Survival through traditions: Some continuity through art, clothing, and rituals.

Decline of knowledge/identity: Each generation loses more cultural knowledge due to language erosion.

Solution: Greater respect from Canadian society could help restore pride, language, and well-being.

Cycle: Assimilation reduces cultural pride → worsens health and community cohesion.

Systemic racism: Found in government, justice, and healthcare systems. Language consequences: Fear of discrimination → younger generations abandon language to assimilate.

Mental health effects: Racism causes depression, anxiety, PTSD, low self-worth, safety concerns. Physical effects: Linked to poor sleep, appetite changes, fatigue. Youth impact: Adolescents exposed to ongoing racism are at higher risk of suicide, substance abuse, behavioral issues.

Consequences: Survivors more likely to attempt suicide, face developmental/mental health issues, and perpetuate cycles of abuse → further disrupts cultural and linguistic continuity.

Isolation: Students felt disconnected from family/community after being punished for speaking native languages.

Legacy of residential schools: Elders suffer PTSD and trauma even decades after closures. Intergenerational trauma: Children of survivors inherit effects, including weakened language transmission.

Themes (Sivak et al.): language connects body, mind/emotions, family, community, culture, land, spirit, ancestors.

Language reclamation improves mood, belonging, happiness, and community strength.

Some Indigenous youth perceive culture/heritage as undervalued in wider society → discourages cultural connection.

Generational gap: elders fluent, grandchildren not → communication breakdown. Leads to isolation, seclusion, loneliness → precursors to later mental health issues.

Language loss disrupts oral tradition → youth lack knowledge of history.

Suicide rates 6x higher in communities where <50% speak ancestral language.

Cultural continuity (through language) = better health outcomes.

Negative consequences of residential schools → trauma, substance abuse, suicide, poor mental health.

Language = tied to cultural identity and mental health (UN Declaration on Rights of Indigenous Peoples).

History shows systematic erasure of language + culture, creating long-lasting

2002 INAC report → many Indigenous languages extinct or nearly extinct. 2021 discovery of 215 children at Kamloops residential school → renewed awareness + urgency.

2002 INAC report → many Indigenous languages extinct or nearly extinct. 2021 discovery of 215 children at Kamloops residential school → renewed awareness + urgency.

Even post-1982 Charter of Rights → Indigenous languages not recognized as rights.

Other policies: Gradual Civilization Act (1857), cultural bans until 1951.

Residential schools (1876–1996): ・Forced assimilation of children. ・Children separated from parents/siblings. ・Speaking native languages punished → corporal punishment. ・Language + cultural practices (e.g., Potlatch, ceremonies) banned.

Colonialism = ongoing system of oppression → alienation of land + assimilation policies. Indigenous languages historically framed as “primitive,” barriers to modernity.

Article's goal: explore consequences of language loss (identity + health) + propose remedies (adult language programs, institutional change).

Language loss tied to culture + self-identity → without language, cultural identity weakens, leading to psychosocial impacts. Strong cultural identity = better mental health outcomes.

This phrase recognizes that loss of language leads to a loss of culture, indicating that language and cultural attachment has a correlation.

Indigenous language is essential to the collective identity of the tribe.

Language seen as more than communication → a “natural resource” needing stewardship.

brutal 🥀

paragraph duplicates Table 3. Remove.

What are the typical turnaround times for transfer pricing analyses and reports? A standard benchmarking study is usually completed within around 4 business days. Simple financial data updates can be finalized in as little as 48 hours, while a complete documentation update typically takes about 1 week. Master Files are also delivered within 1 week, and Local Files usually require 2–3 weeks depending on complexity and the number of transactions involved.

ez a rést fasza maradjon, de a szolgáltatások doksi alapján frissythető, tp doc update 3 szűrésfrissítés felett 10% kedvezmény a végösszegből (kieg szolgáltatással ugyanez), szűrés szintén kedvezményes (search step-es) három db-tól 10% kedvezmény, master filenál nincs kedvezmény, local file.nál pedig, ha egy cégnek kell a tranzakcióit elemezni és az elemzendő tranzakciók száma a tárgyévre több mint 3, akkor szintén 10% kedvezmény.

illetve a featureeket is frissíteni, a 48 órás delivery date az jó a csak pénzügyi adatok frissítésére. ha a komplett doksit frissítjük (kieg. szolgáltatás) akkor 1 hét, benchmark study 4 nap, local file és master file komplexitástól függően 2, maximum 3 hét.

itt is lehet a 3 fő service

DOI: 10.1158/2767-9764.CRC-24-0296

Resource: UpSetR (RRID:SCR_026112)

Curator: @scibot

SciCrunch record: RRID:SCR_026112

What is this?

DOI: 10.1038/s44321-025-00287-3

Resource: Adobe Photoshop (RRID:SCR_014199)

Curator: @scibot

SciCrunch record: RRID:SCR_014199

What is this?

DOI: 10.1038/s44321-025-00287-3

Resource: RRID:Addgene_82416

Curator: @scibot

SciCrunch record: RRID:Addgene_82416

What is this?

DOI: 10.1038/s44321-025-00287-3

Resource: RRID:Addgene_42230

Curator: @scibot

SciCrunch record: RRID:Addgene_42230

What is this?

DOI: 10.1038/s44321-025-00287-3

Resource: RRID:Addgene_119816

Curator: @scibot

SciCrunch record: RRID:Addgene_119816

What is this?

DOI: 10.1038/s44321-025-00287-3

Resource: QuPath (RRID:SCR_018257)

Curator: @scibot

SciCrunch record: RRID:SCR_018257

What is this?

DOI: 10.1038/s44321-025-00287-3

Resource: GraphPad Prism (RRID:SCR_002798)

Curator: @scibot

SciCrunch record: RRID:SCR_002798

What is this?

DOI: 10.1038/s44321-025-00287-3

Resource: Adobe Illustrator (RRID:SCR_010279)

Curator: @scibot

SciCrunch record: RRID:SCR_010279

What is this?

DOI: 10.1038/s44321-025-00287-3

Resource: Fiji (RRID:SCR_002285)

Curator: @scibot

SciCrunch record: RRID:SCR_002285

What is this?

DOI: 10.1038/s44321-025-00287-3

Resource: RRID:Addgene_40973

Curator: @scibot

SciCrunch record: RRID:Addgene_40973

What is this?

The numbers show the massive scale of the transatlantic slave trade. It was a global economic system that reshaped populations and economies on three continents. This fact is significant for understanding how modern racial inequalities were formed. By recognizing the scope it helps explain the enduring cultural as well as political consequences of slavery. The current discussion about repartions and systemic racism directly relate to the impact of forced migration and historical scale.

This highlights the economic and political complexity of African societies before the colonization of the European's. It proves that the stereotypes that depict pre-colonial Africa as lacking organization wrong. The mention of trade and taxation shows that African civilizations managed recources on a high level. This is important because in reframes Africa as a center of innovation, rather than a victim of later colonization. This idea ties to the currect efforts to include African history in global curriculums, countering Eurocentric narratives and it stresses Africa's foundational role in world history .

The highlights how racism was created to justify slavery and how those beliefs persisted beyond abolition. Its puts an emphasis on how racial hierarchies aren't natural but socially engineered for political gain. By understaning this it helps explain why racial disparities continued after legal changes. It also speculates questions about how societies and dismantle ideologies that were foundational. This relates to the modern movements against systemic racism, which adreses the long-lasting sturctures that were build during the period of chattel slavery

Akum's endurance underscores the stability and influence of African empires. A thousand years of continuous goverenace urged complex infrastructures, diplomacy, as well as trade. It also points out that African states were not isolated. Aksum was a popular trading hub that was linked to the Red Sea and the Indian Ocean routes. This passage reminds us that African civilization were essential in early global commerce. Today, we can find Ethiopia's rich cultural heritage and independence from European colonization being traced to the legacy of states like Aksum.

Збереження стану змінних у Jupiter

On this website, there are many examples of good practices regarding accessibility.

1) There is a link that says "Skip to main content" which is accessible by pressing the tab key. For users who are unable to use a mouse, this makes the website a lot easier to navigate.

2) Another thing that this website does well is large and easily readable text. Having large font size is crucial for people who are visually impaired.

3) Similar to the second point, there is good amount of spacing between the lines which improves readability. Having these features also improve perceivability and make them more understandable according to POUR principles.

4) Another thing I noticed when navigating this site was the contrast of colours. The text stands out really well, and would meet perceivability standards.

5) Finally, this site has a very well structured page making it easy to operate and navigate. It utilizes clear, bold headings to state key topics. They also integrate landmark regions into headings which makes it even easier for readers to navigate

Td.com/ca TD practices web accessibility by having a TD Accessibility Adapter. This is a free browser plug in which allows adjustable font sizes, dyslexia-friendly fonts, reading guides, dark and monochrome modes, and ability to turn off auto play videos. They have TTY services, which is available for teletypewriter users. Customers can request documents in braille, large print, or accessible digital formats. They have videos in ASL (American Sign Language) Simple colours (Green, White, Black)

These 5 examples are good examples of good practices of web accessibility because it is perceivable by anyone due their ASL videos, TTY services, and Braille documents. Their website layout is easy to understand and operate, they only use 3 colors and don't overcrowd their screen with many options to choose from. One thing TD can improve on is how robust they are, interactive elements like sliders and dropdowns may not be fully navigable by screen readers or keyboard only users.

A short term goal is I want to finish all my work on time, this week is to research what career I would like to do, this month goal is not academically but it is go to the gym aleast 3-4x a week.

A short term goal is I want to finish all my work on time, this week is to research what career I would like to do, this month goal is not academically but it is go to the gym aleast 3-4x a week.

تسليم على كانفاس

After preparing the lesson and reading the text, annotate the paragraph assigned to you on

Hypothesis as follows:

1- Write a summary in your own words for the paragraph assigned to you in Arabic. 

2- Highlight and annotate the new vocabulary and expressions from this unit in your paragraph, and write one example sentence for each highlighted word.

3- Highlight and annotate any grammatical rules that you studied so far, for example, passive, masdar, verb forms, قد, etc. Just highlight it and comment, what rule it is. 

4- Post Questions you have on the article as a whole. 

Alp من البداية حتى نهاية فقرة الوظائف والمسؤوليات

Yousef التجربة الهندسية

Sophia الأوسمة والجوائز

Doaa الوفاة

1) slim / skinny / curvy / thin 👉 Odd one out: curvy Why: slim, skinny, and thin describe people who are not fat. Curvy describes someone (usually a woman) with more shape, not thin.

2) good-looking / ugly / attractive / beautiful 👉 Odd one out: ugly Why: the others are positive words to describe appearance, but ugly is negative.

3) short / brunette / blonde / dark-haired 👉 Odd one out: short Why: brunette, blonde, and dark-haired all describe hair colour, while short describes height.

4) beard / pale / moustache / clean-shaven 👉 Odd one out: pale Why: beard, moustache, and clean-shaven describe facial hair, while pale describes skin colour/complexion.

5) well-built / stocky / slender / fair 👉 Odd one out: fair Why: well-built, stocky, and slender describe body shape/size, while fair describes hair or skin colour.

Reviewer #4 (Public review):

Summary:

In this study Tateishi et al. used TnSeq to identify 131 shared essential or growth defect-associated genes in eight clinical MAC-PD isolates and the type strain ATCC13950 of Mycobacterium intracellulare which are proposed as potential drug targets. Genes involved in gluconeogenesis and the type VII secretion system which are required for hypoxic pellicle-type biofilm formation in ATCC13950 also showed increased requirement in clinical strains under standard growth conditions. These findings were further confirmed in a mouse lung infection model.

Strengths:

This study has conducted TnSeq experiments in reference and 8 different clinical isolates of M. intracellulare thus producing large number of datasets which itself is a rare accomplishment and will greatly benefit the research community.

Weaknesses:

(1) A comparative growth study of pure and mixed cultures of clinical and reference strains under hypoxia will be helpful in supporting the claim that clinical strains adapt better to such conditions. This should be mentioned as future directions in the discussion section along with testing the phenotype of individual knockout strains.<br /> (2) Authors should provide the quantitative value of read counts for classifying a gene as "essential" or "non-essential" or "growth-defect" or "growth-advantage". Merely mentioning "no insertions in all or most of their TA sites" or "unusually low read counts" or "unusually high low read counts" is not clear.<br /> (3) One of the major limitations of this study is the lack of validation of TnSeq results with individual gene knockouts. Authors should mention this in the discussion section.

Reviewer #5 (Public review):

Summary:

In the research article, "Functional genomics reveals strain-specific genetic requirements conferring hypoxic growth in Mycobacterium intracellulare" Tateshi et al focussed their research on pulmonary disease caused by Mycobacterium avium-intracellulare complex which has recently become a major health concern. The authors were interested in identifying the genetic requirements necessary for growth/survival within host and used hypoxia and biofilm conditions that partly replicate some of the stress conditions experienced by bacteria in vivo. An important finding of this analysis was the observation that genes involved in gluconeogenesis, type VII secretion system and cysteine desulphurase were crucial for the clinical isolates during standard culture while the same were necessary during hypoxia in the ATCC type strain.

Strength of the study:

Transposon mutagenesis has been a powerful genetic tool to identify essential genes/pathways necessary for bacteria under various in vitro stress conditions and for in vivo survival. The authors extended the TnSeq methodology not only to the ATCC strain but also to the recently clinical isolates to identify the differences between the two categories of bacterial strains. Using this approach they dissected the similarities and differences in the genetic requirement for bacterial survival between ATCC type strains and clinical isolates. They observed that the clinical strains performed much better in terms of growth during hypoxia than the type strain. These in vitro findings were further extended to mouse infection models and similar outcomes were observed in vivo further emphasising the relevance of hypoxic adaptation crucial for the clinical strains which could be explored as potential drug targets.

Weakness:

The authors have performed extensive TnSeq analysis but fail to present the data coherently. The data could have been well presented both in Figures and text. In my view this is one of the major weakness of the study.

OJO, Dataset

ENTENDER

Reviewer #3 (Public review):

Summary

This study aimed to investigate whether the differences observed in the organization of visual brain networks between blind and sighted adults result from a reorganization of an early functional architecture due to blindness, or whether the early architecture is immature at birth and requires visual experience to develop functional connections. This question was investigated through the comparison of 3 groups of subjects with resting-state functional MRI (rs-fMRI). Based on convincing analyses, the study suggests that: 1) secondary visual cortices showed higher connectivity to prefrontal cortical regions (PFC) than to non-visual sensory areas (S1/M1 and A1) in infants like in blind adults, in contrast to sighted adults; 2) the V1 connectivity pattern of infants lies between that of sighted adults (showing stronger functional connectivity with non-visual sensory areas than with PFC) and that of blind adults (showing stronger functional connectivity with PFC than with non-visual sensory areas); 3) the laterality of the connectivity patterns of infants resembled those of sighted adults more than those of blind adults, but infants showed a less differentiated fronto-occipital connectivity pattern than adults.

Strengths

The question investigated in this article is important for understanding the mechanisms of plasticity during typical and impaired development, and the approach considered, which compares different groups of subjects including, neonates/infants and blind adults, is highly original.

Overall, the presented analyses are solid and well detailed, and the results and discussion are convincing.

Weaknesses

While it is informative to compare the "initial" state (close to birth) and the "final" states in blind and sighted adults to study the impact of post-natal and visual experience, this study does not analyze the chronology of this development and when the specialization of functional connections is completed. This would require investigating the evolution of functional connectivity of the visual system as a function of visual experience and thus as a function of age, at least during toddlerhood given the early and intense maturation of the visual system after birth. This could be achieved by analyzing different developmental periods using open databases such as the Baby Connectome Project.

The rationale for grouping full-term neonates and preterm infants (scanned at term-equivalent age) is not understandable when seeking to perform comparisons with adults. Even if the study results do not show differences between full-terms and preterms in terms of functional connectivity differences between regions and of connectivity patterns, preterms group had different neurodevelopment and post-natal (including visual) experiences (even a few weeks might have an impact). And actually they show reduced connectivity strength systematically for all regions compared with full-terms (Sup Fig 7). Considering a more homogeneous group of neonates would have strengthen the study design.

The rationale for presenting results on the connectivity of secondary visual cortices before the one of primary cortices (V1) could be clarified.

The authors acknowledge the methodological difficulties for defining regions of interest (ROIs) in infants in a similar way as adults. Since the brain development is not homogeneous and synchronous across brain regions (in particular with the frontal and parietal lobes showing a delayed growth), this poses major problems for registration. This raises the question of whether the study findings could be biased by differences in ROI positioning across groups.

Author response:

Reviewer #1 (Public Review):

Summary:

The present study evaluates the role of visual experience in shaping functional correlations between extrastriate visual cortex and frontal regions. The authors used fMRI to assess "resting-state" temporal correlations in three groups: sighted adults, congenitally blind adults, and neonates. Previous research has already demonstrated differences in functional correlations between visual and frontal regions in sighted compared to early blind individuals. The novel contribution of the current study lies in the inclusion of an infant dataset, which allows for an assessment of the developmental origins of these differences.

The main results of the study reveal that correlations between prefrontal and visual regions are more prominent in the blind and infant groups, with the blind group exhibiting greater lateralization. Conversely, correlations between visual and somato-motor cortices are more prominent in sighted adults. Based on these data, the authors conclude that visual experience plays an instructive role in shaping these cortical networks. This study provides valuable insights into the impact of visual experience on the development of functional connectivity in the brain.

Strengths:

The dissociations in functional correlations observed among the sighted adult, congenitally blind, and neonate groups provide strong support for the study's main conclusion regarding experience-driven changes in functional connectivity profiles between visual and frontal regions.

In general, the findings in sighted adult and congenitally blind groups replicate previous studies and enhance the confidence in the reliability and robustness of the current results.

Split-half analysis provides a good measure of robustness in the infant data.

Weaknesses:

There is some ambiguity in determining which aspects of these networks are shaped by experience.

This uncertainty is compounded by notable differences in data acquisition and preprocessing methods, which could result in varying signal quality across groups. Variations in signal quality may, in turn, have an impact on the observed correlation patterns.

The study's findings could benefit from being situated within a broader debate surrounding the instructive versus permissive roles of experience in the development of visual circuits.

Reviewer #2 (Public Review):

Summary:

Tian et al. explore the developmental organs of cortical reorganization in blindness. Previous work has found that a set of regions in the occipital cortex show different functional responses and patterns of functional correlations in blind vs. sighted adults. In this paper, Tian et al. ask: how does this organization arise over development? Is the "starting state" more like the blind pattern, or more like the adult pattern? Their analyses reveal that the answer depends on the particular networks investigated; some functional connections in infants look more like blind than sighted adults; other functional connections look more like sighted than blind adults; and others fall somewhere in the middle, or show an altogether different pattern in infants compared with both sighted and blind adults. 

