sets sufficient to classify new, unknown blood cells into these groups' is not supported by the data.

3. The key resource table should include all reagents, including sample preparation. This resource table should also include data sets as a resource, which are currently in the 'Data availability statement'.

4. Provide tables with the results on manual segmentation, automatic segmentation, and analysis of cellular phenotypes used for LDA.

Reviewer #2 (Public Review):

Understanding disease conditions often yields valuable insights into the physiological regulation of biological functions, as well as potential therapeutic approaches. In previous investigations, the author's research group identified abnormal expression of brain-derived neurotrophic factor (BDNF) in the hypothalamus of a mouse model exhibiting Smith-Magenis syndrome (SMS), which is caused by heterozygous mutations of the Rai1 gene. Human SMS is associated with distinct facial characteristics, sleep disturbances, behavioral issues, and intellectual disabilities, often accompanied by obesity. Conditional knockout (cKO) of the Bdnf gene from the paraventricular hypothalamus (PVH) in mice led to hyperphagic obesity, while overexpression of the Bdnf gene in the PVH of Rai1 heterozygous mice restored the SMS-like obese phenotype. Based on these preceding findings, the authors of the present study discovered that homozygous Rai1 cKO restricted to Bdnf-expressing cells, or Rai1 gene knockdown solely in Bdnf-positive neurons in the PVH, induced obesity along with intricate alterations in adipose tissue composition, energy expenditure, locomotion, feeding patterns, and glucose tolerance, some of which varied between sexes. Additionally, the authors demonstrated that a brain-penetrating drug capable of activating the AKT cascades, a downstream signaling pathway of BDNF, partially alleviated the SMS-like obesity phenotype in female mice with Rai1 heterozygous mutations. Although the specific (neural) cell type responsible for this signaling remains an open question, the present study unequivocally highlights the importance of Rai1 gene function in PVH Bdnf neurons for the obesity phenotype, providing valuable insights into potential therapeutic strategies for managing obesity associated with SMS.

In the proteomic analysis (Fig. 1), the authors elucidated that multiple phospho-protein signaling pathways, including Akt and mTOR pathways, exhibited significant attenuation in the SMS model mice. Of significance, the manifestation of haploinsufficiency of the Rai1 gene exclusively within the BDNF+ cells demonstrated negligible impact on body weight (Fig. 2-supple 3D), despite observing a reduction in BDNF levels in the heterozygous Rai1 mutant (Fig. 1A). Conversely, the homozygous Rai1 cKO in the BDNF+ cells prominently displayed an obesity phenotype, suggesting substantial dissimilarities in the gene expression profiles between Rai1 heterozygous and homozygous conditions within the BDNF+ cell population. It would be advantageous to precisely identify the responsible differentially expressed genes, possibly including Bdnf itself, in the homozygous cKO model. The observed reduction in the excitability of PVH BDNF+ cells (Fig. 3) is presumably attributed to aberrant gene expression other than Bdnf itself, which may serve as a prospective target for gene expression analysis. Notably, the Rai1 homozygous cKO mice in BDNF+ cells exhibited some sexual dimorphisms in feeding and energy expenditures, as evidenced by Fig. 2 and related figures. Exploring the potential relevance of these sexual differences to human SMS cases and investigating the underlying cellular/molecular mechanisms in the future would provide valuable insights.

The CRISPR-mediated knockdown of the Rai1 gene appears to be highly effective, and the majority of Rai1 cKO effects in Bdnf+ cells are primarily attributed to PVH-Bdnf+ cells based on the similarity of phenotypes observed. With regards to the apparent rescue of the body weight phenotype in Rai1 heterozygous mutants using an AKT pathway activator, the specific biological processes, and neurons responsible for this effect remain unclear. Elucidating these aspects in future studies would be significant when considering potential applications to human SMS cases.

Overall, the present study represents a valuable addition to the authors' series of high-quality molecular genetic investigations into the in vivo functions of the Rai1 gene. This reviewer particularly commends their diligent efforts to enhance our comprehension of SMS and contribute to the future development of more effective therapies for this syndrome.

Reviewer #3 (Public Review):

Summary:<br /> Smith-Magenis syndrome (SMS) is associated with obesity and is caused by deletion or mutations in one cope of the Rai1 gene which encodes a transcriptional regulator. Previous studies have shown that Bdnf gene expression is reduced in the hypothalamus of Rai1 heterozygous mice. This manuscript by Javed et al. further links SMS-associated obesity with reduced Bdnf gene expression in the PVH by providing three lines of evidence. First, the authors conducted proteomic analysis of hypothalamic extracts from WT and SMS (Rai1 +/-) mice and showed that several signaling cascades downstream of BDNF (e.g., PI3K-AKT and mTOR) were down regulated in SMS mice. Second, the authors found that deletion of both copies of the Rai1 gene in all BDNF-expressing cells or BDNF-expressing neurons in the PVH led to obesity, although the phenotype is more subtle than that observed in SMS mice. Third, they found that Rai1 deletion reduced excitability of PVH BDNF neurons.

Strengths:<br /> The study provides additional evidence linking BDNF deficiency to hyperphagia and obesity associated with SMS. Furthermore, the study shows that deletion of only one copy of the Rai1 gene in all BDNF-expressing cells did not cause obesity. This result indicates that BDNF deficiency only has a minor contribution to the metabolic symptoms associated with SMS patients who lose one copy of the RAI1 gene. The discovery that Rai1 is important for excitability of PVH BDNF neurons is interesting.

Weaknesses:<br /> The main mechanism underlying SMS-associated obesity remains to be identified. This limitation is discussed in this revised manuscript. The authors also address my previous concerns in this revised manuscript.

Reviewer #1 (Public Review):

Summary:<br /> The organization of cell surface receptors in membrane nanodomains is important for signaling, but how this is regulated is poorly understood. In this study, the authors employ TIRFM single-molecule tracking combined with multiple analyses to show that ligand exposure increases the diffusion of the immune receptor FLS2 in the plasma membrane and its co-localization with remorin REM1.3 in a manner dependent on the phosphosite S938. They additionally show that ligand increases the dwell time of FLS2, and this is linked to FLS2 endocytosis, also in a manner dependent on S938 phosphorylation. The study uncovers a regulatory mechanism of FLS2 localization in the nanodomain crucial for signaling.

Strengths:<br /> TIRFM single-molecule tracking, FRAP, FRET, and endocytosis experiments were nicely done. The role of S938 phosphorylation is convincing.

Weaknesses:<br /> 1. The model suggests that S938 is phosphorylated upon flg22 treatment. This is actually not known. In addition, the S938D mutant does not show constitutively increased diffusion and co-localization with remorin. It is necessary to soften the tone in the conclusion.

2. The introduction (only two paragraphs) and discussion are not properly written in the context of the current understanding of plant receptors in nanodomains. The authors basically just cited a few publications of their own, and this is not acceptable.

Reviewer #2 (Public Review):

Summary:<br /> The research conducted by Yaning Cui and colleagues delves into understanding FLS2-mediated immunity. This is achieved by comparing the spatiotemporal dynamics of an FLS2-S938A mutant and FLS2-WT, especially in relation to their association with the remorin protein. To delineate the differences between the FLS2-S938A mutant and FLS2-WT, they utilized a plethora of advanced fluorescent imaging techniques. By analyzing surface dynamics and interactions involving the receptor signal co-receptor BAK1 and remorin proteins, the authors propose a model of how FLS2 and BAK1 are assembled and positioned within a remorin-specific nano-environment during FLS2 ligand-induced immune responses.

Strengths:<br /> These techniques offer direct visualizations of molecular dynamics and interactions, helping us understand their spatial relationships and interactions during innate immune responses.

Advanced cell biology imaging techniques are crucial for obtaining high-resolution insights into the intracellular dynamics of biomolecules. The demonstrated imaging systems are excellent examples to be used in studying plant immunity by integrating other functional assays.

Weaknesses:<br /> It's essential to acknowledge that every fluorescence-based method, just like biochemical assays, comes with its unique limitations. These often pertain to spatial and temporal resolutions, as well as the sensitivity of the cameras employed in each setup. Meticulous interpretation is pivotal to guarantee an accurate depiction and to steer clear of potential misunderstandings when employing specific imaging systems to analyze molecular attributes. Moreover, a discerning interpretation and accurate image analysis can offer invaluable guidance for future studies on plant signaling molecules using these nice cell imaging techniques.

For instance, although single-particle analysis couldn't conclusively link FLS2 and remorin, FLIM-FRET effectively highlighted their ligand-triggered association and the disengagement brought on by mutations. While these methodologies seemed to present differing outcomes, they were described in the manuscript as harmonious. In reality, these differences could highlight distinct protein populations active in immune responses, each accentuated differently by the respective imaging techniques due to their individual spatial and temporal limitations. Addressing these variations is imperative, especially when designing future imaging explorations of immune complexes.

Reviewer #3 (Public Review):

Summary:<br /> Receptor kinases (RKs) perceive extracellular signals to regulate many processes in plants. FLS2 is an RK that acts as a pattern-recognition receptor (PRR) to recognize bacterial flagellin and activate pattern-triggered immunity (PTI). PRRs such as FLS2 have been previously shown to reside within PM nanodomains, which can regulate downstream PTI signaling. In the current manuscript, Cui et al use single particle tracking to characterize the effect of previously-described phosposite mutants (FLS2-S938A/D) on the PM organization, endocytosis, and signaling functions of FLS2. The authors confirm that FLS2-S938D but not -S938A is functional for flg22-induced responses, while also demonstrating that phopshodead mutation at this site (S938A) prevents flg22-induced sorting into nanodomains and endocytosis. These results are consistent with S938 being an important phosphorylation site for FLS2 function, however, they fall short of demonstrating that membrane disorganization of FLS2-938A is responsible for downstream signaling defects.

Strengths:<br /> The authors' experiments (single particle tracking, co-localization, etc) do a good job of demonstrating how a non-functional version of FLS2 (S938A) does not alter its spatio-temporal dynamics, nanodomain organization, and endocytosis in response to flg22, suggesting that these require a functional receptor and are regulated by intracellular signaling components.

Weaknesses:<br /> The authors do not provide direct evidence that S938 phosphorylation specifically affects membrane organization, rather than FLS2 signaling more generally. All evidence is consistent with S938A being a non-functional version of FLS2, wherein an activated/functional receptor is required for all downstream events including membrane re-organization, downstream signalling, internalization, etc. Furthermore, the authors never demonstrate that this site is phosphorylated in planta in the basal or flg22-elicited state.

As written, the manuscript also has numerous scientific issues, including a misleading/incomplete description of plant immune signaling, lack of context from previous work, and extensive use of inappropriate references.

Reviewer #1 (Public Review):

Summary: Seizure stimuli has long been recognized to exhibit potent effects on adult neurogenesis, from depletion of the NSC pool to promoting aberrant migration of adult-born neurons. However, the identity and source of extrinsic signals is still incompletely understood. The work by Noguchi et al., demonstrates that Shh from mossy cells is a major source of Shh signaling after KA-mediated acute seizures. This work is interesting because mossy cells undergo hyperactivation during seizures, so this study provides a mechanistic link between mossy cell neuronal activity control of neurogenesis through Shh signaling. Weaknesses are that only male mice were analyzed in the seizure induction experiments and several control groups are missing for seizure induction, tamoxifen induction, and the DREADD experiment.

Strengths:

1. The study uses rigorous and specific genetic approaches (e.g., GliLacZ/+ mice; ShhEGFP-Cre/+ mice; mossy cell selective conditional Shh knockout using Crlr-Cre mice) to demonstrate Shh signaling is activated by seizures in mossy cells and contributes to aberrant neurogenesis.

2. Use of DREADDs (Crlr-Cre; hM3Dq) to show mossy cells control adult neurogenesis through Shh in an activity-dependent manner.

3. Demonstration that Shh deletion in mossy cells leads to reduction of the NSC pool uses stringent methods and analysis, including BrdU pulse-chase and co-labeling with NSC markers.

Weaknesses:

1. The analysis of Shh deletion in mossy cells and influences of aging related NSC pool decline is not well connected with the rest of the study on the expression/requirement of Shh in mossy cells to regulate seizure-induced neurogenesis. To promote cohesion, the authors should examine/discuss what happens to mossy cells during aging - it is similar or different to what happens to mossy cell neuronal activity during seizures?

2. Only male mice were analyzed in the seizure induction experiments, leaving open the possibility of sex differences since previous reports suggest sex differences in adult neurogenesis.

3. Several control groups are missing:<br /> -For seizure induction: missing vehicle (instead of no KA treatment).<br /> -For TAM induction: missing corn oil only to check leakiness and specificity of transgene.<br /> -For DREADD experiment: missing vehicle (to control for hM3 non-specific effects)

Reviewer #2 (Public Review):

Summary:<br /> The mechanisms by which seizures induce neurogenesis has remained unclear. Prior work from the authors demonstrated Mossy cell expressed Shh, that altered Shh expression follows epileptic seizures, and that Shh is a neural mitogen. Here authors show that Shh from mossy cells, which are well positioned between the pyramidal and granule cell layers, are a major source of signaling after seizures, contributing to seizure-induced neurogenesis. Moreover, they find that Mossy cell-sourced Shh is required for self-renewal of NSCs even outside of the context of seizures.

SVZ Gli1 expression was detected in NSCs and Gli1 reporter activity follows kainate-induced seizures. Heterozygous Shh mice show reduced seizure induced Shh signaling and reduced neurogenesis. After localizing Shh production to Mossy cells, authors removed Shh from Mossy cells and found reduced neurogenesis. By activating mossy cells through chemogenetic DREADD, they found that the effect of mossy cells on SVZ neurogenesis is activity-dependent, that Shh signaling activity is upregulated in NSCs by mossy cell neuronal activity, and that the induction of neurogenesis by mossy cell neuronal activity is compromised in the absence of Shh from mossy cells. In a series of experiments incorporating AAV DREADD, they find that mossy cell activity can contribute to neurogenesis in contralateral DG, and that seizure induced Shh may be transported along mossy axons. To examine long-term effects, they study mice several weeks after seizure, and find that suggesting that NSCs are less likely to return to their stem cell state after seizure-induced proliferation in the absence of Shh from mossy cells, and that Shh from mossy cells contributes to persistence of the NSC state during aging.

Strengths:<br /> The results are compelling and impactful, and the study is extremely well done. The various genetic lines in the study ensure robust results. Adequate consideration of statistics, methods of quantification, and avoidance of artifact is given.

Weaknesses:<br /> None identified.

Reviewer #1 (Public Review):

Referring to previous research findings, the authors explain the connection between NINJ1 and MVs. Additional experiments and clarifications will strengthen the conclusions of this study.

Below are some comments I feel could strengthen the manuscript:

1. The authors mentioned their choice of using heterozygous NINJ1+/- mice on page 4, because of lethality and hydrocephalus. Nonetheless, there is a substantial number of references that use homozygous NINJ1-/- mice. Could there be any other specific reasons for using heterozygous mice in this study?

2. Figure S2 clearly shows the method of pyroptosis induction by flagellin. It is also necessary as a prerequisite for this paper to show the changes in flagellin-induced pyroptosis in heterozygous NINJ1+/- mice.

3. IL-1ß levels controlled by GSDMD were not affected by NINJ1 expression according to previous studies (Ref 37, 29, Nature volume 618, pages 1065-1071 (2023)). GSDMD also plays an important role in TF release in pyroptosis. Are GSDMD levels not altered in heterozygous NINJ1 +/- mice?

4. In Fig 1 F, the authors used a fibrin-specific monoclonal antibody for staining fibrin, but it's not clearly defined. There may be some problem with the quality of antibody or technical issues. Considering this, exploring alternative methods to visualize fibrin might be beneficial. Fibrin is an acidophil material, so attempting H&E staining or Movat's pentachrome staining might help for identify fibrin areas.