Strengths:

The question raised in this paper is extremely important: what is the starting state in development for visual cortical regions, and how is this organization shaped by experience? This paper is among the first to examine this question, particularly by comparing infants not only with sighted adults but also blind adults, which sheds new light on the role of visual (and cross-modal) experience. Another clear strength lies in the unequivocal nature of many results. Many results have very large effect sizes, critical interactions between regions and groups are tested and found, and infant analyses are replicated in split halves of the data. 

Weaknesses:

A central claim is that "infant secondary visual cortices functionally resemble those of blind more than sighted adults" (abstract, last paragraph of intro). I see two potential issues with this claim. First, a minor change: given the approaches used here, no claims should be made about the "function" of these regions, but rather their "functional correlations". Second (and more importantly), the claim that the secondary visual cortex in general resembles blind more than sighted adults is still not fully supported by the data. In fact, this claim is only true for one aspect of secondary visual area functional correlations (i.e., their connectivity to A1/M1/S1 vs. PFC). In other analyses, the infant secondary visual cortex looks more like sighted adults than blind adults (i.e., in within vs. across hemisphere correlations), or shows a different pattern from both sighted and blind adults (i.e., in occipito-frontal subregion functional connectivity). It is not clear from the manuscript why the comparison to PFC vs. non-visual sensory cortex is more theoretically important than hemispheric changes or within-PFC correlations (in fact, if anything, the within-PFC correlations strike me as the most important for understanding the development and reorganization of these secondary visual regions). It seems then that a more accurate conclusion is that the secondary visual cortex shows a mix of instructive effects of vision and reorganizing effects of blindness, albeit to a different extent than the primary visual cortex.

Relatedly, group differences in overall secondary visual cortex connectivity are particularly striking as visualized in the connectivity matrices shown in Figure S1. In the results (lines 105-112), it is noted that while the infant FC matrix is strongly correlated with both adult groups, the infant group is nonetheless more strongly correlated with the blind than sighted adults. I am concerned that these results might be at least partially explained by distance (i.e., local spread of the bold signal), since a huge portion of the variance in these FC matrices is driven by stronger correlations between regions within the same system (e.g., secondary-secondary visual cortex, frontal-frontal cortex), which are inherently closer together, relative to those between different systems (e.g., visual to frontal cortex). How do results change if only comparisons between secondary visual regions and non-visual regions are included (i.e., just the pairs of regions within the bold black rectangle on the figure), which limits the analysis to long-rang connections only? Indeed, looking at the off-diagonal comparisons, it seems that in fact there are three altogether different patterns here in the three groups. Even if the correlation between the infant pattern and blind adult pattern survives, it might be more accurate to claim that infants are different from both adult groups, suggesting both instructive effects of vision and reorganizing effects of blindness. It might help to show the correlation between each group and itself (across independent sets of subjects) to better contextualize the relative strength of correlations between the groups. 

It is not clear that differences between groups should be attributed to visual experience only. For example, despite the title of the paper, the authors note elsewhere that cross-modal experience might also drive changes between groups. Another factor, which I do not see discussed, is possible ongoing experience-independent maturation. The infants scanned are extremely young, only 2 weeks old. Although no effects of age are detected, it is possible that cortex is still undergoing experience-independent maturation at this very early stage of development. For example, consider Figure 2; perhaps V1 connectivity is not established at 2 weeks, but eventually achieves the adult pattern later in infancy or childhood. Further, consider the possibility that this same developmental progression would be found in infants and children born blind. In that case, the blind adult pattern may depend on blindness-related experience only (which may or may not reflect "visual" experience per se). To deal with these issues, the authors should add a discussion of the role of maturation vs. experience and temper claims about the role of visual experience specifically (particularly in the title). 

The authors measure functional correlations in three very different groups of participants and find three different patterns of functional correlations. Although these three groups differ in critical, theoretically interesting ways (i.e., in age and visual/cross-modal experience), they also differ in many uninteresting ways, including at least the following: sampling rate (TR), scan duration, multi-band acceleration, denoising procedures (CompCor vs. ICA), head motion, ROI registration accuracy, and wakefulness (I assume the infants are asleep).

Addressing all of these issues is beyond the scope of this paper, but I do feel the authors should acknowledge these confounds and discuss the extent to which they are likely (or not) to explain their results. The authors would strengthen their conclusions with analyses directly comparing data quality between groups (e.g., measures of head motion and split-half reliability would be particularly effective).

Response #1: We appreciate the reviewer’s comments. In response, we have revised the paper to provide a more balanced summary of the data and clarified in the introduction which signatures the paper focuses on and why. Additionally, we have included several control analyses to account for other plausible explanations for the observed group differences. Specifically, we randomly split the infant dataset into two halves and performed split-half cross-validation. Across all comparisons, the results from the two halves were highly similar, suggesting that the effects are robust (see Supplementary Figures S3 and S4).

Furthermore, we compared the split-half noise ceiling across the groups (infants, sighted adults, and blind adults) and found no significant differences between them (details in response #6). Finally, we repeated our analysis after excluding infants with a radiology score of 4 or 5, and the results remained consistent, indicating that our findings are not confounded by potential brain anomalies (details in response #2).

We hope these control analyses help strengthen our conclusions.

Reviewer #3 (Public Review):

Summary:

This study aimed to investigate whether the differences observed in the organization of visual brain networks between blind and sighted adults result from a reorganization of an early functional architecture due to blindness, or whether the early architecture is immature at birth and requires visual experience to develop functional connections. This question was investigated through the comparison of 3 groups of subjects with resting-state functional MRI (rs-fMRI). Based on convincing analyses, the study suggests that: 1) secondary visual cortices showed higher connectivity to prefrontal cortical regions (PFC) than to non-visual sensory areas (S1/M1 and A1) in sighted infants like in blind adults, in contrast to sighted adults; 2) the V1 connectivity pattern of sighted infants lies between that of sighted adults (stronger functional connectivity with non-visual sensory areas than with PFC) and that of blind adults (stronger functional connectivity with PFC than with non-visual sensory areas); 3) the laterality of the connectivity patterns of sighted infants resembled those of sighted adults more than those of blind adults, but sighted infants showed a less differentiated fronto-occipital connectivity pattern than adults.

Strengths:

The question investigated in this article is important for understanding the mechanisms of plasticity during typical and impaired development, and the approach considered, which compares different groups of subjects including, neonates/infants and blind adults, is highly original.

-Overall, the analyses considered are solid and well-detailed. The results are quite convincing, even if the interpretation might need to be revised downwards, as factors other than visual experience may play a role in the development of functional connections with the visual system.

Weaknesses:

While it is informative to compare the "initial" state (close to birth) and the "final" states in blind and sighted adults to study the impact of post-natal and visual experience, this study does not analyze the chronology of this development and when the specialization of functional connections is completed. This would require investigating when experience-dependent mechanisms are important for the setting- establishment of multiple functional connections within the visual system. This could be achieved by analyzing different developmental periods in the same way, using open databases such as the Baby Connectome Project. Given the early, "condensed" maturation of the visual system after birth, we might expect sighted infants to show connectivity patterns similar to those of adults a few months after birth.

The rationale for mixing full-term neonates and preterm infants (scanned at term-equivalent age) from the dHCP 3rd release is not understandable since preterms might have a very different development related to prematurity and to post-natal (including visual) experience. Although the authors show that the difference between the connectivity of visual and other sensory regions, and the one of visual and PFC regions, do not depend on age at birth, they do not show that each connectivity pattern is not influenced by prematurity. Simply not considering the preterm infants would have made the analysis much more robust, and the full-term group in itself is already quite large compared with the two adult groups. The current study setting and the analyses performed do not seem to be an adequate and sufficient model to ascertain that "a few weeks of vision after birth is ... insufficient to influence connectivity".

In a similar way, excluding the few infants with detected brain anomalies (radiological scores higher or equal to 4) would strengthen the group homogeneity by focusing on infants supposed to have a rather typical neurodevelopment. The authors quote all infants as "sighted" but this is not guaranteed as no follow-up is provided.

Response #2: We appreciate the reviewer’s suggestion. We re-analyzed the infant cohort after excluding all cases with radiological scores ≥4 (n =39 infants excluded). The revised analysis confirmed that the connectivity patterns reported in the main text remain statistically unchanged (see Supplementary Fig. S11). This demonstrates the robustness of our findings to potential confounding effects from potential brain anomalies. We have explicitly clarified this in the revised Methods section (page 14, line 391in the manuscript).

In our dataset, newborns (average age at scan = 2.79 weeks) have very limited and immature vision. We agree with the reviewer that long-term visual outcomes cannot be guaranteed without follow-up data. The term "sighted infants" was used operationally to distinguish this cohort from congenitally blind populations.

The post-menstrual age (PMA) at scan of the infants is also not described. The methods indicate that all were scanned at "term-equivalent age" but does this mean that there is some PMA variability between 37 and 41 weeks? Connectivity measures might be influenced by such inter-individual variability in PMA, and this could be evaluated.

The rationale for presenting results on the connectivity of secondary visual cortices before one of the primary cortices (V1) was not clear to understand. Also, it might be relevant to better justify why only the connectivity of visual regions to non-visual sensory regions (S1-M1, A1) and prefrontal cortex (PFC) was considered in the analyses, and not the ones to other brain regions.

In relation to the question explored, it might be informative to reposition the study in relation to what others have shown about the developmental chronology of structural and functional long-distance and short-distance connections during pregnancy and the first postnatal months.

The authors acknowledge the methodological difficulties in defining regions of interest (ROIs) in infants in a similar way as adults. The reliability and the comparability of the ROIs positioning in infants is definitely an issue. Given that brain development is not homogeneous and synchronous across brain regions (in particular with the frontal and parietal lobes showing delayed growth), the newborn brain is not homothetic to the adult brain, which poses major problems for registration. The functional specialization of cortical regions is incomplete at birth. This raises the question of whether the findings of this study would be stable/robust if slightly larger or displaced regions had been considered, to cover with greater certainty the same areas as those considered in adults. And have other cortical parcellation approaches been considered to assess the ROIs robustness (e.g. MCRIB-S for full-terms)?

Recommendations for the Authors:

Reviewer #1(Recommendations for the authors):

Further consideration should be given to the underlying changes in network architecture that may account for differences in functional correlations across groups. An increase (or decrease) in correlation between two regions could signify an increase (decrease) in connection or communication between those regions. Alternatively, it might reflect an increase in communication or connection with a third region, while the physical connections/interactions between the two original regions remain unchanged. These possibilities lead to distinct mechanistic interpretations. For example, there are substantial changes in connectivity during early visual (e.g. Burkhalter A. 1993, Cerebral Cortex) and visuo-motor development (e.g., Csibra et al. 2000 Neuroreport). It's not clear whether increases in communication within the visual network and improvements in visuo-motor behavior (e.g., Yizhar et al. 2023 Frontiers in Neuroscience) wouldn't produce a qualitatively similar pattern of results.

Relatedly, the within-network correlation patterns between visual ROIs and frontal ROIs appear markedly different between sighted adults and infants (Supplementary Figure S1). To what extent do the differences in long-range correlations between visual and frontal regions reflect these within-network differences in functional organization?

Response #3: The reviewer is raising some interesting questions about possible mechanisms and network changes. Resting state studies are indeed always subject to possibility that some effects are mediated by a third, unobserved region. Prior whole-cortex connectivity analyses have observed primarily changes in occipito-frontal connectivity in blindness, so there is not a clear cortical ‘third region’ candidate (Deen et al., 2015). However, some thalamic affects have also been observed and could contribute to the phenomenon (Bedny et al., 2011). Resting state changes in correlation between two areas do not imply changes in strength of long-range anatomical connectivity. Indeed, in the current case they may well reflect differential functional coupling, rather than strengthening or weakening of anatomical connections. We now discuss this in the Discussion section on page 12, line 301 as follows:

“Despite these insights, many questions remain regarding the neurobiological mechanisms underlying experience-based functional connectivity changes and their relationship to anatomical development. Long-range anatomical connections between brain regions are already present in infants—even prenatally—though they remain immature (Huang et al., 2009; Kostović et al., 2019, 2021; Takahashi et al., 2012; Vasung, 2017). Functional connectivity changes may stem from local synaptic modifications within these stable structural pathways, consistent with findings that functional connectivity can vary independently of structural connection strength (Fotiadis et al., 2024). Moreover, functional connectivity has been shown to outperform structural connectivity in predicting individual behavioral differences, suggesting that experience-based functional changes may reflect finer-scale synaptic or network-level modulations not captured by macrostructural measures (Ooi et al., 2022). Prior studies also suggest that, even in adults, coordinated sensory-motor experience can lead to enhancement of functional connectivity across sensory-motor systems, indicating that large-scale changes in functional connectivity do not necessarily require corresponding changes in anatomical connectivity (Guerra-Carrillo et al., 2014; Li et al., 2018).”

It is not clear how changes in correlation patterns among visual areas would produce the connectivity between visual areas and prefrontal areas reported in the current study. Activity in visual areas drives correlations both among visual areas and between visual and prefrontal areas and the same is true of prefrontal corticies.

The findings from this study should be more closely linked to the extensive literature surrounding the debate on whether experience plays an instructive or permissive role in visual development (e.g., Crair 1999 Current Opin Neurobiol; Sur et al. 1999 J Neurobiol; Kiorpes 2016 J Neurosci; Stellwagen & Shatz 2002 Neuron; Roy et al. 2020 Nature Communications).

Response #4: The instructive role suggests that specific experiences or patterns of neural activity directly shape and organize neural circuitry, while the permissive role indicates that such experiences or activity merely enable other factors, such as molecular signals, to influence neural circuit formation(Crair, 1999; Sur et al., 1999). To distinguish whether experience plays an instructive or permissive role, it is essential to manipulate the pattern or information content of neural activity while maintaining a constant overall activity level (Crair, 1999; Roy et al., 2020; Stellwagen & Shatz, 2002). However, both the sighted and blind adult groups have had extensive experience and neural activity in the visual cortices. For the sighted group, activity in the visual cortex is partly driven by bottom-up input from the external environment, through the retina, LGN, and ultimately to the cortex. In contrast, the blind group’s visual cortex activity is partially driven by top-down input from non-visual networks. The precise role of this activity in shaping the observed connectivity patterns remains unclear. Although our study cannot speak to this issue directly, we now link to the relevant literature on page 12,line 320 of the manuscript in the Discussion section as follows:

“The current findings reveal both effects of vision and effects of blindness on the functional connectivity patterns of the visual cortex. A further open question is whether visual experience plays an instructive or permissive role in shaping neural connectivity patterns. An instructive role suggests that specific sensory experiences or patterns of neural activity directly shape and organize neural circuitry. In contrast, a permissive role implies that sensory experience or neural activity merely facilitates the influence of other factors—such as molecular signals—on the formation and organization of neural circuits (Crair, 1999; Sur et al., 1999). Studies with animals that manipulate the pattern or informational content of neural activity while keeping overall activity levels constant could distinguish between these hypotheses (Crair, 1999; Roy et al., 2020; Stellwagen & Shatz, 2002).”

The assertion that a few weeks of vision after birth is insufficient to influence connectivity is provocative. Though supported by the study's results, it would benefit from integration with research in animal models showing considerable malleability of networks from early experience (e.g., Akerman et al. 2002 Neuron; Li et al. 2006 Nature Neuroscience; Stacy et al. 2023 J Neuroscience).

Response #5: We thank the reviewer for their suggestion. The present study found that several weeks of postnatal visual experience is insufficient to significantly alter the long-term connectivity patterns of the visual cortices. While animal studies have shown that acute visual experience, or even exposure to visual stimuli through unopened eyelids, can robustly influence visual system development(Akerman et al., 2002; Li et al., 2008; Van Hooser et al., 2012). We think this discrepancy may be attributed to the substantial differences in developmental timelines between species. The human lifespan is much longer, and so is the human critical period, making it unclear how to map duration from one species to another. We briefly touched upon the time course issue in page 11 line 289 in the Discussion section as follows:

“The present results reveal the effects of experience on development of functional connectivity between infancy and adulthood, but do not speak to the precise time course of these effects. Infants in the current sample had between 0 and 20 weeks of visual experience. Comparisons across these infants suggests that several weeks of postnatal visual experience is insufficient to produce a sighted-adult connectivity profile. The time course of development could be anywhere between a few months and years and could be tested by examining data from children of different ages.”

Substantial differences between the groups are evident in several key aspects of the study, including the number of subjects, brain sizes, imaging parameters, and data preprocessing, all of which are likely to have an impact on the overall signal quality. To clarify how these differences might have impacted correlation differences between groups, it would be essential to include information on the noise ceilings for each correlation analysis within each group.

Response #6: We thank the reviewer for their suggestion. We now report the split-half noise ceiling for adult and infant groups. For each participant, we first split the rs-fMRI time series into two halves, then calculated the ROI-wise rsFC pattern from the two splits. The split-half noise ceiling was estimated according to Lage-Castellanos et al (2019). The noise ceilings of the three groups (infants: 0.90 ± 0.056,blind adults: 0.88 ± 0.041, sighted adults: 0.90 ± 0.055) showed no significant difference (One-way ANOVA_, F(2,552) = 2.348, p = 0.097). Therefore, we believe that overall signal quality is unlikely to impact our results. We also add the relevant context in the Method section in page 16 Line 447 as follows:

“Substantial differences between the groups exist in this study, including the number of subjects, brain sizes, imaging parameters, and data preprocessing, all of which are likely to have an impact on the overall signal quality. To address this concern, we compared the split-half noise ceiling across the groups (infants, sighted adults, and blind adults). For each participant, we first split the rs-fMRI time series into two halves, then calculated the ROI-wise rsFC pattern from the two splits. The split-half noise ceiling was estimated according to Lage-Castellanos et al (Lage-Castellanos et al., 2019). The noise ceilings of the three groups (infants: 0.90 ± 0.056, blind adults: 0.88 ± 0.041, sighted adults: 0.90 ± 0.055) showed no significant difference (One-way ANOVA, F (2,552) = 2.348, p = 0.097). Therefore, overall signal quality is unlikely to impact our results.”

In general, it appears that the infant correlations are stronger compared to the other groups. While this could reflect increased coherence or lack of differentiation, it is also possible that it is simply due to the presence of a non-neuronal global signal. Such a signal has the potential to substantially limit the effective range of functional correlations and comparisons with adults. To address this, it is advisable to conduct control analyses aimed at assessing and potentially removing global signals.

Response #7: We agree with the reviewer that global signal regression (GSR) may help reduce non-neuronal artifacts, such as motion, cardiac, and respiratory signals, which are known to correlate with the global signal. However, the global signal also contains neural signals from gray matter, and removing it can introduce unwanted artifacts, especially for the current study. First, GSR can reduce the physiological accuracy of functional connectivity (FC); second, GSR may have differential effects across groups, potentially introducing additional artifacts in between-group comparisons, as noted by Murphy et al (Murphy & Fox, 2017). The CompCor method (Behzadi et al., 2007; Whitfield-Gabrieli & Nieto-Castanon, 2012) is capble to estimate the global non-neuronal artifacts like the GSR method. Meanwhile as it estimate global non-neuronal artifacts from signals within the white matter (WM) and cerebrospinal fluid (CSF) masks, but not the gray matter (GM), CompCor could introduce minimal unwanted bias to the GM signal.