Reviewer #2 (Public Review):

Summary:<br /> The author's main goal is to understand the mechanism by which pyroptosis (through the formation of Gasdermin D (GSDMD) pores in the plasma membrane) contributes to increased release of procoagulant Tissue Factor-containing microvesicles (MV). Their previous data demonstrate that GSDMD is critical for the release of MV that contains Tissue Factor (TF), thus making a link between pyroptosis and hypercoagulation. Given the recent identification of NINJ1 being responsible for plasma membrane rupture (Kayagaki et al. Nature 2011), the authors wanted to determine if NINJ1 is responsible for TF-containing MV release. Given the constitutive ninj1 KO mouse leads to partial embryonic lethality, the authors decided to use a heterozygous ninj1 KO mouse (ninj1+/-). While the data are well controlled, there is limited understanding of the mechanism of action. Also, given that the GSDMD pores have an ~18 nm inner diameter enough to release IL-1β, while larger molecules like LDH (140 kDa) and other DAMPs require plasma membrane rupture (likely mediated by NINJ1), it s not unexpected that large MVs require NINJ1-mediated plasma cell rupture.

Strengths:<br /> The authors convincingly demonstrate that ninj1 haploinsufficiency leads to decreased prothrombin time, plasma TAT and plasma cytokines 90 minutes post-treatment in mice, which leads to partial protection from lethality.

Weaknesses:<br /> - In the abstract, the authors say "...cytokines and protected against blood coagulation and lethality triggered by bacterial flagellin". This conclusion is not substantiated by the data, as you still see 70% mortality at 24 hours in the ninj1+/- mice.

- The previous publication by the authors (Wu et al. Immunity 2019) clearly shows that GSDMD-dependent pyroptosis is required for inflammasome-induced coagulation and mouse lethality. However, as it is not possible for the authors to use the homozygous ninj1 KO mouse due to partial embryonic lethality, it becomes challenging to compare these two studies and the contributions of GSDMD vs. NINJ1. Comparing the contributions of GSDMD and NINJ1 in human blood-derived monocytes/macrophages where you can delete both genes and assess their relevant contributions to TF-containing MV release within the same background would be crucial in comparing how much contribution NINJ1 has versus what has been published for GSDMD? This would help support the in vivo findings and further corroborate the proposed conclusions made in this manuscript.

- What are the levels of plasma TAT, PT, and inflammatory cytokines if you collect plasma after 90 minutes? Given the majority (~70%) of the ninj+/- mice are dead by 24 hours, it is imperative to determine whether the 90-minute timeframe data (in Fig 1A-G) is also representative of later time points. The question is whether ninj1+/- just delays the increases in prothrombin time, plasma TAT, and plasma cytokines.

Reviewer #1 (Public Review):

Summary:<br /> The study conducted on mice establishes a noteworthy connection between dietary protein intake and resistance exercise impact on metabolic health and muscle development. In sedentary mice, a diet rich in protein resulted in excessive fat accumulation and compromised blood sugar regulation in comparison to a diet low in protein. Intriguingly, when mice followed the high protein diet alongside progressive resistance training, they exhibited protection against surplus fat gain, though blood glucose regulation remained impaired. The research also revealed that resistance training notably enhanced muscle hypertrophy induced by exercise, particularly in mice on the high protein diet. Although the maximum strength achieved was similar across diets, this highlights the potential synergy between high protein consumption and resistance exercise in promoting skeletal muscle growth.

Strengths:<br /> The study possesses several significant strengths. Firstly, it combines controlled dietary manipulations with resistance exercise, providing a comprehensive understanding of their combined effects on metabolic health and muscle growth. The use of mouse models, while not directly translatable to humans, offers a controlled experimental environment, enabling precise measurements and observations. Moreover, the study reveals nuanced outcomes such as the differential impact of high protein intake on adiposity and muscle hypertrophy. The emphasis on both positive and negative findings lends balance to the conclusions, enhancing the overall credibility of the study. Additionally, the clear delineation of diet-exercise interactions contributes to the broader understanding of dietary and exercise recommendations for metabolic health and muscle development.

Weaknesses:<br /> Certain limitations warrant consideration. Firstly, the study's exclusive reliance on mice might limit the generalizability of the findings to humans due to inherent physiological differences. Additionally, the absence of direct investigation into the underlying molecular mechanisms responsible for the observed outcomes leaves room for speculation. Moreover, the research's concentration on male and young mice raises questions about the applicability of these findings to female and older subjects. Lastly, the study's duration and the specific resistance exercise protocol utilized might not fully reflect long-term human scenarios, underscoring the need for further research in more diverse populations and over extended timeframes.

Reviewer #2 (Public Review):

Summary: In this manuscript, Trautman et al. set out to test the hypothesis that increased intake of dietary protein is deleterious to health when uncoupled from resistance training.

Strengths: The experimental design is well crafted and the experiments provide useful information supporting the hypothesis. The authors take into account the limitations of their study in the discussion, and guide the reader through their results and the interpretation in a fair and measured way, without overstating claims.

Weaknesses: As acknowledged by the authors in the discussion section, this study only features a small sample of male mice from a single strain. Thus the results may not hold when female mice and diverse genetic backgrounds are analyzed. The lack of repeated measures of physiological parameters is also a limitation of the study. Measurements of body weight, body composition, food (calorie) consumption, and locomotor/strength assays could have been provided throughout the study and compared to a baseline value for each animal.

Reviewer #1 (Public Review):

Summary:<br /> In the manuscript titled "Disease modeling and pharmacological rescue of autosomal dominant Retinitis Pigmentosa associated with RHO copy number variation" the authors describe the use of patient iPSC-derived retinal organoids to evaluate the pathobiology of a RHO-CNV in a family with dominant retinitis pigmentosa (RP). They find significantly increased expression of rhodopsin, especially within the photoreceptor cell body, and defects in photoreceptor cell outer segment formation/maturation. In addition, they demonstrate how an inhibitor of NR2E3 (a rod transcription factor required for inducing rhodopsin expression), can be used to rescue the disease phenotype.

Strengths:<br /> The manuscript is very well written, the illustrations and data presented are compelling, and the authors' interpretation/discussion of their findings is logical.

Weaknesses:<br /> A weakness, which the authors have addressed in the discussion section, is the lack of an isogenic control, which would allow for direct analysis of the RHO-CNV in the absence of the other genetic sequence contained within the duplicated region. As the authors suggest, CRISPR correction of a large CNV in the absence of inducing unwanted on-target editing events in patient iPSCs is often very challenging. Given that they have used a no-disease iPSC line obtained from a family member, controlled for organoid differentiation kinetics/maturation state, and that no other complete disease-causing gene is contained within the duplicated region, it is unlikely that the addition of an isogenic control would yield significantly different results.

Aims and conclusions:<br /> This reviewer is of the opinion that the authors have achieved their aims and that their results support their conclusions.

Discussion:<br /> The authors have provided adequate discussion on the utility of the methods and data as well as the impact of their work on the field.

Reviewer #2 (Public Review):

Summary:<br /> The manuscript by Kandoi et al. describes a new 3D retinal organoid model of a mono-allelic copy number variant of the rhodopsin gene that was previously shown to induce autosomal dominant retinitis pigmentosa via a dominant negative mechanism in patients. With advancements in the low-cost genomics application to detect copy number variations, this is a timely article that highlights a potential disease mechanism that goes beyond the retina field. The evidence is relatively strong that the rod photoreceptor phenotype observed in an adult patient with RP in vivo is similar to that phenotype observed in human stem cell-derived retinal organoids. Increases in RHO expression detected by qPCR, RNA-seq, and IHC support this phenotype. Importantly, the amelioration of photoreceptor rhodopsin mislocalization and related defects using the small molecule drug photoregulin demonstrates an important potential clinical application.

Overall, the authors succeeded in providing solid evidence that copy number variation via a genomic RHO duplication leads to abnormalities in rod photoreceptors that can be partially blocked by photoregulin. However, there are several points that should be addressed that will enhance this paper.

Strengths:<br /> - The use of patient-derived organoids from patients that have visual defects is a major strength of this work and adds relevance to the disease phenotype.<br /> - The rod phenotype assessed by qPCR, RNA-seq, and IHC supports a phenotype that shares similarities with the patient.<br /> - The use of a small molecule drug that selectively targets rod photoreceptors, as opposed to cones, is a noteworthy strength.

Weaknesses:<br /> 1. The chromosomal segment that was duplicated had 3 copies of RHO in addition to three copies of each of the flanking genes (IFT122, HIF100, PLXND1). Discussion of the involvement of these genes would be helpful. Would duplication of any of these genes alone cause or contribute to adRP? As an example, a missense mutation in IFT122 was previously implicated in photoreceptor loss (PMID: 33606121 PMCID: PMC8519925).

2. Related to #1, have the authors considered inserting extra copies of RHO (and/or the flanking genes) of these at a genomic safe harbor site? Although not required, this would allow one to study cells with isogenic-matched genetic backgrounds and would partially address the technical challenge of repairing a 188kb duplication, which as the authors note would be difficult to do. Demonstrating that excess copy numbers in different genetic backgrounds would be a huge contribution to the field. At a minimum, a discussion of the role of the nearby genes should be included. 


3. In the patient, the central foveal region was spared suggesting that cones were normal. Was there a similar assessment that cones are unaffected in retinal organoids? 


4. Pathway analysis indicated that glycosylation was perturbed and this was proposed as an explanation as to why rhodopsin was mislocalized. Have the authors verified that there is an actual decrease in glycosylation? 


5. Line 182: by what criteria are the authors able to state that " there were no clear visible anatomical changes in apical-basal retinal cell type distribution during the early differentiation timeframe (data not shown)." Was this based on histological staining with antibodies, nuclear counter-staining, or some other evaluation?


6. Figure 2C - the appearance of the inner segments in RC and RM looks very different from one another. Have the authors ruled out the possibility that the RC organoid cell isn't a cone? In addition, the RM structure has what appears to be a well-defined OLM which would suggest well-formed Muller glia. Do these structures also exist in RC organoids? Typically the OLM does form in older organoids. In addition, was this representative in numerous EM preparations?


7. What criteria were used to assess cell loss? Has any TUNEL labeling been performed to confirm cell loss? From the existing data, it seems that rod outer segments appear to be affected in organoids. However, it's not clear if the photoreceptors themselves actually die in this model.

8. Figure 5B. The RHO staining in the vehicle-treated sample is perturbed relative to the PR3 treatments as indicated in the text. In the vehicle-treated sample, the number of DAPI-positive cells that are completely negative proximal to the inner segments suggests that there might be non-rod cells there. Have the authors confirmed whether these are cones? Labels would be helpful in the left vehicle panel as the morphology looks very different than the treated samples.
<br /> <br /> 9. It is interesting that in addition to increases in RHO, and photo-transduction, there are also increases in PTPRT which is related to synaptic adhesion. Is there evidence of ectopic neurites that result from PTPRT over-expression?

Reviewer #3 (Public Review):

This manuscript reports a novel pedigree with four intact copies of RHO on a single chromosome which appears to lead to overexpression of rhodopsin and a corresponding autosomal dominant form of RP. The authors generate retinal organoids from patient- and control-derived cells, characterize the phenotypes of the organoids, and then attempt to 'treat' aberrant rhodopsin expression/mislocalization in the patient organoids using a small molecule called photoregulin 3 (PR3). While this novel genetic mechanism for adRP is interesting, the organoid work is not compelling. There are multiple problems related to the technical approaches, the presentation of the results, and the interpretations of the data. I will present my concerns roughly in the order in which they appear in the manuscript.

Major concerns:<br /> (1) Individual human retinal organoids in culture can show a wide range of differentiation phenotypes with respect to the expression of specific markers, percentages of given cell types, etc. For this reason, it can be very difficult to make rigorous, quantitative comparisons between 'wild-type' and 'mutant' organoids. Despite this difficulty, the author of the present manuscript frequently presents results in an impressionistic manner without quantitation. Furthermore, there is no indication that the investigator who performed the phenotypic analyses was blind with respect to the genotype. In my opinion, such blinding is essential for the analysis of phenotypes in retinal organoids.

To give an example, in lines 193-194 the authors write "we observed that while the patient organoids developing connecting cilium and the inner segments similar to control organoids, they failed to extend outer segments". Outer segments almost never form normally in human retinal organoids, even when derived from 'wild-type' cells. Thus, I consider it wholly inadequate to simply state that outer segment formation 'failed' without a rigorous, quantitative, and blinded comparison of patient and control organoids.

(2) The presentation of qPCR results in Figure 3A is very confusing. First, the authors normalize expression to that of CRX, but they don't really explain why. In lines 210-211, they write "CRX, a ubiquitously expressing photoreceptor gene maintained from development to adulthood." Several parts of this sentence are misleading or incomplete. First, CRX is not 'ubiquitously expressed' (which usually means 'in all cell types') nor is it photoreceptor-specific: CRX is expressed in rods, cones, and bipolar cells. Furthermore, CRX expression levels are not constant in photoreceptors throughout development/adulthood. So, for these reasons alone, CRX is a poor choice for the normalization of photoreceptor gene expression.

Second, the authors' interpretation of the qPCR results (lines 216-218) is very confusing. The authors appear to be saying that there is a statistically significant increase in RHO levels between D120 and D300. However, the same change is observed in both control and patient organoids and is not unexpected, since the organoids are more mature at D300. The key comparison is between control and patient organoids at D300. At this time point, there appears to be no difference between control and patient. The authors don't even point this out in the main text.

Third, the variability in the number of photoreceptor cells in individual organoids makes a whole-organoid comparison by qPCR fraught with difficulty. It seems to me that what is needed here is a comparison of RHO transcript levels in isolated rod photoreceptors.

(3) I cannot understand what the authors are comparing in the bulk RNA-seq analysis presented in the paragraph starting with line 222 and in the paragraph starting with line 306. They write "we performed bulk-RNA sequencing on 300-days-old retinal organoids (n=3 independent biological replicates). Patient retinal organoids demonstrated upregulated transcriptomic levels of RHO... comparable to the qRT-PCR data." From the wording, it suggests that they are comparing bulk RNA-seq of patients and control organoids at D300. However, this is not stated anywhere in the main text, the figure legend, or the Methods. Yet, the subsequent line "comparable to the qRT-PCR data" makes no sense, because the qPCR comparison was between patient samples at two different time points, D120 and D300, not between patient and control. Thus, the reader is left with no clear idea of what is even being compared by RNA-seq analysis.

Remarkably, the exact same lack of clarity as to what is being compared is found in the second RNA-seq analysis presented in the paragraph starting with line 306. Here the authors write "We further carried out bulk RNA-sequencing analysis to comprehensively characterize three different groups of organoids, 0.25 μM PR3-treated and vehicle-treated patient organoids and control (RC) organoids from three independent differentiation experiments. Consistent with the qRT-PCR gene expression analysis, the results showed a significant downregulation in RHO and other rod phototransduction genes." Here, the authors make it clear that they have performed RNA-seq on three types of samples: PR3-treated patient organoids, vehicle-treated patient organoids, and control organoids (presumably not treated). Yet, in the next sentence, they state "the results showed a significant downregulation in RHO", but they don't state what two of the three conditions are being compared! Although I can assume that the comparison presented in Fig. 6A is between patient vehicle-treated and PR3-treated organoids, this is nowhere explicitly stated in the manuscript.

(4) There are multiple flaws in the analysis and interpretation of the PR3 treatment results. The authors wrote (lines 289-2945) "We treated long-term cultured 300-days-old, RHO-CNV patient retinal organoids with varying concentrations of PR3 (0.1, 0.25 and 0.5 μM) for one week and assessed the effects on RHO mRNA expression and protein localization. Immunofluorescence staining of PR3-treated organoids displayed a partial rescue of RHO localization with optimal trafficking observed in the 0.25 μM PR3-treated organoids (Figure 5B). None of the organoids showed any evidence of toxicity post-treatment."