Was there a difference in correlations for preterm vs term neonates? Recent research has suggested that preterm births can have an impact on functional networks, particularly in frontal cortices. e.g., Tokariev et al. 2019, Li et al. 2021 elife; Zhang et al. 2022 Fronteirs in Neuroscience.

Response #8: We have compared preterm and term neonates for all the main results, including the connectivity from the secondary visual cortex/V1 to non-visual sensory cortices versus prefrontal cortices, the laterality of occipito-frontal connectivity, and the specialization across different fronto-occipital networks. This information is reported in Page 6 line 169 and Supplementary Figure S7. The connectivities of full-term infants are generally higher than those of preterm infants. However, the connectivity patterns of term and preterm infants are very similar.

The consistency between the current results and prior work (e.g., Burton et al. 2014) is notable, particularly in the observed greater correlations in prefrontal regions and weaker correlations in somato-motor regions for early blind individuals compared to sighted. However, almost all visual-frontal correlations in both groups were negative in that prior study. Some discussion on why positive correlations were found in the current study could help to clarify.

Response #9: Many other papers have reported positive correlations similar to those found in our study (e.g., Deen et al., 2015; Kanjlia et al., 2021). In contrast, Burton's study identified predominantly negative visual-frontal correlations, we think this is likely because the global signal was regressed out during preprocessing. This methodological choice can lead to an increase in negative connections (Murphy & Fox, 2017).

The term "secondary visual areas" used throughout the paper lacks specificity, and its usage in terms of underlying anatomical and functional areas has been inconsistent in the literature. It would be advisable to adopt a more precise characterization based on functional and/or anatomical criteria.

Response #10: We specified in the article that Tthe occipital ROIs were defined in the current study are functional areas in people born blind identified in prior studies as regions that respond to three non-visual tasks such as language, math, or executive function, and show functional connectivity changes in blind adults in previous studies (Kanjlia et al., 2016, 2021; Lane et al., 2015). These regions respond to language, math and executivie function in the congenitally blind population (see Figure 1.) The are refered collectively as ‘secondary visual areas’ to destinguish them from V1. Anatomically, these three regions cover the majority of the lateral occipital cortex and part of the ventral occipital cortex, providing a good sample of the connectivity profile of higher-order visual areas. Thus, we are using the term "secondary visual areas" to refer to these regions. In blind individuals, although these regions respond to non-visual tasks, their exact functions are unknown.

The inclusion of the ventral temporal cortex in the visual ROIs is currently only depicted in Supplementary Figure S7. To enhance the clarity of the areas of interest analyzed, it would be advisable to illustrate the ventral temporal areas in the main text. Were there notable differences in the frontal correlations between the lateral occipital visual areas and ventral temporal areas?

Response #11: We thank the reviewer for pointing out this issue. We added a statement about the ventral visual cortex in describing the location of the ROI and added the ventral view of ROIs in the Figure 1. The language-responsive and math -responsive ROIs covers both the lateral and ventral visual cortex, whereas executive function (response-conflict) regions cover only the lateral visual cortex. We compared the connectivity patterns of these three regions and found no differences (see supplementary Fig S2).

The blind group results are characterized as reflecting a reorganization in comparison to sighted adults while the results for sighted adults compared to infants are discussed more as a maturation ("adult pattern isn't default but requires experience to establish"). Both the sighted and blind adult groups showed differences from the infant group, and these differences are attributed to the role of experience. Why use "reorganization" for one result and maturation for another?

Response #12: We agree with the reviewer that both of the adult groups should be thought of as equal in relation to the infants. In other words, the brain develops under one set of experiential conditions or another. We do not think that the adult sighted pattern reflects maturation. Rather, the sighted adult pattern reflects the combined influence of maturation and visual experience. The adult blind pattern reflects the combined influence of maturation and blindness. We use the term ‘reorganization’ to label differences in the blind adults relative to sighted infants. We do so for the purpose of clarity and to remain consistent with terminology in prior liaterature. However, we agree with the reviewer that the blind group does not reflect ‘reorganization’ intrinsically any more than the sighted adult group.

The statement that "visual experience is required to set up long-range functional connectivity" is unclear, especially since the infant and blind groups showed stronger long-range functional correlations with PFC.

Response #13: We revised this sentence to specifically as “visual experience establishes elements of the sighted-adult long-range connectivity” in tha Abstract line 17.

The statement that the visual ROIS roughly correspond to "the anatomical location of areas such as V5/MT+, LO, V3a, and V4v" appears imprecise. From Supplementary Figure S7, these areas cover anterior portions of ventral temporal cortex (do these span the anatomical location of putative category-selective areas?) and into the intraparietal sulcus.

Response #14: Thanks to the reviewer for the clarification. The ventral ROIs cover the middle and part of the anterior portion of the ventral temporal lobe, including the putative category-selective areas. Additionally, the dorsal ROIs extend beyond the occipital lobe to the intraparietal sulcus and superior parietal lobule. We have added a more detailed description of the anatomical location of the ROI in the Methods section Page 17 line 489 as follows:

“Each functional ROI spans multiple anatomical regions and together the secondary visual ROIs tile large portions of lateral occipital, occipito-temporal, dorsal occipital and occipito-parietal cortices. In sighted people, the secondary visual occipital ROIs include the anatomical locations of functional regions such as motion area V5/MT+, the lateral occipital complex (LO), category specific ventral occipitotemporal cortices and dorsally, V3a and V4v.  The occipital ROI also covers the middle of the ventral temporal lobe. Dorsally, it extended to the intraparietal sulcus and superior parietal lobule.”

The motivation for assessing correlations with motor and frontal regions was briefly discussed in the introduction. It would be helpful to reiterate this motivation when first introducing the analyses in the results.

Response #15: Thank you for the thoughtful suggestion. Upon reflection, we chose to substantially revise the Introduction to more clearly and comprehensively explain the rationale for examining the couplings with motor and frontal regions, rather than reiterating it in the Results section. We believe this revised framing provides a stronger foundation for the analyses that follow, while avoiding redundancy across sections. We hope this addresses the reviewer’s concern.

Reviewer #2 (Recommendations for the authors):

Congratulations on a well-written paper and an interesting set of results.

Reviewer #3 (Recommendations for the authors):

Abstract:

Mentioning "sighted infants" does not seem adequate.

Response #16: In our dataset, newborns (average age at scan = 2.79 weeks) have very limited and immature vision. We agree with the reviewer that long-term visual outcomes cannot be guaranteed without follow-up data. The term "sighted infants" was used operationally to distinguish this cohort from congenitally blind populations.

In sentences after "Specifically...", it was not clear whether the authors referred to V1 connectivity.

Response #17: We thank the reviewer for this comment. In the revised abstract, we have removed the original "Specifically..." phrasing and clarified the results.

Introduction

Talking about the "instructive effects" of vision might be confusing or misleading. Visual experiences like exposure to oral language are part of the normal/spontaneous environment that allows the infant behavioral acquisitions (contrarily with learnings that occur later during development with instruction like for reading).

Response #18: We appreciate the reviewer’s concern and would like to clarify that the term “instructive effect” is used here derived from neurodevelopmental studies (Crair, 1999; Sur et al., 1999). In this context, “instructive” refers to activity-dependent mechanisms where patterns of neural activity actively guide the organization of synaptic connectivity, emphasizing that spontaneous or sensory-driven activity (e.g., retinal waves, visual experience) can directly shape circuit refinement, as seen in ocular dominance column formation. In the context of our study, we emphasize that vision plays an instructive role in setting up the balance of connectivity between occipital cortex and non-visual networks.

For references on the development of connectivity, I would advise citing MRI studies but also studies based on histological approaches (see for example the detailed review by Kostovic et al, NeuroImage 2019).

Response #19: We thank the reviewer for this suggestion. We have incorporated a discussion on the long-range anatomical connections that emerge as early as infancy, referencing studies that employed diffusion MR imaging and histological methods, as detailed below.

“Many long-range anatomical connections between brain regions are already established in infants, even before birth, although they are not yet mature (Huang et al., 2009; Kostović et al., 2019, 2021; Takahashi et al., 2012; Vasung, 2017).” (Page 12, line 303 in the manuscript)

Results

P7 l170: It might be helpful to be precise that this is "compared with inter-hemispheric connectivity".

Response #20: We thank the reviewer for this suggestion. To align with our established terminology, we have revised the statement to explicitly contrast within-hemisphere connectivity with between-hemisphere connectivity. The modified text now reads (page 7, line 183 in the manuscript):

“Compared to sighted adults, blind adults exhibited a stronger dominance of within-hemisphere connectivity over between-hemisphere connectivity. That is, in people born blind, left visual networks are more strongly connected to left PFC, whereas right visual networks are more strongly connected to right PFC.

L176-181: It was not clear to me what was the difference between "across" and "between hemisphere connectivity". Would it be informative to test the difference between blind and sighted adults?

Response #21: We clarify that there is no distinction between the terms “across” and “between hemisphere connectivity”—they refer to the same concept. To ensure consistency, we have revised the text to exclusively use “between hemisphere connectivity” throughout the manuscript. Regarding the comparison between blind and sighted adults, we conducted statistical comparisons between these groups in our analysis, and the results have been incorporated into the revised version (Page 7, line 187 in the manuscript).

Adding statistics on Figure 3, but also on Figures 1 and 2 might help the reading.

Response #22: We have added the statistics in Figure 1-4.

Adding the third comparison in Figure 4 would be possible in my view.

Response #23: We explored integrating the response-conflict region into Figure 4, but this would require a 3x3 bar chart with pairwise statistical significance markers, which introduced excessive visual complexity that hindered readers’ ability to grasp our intended message. To ensure clarity, we retained the original Figure 4 while providing the complete three-region analysis (including all statistical comparisons) in Supplementary Figure S8 to ensure completeness.

Methods

The authors might have to specify ages at birth, and ages at scan (median + range?).

Response #24: We have added that information in the Methods section as follows:

“The average age from birth at scan = 2.79 weeks (SD = 3.77, median = 1.57, range = 0 – 19.71); average gestational age at scan = 41.23 weeks (SD = 1.77, median = 41.29, range = 37 – 45.14); average gestational age at birth = 38.43 weeks (SD = 3.73, median = 39.71, range = 23 – 42.71).” (Page 14, line 379 in the manuscript)

It might be relevant to comment on the range of available fMRI volumes, and the fact that connectivity measures might then be less robust in infants.

Response #25: We report the range of fMRI volumes in the Methods section (Page 16, Line 449). Adult participants (blind and sighted) underwent 1–4 scanning sessions, each containing 240 volumes (mean scan duration: 710.4 seconds per participant). For infants, all subjects had 2300 fMRI volumes, and we retained a subset of 1600 continuous volumes per subject with the minimum number of motion outliers. While infant connectivity measures may inherently exhibit lower robustness due to developmental and motion-related factors, our infant cohort’s large sample size (n=475) and stringent motion censoring criteria enhance the reliability of group-level inferences. We have integrated this clarification into the Methods section (Page 16, Line 444) as follows:

"While infant connectivity estimates may be less robust at the individual level compared to adults due to shorter scan durations and higher motion, our cohort’s large sample size (n=475) and rigorous motion censoring mitigate these limitations for group-level analyses. "

The mention of dHCP 2nd release should be removed from the paragraph on data availability.

Response #26: We have removed it.

Reviewer #2 (Public review):

Summary:

The study by Fisher et al investigates therpauetic role for SZN-043, a hepatocyte-targeted R-spondin mimetic, for its potential role in restoring Wnt signaling and promoting liver-regeneration in alcohol-associated liver disease (ALD). Using multiple preclinical models, the compound was shown to promote hepatocyte proliferation and reduce fibrosis. This study highlights the efficacy in promoting liver regeneration while maintaining controlled signaling. Limitations include a need for further exploration of off-target effects and fibrosis mechanisms. The findings support SZN-043 as a promising candidate for ALD therapy, warranting further clinical evaluation. This is a well deigned study with thorough investigation using multiple disease models.

Strengths:

(1) Well-written manuscript with clear design, robust methods, and discussion.

(2) Using multiple models strengthens the findings and expands beyond ALD.

(3) Identification of SZN-043 as a novel potent drug for liver regeneration.

Author response:

Response to Comments from reviewer #1

Many thanks for appreciating that SZN-043 can promote hepatocyte proliferation via the Wnt-signaling pathway.

(1) The reviewer is concerned with using only CYP1A2 expression as an endpoint to make a conclusion about the effect of SZN-043 on Wnt activity in human ALD samples. The reviewer raises a good point as the more commonly used Wnt target gene, AXIN2, is not consistantly changed in both cohorts. We were at first also surprised by this finding. However, upon closer analysis we found that the expression of hepatocyte-specific target genes such as CYP1A2 (Figure 2), CYP2E1, OAT, LGR5, GLUL (Table 1) and ZNRF3 were mostly expressed in hepatocytes and ductal cells were all down-regulated in ALD samples. Others Wnt target genes expressed in epithelial and mesenchymal liver cell populations, such as AXIN2, CCND1 and NOTUM are indeed not consistently and significantly changed. Given that SZN-043 is not active on mesenchymal cells, this discrepancy could be best explained by the large increase in mesenchymal cells in ALD tissue samples, thereby confounding the results. We have now clarified this in the discussion. Another method to assess Wnt activity is to measure b-catenin phosphorylation and nuclear transfer. In our hands, this method was found to be better suited for tissue culture than histological sections from in vivo studies. We have also amended the manuscript title to refer to expression of Wnt target genes, rather than Wnt activity.

(2) We have now added a supplemental figure to show the lack of Ki-67+ human hepatocytes in the cirrhotic tissue samples to confirm the absence of hepatocyte proliferation (Figure S1).

(3) The differences in amino acid sequence between SZN-043 and its precursor, αASGR1-RSPO2-RAIgG, can be found in the material and method section. These changes in amino acid sequences improved the biophysical properties of the final clinical candidate, such as oxidation and nonspecific binding. The biochemical analysis of those differences exceeds the scope of the current manuscript. We present here the pharmacokinetic properties of SZN-043 only, as this was the only molecule advanced to clinical trial and used in the studies presented here.

(4) The reviewer suggests to assess the effect of SZN-043 in Ctnnb1-KO mice to confirm that SZN043 acts via a canonical Wnt pathway. Indeed, there were several reports on the ability of Rspondin to act on other pathways besides the Wnt signaling pathway (for recent review, Niehrs et al, 2024, Bioessays). However, while an interesting suggestion, this line of investigation belongs to MOA studies and exceeds the scope of the current manuscript. An additional manuscript presenting MOA studies for SZN-043 was recently submitted elsewhere. Still, we have added this possibility in the discussion section.

(5) The reviewer is asking how SZN-043 is affecting liver functions in general. Indeed, we have observed a consistent reduction in the international normalized ratio of prothrombin time using the thioacetamide (TAA)-induced fibrosis model and previously published those findings (Zhang, 2020). In our hands, the TAA is the only liver injury model that significantly increases INR. This increase is modest compared to that observed in clinical patients. Therefore, we do not report INR findings for other models. We have not seen any effects of SZN-043 on hepatocyte differentiation markers such as HNF4A (data not shown) and the hepatocyte specific ASGR1/2 as shown in Figure 5. Rather we focused on proliferation as the main potentially beneficial endpoint, to restore the parenchymal mass in injured livers. Finally, consistent with what was reported in the literature, we have observed a transient and reciprocal effect on albumin and alfa-fetoprotein expression during the proliferative phase of liver regeneration. These results are detailed in an additional manuscript presenting MOA studies for SZN-043, which was recently submitted elsewhere.

(6) We have used females only in the ethanol-induced injury models because there are numerous reports in the literature stating that males are not as susceptible to those injuries.  

(7) The reviewer questions the relevance of the ethanol-induced injury model used to evaluate SZN043 efficacy. Indeed, none of the disease model developed to date reproduce the severity and complexity of alcohol-associated liver diseases, although some, such as the ethanol supplemented Lieber DeCarli diet, are more commonly used than others – which is the reason why this model was selected. 

(8) The reviewer questions the relevance of the fibrosis model used to evaluate SZN-043 efficacy. Indeed, none of the fibrosis models developed to date reproduce the severity and complexity of cirrhosis in human livers. While combining ethanol with CCl4 would lead to more severe fibrotic livers, CCl4 itself is not involved in ALD in humans. Both models are likely to result in similar pericentral fibrosis with central-to-central bridging. In this study, we were mostly interested in addressing the effects of SZN-043 in a tissue affected by fibrotic scars.  

(9) The sex of CCl4-treated mice is male. We added this information in the methods section.

(10) A summary of histology and fibrosis assessment data for alcohol-fed mice was added in supplemental Table S3. In our hands, the use of aging mice did not induce the presence of fibrosis, in contrast to published results.  

(11) The rationale for using 13.5-month-old mice in the alcohol studies and scid mice in the CCl4 studies has been clarified in the results and discussion sections. 

a. Briefly, aging mice were reported to be more susceptible to ethanol-induced injury than young mice and to include induction of fibrosis. However, we were unable to reproduce the presence of fibrosis reported in the literature.  

b. Scid mice were used in the CCl4 studies to test whether a stronger response could be observed in the absence of a potential anti-drug antibodies response. While a modest reduction in fibrosis was observed in both B6 and scid mice following the SZN-043 treatment, the effect size did not seem affected by the mouse strain. 

Response to Comments from reviewer #2

Many thanks for appreciating that the use of multiple disease models to identify SZN-043 as a potential novel drug for liver regeneration.

(1) The importance of restoring liver regeneration capacity to reduce the need for liver transplantation had been emphasized in the introduction.

(2) There is continuous damage to the mouse hepatocytes in the FRG mice, due to the Fah mutation. They undergo repair mechanisms favoring the proliferation of human hepatocytes during the production period. Injury models that affect the human hepatocytes population have been developed in these mice. However, the primary goal of this study was to confirm that SZN043 was efficacious in inducing human hepatocytes proliferation, a feature difficult to reproduce in primary hepatocyte cultures. Given the artefactual nature of the chimeric liver in FRG mice and the high cost of these mice, further studies were not judged to be necessary.

(3) Corrected

(4) A figure including DAPI staining has now been included in supplemental Figure S2.

(5) Clarification that the 8 weeks alcohol feeding used in our study design is a modification of the NIAAA model. While some ASGR1 has been reported on the surface of macrophages, additional data from MOA studies strongly suggest that the effect of SZN-043 is mediated via a hepatocytespecific mechanism (submitted manuscript).

(6) The reviewer inquired about the potential role of macrophages in promoting an antiinflammatory state in response to SZN-043. While a direct effect is unlikely, a potential effect of macrophages in response to SZN-043 is plausible. Wnt activation is known to induce the secretion of hepatokines, such as LECT2, which in turn can influence macrophage activity. This possibility is discussed in the discussion section.

(7) The potential off-target effects of SZN-043 such as stellate cell activation is discussed in the discussion section.

(8) The discussion of the limitations of current models has been included in the discussion section of the manuscript.