There are multiple problems here. First, the results are impressionistic and not quantitative. Second, it's not clear that the investigator was blinded with respect to the treatment condition. Third, in the sections presented, the organoids look much more disorganized in the PR3-treated conditions than in the control. In particular, the ONL looks much more poorly formed. Overall, I'd say the organoids looked considerably worse in the 0.25 and 0.5 microM conditions than in the control, but I don't know whether or not the images are representative. Without rigorously quantitative and blinded analysis, it is impossible to draw solid conclusions here. Lastly, the authors state that "none of the organoids showed any evidence of toxicity post-treatment," but do not explain what criteria were used to determine that there was no toxicity.

(5) qPCR-based quantitation of rod gene expression changes in response to PR3 treatment is not well-designed. In lines 294-297 the authors wrote "PR3 drove a significant downregulation of RHO in a dose-dependent manner. Following qRT-PCR analysis, we observed a 2-to-5 log2FC decrease in RHO expression, along with smaller decreases in other rod-specific genes including NR2E3, GNAT1 and PDE6B." I assume these analyses were performed on cDNA derived from whole organoids. There are two problems with this analysis/interpretation. First, a decrease in rod gene expression can be caused by a decrease in the number of rods in the treated organoids (e.g., by cell death) or by a decrease in the expression of rod genes within individual rods. The authors do not distinguish between these two possibilities. Second, as stated above, the percentage of cells that are rods in a given organoid can vary from organoid to organoid. So, to determine whether there is downregulation of rod gene expression, one should ideally perform the qPCR analysis on purified rods.

(6) In Figure 4B 'RM' panels, the authors show RHO staining around the somata of 'rods' but the inset images suggest that several of these cells lack both NRL and OTX2 staining in their nuclei. All rods should be positive for NRL. Conversely, the same image shows a layer of cells scleral to the cells with putative RHO somal staining which do not show somal staining, and yet they do appear to be positive for NRL and OTX2. What is going on here? The authors need to provide interpretations for these findings.

Reviewer #1 (Public Review):

Summary:<br /> Spinal cord injury (SCI) causes immediate and prolonged bladder dysfunction, for which there are poor treatments. Following up on evidence that AMPA glutamatergic receptors play a key role in bladder function, the authors induced spinal cord injury and its attendant bladder dysfunction and examined the effects of graded doses of allosteric AMPA receptor activators (ampakines). They show that ampakines ameliorate several prominent derangements in bladder function resulting from SCI, improving voiding intervals and pressure thresholds for voiding and sphincter function.

Strengths:<br /> Well-performed studies on a relevant model system. The authors induced SCI reproducibly and showed that they had achieved their model. The drugs revealed clear and striking effects. Notably, in some mice that had such bad SCI that they could not void, the drug appeared to restore voiding function.

Weaknesses:<br /> The studies are well conducted, but it would be helpful to include information on the kinetics of the drugs used, their half-life and how long they are present in rats after administration. What blood levels of the drugs are achieved after infusion? How do these compare with blood levels achieved when these drugs are used in humans?

Reviewer #2 (Public Review):

Summary:<br /> In this study, Rana and colleagues present interesting findings demonstrating the potential beneficial effects of AMPA receptor modulators with ampakines in the context of the neurogenic bladder following acute spinal cord injury. Neurogenic bladder dysfunction is characterized by urinary retention and/or incontinence, with limited treatments available. Based on recent observations showing that ampakines improved respiratory function in rats with SCI, the authors explored the use of ampakine CX1739 on bladder and external urethral sphincter (EUS) function and coordination early after mid-thoracic contusion injury. Using continuous flow cystometry and EUS myography the authors showed that ampakine treatment led to decreased peak pressures, threshold pressure, intercontraction interval, and voided volume in SCI rats versus vehicle-treated controls. Although CX1739 did not alter EUS EMG burst duration, treatment did lead to EUS EMG bursting at lower bladder pressure compared to baseline. In a subset of rats that did not show regular cystometric voiding, CX1739 treatment diminished non-voiding contractions and improved coordinated EUS EMG bursting. Based on these findings the authors conclude that ampakines may have utility in recovery of bladder function following SCI.

Strengths:<br /> The experimental design is thoughtful and rigorous, providing an evaluation of both the bladder and external urethral sphincter function in the absence and presence of ampakine treatment. The data in support of a role for CX1789 treatment in the context of the neurogenic bladder are presented clearly, and the conclusions are adequately supported by the findings.

Weaknesses:<br /> Since CX1789 was administered in the context of cystometry and urethral sphincter EMG, a brief discussion of how ampakines could be used in a therapeutic context in humans would help to understand the translational significance of the work. The study lacks information on the half-life of CX1789 and how might this impact the implementation of CX1789 for clinical use. In addition, the study was limited to female rats. Lastly, given the male bias of traumatic SCI in humans, a brief discussion of this limitation is warranted.

Reviewer #3 (Public Review):

Summary:<br /> In this manuscript, Rana and colleagues examined the effect of a "low impact" ampakine, an AMPA receptor allosteric modulator, on the voiding function of rats subjected to midline T9 spinal cord contusion injury. Previous studies have shown that the micturition reflex fully depends on AMPA glutaminergic signaling, and, that the glutaminergic circuits are reorganized after spinal cord injury. In chronic paraplegic rats, other circuits (no glutaminergic) become engaged in the spinal reflex mechanism controlling micturition. The authors employed continuous flow cystometry and external urethral sphincter electromyography to assess bladder function and bladder-urethral sphincter coordination in naïve rats (control) and rats subjected to spinal cord injury (SCI). In the acute phase after SCI, rats exhibit larger voids with lower frequency than naïve rats. This study shows that CX1739 improves, in a dose-dependent manner, bladder function in rats with SCI. The interval between voids and the voided volume was reduced in rats with SCI when compared to controls. In summary, this is an interesting study that describes a potential treatment for patients with SCI.

Strengths:<br /> The findings described in this manuscript are significant because neurogenic bladder predisposes patients with SCI to urinary tract infections, hydronephrosis, and kidney failure. The manuscript is clearly written. The study is technically outstanding, and the conclusions are well justified by the data.

Weaknesses:<br /> The study was conducted 5 days after spinal cord contusion when the bladder is underactive. In rats with chronic SCI, the bladder is overactive. Therefore, the therapeutic approach described here is expected to be effective only in the underactive bladder phase of SCI. The mechanism and site of action of CX1739 is not defined.

Reviewer #1 (Public Review):

The process of EMT is a major contributor to metastasis and chemoresistance in breast cancer. By using a modified PyMT model that allows the identification of cells undergoing EMT and their decedents via S100A4-Cre mediated recombination of the mTmG allele, Ban et al. tackle a very important question of how tumor metastasis and therapy resistance by EMT can be blocked. They identified that pathways associated with ribosome biogenesis (RiBi) are activated during transition cell states. This finding represents a promising therapeutic target to block any transition from E to M (activated during cell dissemination and invasion) as well as from M to E (activated during metastatic colonization). Inhibition of RiBi-blocked EMT also reduced the establishment of chemoresistance that is associated with an EMT phenotype. Hence, RiBi blockage together with standard chemotherapy showed synergistic effects, resulting in impaired colonization/metastatic outgrowth in an animal model. The study is of great interest and of high clinical relevance as the authors show that blocking the transition from E to M or vice versa targets both aspects of metastasis, dissemination from the primary tumor, and colonization in distant organs.

The study is done with high skill using state-of-the-art technology and the conclusions are convincing and solid, but some aspects require some additional experimental support and clarification. It remains elusive whether blocking of EMT/MET is necessary for the synergistic effect of standard chemotherapy together with RiBi blockage or whether a general growth disadvantage of RiBi-treated cells independent of blocking transition is responsible. How can specific effects on state transition by RiBI block be separated from global effects attributed to overall reduced protein biosynthesis, proliferation etc.? Some other aspects are misleading or need extension.