(9) We have now included a discussion of prior RSPO-based therapies, such as OMP-131R10. We explain why the hepatocyte-targeting of RSPO activity minimizes undesired effects.

Author response:

The following is the authors’ response to the original reviews.

Reviewer #1 (Public review):

Summary:

The work from this paper successfully mapped transcriptional landscape and identified EA-responsive cell types (endothelial, microglia). Data suggest EA modulates BBB via immune pathways and cell communication. However, claims of "BBB opening" are not directly proven (no permeability data).

(1) No in vivo/in vitro assays confirm BBB permeability changes (e.g., Evans blue leakage, TEER).

(2) Only male rats were used, ignoring sex-specific BBB differences.

(3) Pericytes and neurons, critical for the BBB, were not captured, likely due to dissociation artifacts.

(4) Protein-level validation (Western blot, IHC) absent for key genes (e.g., LY6E, HSP90).

(5) Fixed stimulation protocol (2/100 Hz, 40 min); no dose-response or temporal analysis.

We sincerely apologize for the oversight regarding the description of changes in blood-brain barrier permeability. In fact, our team conducted a series of preliminary studies that verified this aspect, and we hace provided a more detailed introduction in the introduction section, in lines 60-71 of the manuscript.

We are very grateful to the reviewers for pointing out the important and meaningful issue of "gender-specific BBB differences." We will make this a focal point in our future research.

As for pericytes and neurons, we acknowledge their importance in the function of the blood-brain barrier. We acknowledge the importance of pericytes and neurons in the blood-brain barrier. However, neurons are absent because our sample processing method involves dissociation. During the dissociation procedure, neuronal axons, which are relatively long, are filtered out during the frequent cell suspension steps and cannot enter the downstream microfluidic system for analysis, so they are not present in our data. Since this experiment is primarily focused on non-neuronal cells, we did not choose to use nucleus extraction for sample processing. As for pericytes, we believe they are not captured because their proportion in our samples is extremely low, which is why they are not present in the data. Further research may require single-nucleus transcriptomics or the separate isolation of these two cell types for study. Of course, in our current mechanistic studies, we are also fully considering the important roles these two cell types play in BBB function.

In addition, to validate the results at the protein level, we have recently conducted some experiments. However, as several proteins are currently at a critical stage of further experimental validation, it is not appropriate to present them in the manuscript at this time. Instead, we have uploaded the relevant data as an appendix for your review. This includes a figure of several protein markers we examined, as well as a table of the antibodies used.

This section is also further elaborated in the introduction and its references.

Reviewer #2 (Public review):

Summary:

This study uses single-cell RNA sequencing to explore how electroacupuncture (EA) stimulation alters the brain's cellular and molecular landscape after blood-brain barrier (BBB) opening. The authors aim to identify changes in gene expression and signaling pathways across brain cell types in response to EA stimulation using single-cell RNA sequencing. This direction holds promise for understanding the consequences of noninvasive methods of BBB opening for therapeutic drug delivery across the BBB.

(1) The work falls short in its current form. The experimental design lacks a clear justification, and readers are not provided with sufficient background information on the extent, timing, or regional specificity of BBB opening in this EA model. These details, established in prior work, are critical to understanding the rationale behind the current transcriptomic analyses.

(2) Further, the results are often presented with minimal context or interpretation. There is no model of intercellular or molecular coordination to explain the BBB-opening process, despite the stated goal of identifying such mechanisms. The statement that EA induces a "unique frontal cortex-specific transcriptome signature" is not supported, as no data from other brain regions are presented. Biological interpretation is at times unclear or inaccurate - for instance, attributing astrocyte migration effects to endothelial cell clusters or suggesting microglial tight junction changes without connecting them meaningfully to endothelial function.

(3) The study does include analyses of receptor-ligand signaling and cell-cell communication, which could be among its most biologically rich outputs. However, these are relegated to supplementary material and not shown in the leading figures. This choice limits the utility of the manuscript as a hypothesis-generating resource.

(4) Overall, while the dataset may be of interest to BBB researchers and those developing technologies for drug delivery across the BBB, the manuscript in its current form does not yet fulfill its interpretive goals. A more integrated and biologically grounded analysis would be beneficial.

This section is also further elaborated in the introduction and its references.

Our current study is actually based on previous findings that electroacupuncture can open the BBB, with a more pronounced effect observed in the frontal lobe (this aspect should be further described in the research background). Building on this foundation, our aim is to delineate the potential biological mechanisms involved. Therefore, we selected frontal lobe tissue as our primary choice for sequencing and have not yet investigated differences across other brain regions, although this may become a focus of future research. Additionally, we recognize that the mechanism underlying BBB opening is complex, and at present, we cannot determine whether it is driven by a single direct factor or by coordinated actions between cells or molecules. As such, our results are presented only briefly for now, and we will carefully consider whether to supplement our findings by incorporating insights from other studies.

Considering the overall data layout and the length of the article, we ultimately decided not to make any changes to the presentation of the article's data. The images included in the supplementary materials are also thoroughly described and referenced in the manuscript, allowing readers to selectively view any data they are interested in.

Indeed, our current dataset and analysis tend to present objective data results. We are also conducting a series of validations that may be related to the biology of the blood-brain barrier, and we look forward to sharing and discussing any future research findings with you and everyone.

Reviewer #1 (Recommendations for the authors):

(1) Figures 3-7: Label treatment groups (CON vs. EA) consistently in legends.

(2) Methods: Specify rat strain (Sprague-Dawley) in the abstract.

(3) Clarify Limitations: Explicitly state that BBB opening is inferred, not proven.

This section has been revised at lines 743-733, 748, 949, 754-755, and 759-760 of the manuscript.

Revised at line 31 of the manuscript.

Thank you for your feedback. The background information on the open evidence of BBB has been added to the introduction.

Reviewer #2 (Recommendations for the authors):

(1) Abstract and Introduction

• Include specific key findings in the abstract to improve clarity and reader engagement.

• Expand the introduction to situate this work in the context of other BBB-opening methods (e.g., ultrasound) and the known consequences of BBB disruption.

• Clarify the rationale for choosing electroacupuncture.

• Include information (perhaps summarized from previous studies) about the extent, timeline, and functional assessment of BBB opening in this model to help justify the single-cell RNA-seq design.

(2) Experimental Rationale and Context

• Reiterate experimental design and rationale in each results section, rather than relying exclusively on the Methods section.

• Specify the time point of tissue collection relative to the EA intervention.

• Describe the anatomical sites of acupuncture stimulation and their physiological relevance.

(3) Data Presentation

• Replace the human brain cartoon in Figure 1 with an anatomically appropriate rat brain schematic.

• Reevaluate which data are presented in the main versus supplementary figures. Highlight biologically meaningful results, such as cell-cell communication and ligand-receptor interactions, in the main figures rather than supplementary data.

(4) Interpretation and Modeling

• More carefully link transcriptional changes (e.g., Wnt signaling in microglia) to biologically plausible mechanisms of BBB regulation-e.g., microglial signaling to endothelial cells.

• Clarify whether the presence of granulocytes and T cells might result from a lack of perfusion prior to brain dissection.

• Consider proposing a model (even speculative) of how EA leads to BBB opening based on observed transcriptional changes.

First, for the sake of brevity in the abstract, we did not present specific results in this section. Second, since BBB opening via EA is a unique strategy, our previous studies have examined the opening time window and the recovery of the BBB after EA intervention (as mentioned in the introduction). We believe its characteristics differ from those of ultrasound-induced BBB opening and BBB disruption, so we did not conduct comparative discussions, but objectively presented our research findings. In further functional validation experiments, we may consider integrating other opening strategies in our studies. Additionally, the choice of electroacupuncture was based on our previous series of studies, which have already been outlined in the research background. Finally, we did indeed determine the experimental design of this study based on prior research, as described in the background section of the introduction.

We decided not to make changes to this section in the manuscript after careful consideration. The setup of electroacupuncture intervention and controls has been thoroughly discussed in our previous studies (as referenced in the introduction), so we have not repeated it in this manuscript. Overall, building on all our previous findings, this study focuses primarily on the potential mechanisms of EA intervention. The anatomical sites of acupuncture stimulation and their physiological relevance are another key area of our research, and we are currently conducting a series of related studies. We look forward to sharing these findings with you in the future.

We have already changed the human brain diagram in Figure 1 to a rat brain diagram, and have replaced Figure 1 in the files with the revised version. However, considering the overall data layout and the length of the article, we ultimately decided not to make changes to the data presentation in the manuscript. The images in the supplementary materials are also thoroughly described and referenced in the manuscript, allowing readers to selectively view the data they are interested in.

This section has provided us with excellent suggestions for further exploration, although no changes have been made to the manuscript at this time. In the future, we may conduct more detailed transcriptomic studies focusing on sex differences and different brain regions, which will allow for a more comprehensive analysis of the biological mechanisms involved in BBB regulation.

Reviewer #3 (Public review):

Summary:

The authors generated knockout mice for Atad2, a conserved bromodomain-containing factor expressed during spermatogenesis. In Atad2 KO mice, HIRA, a chaperone for histone variant H3.3, was upregulated in round spermatids, accompanied by an apparent increase in H3.3 levels. Furthermore, the sequential incorporation and removal of TH2B and PRM1 during spermiogenesis were partially disrupted in the absence of ATAD2, possibly due to delayed histone removal. Despite these abnormalities, Atad2 KO male mice were able to produce offspring normally.

Strengths:

The manuscript addresses the biological role of ATAD2 in spermatogenesis using a knockout mouse model, providing a valuable in vivo framework to study chromatin regulation during male germ cell development. The observed redistribution of H3.3 in round spermatids is clearly presented and suggests a previously unappreciated role of ATAD2 in histone variant dynamics. The authors also document defects in the sequential incorporation and removal of TH2B and PRM1 during spermiogenesis, providing phenotypic insight into chromatin transitions in late spermatogenic stages. Overall, the study presents a solid foundation for further mechanistic investigation into ATAD2 function.

Weaknesses:

While the manuscript reports the gross phenotype of Atad2 KO mice, the findings remain largely superficial and do not convincingly demonstrate how ATAD2 deficiency affects chromatin dynamics. Moreover, the phenotype appears too mild to elucidate the functional significance of ATAD2 during spermatogenesis.

(1) Figures 4-5: The analyses of differential gene expression and chromatin organization should be more comprehensive. First, Venn diagrams comparing the sets of significantly differentially expressed genes between this study and previous work should be shown for each developmental stage. Second, given the established role of H3.3 in MSCI, the effect of Atad2 knockout on sex chromosome gene expression should be analyzed. Third, integrated analysis of RNA-seq and ATAC-seq data is needed to evaluate how ATAD2 loss affects gene expression. Finally, H3.3 ChIP-seq should be performed to directly assess changes in H3.3 distribution following Atad2 knockout.

(2) Figure 3: The altered distribution of H3.3 is compelling. This raises the possibility that histone marks associated with H3.3 may also be affected, although this has not been investigated. It would therefore be important to examine the distribution of histone modifications typically associated with H3.3. If any alterations are observed, ChIP-seq analyses should be performed to explore them further.

(3) Figure 7: While the authors suggest that pre-PRM2 processing is impaired in Atad2 KO, no direct evidence is provided. It is essential to conduct acid-urea polyacrylamide gel electrophoresis (AU-PAGE) followed by western blotting, or a comparable experiment, to substantiate this claim.

(4) HIRA and ATAD2: Does the upregulation of HIRA fully account for the phenotypes observed in Atad2 KO? If so, would overexpression of HIRA alone be sufficient to phenocopy the Atad2 KO phenotype? Alternatively, would partial reduction of HIRA (e.g., through heterozygous deletion) in the Atad2 KO background be sufficient to rescue the phenotype?

(5) The mechanism by which ATAD2 regulates HIRA turnover on chromatin and the deposition of H3.3 remains unclear from the manuscript and warrants further investigation.

Author response:

Reviewer #1 (Public review): 

Summary: 

The authors analyzed the expression of ATAD2 protein in post-meiotic stages and characterized the localization of various testis-specific proteins in the testis of the Atad2 knockout (KO). By cytological analysis as well as the ATAC sequencing, the study showed that increased levels of HIRA histone chaperone, accumulation of histone H3.3 on post-meiotic nuclei, defective chromatin accessibility and also delayed deposition of protamines. Sperm from the Atad2 KO mice reduces the success of in vitro fertilization. The work was performed well, and most of the results are convincing. However, this manuscript does not suggest a molecular mechanism for how ATAD2 promotes the formation of testis-specific chromatin. 

We would like to take this opportunity to highlight that the present study builds on our previously published work, which examined the function of ATAD2 in both yeast S. pombe and mouse embryonic stem (ES) cells (Wang et al., 2021). In yeast, using genetic analysis we showed that inactivation of HIRA rescues defective cell growth caused by the absence of ATAD2. This rescue could also be achieved by reducing histone dosage, indicating that the toxicity depends on histone over-dosage, and that HIRA toxicity, in the absence of ATAD2, is linked to this imbalance.

Furthermore, HIRA ChIP-seq performed in mouse ES cells revealed increased nucleosome-bound HIRA, particularly around transcription start sites (TSS) of active genes, along with the appearance of HIRA-bound nucleosomes within normally nucleosome-free regions (NFRs). These findings pointed to ATAD2 as a major factor responsible for unloading HIRA from nucleosomes. This unloading function may also apply to other histone chaperones, such as FACT (see Wang et al., 2021, Fig. 4C).

In the present study, our investigations converge on the same ATAD2 function in the context of a physiologically integrated mammalian system—spermatogenesis. Indeed, in the absence of ATAD2, we observed H3.3 accumulation and enhanced H3.3-mediated gene expression. Consistent with this functional model of ATAD2— unloading chaperones from histone- and non-histone-bound chromatin—we also observed defects in histone-toprotamine replacement.

Together, the results presented here and in Wang et al. (2021) reveal an underappreciated regulatory layer of histone chaperone activity. Previously, histone chaperones were primarily understood as factors that load histones. Our findings demonstrate that we must also consider a previously unrecognized regulatory mechanism that controls assembled histone-bound chaperones. This key point was clearly captured and emphasized by Reviewer #2 (see below).

Strengths: 

The paper describes the role of ATAD2 AAA+ ATPase in the proper localization of sperm-specific chromatin proteins such as protamine, suggesting the importance of the DNA replication-independent histone exchanges with the HIRA-histone H3.3 axis. 

Weaknesses: 

(1) Some results lack quantification. 

We will consider all the data and add appropriate quantifications where necessary.

(2) The work was performed well, and most of the results are convincing. However, this manuscript does not suggest a molecular mechanism for how ATAD2 promotes the formation of testis-specific chromatin. 

Please see our comments above.

Reviewer #2 (Public review): 

Summary: 

This manuscript by Liakopoulou et al. presents a comprehensive investigation into the role of ATAD2 in regulating chromatin dynamics during spermatogenesis. The authors elegantly demonstrate that ATAD2, via its control of histone chaperone HIRA turnover, ensures proper H3.3 localization, chromatin accessibility, and histone-toprotamine transition in post-meiotic male germ cells. Using a new well-characterized Atad2 KO mouse model, they show that ATAD2 deficiency disrupts HIRA dynamics, leading to aberrant H3.3 deposition, impaired transcriptional regulation, delayed protamine assembly, and defective sperm genome compaction. The study bridges ATAD2's conserved functions in embryonic stem cells and cancer to spermatogenesis, revealing a novel layer of epigenetic regulation critical for male fertility. 

Strengths: 

The MS first demonstration of ATAD2's essential role in spermatogenesis, linking its expression in haploid spermatids to histone chaperone regulation by connecting ATAD2-dependent chromatin dynamics to gene accessibility (ATAC-seq), H3.3-mediated transcription, and histone eviction. Interestingly and surprisingly, sperm chromatin defects in Atad2 KO mice impair only in vitro fertilization but not natural fertility, suggesting unknown compensatory mechanisms in vivo. 

Weaknesses:

The MS is robust and there are not big weaknesses 

Reviewer #3 (Public review): 

Summary: 

The authors generated knockout mice for Atad2, a conserved bromodomain-containing factor expressed during spermatogenesis. In Atad2 KO mice, HIRA, a chaperone for histone variant H3.3, was upregulated in round spermatids, accompanied by an apparent increase in H3.3 levels. Furthermore, the sequential incorporation and removal of TH2B and PRM1 during spermiogenesis were partially disrupted in the absence of ATAD2, possibly due to delayed histone removal. Despite these abnormalities, Atad2 KO male mice were able to produce offspring normally. 

Strengths: 

The manuscript addresses the biological role of ATAD2 in spermatogenesis using a knockout mouse model, providing a valuable in vivo framework to study chromatin regulation during male germ cell development. The observed redistribution of H3.3 in round spermatids is clearly presented and suggests a previously unappreciated role of ATAD2 in histone variant dynamics. The authors also document defects in the sequential incorporation and removal of TH2B and PRM1 during spermiogenesis, providing phenotypic insight into chromatin transitions in late spermatogenic stages. Overall, the study presents a solid foundation for further mechanistic investigation into ATAD2 function. 

Weaknesses:

While the manuscript reports the gross phenotype of Atad2 KO mice, the findings remain largely superficial and do not convincingly demonstrate how ATAD2 deficiency affects chromatin dynamics. Moreover, the phenotype appears too mild to elucidate the functional significance of ATAD2 during spermatogenesis. 

We respectfully disagree with the statement that our findings are largely superficial. Based on our investigations of this factor over the years, it has become evident that ATAD2 functions as an auxiliary factor that facilitates mechanisms controlling chromatin dynamics (see, for example, Morozumi et al., 2015). These mechanisms can still occur in the absence of ATAD2, but with reduced efficiency, which explains the mild phenotype we observed.

This function, while not essential, is nonetheless an integral part of the cell’s molecular biology and should be studied and brought to the attention of the broader biological community, just as we study essential factors. Unfortunately, the field has tended to focus primarily on core functional actors, often overlooking auxiliary factors. As a result, our decade-long investigations into the subtle yet important roles of ATAD2 have repeatedly been met with skepticism regarding its functional significance, which has in turn influenced editorial decisions.

We chose eLife as the venue for this work specifically to avoid such editorial barriers and to emphasize that facilitators of essential functions do exist. They deserve to be investigated, and the underlying molecular regulatory mechanisms must be understood.

(1) Figures 4-5: The analyses of differential gene expression and chromatin organization should be more comprehensive. First, Venn diagrams comparing the sets of significantly differentially expressed genes between this study and previous work should be shown for each developmental stage. Second, given the established role of H3.3 in MSCI, the effect of Atad2 knockout on sex chromosome gene expression should be analyzed. Third, integrated analysis of RNA-seq and ATAC-seq data is needed to evaluate how ATAD2 loss affects gene expression. Finally, H3.3 ChIP-seq should be performed to directly assess changes in H3.3 distribution following Atad2 knockout.  

(1) In the revised version, we will include Venn diagrams to illustrate the overlap in significantly differentially expressed genes between this study and previous work. However, we believe that the GSEAs presented here provide stronger evidence, as they indicate the statistical significance of this overlap (p-values). In our case, we observed p-value < 0.01 (**) and p < 0.001 (***).

(2) Sex chromosome gene expression was analyzed and is presented in Fig. 5C.

(3) The effect of ATAD2 loss on gene expression is shown in Fig. 4A, B, and C as histograms, with statistical significance indicated in the middle panels.

(4) Although mapping H3.3 incorporation across the genome in wild-type and Atad2 KO cells would have been informative, the available anti-H3.3 antibody did not work for ChIP-seq, at least in our hands. The authors of Fontaine et al., 2022, who studied H3.3 during spermatogenesis in mice, must have encountered the same problem, since they tagged the endogenous H3.3 gene to perform their ChIP experiments.

(2) Figure 3: The altered distribution of H3.3 is compelling. This raises the possibility that histone marks associated with H3.3 may also be affected, although this has not been investigated. It would therefore be important to examine the distribution of histone modifications typically associated with H3.3. If any alterations are observed, ChIP-seq analyses should be performed to explore them further.  

Based on our understanding of ATAD2’s function—specifically its role in releasing chromatin-bound HIRA—in the absence of ATAD2 the residence time of both HIRA and H3.3 on chromatin increases. This results in the detection of H3.3 not only on sex chromosomes but across the genome. Our data provide clear evidence of this phenomenon. The reviewer is correct in suggesting that the accumulated H3.3 would carry H3.3-associated histone PTMs; however, we are unsure what additional insights could be gained by further demonstrating this point.

(3) Figure 7: While the authors suggest that pre-PRM2 processing is impaired in Atad2 KO, no direct evidence is provided. It is essential to conduct acid-urea polyacrylamide gel electrophoresis (AU-PAGE) followed by western blotting, or a comparable experiment, to substantiate this claim. 

Figure 7 does not suggest that pre-PRM2 processing is affected in Atad2 KO; rather, this figure—particularly Fig. 7B—specifically demonstrates that pre-PRM2 processing is impaired, as shown using an antibody that recognizes the processed portion of pre-PRM2. ELISA was used to provide a more quantitative assessment; however, in the revised manuscript we will also include a western blot image.

(4) HIRA and ATAD2: Does the upregulation of HIRA fully account for the phenotypes observed in Atad2 KO? If so, would overexpression of HIRA alone be sufficient to phenocopy the Atad2 KO phenotype? Alternatively, would partial reduction of HIRA (e.g., through heterozygous deletion) in the Atad2 KO background be sufficient to rescue the phenotype? 

These are interesting experiments that require the creation of appropriate mouse models, which are not currently available.

(5)The mechanism by which ATAD2 regulates HIRA turnover on chromatin and the deposition of H3.3 remains unclear from the manuscript and warrants further investigation. 

The Reviewer is absolutely correct. In addition to the points addressed in response to Reviewer #1’s general comments (see above), it would indeed have been very interesting to test the segregase activity of ATAD2 (likely driven by its AAA ATPase activity) through in vitro experiments using the Xenopus egg extract system described by Tagami et al., 2004. This system can be applied both in the presence and absence (via immunodepletion) of ATAD2 and would also allow the use of ATAD2 mutants, particularly those with inactive AAA ATPase or bromodomains. However, such experiments go well beyond the scope of this study, which focuses on the role of ATAD2 in chromatin dynamics during spermatogenesis

Reference

Wang T, Perazza D, Boussouar F, Cattaneo M, Bougdour A, Chuffart F, Barral S, Vargas A, Liakopoulou A, Puthier D, Bargier L, Morozumi Y, Jamshidikia M, Garcia-Saez I, Petosa C, Rousseaux S, Verdel A, Khochbin S. ATAD2 controls chromatin-bound HIRA turnover. Life Sci Alliance. 2021 Sep 27;4(12):e202101151. doi: 10.26508/lsa.202101151. PMID: 34580178; PMCID: PMC8500222.

Morozumi Y, Boussouar F, Tan M, Chaikuad A, Jamshidikia M, Colak G, He H, Nie L, Petosa C, de Dieuleveult M, Curtet S, Vitte AL, Rabatel C, Debernardi A, Cosset FL, Verhoeyen E, Emadali A, Schweifer N, Gianni D, Gut M, Guardiola P, Rousseaux S, Gérard M, Knapp S, Zhao Y, Khochbin S. Atad2 is a generalist facilitator of chromatin dynamics in embryonic stem cells. J Mol Cell Biol. 2016 Aug;8(4):349-62. doi: 10.1093/jmcb/mjv060. Epub 2015 Oct 12. PMID: 26459632; PMCID: PMC4991664.

Fontaine E, Papin C, Martinez G, Le Gras S, Nahed RA, Héry P, Buchou T, Ouararhni K, Favier B, Gautier T, Sabir JSM, Gerard M, Bednar J, Arnoult C, Dimitrov S, Hamiche A. Dual role of histone variant H3.3B in spermatogenesis: positive regulation of piRNA transcription and implication in X-chromosome inactivation. Nucleic Acids Res. 2022 Jul 22;50(13):7350-7366. doi: 10.1093/nar/gkac541. PMID: 35766398; PMCID: PMC9303386.

Tagami H, Ray-Gallet D, Almouzni G, Nakatani Y. Histone H3.1 and H3.3 complexes mediate nucleosome assembly pathways dependent or independent of DNA synthesis. Cell. 2004 Jan 9;116(1):51-61. doi:10.1016/s0092-8674(03)01064-x. PMID: 14718166.

This line calls back to the Book of Ezekiel, in two places in Ezek.6. God comes upon Ezekiel, ordering to “prophesy against” the people of Israel, but his words turn from warning with room for correction (Ezek.3) to a fierce threat of immediate destruction: “Behold, I, even I, will bring a sword upon you, and I will destroy your high places. And your altars shall be desolate, and your images shall be broken…and your images may be cut down, and your works abolished.”

This destruction/waste that is to come/comes is not directly at the hands of sin and iniquity; it is at the hands of God, punishing sin and iniquity. This raises again a question of agency. Why aren’t the people of Israel allowed a chance at redemption anymore? What about those born into this way of sin and iniquity?

When Eliot writes, “Son of man, You cannot say, or guess, for you know only A heap of broken images,” it is strongly suggested that whoever Eliot is addressing—“son of man” feels encompassing—is separate from the settling of the waste condition, for it is all they know. God refers to Ezekiel as “son of man,” and it also feels inherently removed with the “son of”—removed from God, but removed from something else, too.

This calls the title back into question, where in my first annotation I explored how there is/could be agency and movement and hope. But perhaps the set-up with “The Waste Land” where “waste” is a noun/subject and “land” a verb is that this landing is a pre-established condition. What hope then?

Beyond the differences between the working and final title of “The Wasteland,” I found the change the epigraph used noteworthy. In most circumstances, an epigraph suggests the general theme or tone of a certain piece– second to the title, it is the first impression a reader has when encountering a work of writing. This implies that the change in the epigraph likely reflected a significant shift in Eliot’s perception of his poem and the message he hoped it to convey.

The working epigraph draws from Heart of Darkness, an 1899 novella by Joseph Conrad. In the moment of this excerpt, the narrator, Charles Marlow, stumbled upon Kurtz, a successful former station chief, on the brink of death. Just as Marlow encounters Kurtz “lying on his back with closed eyes,” Marlow hears him mumble: “‘Live rightly, die, die’” (3). In his nearly unconscious state, Kurtz reveals a newfound clarity in the purpose of one’s life: to live virtuously (likely following Christian values), so that he may die peacefully and move weightlessly into the next realm of existence. However, just before Kurtz passes, and just before he exclaims “‘The horror! the horror!”, Marlow notes a significant turn of expression on the dying man’s face: an “expression of sombre pride, of ruthless power, of craven terror– of an intense and hopeless despair” (4). This moment illustrates a the process of realization undergone by Kurtz in his final moments: first, his satisfaction in his life’s achievements; then, a surge of power and authority in remembering his esteemed working position; and terror in realizing that his life and choices have not been so righteous as he formerly believed them to be. This leads to his final statement: “‘the horror, the horror!’” (4). While the new version of the epigraph suggests a kind of longing for death after enduring the consequences of a youthless immortality, the old epigraph expresses a different kind of anguish: the despair and horror when one comes to the realization of living a wasted, and in some ways dishonest, life.

Author response:

The following is the authors’ response to the original reviews.

Reviewer #1 (Public review):

Summary:

Desveaux et al. describe human mAbs targeting protein from the Pseudomonas aeruginosa T3SS, discovered by employing single cell B cell sorting from cystic fibrosis patients. The mAbs were directed at the proteins PscF and PcrV. They particularly focused on two mAbs binding the T3SS with the potential of blocking activity. The supplemented biochemical analysis was crystal structures of P3D6 Fab complex. They also compared the blocking activity with mAbs that were described in previous studies, using an assay that evaluated the toxin injection. They conducted mechanistic structure analysis and found that these mAbs might act through different mechanisms by preventing PcrV oligomerization and disrupting PcrVs scaffolding function.

Strengths:

The antibiotic resistance crisis requires the development of new solutions to treat infections caused by MDR bacteria. The development of antibacterial mAbs holds great potential. In that context, this report is important as it paves the way for the development of additional mAbs targeting various pathogens that harbor the T3SS. In this report, the authors present a comparative study of their discovered mAbs vs. a commercial mAb currently in clinical testing resulting in valuable data with applicative implications. The authors investigated the mechanism of action of the mAbs using advanced methods and assays for the characterization of antibody and antigen interaction, underlining the effort to determine the discovered mAbs suitability for downstream application.

Weaknesses:

Although the information presented in this manuscript is important, previous reports regarding other T3SS structures complexed with antibodies, reduce the novelty of this report. Nevertheless, we provide several comments that may help to improve the report. The structural analysis of the presented mAbs is incomplete and unfortunately, the authors did not address any developability assessment. With such vital information missing, it is unclear if the proposed antibodies are suited for diagnostic or therapeutic usage. This vastly reduces the importance of the possibly great potential of the authors' findings. Moreover, the structural information does not include the interacting regions on the mAb which may impede the optimization of the mAb if it is required to improve its affinity.

As described in the manuscript (Fig. 6), our mAbs are markedly less effective in every in vitro T3SS inhibition assay than the mAbs recently described by Simonis et al. They are therefore very unlikely to outperform these mAbs in in vivo animal models of P. aeruginosa infection. Considering the high cost of animal experiments and ethical concerns-and in accordance with the Reduction principal of the 3Rs guidelines-we chose not to pursue in vivo experiments. Instead, we focused on leveraging the new isolated mAbs to investigate the mechanisms of action and structural features of anti-PcrV mAbs.

Following the reviewer's suggestion, we have now added mAb interaction features into the structural data presented in the manuscript. However, based on the efficiency data, the structural analysis and the mechanistic insights presented, we do not consider further therapeutic use and optimization of our mAbs to be warranted.

Reviewer #2 (Public review):

Summary:

Desveaux et al. performed Elisa and translocation assays to identify among 34 cystic fibrosis patients which ones produced antibodies against P. aeruginosa type three secretion system (T3SS). The authors were especially interested in antibodies against PcrV and PcsF, two key components of the T3SS. The authors leveraged their binding assays and flow cytometry to isolate individual B cells from the two most promising sera, and then obtained monoclonal antibodies for the proteins of interest. Among the tested monoclonal antibodies, P3D6 and P5B3 emerged as the best candidates due to their inhibitory effect on the ExoS-Bla translocation marker (with 24% and 94% inhibition, respectively). The authors then showed that P5B3 binds to the five most common variants of PcrV, while P3D6 seems to recognize only one variant. Furthermore, the authors showed that P3D6 inhibits translocon formation, measured as cell death of J774 macrophages. To get insights into the P3D6PcrV interaction, the authors defined the crystal structure of the P3D6-PcrV complex. Finally, the authors compared their new antibodies with two previous ones (i.e., MEDI3902 and 30-B8).

Strengths:

(1) The article is well written.

(2) The authors used complementary assays to evaluate the protective effect of candidate monoclonal antibodies.

(3) The authors offered crystal structure with insights into the P3D6 antibody-T3SS interaction (e.g., interactions with monomer vs pentamers).

(4) The authors put their results in context by comparing their antibodies with respect to previous ones.

Weaknesses:

The authors used a similar workflow to the one previously reported in Simonis et al. 2023 (antibodies from cystic fibrosis patients that included B cell isolation, antibody-PcrV interaction modeling, etc.) but the authors do not clearly explain how their work and findings differentiate from previous work.   

We employed a similar mAb isolation pipeline to that used by Simonis et al., beginning with the screening of a cohort of cystic fibrosis patients chronically infected with P. aeruginosa. As in Simonis et al., we isolated specific B cells using a recombinant PcrV bait, followed by single-cell PCR amplification of immunoglobulin genes. The main differences in methodology between the two studies are as follows: i) the use of individuals from different cohorts, and therefore having different Ab repertoires; ii) the nature of the screening assays, although in both cases the screening was focused on the inhibition of T3SS function; iii) the PcrV labeling strategy, with Simonis et al. employing direct labeling, whereas we used a biotinylated tag combined with streptavidin;

The number of specific mAbs obtained and produced was higher in Simonis et al. (47 versus 9 in our study). They sorted B cells from three individuals compared to two in our work and possibly started with a larger amount of PBMCs per donor, which may account for the higher number of specific B cells and mAbs isolated. Considering that the strategies were overall very similar, the greater number of mAbs isolated in Simonis et al. likely explains, to a large extent, why they identified mAbs targeting different epitopes compared to ours, including highly potent mAbs that we did not recover. 

Our modeling study, unlike that of Simonis et al., which relied on an AlphaFold prediction of the multimeric structure of P. aeruginosa PcrV, was based on the experimentally determined structure of the homologous Salmonella SipD pentamer, as described in the manuscript. Furthermore, we compared our mAb P3D6 not only with 30-B8 from Simonis et al., but also with MEDI3902. Finally, in contrast to the approach of Simonis et al., we used functional assays to investigate the differences in mechanisms of action among these mAbs, which target three distinct epitopes.

(2) Although new antibodies against P. aeruginosa T3SS expand the potential space of antibodybased therapies, it is unclear if P3D6 or P5B3 are better than previous antibodies. In fact, in the discussion section authors suggested that the 30-B8 antibody seems to be the most effective of the tested antibodies.  

As explained above and shown in the Results section (Figure 6), the 30-B8 mAb is markedly more effective at inhibiting T3SS activity in both in vitro assays used.

(3) The authors should explain better which of the two antibodies they have discovered would be better suited for follow-up studies. It is confusing that the authors focused the last sections of the manuscript on P3D6 despite P3D6 having a much lower ExoS-Bla inhibition effect than P5B3 and the limitation in the PcrV variant that P3D6 seems to recognize. A better description of this comparison and the criteria to select among candidate antibodies would help readers identify the main messages of the paper. 

The P3D6 mAb shows stronger inhibitory activity than P5B3 in the two assays used, as shown in Supplementary Figure 1. An error in the table in Figure 2B was corrected and this table now reflects the results presented in Supplementary Figure 1. 

The final sections of the manuscript focus on P3D6, which is more potent than P5B3, and for which we successfully determined a co-crystal structure with PcrV*. All parallel attempts to obtain a structure of P5B3 in complex with PcrV* failed. The P3D6-PcrV* structure was used to analyze epitope recognition and mechanisms of action in comparison to previously described mAbs. As previously mentioned, we do not consider further studies aimed at therapeutic development and optimization of our mAbs to be justified given the current data. Therefore, we believe that the main message of the paper is adequately captured in the title.

(4) This work could strongly benefit from two additional experiments:

(a) In vivo experiments: experiments in animal models could offer a more comprehensive picture of the potential of the identified monoclonal antibodies. Additionally, this could help to answer a naïve question: why do the patients that have the antibodies still have chronic P. aeruginosa infections? 

As explained above, the mAbs we isolated are significantly less potent than those described by Simonis et al., and are therefore unlikely to outperform the best anti-PcrV candidates in vivo. In light of the data, and considering ethical concerns related to animal use in research and budgetary constraints, we decided not to proceed with in vivo experiments.

There are a number of reasons that may explain why patients with anti-PcrV Abs blocking the T3SS can still be chronically infected with Pa. First these Abs may be at limiting concentration, particularly in sites where Pa replicates, and thus unable to clear infection. in addition, it has been described that the T3SS is downregulated in chronic infection in cystic fibrosis patients. This suggests that a therapeutic intervention with T3SS inhibiting Abs may be more efficient if done early in cystic fibrosis patients to prevent colonization when Pa possesses an active T3SS. Finally, T3SS is not the only virulence mechanism employed by P. aeruginosa during infection. Indeed, multiple protein adhesins and polysaccharides are important factors facilitating the formation of bacterial biofilms that are crucial for establishing chronic persistent infection. In this regard, a combination of Abs targeting different factors on the P. aeruginosa surface may be needed to treat chronic infections.  

(b) Multi-antibody T3SS assays (i.e., a combination of two or more monoclonal antibodies evaluated with the same assays used for characterization of single ones). This could explore the synergistic effects of combinatorial therapies that could address some of the limitations of individual antibodies. 

Given the high potency of the Simonis mAbs and the mechanisms of action highlighted by our analysis, it is unlikely that our mAbs would synergize with those described by Simonis. Additionally, since our two mAbs cross-compete for binding, synergy between them is also improbable.

Reviewer #1 (Recommendations for the authors):

Line 166: How was the serum-IgG purified? (e.g., protein A, protein G). 

Protein A purification was used, as now mentioned in the manuscript. Purified Igs were thus predominantly IgG1, IgG2 and IgG4, as indicated.

(2) Line 196: When mentioning affinities, it is preferable to present in molar units. 

To facilitate comparisons, Ab concentrations were presented in µg/mL as in Simonis et al.

(3) Line 206: The author states that P3D6 displays significantly reduced ExoS-Bla injection (Figure 2B), but according to the presented table, ExoS-Bla inhibition was higher for P5B3. Additionally, when using "significantly", what was the statistical test that was used to evaluate the significance? Please clarify.

We thank the reviewer for pointing out this inconsistency. Indeed, the names of P3D6 and P5B3 were exchanged when building the table related to Figure 2B. The corrected version of this figure is now presented in the new version of the manuscript. An ANOVA was performed to evaluate the significance of the observed difference (adjusted p-values < 0.001) and it is now mentioned in the figure caption.  

(4) Line 215: "P3B3" typo.

This was corrected.

(5) Figure 3B: Could the author explain the higher level of ExoS-Bla injection when using VRCO1 antibody compared to no antibody.  

A slightly higher level of the median is observed in the case of three variants out of five. However, this difference is not statistically significant (p-value > 0.05).

(6) Supplement Figure 1: the presented grey area is not clear (is it the 95%CI?) and how was the IC50 calculated? With what model was it projected? Are the values for IC50 beyond the 100µg/mL mark a projection? It seems that projecting such greater values (such as the IC50 of over 400µg/mL for variant 5) is prone to high error probability.