Reviewer #2 (Public Review):

The current manuscript by Ban et al describes that cells undergoing EMT have increased rRNA synthesis, as analyzed by RNA seq-based gene expression analysis, and that the increased rRNA synthesis provides a therapeutic opportunity to target chemoresistance. The cells utilized in this manuscript were isolated from the authors' Tri-PyMT EMT lineage tracing model published a few years ago which demonstrated that cells undergoing EMT are not the cells that are contributing to metastasis but rather to tumor chemoresistance (Fischer, Nature 2015). This in vivo model has since then been criticized for not capturing all relevant EMT events which the authors also acknowledge in the introduction. The authors therefore reason that they use this lineage tracing model to better understand the role of EMT in chemoresistance.

A major problem with the current manuscript is that the authors present many of their findings as a novel without the proper acknowledgment of previously published literature in particular, Prakash et al., Nature Communications, 2019 and Dermitt, Dev Cell, 2020. In the studies by Prakash, the authors demonstrate that maintaining ongoing rRNA biogenesis is essential for the execution of the EMT program, and thus the ability of cancer cells to become migratory and invasive. Further, Prakash et al showed that blocking rRNA biogenesis with a small molecule inhibitor, CX-5461 (which is also used in the study by Ban et al) specifically inhibits breast cancer growth, invasion, EMT, and metastasis in animal models without significant toxicity to normal tissues. As such a significant revision that is necessary at this time is a rewrite of the manuscript especially the introduction and the discussion to more accurately describe and cite previously published findings and then highlight the current work by Ban et al which nicely builds on the previously published literature as it highlights the contribution of EMT to chemoresistance rather than metastasis. The suggestion for the authors is that they therefore should focus on highlighting the chemotherapy resistance angle as their Tri-PyMT EMT lineage tracing was chosen to test this angle and as such focus on both primary tumor growth and metastasis.

Additional major revisions:<br /> The authors use the FSP1-Cre Model which in the field has been questioned as to not capture all the relevant EMT events and therefore their findings should be corroborated by another EMT model system.

In the current version of the manuscript, there are no measurements of rRNA synthesis, but the gene expression profiles are used as a proxy for rRNA synthesis. The authors therefore need to include measurements of rRNA synthesis corroborating the RNA sequencing data to support their scientific findings and claims. This can be accomplished by qPCR, Northern blot, or EU staining of the respective sorted cell population. Quantification of rRNA synthesis is also needed for the CX-5461/BMH-21 and silencing studies.

Currently, there is no mechanistic insight as to how rRNA synthesis is increased during EMT, which would also strengthen the manuscript. This could be done through targeted ChIP analysis.

rRNA synthesis has canonically been linked to the cell cycle therefore it will be necessary for the authors to determine the cell cycle state of their respective cell populations throughout the manuscript.

Statistics and quantifications are currently missing in several figures and need to be better explained throughout the manuscript to strengthen the scientific rigor of the studies.

Only metastasis studies are shown in the current version of the manuscript. These studies should be complemented with primary tumor studies as the main focus of the paper is the contribution of EMT to chemoresistance.

Reviewer #3 (Public Review):

Summary:<br /> Ban et al. investigated the role of ribosome biogenesis (RiBi) in epithelial-to-mesenchymal transition (EMT) and its contribution to chemoresistance in breast cancer. They used a Tri-PyMT EMT lineage-tracing model and scRNA-seq to analyze EMT status and found that RiBi was elevated during both EMT and mesenchymal-to-epithelial transition (MET) of cancer cells. They further revealed that nascent protein synthesis mediated by ERK and mTOR signaling pathways was essential for the completion of RiBi. Inhibiting excessive RiBi impaired EMT and MET capability. More importantly, combinatorial treatment with RiBi inhibitors and chemotherapy drugs reduced metastatic outgrowth of both epithelial and mesenchymal tumor cells. These results suggest that targeting the RiBi pathway may be an effective strategy for treating advanced breast cancer with EMT-related chemoresistance.

Strengths:<br /> The conclusions of this study are generally supported by the data. However, some weaknesses still exist as mentioned below.

Weaknesses:<br /> 1) The study predominantly focused on RiBi as a target for overcoming EMT-related chemoresistance. Thus, it will be necessary to provide some canonical outcomes after upregulating ribosome biogenesis, such as translation activity. I would suggest ribosome profiling or puromycin-incorporation assay, or other more suitable experiments.

2) The results were basically obtained from mice and in vitro experiments. While these results provide valuable insights, it will be valuable to validate part of the findings using some tissue samples from patients (e.g. RiBi activity) to determine the clinical relevance and potential therapeutic applications.

3) The results revealed that mTORC1 and ERK mediated RiBi activation. How about mTORC2? It will be informative to evaluate mTORC2 signaling.

4) The results also demonstrated promising synergic effects of Pol I inhibitor (BMH21) and chemotherapy drug (CTX) on chemo-resistant metastasis. How about using the inhibitors of mTORC1 together with CTX?

5) While the results demonstrate the potential efficacy of RiBi inhibitors in reducing metastatic outgrowth, other factors and mechanisms contributing to chemoresistance may exist and need further investigation. I would suggest some discussion about this aspect.

Reviewer #1 (Public Review):

Summary: This study presents fundamental new insights into vesicular monoamine transport and the binding pose of the clinical drug tetrabenazine (TBZ) to the mammalian VMAT2 transporter. Specifically, this study reports the first structure for the mammalian VMAT (SLC18) family of vesicular monoamine transporters. It provides insights into the mechanism by which this inhibitor traps VMAT2 into a 'dead-end' conformation. The structure also provides some evidence for a novel gating mechanism within VMAT2, which may have wider implications for understanding the mechanism of transport in the wider SLC18 family.

Strengths: The structure is high quality, and the method used to determine the structure via fusing mVenus and the anti-GFP nanobody to the amino and carboxyl termini is novel. The binding and transport data are convincing, although limited. The binding position of TBZ is of high value, given its role in treating Huntington's chorea and for being a 'dead-end' inhibitor for VMAT2.

Weaknesses: The lack of additional mutational data and/or analyses on the impact of pH on ligand binding reduces the insights from these experiments. This reduces the strength of the conclusions that can be drawn about the mechanism of binding and transport or the novelty of the gating mechanism discussed above.

Reviewer #2 (Public Review):

Overview:

As a report of the first structure of VMAT2, indeed the first structure of any vesicular monoamine transporter, this manuscript represents an important milestone in the field of neurotransmitter transport. VMAT2 belongs to a large family (the major facilitator superfamily, MFS) containing transporters from all living species. There is a wealth of information relating to the way that MFS transporters bind substrates, undergo conformational changes to transport them across the membrane, and couple these events to the transmembrane movement of ions. VMAT2 couples the movement of protons out of synaptic vesicles to the vesicular uptake of biogenic amines (serotonin, dopamine, and norepinephrine) from the cytoplasm. The new structure presented in this manuscript can be expected to contribute to an understanding of this proton/amine antiport process.

The structure contains a molecule of the inhibitor TBZ bound in a central cavity, with no access to either luminal or cytoplasmic compartments. The authors carefully analyze which residues interact with bound TBZ and measure TBZ binding to VMAT2 mutated at some of those residues. These measurements allow well-reasoned conclusions about the differences in inhibitor selectivity between VMAT1 and VMAT2 and differences in affinity between TBZ derivatives.

The structure also reveals polar networks within the protein and hydrophobic residues in positions that may allow them to open and close pathways between the central binding site and the cytoplasm or the vesicle lumen. The authors propose the involvement of these networks and hydrophobic residues in the coupling of transport to proton translocation and conformational changes. However, these proposals are quite speculative in the absence of supporting structures and experimentation that would test specific mechanistic details.