The grey area represents the 95% confidence interval (95% CI) and it is now mentioned in the figure caption. The IC50 and 95% CI were both inferred by the dose-response drc R package based on a three-parameters log-logistic model and it is now explained in the Materials & Methods section. The p-values for IC50 beyond the 100µg/mL were below 0.05 but we agree that such extrapolation should be considered with precaution (see below our response to comment number 7).

(7) Line 227: The author describes that P5B3 has similar IC50 values towards variants 1-4, but the  IC50 towards variant 5 is substantially higher with 400µg/mL, albeit the only difference between variant 4 and 5 is the switch position 225 Arg -> Lys which are very similar in their properties. Please provide an explanation. 

As explained in our response to comment number 6, we agree that the comparison of IC50 that are estimated to be close or higher than the highest experimental concentration is somehow speculative. Indeed, we performed further statistical analysis that showed no significant difference between the IC50 toward the five PcrV variants of mAb P5B3. In contrast, the difference between the IC50 of mAbs P5B3 and P3D6 toward variant 1 is statistically significant. This is now explained in the manuscript.

(8) Line 233: Pore assembly: It is not clear how the data was normalized. The authors mention the methods normalization against the wildtype strain in the absence of antibodies, but did not elaborate clearly if the mutant strain has the same base cytotoxicity as the wild type. It would be helpful to show the level of cytotoxicity of the wild type compared to the mutant in the absence of antibodies to understand the baseline of cytotoxicity of both strains.  

In these experiments we did not use the wild-type strain. As explained, the only strain that allows the measurement of pore formation by translocators PopB/PopD is the one lacking all effectors. All the experiments were done with this strain, and all the measurements were normalized accordingly. 

(9) Figure 4: The explanation is redundant as it is clearly stated in the results. It would be better for the caption to describe the figure and leave interpretation to the results section. Overall, this comment is relevant to all figure captions, as it will reduce redundancy. My suggestion is to keep the figure caption as a road map to understand what is shown in the figure. For example, the Figure 4 caption should include that the concentration is presented in logarithmic scale, what is the dashed line, what is the grey area (what interval does it represent?), what each circle represents, and what is the regression model used? 

Figure captions have been improved as suggested. 

(10) Line 432: The authors apparently misquoted the original article describing the chimeric form PcrV* by describing the fusion of amino acids 1-17 and 136-249. I quote the original article by Tabor et al. "[...] we generated a truncated PcrV fragment (PcrVfrag) comprising PcrV amino acids 1-17 fused to amino acids 149-236 [...]". Additionally, how does the absence of amino acid 21 in the variant affect the conclusion? 

Our construct was inspired by the one described in Tabor et al. but was not identical. We have therefore replaced "was constructed based on a construct by Tabor et al." for "whose design was inspired by the construct described in Tabor et al."

Amino acid 21 is only absent in the construct used for crystallization experiments; all other experiments looking at Ab activity were performed with bacteria bearing full-length PcrV. The difference in P3D6 activity between variants V1 and V2-appears to be explained by the nature of the residue at position 225, according to the structural data, as explained now in more detail in the manuscript. Accordingly, the difference in efficiency of P3D6 against the V1 and V2  variants is explained by the residue at position 225, as both variants have the same residue at position 21. However, while the nature of the residue at position 225 appears to explain the absence of efficiency of the Ab for the variants studied, an impact of residue 21 could not be totally ruled out in putative variants with a Ser at 225 but different amino acids at 21.

(11) Line 569: Missing word - ESRF stands for European Synchrotron Radiation Facility. 

This has been corrected.

(12) Line 268-269 (Figure 5A): The description of the alpha helices in relation to the figure is incomplete. Helices 2,3 and 5 are not indicated. 

Indeed, since the structure is well-known and in the interest of visibility and simplicity, we only included the most relevant secondary structure features.

(13) Line 271-272: It would be good to elaborate on the exact binding platform between LC and HC of the Fab and the residues on the PcrV side. For example, the author could apply the structure to PDBePISA (EMBL-EBI) which will provide details about the interface between the PcrV and the antibody. It is very interesting to learn what regions of the antibody are in charge of the binding, such as: is the H-CDR3 the major contributor of the binding or are other CDRs more involved? Additionally, in line 275 they state that the substitution of Ser 225 with Arg or Lys is consistent with the P3D6 insufficient binding. What contributed to this result on the antibodies side? 

In order to address this question, we are now providing a LigPlot figure (supplementary Figure 3) in which specific interactions between PcrV* and the Fab are shown.

(14) Line 291: It is unclear from what data the authors concluded that anti-PscF targets 3 distinct regions of PscF. 

The data are shown in Supplementary Table 2, as mentioned in the manuscript. We have now modified the order of the anti-PcrV mAbs in the table to better illustrate the three identified epitope clusters (Sup table 2). Similarly, the anti-PscF mAbs appear to group into three clusters as P3G9 and P5E10 only compete with themselves, while mabs P3D6 and P5B3 compete with themselves and each other.

(15) Line 315: It is preferable to introduce results in the results section instead of the discussion. 

While preparing the manuscript, we initially included these results as a separate paragraph in the Results section, but ultimately chose the current format to improve flow and avoid redundancy.

(16) Supplement Figure 2: What was the regression model used to evaluate IC50, and what is presented in the graph? What is the dashed line (see comment for Figure 4 above)? 

The regression is based on a three-parameters log-logistic model and the light-colors area correspond to the 95% IC. The dashed lines visually represents 100% of ExoS-Bla injection. These information are now mentioned in the figure caption.

(17) Figure 6B: It would be better to show an additional rotation of the PcrV bound by Fab 30-B8 that corresponds to the same as the one represented with Fab MEDI3092. This would clear up the differences in binding regions. Same for Fab P3D6. 

Figure 6 already depicts two orientations. Despite the fact that we agree that additional orientations could be of interest, we believe that this would add unnecessary complexity to the figure, and would prefer to maintain the figure as is, if possible.

(18) Line 356-358: The author proposes an experiment to support the suggested mechanism of P3D6, it would follow up with a bio-chemical analysis showing the prevention of PcrV oligomerization in its presence. 

We understand the reviewers’ comment regarding the potential use of biochemical approaches to test our hypothesis. However, this not currently feasible as we have been unable to achieve in vitro oligomerization of PcrV alone, possibly due to the absence of other T3SS components, such as the polymerized PscF needle.

(19) Line 456: Missing details about how the ELISA was conducted including temperature, how the antigen was absorbed, plate type, etc. 

Experimental details have been added.

(20) Line 460: Missing substrate used for alkaline phosphatase. 

The nature of the substrate was added to the methods.

DOI: 10.1016/j.celrep.2025.116298

Resource: (MBL International Cat# K0205-3, RRID:AB_592934)

Curator: @scibot

SciCrunch record: RRID:AB_592934

What is this?

/ ♖/ hyperpost/ 🎭/ gyuri/ do/ web/ search/ via/ google.com/ 📅/ 20/ 25/ 09/ 3

https://bafybeihqknys5nxcauptrrhy5iq645r6ozi66sqr2di7w3mwfgzkaiea6a.ipfs.dweb.link?filename=%EF%BC%82high%20performant%20neuro%20diversity%EF%BC%82.html

search.tag~write-to-think

🧊/ ♖/ hyperpost/ 🎭/ gyuri/ do/ web/ search/ via/ hypothes.is/ tag/ 📅/ 20/ 25/ 09/ 3/ hypothes.is-tag-write-to-think.html

indy0

dweb.link

ipfs.io

"The 2024 Report, ADAPT, ADVANCE, ACHIEVE" is a recurring video that moves very quickly and might be overstimulating to some viewers, as it repeats every 3 seconds.

The yellow bars and the white “ACHIEVE” text overlap in a way that makes the letters hard to distinguish. According to WCAG guidelines, sufficient colour contrast is essential for perceivability. For someone with colour blindness or low vision, this text may be nearly invisible.

"The 2024 Report, ADAPT, ADVANCE, ACHIEVE" is a recurring video that moves very quickly and might be overstimulating to some viewers, as it repeats every 3 seconds.

The yellow bars and the white “ACHIEVE” text overlap in a way that makes the letters hard to distinguish. According to WCAG guidelines, sufficient colour contrast is essential for perceivability. For someone with colour blindness or low vision, this text may be nearly invisible.

Bad: Low contrast in parts of the climate chart (pale colours and small labels). For people with low vision or colour-vision issues, pale colours + small text make reading hard. The chart needs stronger contrast and legible fonts.

The employer must genuinely believe that the qualification is essential to the job. The decision must be based on objective evidence, and the employer has explored reasonable accommodations.If a company requires airline pilots to have perfect vision, it must honestly and in good faith demonstrate that this requirement is reasonably necessary for safety—not just a preference or assumption.

This principle ensures that BFOQs are used narrowly and responsibly, protecting both business needs and employee rights.

Indirect descrimination - Height and weight may relate to disability or specific ethnic groups. Using postal codes may amount to systemic discrimination as it may relate to race, ancestry, or place of origin. Tribunals will consider impact, not just intent. Even if a category isn't listed, if the effect of a policy or decision result in unfair treatment of a protected group, it can still be challenged. Increasingly courts recognize intersectionality and implicit bias.

Annotation #3: The homepage provides a “Translate” option, allowing visitors to view content in multiple languages. This feature is especially helpful for newcomers or individuals with limited English proficiency. According to the Understandable principle, information and the operation of the user interface must be understandable. This means users must be able to comprehend the information being presented, and translation ensures that important city content is not beyond their understanding. Providing language options makes the site more inclusive and represents a strong accessibility practice.

At Ontario Health we use Gap Analysis quite often, one example is the Home First Resource Guide/toolkit. Our current state was a fragmented toolkit with outdated content from 2011. The desired state was a modern, equity-informed guide aligned with ALC Leading Practices and the Transitions Quality Standard. By laying the two side by side, we could see the gaps, missing caregiver engagement tools, outdated role definitions, and lack of standardized discharge planning templates. That gap analysis has been driving the work of our cross-regional planning teams.

There are 3 types of cognitive load: Intrinsic, Extraneous, and Germane. Intrinsic cognitive load is the learning difficulty of the content. Extraneous cognitive load is learning difficulty of the material based on the learning environment. Germane cognitive load is the amount of mental work it is to store and process information into your already existing mental models.

source: https://thedecisionlab.com/reference-guide/psychology/cognitive-load-theory

Groupon shows deals with countdown timers—“Deal ends in 3 hours!” to push users to act quickly, leveraging loss aversion.

E-Commerce Urgency: Amazon shows “Only 3 left in stock!” or “Deal ends in 2 hours.”

Decoy Pricing: A company might introduce a premium product with a very high price to make a more moderately priced product seem like a bargain. For example, a bakery sells a small cupcake for $3, a medium one for $5, and a comically large one for $15. The $15 cupcake is the anchor; its purpose isn't to be sold but to make the $5 cupcake look like a much better value, increasing its sales.

Too many options can overwhelm users. For example, choosing between 3 products is quicker than choosing between 20

is the third dimension time? or are you getting a 3d reconstruction from the hologram?

Hi, I found this study to be interesting and potentially very impactful for diagnostic needs, as you mention. I have a few questions: 1. Do you have any insights into which timepoints or periods were the most useful (or most noisy) for your training purposes? 2. Do you know whether introducing imaging steps every 30 minutes may have had any effects on colony growth patterns? 3. For the species/strains that were most difficult to predict, do you have any idea what factors may have contributed to this, i.e. technical difficulties in holography, heterogeneity within or across colonies, etc Thank you!

Coffee is said to be good for students because it stimulates their mind and assists in their studying, unless they experience severe side effects. Some people claim black tea is a better option as it has less side effects, but black tea still has side effects and doesn't provide the same stimulation as coffee. Others feel that any mental stimulation only encourages addiction; however, this argument has no basis because with the same logic, thirst for water would result in addiction. Enjoy coffee in moderation to boost your productivity and make your work more enjoyable.

Note: This response was posted by the corresponding author to Review Commons. The content has not been altered except for formatting.

Learn more at Review Commons

Reply to the reviewers

• *

1. General Statements [optional]

This section is optional. Insert here any general statements you wish to make about the goal of the study or about the reviews.

• *We appreciate the reviewers' assessment of the significance of our work and would like to highlight where we believe the novelty of this study lies. Our findings identify E4BP4 as a key transcription factor that maintains mitochondrial homeostasis by restraining the overactivation of biological pathways - such as de novo ceramide synthesis - that are known to drive mitochondrial oxidative dysfunction in the context of obesity. We fully acknowledge that the link between C16:0 ceramide and mitochondrial fragmentation has been previously established. However, to our knowledge, our study is the first to connect this phenomenon to a transcriptional safeguard mechanism, thereby providing a new layer of understanding of how transcription factors preserve mitochondrial integrity and function in brown adipocytes. We believe this conceptual advance adds significant value to the field by framing E4BP4 as a transcriptional "guardian" of mitochondrial homeostasis.

2. Description of the planned revisions

Insert here a point-by-point reply that explains what revisions, additional experimentations and analyses are planned to address the points raised by the referees.

• *Reviewer #1 comment:

Figures B: Sample size of EE experiments is too low to draw any meaningful conclusions or to know for certain if the data are reproducible. Small sample sizes, likely coming from one litter and one batch of AAV are prone to type I error.

Response: We agree with reviewer observation that increasing sample size is essential to confirm reproducibility and robustness. We have therefore planned to repeat the EE experiments with a larger number of mice per group, derived from independent litters and AAV preparations, in order to strengthen the statistical power and validate the phenotype observed in the current study.

Reviewer #1 comment:

Figure 3I: Why do cells (none of the groups) show no response to NE stimulation? Please clarify or provide potential mechanistic insight. Perhaps the cells were not differentiated well.

__ ____Response:__ We agree that the absence of a robust NE response in Figure 3I requires further clarification. To address this, we have planned to repeat the in vitro oxygen consumption assay to confirm the phenotype presented in the study.

Reviewer #1 comment: Figures 3I vs 5N. There is a striking discrepancy between these panels. In both, cells were treated with palmitate for 6 h, yet the NE and CCCP responses differ significantly. Are these the same cell types and conditions? Please reconcile the differences.

Response: We would like to clarify that Figures 3I and 5N represent different experimental systems: Figure 3I shows data from primary brown adipocytes with E4bp4 transgene overexpression, whereas Figure 5N shows data from immortalized brown adipocytes with Cas9-mediated mutation of a 65 kb Cers6 enhancer site. Given the distinct cell types and genetic manipulations, a direct comparison between these two panels is not appropriate. Nevertheless, we agree that confirming the consistency of the phenotype across systems is important. To address this, we have planned to repeat oxygen consumption assays in both models to further validate the reproducibility of the observed effects.

Reviewer #2 comment: A key experiment is missing: does adding C16:0 block the mitochondrial benefits of E4BP4-OE?

Response: We thank the reviewer for this excellent suggestion. We agree that a rescue experiment is important to directly test whether C16:0 affects the mitochondrial benefits of E4BP4. To address this, we have planned to perform a co-overexpression of E4bp4 and Cers6 in brown adipocytes. The readouts will include mitochondrial morphology and oxygen consumption, enabling us to determine whether restoration of C16:0 production mitigates the protective mitochondria effects of E4BP4 overexpression. This experiment will provide direct mechanistic confirmation of the proposed model.__ __

__Reviewer #2 comment: __Whether PRDM16-OE mimics the effects of E4BP4 to induce p-Drp1 is not shown.

__Response: __We thank the reviewer for this valuable suggestion. We agree that testing whether PRDM16 overexpression mimics the effects of E4BP4 on p-Drp1 is important to strengthen the mechanistic link between these transcription factors in terms of regulation of mitochondrial fragmentation. To address this, we have planned to include a Western blot analysis of p-Drp1 in the PRDM16-OE in brown adipocytes.

3. Description of the revisions that have already been incorporated in the transferred manuscript

Please insert a point-by-point reply describing the revisions that were already carried out and included in the transferred manuscript. If no revisions have been carried out yet, please leave this section empty.

• *Reviewer #1 comment:

Figure 1F: There is an unexpected dip in gene expression at cold exposure days 3 and 7, followed by a rebound at day 14. Is this fluctuation biologically meaningful or technical?

Response: We thank the reviewer for this thoughtful observation. A previous study demonstrated that E4bp4 (Nfil3) expression displays an early increase (at 2 hours), followed by a decrease in magnitude - while still remaining significantly higher than control - during beige adipocyte differentiation in response to forskolin treatment (DOI: 10.1016/j.molmet.2022.101619). The authors of that study suggested that E4bp4 may contribute to a second wave of cAMP-driven beige adipocyte differentiation. However, in the context of our work, further discussion on whether the fluctuations in BAT E4bp4 expression observed during cold exposure reflect biological regulation would be speculative. Importantly, despite these oscillations across time points, E4bp4 expression remained statistically significant compared with control, supporting the robustness of our findings. We have now introduced this observation in the Results section of the revised manuscript.

Reviewer #1 comment: Figures 2H and 2I (GTT): How was the AUC calculated? The GTT and ITT curves appear largely parallel aside from fasting differences. If total AUC was used instead of incremental AUC, it may overstate group differences. The recommended method is outlined in [DOI: 10.1038/s42255-021-00414-7]. Also, since insulin's half-life is ~10 minutes, later differences in the ITT curve likely reflect counterregulatory responses driven by hepatic gluconeogenesis.

Response: We would like to clarify that in our original manuscript we had already calculated the area of the curve (AOC) rather than the area under the curve (AUC), following the recommended approach (DOI: 10.1038/s42255-021-00414-7). Specifically, the AOC was derived by subtracting the baseline glucose value from each subsequent time point, ensuring that the analysis reflects incremental changes rather than absolute glucose levels. We have now made this description more explicit in the revised version to avoid any ambiguity.

__Reviewer #1 comment: __Figure 4F: How was mitochondrial fragmentation quantified? Please ensure that the ROI boxes shown in zoomed panels match the same region in size and shape - this applies throughout the manuscript.

__ _Response: _We thank the reviewer for this valuable comment. To improve the quality and interpretation of the data, we have now included a quantitative analysis of mitochondrial morphology parameters associated with Figure 4F (Figure S4B)__. Specifically, we analyzed:

• Mitochondrial volume (µm³): reflecting overall mitochondrial size.
• Surface area (µm²): reflecting membrane expansion.
• Sphericity index: indicating morphological rounding, which increases with fragmentation.
• Number of branches and branch junctions per mitochondrion: reflecting mitochondrial networking and fusion. Myriocin treatment preserved mitochondrial volume and surface area, reduced sphericity, and increased both the number of branches and branch junctions, reflecting maintenance of a more interconnected mitochondrial network.

Additionally, we verified that the ROI boxes shown in the zoomed panels are consistent in both size and shape across groups, as requested. We have now introduced this observation in the Methods section of the revised manuscript.

__ ____Reviewer #1 comment: __Figure 3A: The claim that one group contains smaller mitochondria is not convincing. Both small and elongated mitochondria appear in each group. Moreover, it is unclear whether these minor differences are of any physiological relevance or whether they drive phenotypes.

Response: We respectfully disagree with this observation and would like to clarify a few points.

1. We have already demonstrated a statistically significant difference in mitochondrial length between E4bp4-OE and control groups (Figures 3B and 3C). This was based on a random, unbiased analysis, which consistently confirmed longer mitochondria in E4bp4-OE compared with control.

Some degree of variability in mitochondrial length is expected in electron microscopy analyses, particularly because mitochondria from multiple cell types within iBAT are captured. It is important to note that the protective action of E4bp4 against mitochondrial fragmentation occurs specifically in brown adipocytes, where the transgene is expressed under the control of the adiponectin promoter.

To address the potential confounding heterogeneity of iBAT mitochondria, we performed complementary cell-autonomous analyses in vitro, allowing us to directly compare mitochondrial dynamics in E4bp4-OE versus control brown adipocytes. This analysis further confirmed that E4bp4-OE prevents lipid overload - induced mitochondrial fragmentation in brown adipocytes.

Finally, we emphasize that several studies have demonstrated that changes in mitochondrial dynamics, particularly under high-fat diet conditions, disrupt systemic energy homeostasis (DOI: 10.1016/j.cmet.2017.05.010; DOI: 10.1016/j.cell.2019.05.008; DOI: 10.1038/s42255-024-00978-0). Therefore, the differences we report are biologically meaningful in the broader context of mitochondrial dynamics and metabolic disease.

__Reviewer #1 comment: __Figure 3E: The claim that confocal microscopy reveals palmitate-induced mitochondrial fragmentation is difficult to discern. The images lack clear morphological differences.

__ _Response: _We thank the reviewer for this observation. To improve the interpretation of these results, we have now included a quantitative analysis of mitochondrial morphology parameters associated with Figure 3E.__ Specifically, we measured:

• __Mitochondrial volume (µm³): __reflecting overall mitochondrial size.
• __Surface area (µm²): __reflecting membrane expansion.
• __Sphericity index: __indicating morphological rounding, which increases with fragmentation.
• Number of branches and branch junctions per mitochondrion: __reflecting mitochondrial networking and fusion. __ __As shown in the new analysis (Figure S4A)__, palmitate treatment reduced mitochondrial volume, surface area, branches, and branch junctions, while increasing sphericity, consistent with a more fragmented phenotype in control cells. In contrast, these effects were significantly attenuated in E4bp4-OE cells, supporting our conclusion that E4BP4 overexpression protects against lipid overload-induced mitochondrial fragmentation. This text was added in the Results section of the revised manuscript.

We believe this additional analysis strengthens the robustness of our findings and provides clear quantitative evidence for the morphological changes that were less apparent from qualitative image inspection alone.

__Reviewer #1 comment: __Figure 3G: Dendra2-labeled mitochondria appear unaffected by palmitate, raising concern about the robustness of the effect across readouts.

__ _Response: _We respectfully disagree with this observation. As shown in Figure 3G__ (bar graphs), palmitate-treated brown adipocytes exhibited a clear reduction in mitochondrial co-localization, which reflects lower levels of fused mitochondria, in the control group compared with E4bp4-OE. Importantly, no difference in mitochondrial co-localization was observed between the two groups under vehicle-treated conditions. This indicates that E4bp4 overexpression does not promote mitochondrial fusion per se, but rather prevents lipid overload - induced mitochondrial fragmentation. We also note that the representative images presented in Figure 3G are single snapshots taken from a time-lapse assay of mitochondrial dynamics. To further illustrate this effect, we direct the reviewer to the supplementary video accompanying this experiment, which clearly demonstrates the differences in mitochondrial behavior over time.

__ ____Reviewer #1 comment: __Figure 5H: Were E4BP4 expression levels equivalent between WT and mutant cells? Quantification should be shown. Figure 5H: Were E4BP4 expression levels equivalent between WT and mutant cells? Quantification should be shown.

Response: __We thank the reviewer for this important point. We have now added the quantification of E4bp4 mRNA levels in cells transduced with either the non-mutated vector (control) and the vector carrying a mutation in the E4bp4 DNA-binding domain (Figure S5)__. The data show no significant difference in E4bp4 expression between the two groups.

__Reviewer #2 comment: __The evidence of mitochondrial fragmentation is not convincing. In the reviewer's opinion, Figures 3E, 3G, 4F, and 5M demonstrated a decrease in mitochondrial quantity, but not fragmentation.

Response: __We thank the reviewer for this observation. We have already addressed the comments from reviewer #1 (above) regarding Figures 3E, 3G and 4F related to measurements of mitochondria fragmentation. To strengthen the interpretation of these results, we have also performed a quantitative analysis of mitochondrial morphology parameters associated with __Figure 5M. Specifically, we measured:

• __Mitochondrial volume (µm³): __reflecting overall mitochondrial size.
• __Surface area (µm²): __reflecting membrane expansion.
• __Sphericity index: __indicating morphological rounding, which increases with fragmentation.
• Number of branches and branch junctions per mitochondrion: __reflecting mitochondrial networking and fusion. As shown in the new analysis (Figure S4C), palmitate treatment significantly reduced mitochondrial volume, surface area, and branching, while increasing sphericity, consistent with enhanced mitochondrial fragmentation in control cells. Notably, these changes were significantly blunted in the Cers6 enhancer edited cells (EΔ), supporting our conclusion that disruption of Cers6 protects against lipid overload-induced mitochondrial fragmentation. __This text was added in the Results section of the revised manuscript.

Regarding the reviewer's understanding of a "decrease in mitochondrial quantity, but not fragmentation," we respectfully disagree. The analyses performed for Figures 3E, 3G, 4F, and 5M clearly demonstrate that E4bp4 overexpression (E4bp4-OE) prevents lipid overload -induced mitochondrial fragmentation.

In relation to mitochondrial quantity, our data do not support differences in mitochondrial biogenesis between groups. Specifically, the expression of thermogenic and mitochondrial biogenesis genes (Figure S2G) as well as the mitochondrial-to-nuclear DNA ratio (Figure S3D) showed no significant changes, indicating that mitochondrial biogenesis is not altered.

Alternatively, it is possible that E4bp4 prevents mitophagy, as our results (Figure 3H) show that E4bp4-OE protects against lipid overload-induced mitochondrial depolarization. In this regard, previous studies have demonstrated that fragmented and depolarized mitochondria are targeted for degradation through mitophagy (DOI: 10.2337/db07-1781; DOI: 10.1074/jbc.M111.242412). While this explanation is consistent with our findings, we acknowledge that it remains speculative at this stage and, although interesting, is beyond the scope of the current study.

__Reviewer #2 comment: __It is confusing whether the association shown in Figure 1C is a positive or an inverse association.

Response: __We thank the reviewer for pointing out this source of confusion. __Figure 1C represents common variant associations for E4BP4, where the y-axis indicates the strength of association (-log10 p-value) rather than the direction (positive or inverse) of the effect. We have clarified this in the revised manuscript to avoid misinterpretation. The associations indicate that genetic variants in E4bp4 are positively linked with anthropometric traits such as weight, BMI, and waist-hip ratio.

5. Description of analyses that authors prefer not to carry out

*Please include a point-by-point response explaining why some of the requested data or additional analyses might not be necessary or cannot be provided within the scope of a revision. *

This can be due to time or resource limitations or in case of disagreement about the necessity of such additional data given the scope of the study. Please leave empty if not applicable.

• *Reviewer #2 comment:

It would be worthwhile to investigate whether in vivo knockdown of E4BP4 blunts the Cers6-suppressing effects of PRDM16-OE.

Response: We agree that assessing in vivo loss-of-function of E4bp4 in the context of Prdm16 overexpression would be highly informative. At present, this experiment is technically not feasible, as it would require the generation and characterization of complex in vivo models beyond the scope of the current study. Nevertheless, we are actively considering this as a future direction. In the meantime, we believe that the in vitro experiments in brown adipocytes provided here are sufficient to establish the mechanistic relationship between E4BP4 and PRDM16 in the regulation of Cers6 expression.

__Reviewer #2 comment: __Whether E4BP4-OE affects cold tolerance in mice is now shown.

__Response: __We thank the reviewer for this thoughtful comment. In our study, we performed an iBAT-specific E4bp4 gain-of-function assay because we observed a downregulation of E4bp4 expression in the context of obesity. The rationale for this approach was to rescue E4bp4 expression in iBAT and thereby evaluate its systemic and mechanistic effects under obesogenic conditions. We recognize that a gain-of-function assay during cold challenge would further enhance E4bp4 expression and, while interesting, this would more directly address the role of E4bp4 in thermogenic regulation rather than in obesity-related metabolic dysfunction. For this reason, we believe that a detailed investigation of E4bp4 in cold-induced thermogenesis is an important but separate question that lies beyond the scope of the current study.

Note: This preprint has been reviewed by subject experts for Review Commons. Content has not been altered except for formatting.

Learn more at Review Commons

Referee #2

Evidence, reproducibility and clarity

Summary: The manuscript by Valdivieso-Rivera et al. investigated the role of a transcription factor, E4BP4, in brown fat functions. Using in vivo AAV gain-of-function studies, in vitro primary cultured brown adipocytes, and transcription regulation studies, authors identified that E4BP4 works together with PRDM16 to suppress Cers6 transcriptions and its derived ceramide C16:0 production. The resulted decreasing C16:0 prevents diet-induced mitochondrial fragmentation within brown adipocytes, thereby promoting brown fat functions. Overall, this study employed state-of-the-art methodologies and the collected evidence generally supported the conclusion. However, there are issues remaining to be addressed.

Major Comments:

1. The evidence of mitochondrial fragmentation is not convincing. In the reviewer's opinion, Figures 3E, 3G, 4F, and 5M demonstrated a decrease in mitochondrial quantity, but not fragmentation.
2. Whether E4BP4-OE affects cold tolerance in mice is now shown.
3. A key experiment is missing: does adding C16:0 block the mitochondrial benefits of E4BP4-OE?
4. Whether PRDM16-OE mimics the effects of E4BP4 to induce p-Drp1 is not shown.

Minor points:

1. It is confusing whether the association shown in Figure 1C is a positive or an inverse association.
2. Results from the PRDM16-OE model were mostly obtained in cultured brown adipocytes. It would be worthwhile to investigate whether in vivo knockdown of E4BP4 blunts the Cers6-suppressing effects of PRDM16-OE.

Cross-commenting

Reviewer #1's comments are all solid, and I agree with all of them.

Significance

Key strengths include state-of-the-art methodologies and detailed mechanistic studies. Key limitations include some unconvincing staining data, lack of key "rescue" experiments, and less novelty in molecular mechanisms (the ceramide-Drp1 pathway).

Overall, this study uncovers a critical role of E4BP4 in maintaining brown adipocyte mitochondrial integrity and function, advancing our understanding of TFs in brown fat biology. This study well fits readers' interests in the adipose biology and metabolism field.

Note: This preprint has been reviewed by subject experts for Review Commons. Content has not been altered except for formatting.

Learn more at Review Commons

Referee #1

Evidence, reproducibility and clarity

Summary of the key results:

Valdivieso-Rivera and colleagues present a novel regulatory mechanism by which E4BP4 modulates C16:0 ceramide production in brown adipocytes. Several points warrant clarification or additional data.

Suggested improvements:

1) Figure 1F: There is an unexpected dip in gene expression at cold exposure days 3 and 7, followed by a rebound at day 14. Is this fluctuation biologically meaningful or technical?

2) Figures B: Sample size of EE experiments is too low to draw any meaningful conclusions or to know for certain if the data are reproducible. Small sample sizes, likely coming from one litter and one batch of AAV are prone to type I error.

3) Figures 2H and 2I (GTT): How was the AUC calculated? The GTT and ITT curves appear largely parallel aside from fasting differences. If total AUC was used instead of incremental AUC, it may overstate group differences. The recommended method is outlined in [DOI: 10.1038/s42255-021-00414-7]. Also, since insulin's half-life is ~10 minutes, later differences in the ITT curve likely reflect counterregulatory responses driven by hepatic gluconeogenesis.

4) Figure 3I: Why do cells (none of the groups) show no response to NE stimulation? Please clarify or provide potential mechanistic insight. Perhaps the cells were not differentiated well.

5) Figure 4F: How was mitochondrial fragmentation quantified? Please ensure that the ROI boxes shown in zoomed panels match the same region in size and shape - this applies throughout the manuscript.

5) Figures 3I vs 5N: There is a striking discrepancy between these panels. In both, cells were treated with palmitate for 6 h, yet the NE and CCCP responses differ significantly. Are these the same cell types and conditions? Please reconcile the differences.

6) Figure 3A: The claim that one group contains smaller mitochondria is not convincing. Both small and elongated mitochondria appear in each group. Moreover, it is unclear whether these minor differences are of any physiological relevance or whether they drive phenotypes.

7) Figure 3E: The claim that confocal microscopy reveals palmitate-induced mitochondrial fragmentation is difficult to discern. The images lack clear morphological differences.

8) Figure 3G: Dendra2-labeled mitochondria appear unaffected by palmitate, raising concern about the robustness of the effect across readouts.

9) Figure 5H: Were E4BP4 expression levels equivalent between WT and mutant cells? Quantification should be shown. Figure 5H: Were E4BP4 expression levels equivalent between WT and mutant cells? Quantification should be shown.

Cross-commenting

I agree with R2's points

Significance

This advance is incremental for the basic science community.

Reviewer #3 (Public review):

A bias in how people infer the amount of control they have over their environment is widely believed to be a key component of several mental illnesses including depression, anxiety, and addiction. Accordingly, this bias has been a major focus in computational models of those disorders. However, all of these models treat control as a unidimensional property, roughly, how strongly outcomes depend on action. This paper proposes---correctly, I think---that the intuitive notion of "control" captures multiple dimensions in the relationship between action and outcome. In particular, the authors identify one key dimension: the degree to which outcome depends on how much *effort* we exert, calling this dimension the "elasticity of control". They additionally argue that this dimension (rather than the more holistic notion of controllability) may be specifically impaired in certain types of psychopathology. This idea has the potential to change how we think about several major mental disorders in a substantial way, and can additionally help us better understand how healthy people navigate challenging decision-making problems. More concisely, it is a *very good idea*.

The more concrete contributions, however, are not as strong. In particular, evidence for the paper's most striking claims is weak. Quoting the abstract, these claims are (1) "the elasticity of control [is] a distinct cognitive construct guiding adaptive behavior" and (2) "overestimation of elasticity is associated with elevated psychopathology involving an impaired sense of control."

Main issues

I'll highlight the key points.

- The task cannot distinguish elasticity inference from general learning processes

- Participants were explicitly instructed about elasticity, with labeled examples

- The psychopathology claims rely on an invalid interpretation of CCA, and are contradicted by simple correlations (elasticity bias and the sense of agency scale is r=0.03)

Distinct construct

Starting with claim 1, there are three subclaims here. (1A) People's behavior is sensitive to differences in elasticity; (1B) there are mental processes specific to elasticity inference, i.e., not falling out of general learning mechanisms; and, implicitly, (1C) people infer elasticity naturally as they go about their daily lives. The results clearly support 1A. However, 1B and 1C are not well supported.

(1B) The data cannot support the "distinct cognitive construct" claim because the task is too simple to dissociate elasticity inference from more general learning processes (also raised by Reviewer 1). The key behavioral signature for elasticity inference (vs. generic controllability inference) is the transfer across ticket numbers, illustrated in Fig 4. However, this pattern is also predicted by a standard Bayesian learner equipped with an intuitive causal model of the task. Each ticket gives you another chance to board and the agent infers the probability that each attempt succeeds. Crucially, this logic is not at all specific to elasticity or even control. An identical model could be applied to inferring the bias of a coin from observations of whether any of N tosses were heads-a task that is formally identical to this one (at least, the intuitive model of the task; see first minor comment).

Importantly, this point cannot be addressed by showing that the author's model fits data better than this or any other specific Bayesian model. It is not a question of whether one particular updating rule explains data better than another. Rather, it is a question of whether the task can distinguish between biases in *elasticity* inference versus biases in probabilistic inference more generally. The present task cannot make this distinction because it does not make separate measurements of the two types of inference. To provide compelling evidence that elasticity inference is a "distinct cognitive construct", one would need to show that there are reliable individual differences in elasticity inference that generalize across contexts but do not generalize to computationally similar types of probabilistic inference (e.g. the coin flipping example).

(1C) The implicit claim that people infer elasticity outside of the experimental task is undermined by the experimental design. The authors explicitly tell people about the two notions of control as part of the training phase: "To reinforce participants' understanding of how elasticity and controllability were manifested in each planet, [participants] were informed of the planet type they had visited after every 15 trips."

In the revisions, the authors seem to go back and forth on whether they are claiming that people infer elasticity without instruction (I won't quote it here). I'll just note that the examples they provide in the most recent rebuttal are all cases in which one never receives explicit labels about elasticity. If people only infer elasticity when it is explicitly labeled, I struggle to see its relevance for understanding human cognition and behavior.

Psychopathology

Finally, I turn to claim 2, that "overestimation of elasticity is associated with elevated psychopathology involving an impaired sense of control." The CCA analysis is in principle unable to support this claim. As the authors correctly note in their latest rebuttal, the CCA does show that "there is a relationship between psychopathology traits and task parameters". The lesion analysis further shows that "elasticity bias specifically contributes to this relationship" (and similarly for the Sense of Agency scale). Crucially, however, this does *not* imply that there is a relationship between those two variables. The most direct test of that relationship is the simple correlation, which the authors report only in a supplemental figure: there is no relationship (r=0.03). Although it is of course possible that there is a relationship that is obscured by confounding variables, the paper provides no evidence-statistical or otherwise-that such a relationship exists.

Minor comments

The statistical structure of the task is inconsistent with the framing. In the framing, participants can make either one or two second boarding attempts (jumps) by purchasing extra tickets. The additional attempt(s) will thus succeed with probability p for one ticket and 2p - p^2 for two tickets; the p^2 captures the fact that you only take the second attempt if you fail on the first. A consequence of this is buying more tickets has diminishing returns. In contrast, in the task, participants always jumped twice after purchasing two tickets, and the probability of success with two tickets was exactly double that with one ticket. Thus, if participants are applying an intuitive causal model to the task, the researcher could infer "biases" in elasticity inference that are probably better characterized as effective use of prior information (encoded in the causal model).

The model is heuristically defined and does not reflect Bayesian updating. For example, it over-estimates maximum control by not using losses with less than 3 tickets (intuitively, the inference here depends on what your beliefs about elasticity). Including forced three-ticket trials at the beginning of each round makes this less of an issue; but if you want to remove those trials, you might need to adjust the model. The need to introduce the modified model with kappa is likely another symptom of the heuristic nature of the model updating equations.