Critique:

Although the structure presented in this MS is clearly important, I feel that the authors have overstated several of the conclusions that can be drawn from it. I don't agree that the structure clearly indicates why TBZ is a non-competitive inhibitor; the proposal that specific hydrophobic residues function as gates will depend on lumen- and cytoplasm-facing structures for verification; the polar networks could have any number of functions - indeed it would be surprising if they were all involved in proton transport. Several of these issues could be resolved by a clearer illustration of the data, but I believe that a more rigorous description of the conclusions and where they fall between firm findings and speculation would help the reader put the results in perspective.

Non-competitive inhibition occurs when the action of an inhibitor can't be overcome by increasing substrate concentration. The structure shows TBZ sequestered in the central cavity with no access to either cytoplasm or lumen. The explanation of competitive vs non-competitive inhibition depends entirely on how TBZ got there. If it is bound from the cytoplasm, cytoplasmic substrate should have been able to compete with TBZ and overcome the inhibition. If it is bound from the lumen, or from within the bilayer, cytoplasmic substrate would not be able to compete, and inhibition would be non-competitive. The structure does not tell us how TBZ got there, only that it was eventually occluded from both aqueous compartments and the bilayer.

The issue of how VMAT2 opens access to the central binding site from luminal and cytoplasmic sides is an important and interesting one, and comparison with other MFS structures in cytoplasmic-open or extracellular/luminal-open is a very reasonable approach. However, any conclusions for VMAT2 should be clearly indicated as speculative in the absence of comparable open structures of VMAT2. As a matter of presentation, I found the illustrations in ED Fig. 6 to be less helpful than they could have been. Specifically, illustrations that focus on the proposed gates, comparing that region of the new structure with the corresponding region of either VGLUT or GLUT4 would better help the reader to compare the position of the proposed gate residues with the corresponding region of the open structure. I realize that is the intended purpose of ED Fig. 6b and 6c, but currently, those show the entire protein, and a focus on the gate regions might make the proposed gate movements clearer. I also appreciate the difference between the Alphafold prediction and the new structure, but I'm not convinced that ED Fig. 6a adds anything helpful.

The polar networks described in the manuscript provide interesting possibilities for interactions with substrates and protons whose binding to VMAT2 must control conformational change. Aside from the description of these networks, there is little evidence presented to assess the role of these networks in transport. Are the networks conserved in other closely related transporters? How could the interaction of the networks with substrate or protons affect conformational change? Of course, any potential role proposed for the networks would be highly speculative at this point, and any discussion of their role should point out their speculative nature and the need for experimental verification. Some speculation, however, can be useful for focusing the field's attention on future directions. However, statements in the abstract (three distinct polar networks... play a role in proton transduction.) and the discussion (...are likely also involved in mediating proton transduction.) should be clearly presented as speculation until they are validated experimentally.

The strongest aspect of this work (aside from the structure itself) is the analysis of TBZ binding. There is a problematic aspect to this analysis. The discussion on how TBZ stabilizes the occluded conformation of VMAT2 is premature without structures of apo-VMAT2 and possibly structures with other ligands bound. We don't really know at this point whether VMAT2 might be in the same occluded conformation in the absence of TBZ. Any statements regarding the effect of interactions between VMAT2 and TBZ depend on demonstrating that TBZ has a conformational effect. The same applies to the discussion of the role of W318 on conformation and to the loops proposed to "occlude the luminal side of the transporter" (line 131).

The description of VMAT2 mechanism makes many assumptions that are based on studies with other MFS transporters. Rather than stating these assumptions as fact (VMAT2 functions by alternating access...), it would be preferable to explain why a reader should believe these assumptions. In general, this discussion presents conclusions as established facts rather than proposals that need to be tested experimentally.

The MD simulations are not described well enough for a general reader. What is the significance of the different runs? ED Fig. 4d is not high enough resolution to see the details.

Reviewer #3 (Public Review):

Summary:

The vesicular monoamine transporter is a key component in neuronal signaling and is implicated in diseases such as Parkinson's. Understanding of monoamine processing and our ability to target that process therapeutically has been to date provided by structural modeling and extensive biochemical studies. However, structural data is required to establish these findings more firmly.

Strengths:

Dalton et al resolved a structure of VMAT2 in the presence of an important inhibitor, tetrabenazine, with the protein in detergent micelles, using cryo-EM and with the aid of domains fused to its N- and C-terminal ends. The resolution of the maps allows clear assignment of the amino acids in the core of the protein. The structure is in good agreement with a wealth of experimental and structural prediction data and provides important insights into the binding site for tetrabenazine and selectivity relative to analogous compounds.

Weaknesses:

The authors follow up their structures with molecular dynamics simulations. The simulations resulted in repositioning of the ligand, which does not seem to be well founded, and raises questions about the methodological choices made for the simulations.

Joint Public Review:

Bull et al aimed to use data from observational studies and mendelian randomisation to explore if changes in circulating metabolites are associated with colorectal cancer development. As Mendelian randomisation uses information on genetic variations which are fixed at birth, it is less vulnerable to confounding than standard observational studies.

Overall, a major strength of the study is that it uses data from large cohort studies, one from childhood, adolescence, and early adulthood when the incidence of colorectal cancer is very low (reducing the likelihood of reverse causation) and before medication (such as statins which have the potential to affect metabolite levels) has been initiated.

This study has some weaknesses which have been acknowledged by the authors. Although the findings of this study indicate the potentially significant role that polyunsaturated fatty acids may have in colorectal cancer risk, the genes and therefore also the genetic variations (SNPs) associated with fatty acids often produce an effect for more than one fatty acid which may introduce bias. This together with the fact that there was limited information available on many specific fatty acids which are known causative metabolites for colorectal cancer, makes it difficult to establish with confidence which specific classes of fatty acids could potentially play a causative role in these associations. Also, the study populations are majority white European descent which may limit the generalizability of these findings to other populations.

The methodology used was largely acceptable to achieve the aims set out and the findings have shown an association between polyunsaturated fat levels and genetic liability to colorectal cancer.<br /> Overall, this is an important piece of work which has the potential to contribute to our understanding of the causal relationship between circulating metabolites at different stages of the life cycle and colorectal cancer risk as it would be extremely difficult to gather such evidence using other study designs. It opens the door for future research aiming to better understand the role that these metabolites could play in colorectal cancer risk prediction and in turn help identify groups of individuals who would benefit most from prevention and early detection interventions.

This work will be of interest not only to epidemiologists working in the area of GI tract cancers but also those interested in the different applications for mendelian randomisation within cancer epidemiology research.

Reviewer #1 (Public Review):

Summary: The authors seek to establish what aspects of nervous system structure and function may explain behavioral differences across individual fruit flies. The behavior in question is a preference for one odor or another in a choice assay. The variables related to neural function are odor responses in olfactory receptor neurons or in the second-order projection neurons, measured via calcium imaging. A different variable related to neural structure is the density of a presynaptic protein BRP. The authors measure these variables in the same fly along with the behavioral bias in the odor assays. Then they look for correlations across flies between the structure-function data and the behavior.

Strengths: Where behavioral biases originate is a question of fundamental interest in the field. In an earlier paper (Honegger 2019) this group showed that flies do vary with regard to odor preference, and that there exists neural variation in olfactory circuits, but did not connect the two in the same animal. Here they do, which is a categorical advance, and opens the door to establishing a correlation. The authors inspect many such possible correlations. The underlying experiments reflect a great deal of work, and appear to be done carefully. The reporting is clear and transparent: All the data underlying the conclusions are shown, and associated code is available online.

Weaknesses: The results are overstated. The correlations reported here are uniformly small, and don't inspire confidence that there is any causal connection. The main problems are<br /> 1. The target effect to be explained is itself very weak. Odor preference of a given fly varies considerably across time. The systematic bias distinguishing one fly from another is small compared to the variability. Because the neural measurements are by necessity separated in time from the behavior, this noise places serious limits on any correlation between the two.<br /> 2. The correlations reported here are uniformly weak and not robust. In several of the key figures, the elimination of one or two outlier flies completely abolishes the relationship. The confidence bounds on the claimed correlations are very broad. These uncertainties propagate to undermine the eventual claims for a correspondence between neural and behavioral measures.<br /> 3. Some aspects of the statistical treatment are unusual. Typically a model is proposed for the relationship between neuronal signals and behavior, and the model predictions are correlated with the actual behavioral data. The normal practice is to train the model on part of the data and test it on another part. But here the training set at times includes the testing set, which tends to give high correlations from overfitting. Other times the testing set gives much higher correlations than the training set, and then the results from the testing set are reported. Where the authors explored many possible relationships, it is unclear whether the significance tests account for the many tested hypotheses. The main text quotes the key results without confidence limits.

Reviewer #2 (Public Review):

Summary:<br /> The authors aimed to identify the neural sources of behavioral variation in a decision between odor and air, or between two odors.

Strengths:<br /> -The question is of fundamental importance.<br /> -The behavioral studies are automated, and high-throughput.<br /> -The data analyses are sophisticated and appropriate.<br /> -The paper is clear and well-written aside from some strong wording.<br /> -The figures beautifully illustrate their results.<br /> -The modeling efforts mechanistically ground observed data correlations.

Weaknesses:<br /> -The correlations between behavioral variations and neural activity/synapse morphology are (i) relatively weak, (ii) framed using the inappropriate words "predict", "link", and "explain", and (iii) sometimes non-intuitive (e.g., PC 1 of neural activity).<br /> -No attempts were made to perturb the relevant circuits to establish a causal relationship between behavioral variations and functional/morphological variations.

Reviewer #3 (Public Review):

Churgin et. al. seeks to understand the neural substrates of individual odor preference in the Drosophila antennal lobe, using paired behavioral testing and calcium imaging from ORNs and PNs in the same flies, and testing whether ORN and PN odor responses can predict behavioral preference. The manuscript's main claims are that ORN activity in response to a panel of odors is predictive of the individual's preference for 3-octanol (3-OCT) relative to clean air, and that activity in the projection neurons is predictive of both 3-OCT vs. air preference and 3-OCT vs. 4-methylcyclohexanol (MCH). They find that the difference in density of fluorescently-tagged brp (a presynaptic marker) in two glomeruli (DC2 and DM2) trends towards predicting behavioral preference between 3-oct vs. MCH. Implementing a model of the antennal lobe based on the available connectome data, they find that glomerulus-level variation in response reminiscent of the variation that they observe can be generated by resampling variables associated with the glomeruli, such as ORN identity and glomerular synapse density.

Strengths:<br /> The authors investigate a highly significant and impactful problem of interest to all experimental biologists, nearly all of whom must often conduct their measurements in many different individuals and so have a vested interest in understanding this problem. The manuscript represents a lot of work, with challenging paired behavioral and neural measurements.

Weaknesses:<br /> The overall impression is that the authors are attempting to explain complex, highly variable behavioral output with a comparatively limited set of neural measurements. Given the degree of behavioral variability they observe within an individual (Figure 1- supp 1) which implies temporal/state/measurement variation in behavior, it's unclear that their degree of sampling can resolve true individual variability (what they call "idiosyncrasy") in neural responses, given the additional temporal/state/measurement variation in neural responses. The statistical analyses in the manuscript are underdeveloped, and it's unclear the degree to which the correlations reported have explanatory (causative) power in accounting for organismal behavior.

Reviewer #1 (Public Review):

Erbacher and colleagues provide further evidence for the function of epithelial cells as major contributors to the transduction of sensory stimuli. This technically advanced imaging study of human skin advances support for the anatomical and functional association of nerve fibers and skin keratinocytes. With combined high-resolution imaging and immunolabeling, the authors also advance the idea that gap junctions are at least one means by which direct neurochemical (e.g., ATP) communication from stimulated keratinocytes to nerve fibers can be achieved.

A major strength of the study is the combined use of super-resolution array tomography (srAT), expansion microscopy, structured illumination microscopy and immunolabeling to analyze human skin in situ as well as co-cultures of human neurons and keratinocytes. High resolution static and video imaging of skin clearly supports the ensheathment by keratinocytes of nerve fiber projections as they traverse layers of the epidermis. Another strength of this study is the srAT imaging combined with connexin Cx43 immunolabeling that focus on sites of nerve fiber-keratinocyte contact zones. Imaging of Cx43+ plaques support these sites as regions of direct epithelial-neural contact and as such, of communication.

Although imaging data support Cx43+/connexin plaques and neural ensheathment as regions of direct epithelial-neural communication, e.g., via keratinocyte release of ATP, this relationship remains correlative and lacking in quantification.

The conclusion of this paper regarding the anatomical relationship between nerves and keratinocytes is well supported. Data also support the proposal of connexin plaques as sites of communication, although analyses that validate this relationship, using experimental models and in human samples, remain for future studies.

Reviewer #2 (Public Review):

Erbacher et al. have used new techniques to explore the neuro-cutaneous structures of human epidermis, which is a valuable goal given the lack of in-depth studies in human skin. Human skin is less studied than rodent skin because it presents challenges in obtaining samples and finding excellent immunohistological labels. They have employed expansion microscopy and super resolution array tomography for histological studies and have developed a human keratinocyte and human iPSC-derived sensory neuron co-culture. The authors have used these techniques to investigate the relation of intraepidermal nerve fibers (IENF) and keratinocytes, as well as to probe the localization of connexin 43. The data offer some anatomical insights, but as is does not add to our understanding of keratinocyte-neuron coupling.

Strengths:<br /> This paper is applying newer techniques to probe structure in human skin and establishes some useful immunohistochemical labels to do this, which sets up a foundation that will be valuable for future studies. The observation that IENF sometimes tunnel through keratinocytes is interesting, and the manuscript does show that Cx43 hemichannels are localized near IENF. Their data definitely represents a technical achievement, as these studies are challenging.

Weaknesses:<br /> Throughout the paper, the authors imply that they make discoveries that shed light on neuro-cutaneous interactions, but the data in this manuscript do not offer any functional insight into connections between IENF and keratinocytes. For example, the final figure legend indicates they have found evidence of "electrical and chemical synapse-like contacts to nerve fibers" (Figure 9), but no such evidence was shown. Only a single neuron vesicular marker (synaptophysin) was shown to localize to neurons in culture, as expected. They also "...propose a crucial role of nerve fiber ensheathment and Cx43-based keratinocyte-fiber contacts in neuropathic pain and small fiber pathology." but do not show any data regarding the contribution of their anatomical findings to sensory function.

Their data do show that IENF are anatomically closely apposed to keratinocytes, but this is inevitable given their location in the epidermis. The expression of Cx43 in human epidermis is also known (PMID: 7518858) and localizing Cx43 plaques near IENF does not add to current knowledge, as wide expression in keratinocytes naturally positions them near the embedded IENF. There is no indication whether IENF also expresses Cx43 to form gap junctions. Moreover, due to the lack of quantification, it is not clear whether Cx43 labeling is enriched at IENF sites as compared to other areas on the keratinocytes.

The authors' implication that their anatomical data offers insight into neuro-cutaneous functional coupling is a leap that is evident throughout the manuscript.

Reviewer #3 (Public Review):

This paper offers a fundamental advance in our understanding of communication between human sensory neurons and keratinocytes in the skin of humans. The work, which used EM and expansion microscopy, shows that axons tunnel through keratinocytes and form gap junctions along the axon as it passes by or potentially where it is ensheathed by the cell. This is a fairly remarkable arrangement and is seen both in vivo and in vitro.

The major strengths are the quality of the imaging, the use of expansion microscopy to reveal new anatomical information and the new insight the detailed work offers to our understanding of sensory neuroscience. Another major strength is that the work was done in humans, and using human cells in vitro. I think the authors have achieved their goal of thoroughly characterizing this interesting interaction between sensory neurons and keratinocytes. The obvious next step is to understand if these interactions become pathological in neuropathies.

I do think there are some weaknesses that should be addressed, and some questions that are outstanding that the authors might want to discuss. Chief amongst these is the question of what types of sensory neurons form these contacts with keratinocytes and do these change in clinical neuropathies. A more thorough discussion of these issues for future investigation would help to place the findings in the broader context of the field, in my opinion.