Author response:

The following is the authors’ response to the previous reviews

Reviewer #1 (Public review):

This research takes a novel theoretical and methodological approach to understanding how people estimate the level of control they have over their environment and how they adjust their actions accordingly. The task is innovative and both it and the findings are well-described (with excellent visuals). They also offer thorough validation for the particular model they develop. The research has the potential to theoretically inform understanding of control across domains, which is a topic of great importance.

We thank the Reviewer for their favorable appraisal and valuable suggestions, which have helped clarify and strengthen the study’s conclusion. 

In its revised form, the manuscript addresses most of my previous concerns. The main remaining weakness pertains to the analyses aimed at addressing my suggesting of Bayesian updating as an alternative to the model proposed by the authors. My suggestion was to assume that people perform a form of function approximation to relate resource expenditure to success probability. The authors performed a version of this where people were weighing evidence for a few canonical functions (flat, step, linear), and found that this model underperformed theirs. However, this Bayesian model is quite constrained in its ability to estimate the function relating resources. A more robust test would be to assume a more flexible form of updating that is able to capture a wide range of distributions (e.g., using basis functions, gaussian processes, or nonparametric estimators); see, e.g., work by Griffiths on human function learning). The benefit of testing this type of model is that it would make contact with a known form of inference that individuals engage in across various settings and therefore could offer a more parsimonious and generalizable account of function learning, whereby learning of resource elasticity is a special case. I defer to the authors as to whether they'd like to pursue this direction, but if not I think it's still important that they acknowledge that they are unable to rule out a more general process like this as an alternative to their model. This pertains also to inferences about individual differences, which currently hinge on their preferred model being the most parsimonious.

We thank the Reviewer for this thoughtful suggestion. We acknowledge that more flexible function learning approaches could provide a stronger test in favor of a more general account. Our Bayesian model implemented a basis function approach where the weights of three archetypal functions (flat, step, linear) are learned from experience Testing models with more flexible basis functions would likely require a task with more than three levels of resource investment (1, 2, or 3 tickets). This would make an interesting direction for future work expanding on our current findings. We now incorporate this suggestion in more detail in our updated manuscript (335-341):

“Second, future models could enable generalization to levels of resource investment not previously experienced. For example, controllability and its elasticity could be jointly estimated via function approximation that considers control as a function of invested resources. Although our implementation of this model did not fit participants’ choices well (see Methods), other modeling assumptions drawn from human function learning [30] or experimental designs with continuous action spaces may offer a better test of this idea.”

Reviewer #2 (Public review):

This research investigates how people might value different factors that contribute to controllability in a creative and thorough way. The authors use computational modeling to try to dissociate "elasticity" from "overall controllability," and find some differential associations with psychopathology. This was a convincing justification for using modeling above and beyond behavioral output and yielded interesting results. Notably, the authors conclude that these findings suggest that biased elasticity could distort agency beliefs via maladaptive resource allocation. Overall, this paper reveals important findings about how people consider components of controllability. The authors have gone to great lengths to revise the manuscript to clarify their definitions of "elastic" and "inelastic" and bolster evidence for their computational model, resulting in an overall strong manuscript that is valuable for elucidating controllability dynamics and preferences. 

We thank the Reviewer for their constructive feedback throughout the review process, which has substantially strengthened our manuscript and clarified our theoretical framework.

One minor weakness is that the justification for the analysis technique for the relationships between the model parameters and the psychopathology measures remains lacking given the fact that simple correlational analyses did not reveal any significant associations.

We note that the existence of bivariate relationships is not a prerequisite for the existence of multivariate relationships. Conditioning the latter on the former, therefore, would risk missing out on important relationships existing in the data. Ultimately, correlations between pairs of variables do not offer a sensitive test for the general hypothesis that there is a relationship between two sets of variables. As an illustration, consider that elasticity bias correlated in our data (r = .17, p<.001) with the difference between SOA (sense of agency) and SDS (self-rating depression). Notably, SOA and SDS were positively correlated (r = .47, p<.001), and neither of them was correlated with elasticity bias (SOA: r=.04 p=.43, SDS: r=-.06, p=.16). It was a dimension that ran between them that mapped onto elasticity bias. This specific finding is incidental and uncorrected for multiple comparisons, hence we do not report it in the manuscript, but it illustrates the kinds of relationships that cannot be accounted for by looking at bivariate relationships alone.  

Reviewer #3 (Public review):

A bias in how people infer the amount of control they have over their environment is widely believed to be a key component of several mental illnesses including depression, anxiety, and addiction. Accordingly, this bias has been a major focus in computational models of those disorders. However, all of these models treat control as a unidimensional property, roughly, how strongly outcomes depend on action. This paper proposes---correctly, I think---that the intuitive notion of "control" captures multiple dimensions in the relationship between action and outcome.

In particular, the authors identify one key dimension: the degree to which outcome depends on how much *effort* we exert, calling this dimension the "elasticity of control". They additionally argue that this dimension (rather than the more holistic notion of controllability) may be specifically impaired in certain types of psychopathology. This idea has the potential to change how we think about several major mental disorders in a substantial way and can additionally help us better understand how healthy people navigate challenging decision-making problems. More concisely, it is a very good idea.

We thank the Reviewer for their thoughtful engagement with our manuscript. We appreciate their recognition of elasticity as a key dimension of control that has the potential to advance our understanding of psychopathology and healthy decision-making.

Starting with theory, the authors do not provide a strong formal characterization of the proposed notion of elasticity. There are existing, highly general models of controllability (e.g., Huys & Dayan, 2009; Ligneul, 2021) and the elasticity idea could naturally be embedded within one of these frameworks. The authors gesture at this in the introduction; however, this formalization is not reflected in the implemented model, which is highly task-specific.

Our formal definition of elasticity, detailed in Supplementary Note 1, naturally extends the reward-based and information-theoretic definitions of controllability by Huys & Dayan (2009) and Ligneul (2021). We now further clarify how the model implements this formalized definition (lines 156-159).

“Conversely, in the ‘elastic controllability model’, the beta distributions represent a belief about the maximum achievable level of control (𝑎_Control, 𝑏_Control) coupled with two elasticity estimates that specify the degree to which successful boarding requires purchasing at least one (𝑎_elastic≥1, 𝑏_elastic≥1) or specifically two (𝑎_elastic2, 𝑏_elastic2) extra tickets. As such, these elasticity estimates quantify how resource investment affects control. The higher they are, the more controllability estimates can be made more precise by knowing how much resources the agent is willing and able to invest (Supplementary Note 1).”

Moreover, the authors present elasticity as if it is somehow "outside of" the more general notion of controllability. However, effort and investment are just specific dimensions of action; and resources like money, strength, and skill (the "highly trained birke") are just specific dimensions of state. Accordingly, the notion of elasticity is necessarily implicitly captured by the standard model. Personally, I am compelled by the idea that effort and resource (and therefore elasticity) are particularly important dimensions, ones that people are uniquely tuned to. However, by framing elasticity as a property that is different in kind from controllability (rather than just a dimension of controllability), the authors only make it more difficult to integrate this exciting idea into generalizable models.

We respectfully disagree that we present elasticity as outside of, or different in kind from, controllability. Throughout the manuscript, we explicitly describe elasticity as a dimension of controllability (e.g., lines 70-72, along many other examples). This is also expressed in our formal definition of elasticity (Supplementary Note 1). 

The argument that vehicle/destination choice is not trivial because people occasionally didn't choose the instructed location is not compelling to me-if anything, the exclusion rate is unusually low for online studies. The finding that people learn more from non-random outcomes is helpful, but this could easily be cast as standard model-based learning very much like what one measures with the Daw two-step task (nothing specific to control here). Their final argument is the strongest, that to explain behavior the model must assume "a priori that increased effort could enhance control." However, more literally, the necessary assumption is that each attempt increases the probability of success-e.g. you're more likely to get a heads in two flips than one. I suppose you can call that "elasticity inference", but I would call it basic probabilistic reasoning.

We appreciate the Reviewer’s concerns but feel that some of the more subjective comments might not benefit from further discussion. We only note that controllability and its elasticity are features of environmental structure, so in principle any controllability-related inference is a form of model-based learning. The interesting question is whether people account in their world model for that particular feature of the environment.   

The authors try to retreat, saying "our research question was whether people can distinguish between elastic and inelastic controllability." I struggle to reconcile this with the claim in the abstract "These findings establish the elasticity of control as a distinct cognitive construct guiding adaptive behavior". That claim is the interesting one, and the one I am evaluating the evidence in light of.

In real-world contexts, it is often trivial that sometimes further investment enhances control and sometimes it does not. For example, students know that if they prepare more extensively for their exams they will likely be able to achieve better grades, but they also know that there is uncertainty in this regard – their grades could improve significantly, modestly, or in some cases, they might not improve at all, depending on the type of exams their study program administers and the knowledge or skills being tested. Our research question was whether in such contexts people learn from experience the degree to which controllability is elastic to invested resources and adapt their resource investment accordingly. Our findings show that they do. 

The authors argue for CCA by appeal to the need to "account for the substantial variance that is typically shared among different forms of psychopathology". I agree. A simple correlation would indeed be fairly weak evidence. Strong evidence would show a significant correlation after *controlling for* other factors (e.g. a regression predicting elasticity bias from all subscales simultaneously). CCA effectively does the opposite, asking whether-with the help of all the parameters and all the surveys-one can find any correlation between the two sets of variables. The results are certainly suggestive, but they provide very little statistical evidence that the elasticity parameter is meaningfully related to any particular dimension of psychopathology.

We agree with the Reviewer on the relationship between elasticity and any particular dimension of psychopathology. The CCA asks a different question, namely, whether there is a relationship between psychopathology traits and task parameters, and whether elasticity bias specifically contributes to this relationship. 

I am very concerned to see that the authors removed the discussion of this limitation in response to my first review. I quote the original explanation here:

- In interpreting the present findings, it needs to be noted that we designed our task to be especially sensitive to overestimation of elasticity. We did so by giving participants free 3 tickets at their initial visits to each planet, which meant that upon success with 3 tickets, people who overestimate elasticity were more likely to continue purchasing extra tickets unnecessarily. Following the same logic, had we first had participants experience 1 ticket trips, this could have increased the sensitivity of our task to underestimation of elasticity in elastic environments. Such underestimation could potentially relate to a distinct psychopathological profile that more heavily loads on depressive symptoms. Thus, by altering the initial exposure, future studies could disambiguate the dissociable contributions of overestimating versus underestimating elasticity to different forms of psychopathology.

The logic of this paragraph makes perfect sense to me. If you assume low elasticity, you will infer that you could catch the train with just one ticket. However, when elasticity is in fact high, you would find that you don't catch the train, leading you to quickly infer high elasticity eliminating the bias. In contrast, if you assume high elasticity, you will continue purchasing three tickets and will never have the opportunity to learn that you could be purchasing only one-the bias remains.

The authors attempt to argue that this isn't happening using parameter recovery. However, they only report the *correlation* in the parameter, whereas the critical measure is the *bias*. Furthermore, in parameter recovery, the data-generating and data-fitting models are identical-this will yield the best possible recovery results. Although finding no bias in this setting would support the claims, it cannot outweigh the logical argument for the bias that they originally laid out. Finally, parameter recovery should be performed across the full range of plausible parameter values; using fitted parameters (a detail I could only determine by reading the code) yields biased results because the fitted parameters are themselves subject to the bias (if present). That is, if true low elasticity is inferred as high elasticity, then you will not have any examples of low elasticity in the fitted parameters and will not detect the inability to recover them.

The logic the Reviewer describes breaks down when one considers the dynamics of participants’ resource investment choices. A low elasticity bias in a participant’s prior belief would make them persist for longer in purchasing a single ticket despite failure, as compared to a person without such a bias. Indeed, the ability of the experimental design to demonstrate low elasticity biases is evidenced by the fact that the majority of participants were fitted with a low elasticity bias (μ = .16 ± .14, where .5 is unbiased). 

Originally, the Reviewer was concerned that elasticity bias was being confounded with a general deficit in learning. The weak inter-parameter correlations in the parameter recovery test resolved this concern, especially given that, as we now noted, the simulated parameter space encompassed both low and high elasticity biases (range=[.02,.76]). Furthermore, regarding the Reviewer's concern about bias in the parameter recovery, we found no such significant bias with respect to the elasticity bias parameter (Δ(Simulated, Recovered)= -.03, p=.25), showing that our experiment could accurately identify low and high elasticity biases.

The statistical structure of the task is inconsistent with the framing. In the framing, participants can make either one or two second boarding attempts (jumps) by purchasing extra tickets. The additional attempt(s) will thus succeed with probability p for one ticket and 2p – p^{^}2 for two tickets; the p^{^}2 captures the fact that you only take the second attempt if you fail on the first. A consequence of this is buying more tickets has diminishing returns. In contrast, in the task, participants always jumped twice after purchasing two tickets, and the probability of success with two tickets was exactly double that with one ticket. Thus, if participants are applying an intuitive causal model to the task, they will appear to "underestimate" the elasticity of control. I don't think this seriously jeopardizes the key results, but any follow-up work should ensure that the task's structure is consistent with the intuitive causal model.

We thank the Reviewer for this comment, and agree the participants may have employed the intuitive understanding the Reviewer describes. This is consistent with our model comparison results, which showed that participants did not assume that control increases linearly with resource investment (lines 677-692). Consequently, this is also not assumed by our model, except perhaps by how the prior is implemented (a property that was supported by model comparison). In the text, we acknowledge that this aspect of the model and participants’ behavior deviates from the true task's structure, and it would be worthwhile to address this deviation in future studies. 

That said, there is no reason that this will make participants appear to be generally underestimating elasticity. Following exposure to outcomes for one and three tickets, any nonlinear understanding of probabilities would only affect the controllability estimate for two tickets. This would have contrasting effects on the elasticity estimated to the second and third tickets, but on average, it would not change the overall elasticity estimated. On the other hand, such a participant is only exposed to outcomes for two and three tickets, they would come to judge the difference between the first and second tickets too highly, thereby overestimating elasticity.  

The model is heuristically defined and does not reflect Bayesian updating. For example, it overestimates maximum control by not using losses with less than 3 tickets (intuitively, the inference here depends on what your beliefs about elasticity). Including forced three-ticket trials at the beginning of each round makes this less of an issue; but if you want to remove those trials, you might need to adjust the model. The need to introduce the modified model with kappa is likely another symptom of the heuristic nature of the model updating equations.

Note that we have tested a fully Bayesian model (lines 676-691), but found that this model fitted participants’ choices worse. 

You're right; saying these analyses provides "no information" was unfair. I agree that this is a useful way to link model parameters with behavior, and they should remain in the paper. However, my key objection still holds: these analyses do not tell us anything about how *people's* prior assumptions influence behavior. Instead, they tell us about how *fitted model parameters* depend on observed behavior. You can easily avoid this misreading by adding a small parenthetical, e.g.

Thus, a prior assumption that control is likely available **(operationalized by \gamma_controllability)** was reflected in a futile investment of resources in uncontrollable environments.

We thank the Reviewer for the suggestion and have added this parenthetical (lines 219, 225).

Reviewer #2 (Public review):

Summary:

This manuscript presents a tactile categorization task in head-fixed mice to test whether Fmr1 knockout mice display differences in vibrotactile discrimination using the forepaw. Tactile discrimination differences have been previously observed in humans with Fragile X Syndrome, autistic individuals, as well as mice with loss of Fmr1 across multiple studies. The authors show that during training, Fmr1 mutant mice display subtle deficits in perceptual learning of "low salience" stimuli, but not "high salience" stimuli, during the task. Following training, Fmr1 mutant mice displayed an enhanced tactile sensitivity under low-salience conditions but not high-salience stimulus conditions. The authors suggest that, under 'high cognitive load' conditions, Fmr1 mutant mouse performance during the lowest indentation stimuli presentations was affected, proposing an interplay of sensory and cognitive system disruptions that dynamically affect behavioral performance during the task.

Strengths:

The study employs a well-controlled vibrotactile discrimination task for head-fixed mice, which could serve as a platform for future mechanistic investigations. By examining performance across both training stages and stimulus "salience/difficulty" levels, the study provides a more nuanced view of how tactile processing deficits may emerge under different cognitive and sensory demands.

Weaknesses:

The study is primarily descriptive. The authors collect behavioral data and fit simple psychometric functions, but provide no neural recordings, causal manipulations, or computational modeling. Without mechanistic evidence, the conclusions remain speculative. Second, the authors repeatedly make strong claims about "categorical priors," "attention deficits," and "choice biases," but these constructs are inferred indirectly from secondary behavioral measures. Many of the effects are based on non-significant trends, and alternative explanations (such as differences in motivation, fatigue, satiety, stereotyped licking, and/or reward valuation) are not considered. Third, the mapping of the behavioral results onto high-level cognitive constructs is tenuous and overstated. The authors' interpretations suggest that they directly tested cognitive theories such as Load Theory, Adaptive Resonance Theory, or Weak Central Coherence. However, the experiments do not manipulate or measure variables that would allow such theories to be tested. More specific comments are included below.

(1) The authors employ a two-choice behavioral task to assess forepaw tactile sensitivity in Fmr1 knockout mice. The data provide an interesting behavioral observation, but it is a descriptive study. Without mechanistic experiments, it is difficult to draw any conclusions, especially regarding top-down or bottom-up pathway dysfunctions. While the task design is elegant, the data remain correlational and do not advance our mechanistic understanding of Fmr1-related sensory and/or cognitive alterations.

(2) The conclusions hinge on speculative inferences about "reduced top-down categorization influence" or "choice consistency bias," but no neural, circuit-level, or causal manipulations (e.g., optogenetics, pharmacology, targeted lesions, modeling) are used to support these claims. Without mechanistic data, the translational impact is limited.

(3) Statistical analysis:

(a) Several central claims are based on "trends" rather than statistically significant effects (e.g., reduced task sensitivity, reduced across-category facilitation). Building major interpretive arguments on non-significant findings undermines confidence in the conclusions.

(b) The n number for both genotypes should be increased. In several experiments (e.g., Figure 1D, 2E), one animal appears to be an outlier. Considering the subtle differences between genotypes, such an outlier could affect the statistical results and subsequent interpretations.

(c) The large number of comparisons across salience levels, categories, and trial histories raises concern for false positives. The manuscript does not clearly state how multiple comparisons were controlled.

(d) The data in Figure 5, shown as separate panels per indentation value, are analyzed separately as t-tests or Mann-Whitney tests. However, individual comparisons are inappropriate for this type of data, as these are repeated stimulus applications across a given session. The data should be analyzed together and post-hoc comparisons reported. Given the very subtle difference in miss rates across control and mutant mice for 'low-salience' stimulus trials, this is unlikely to be a statistically meaningful difference when analyzed using a more appropriate test.

(4) Emphasis on theoretical models:

The paper leans heavily on theories such as Adaptive Resonance Theory, Load Theory of Attention, and Weak Central Coherence, but the data do not actually test these frameworks in a rigorous way. The discussion should be reframed to highlight the potential relevance of these frameworks while acknowledging that the current data do not allow them to be assessed.

Reviewer #3 (Public review):

Summary:

Developing consistent and reliable biomarkers is critically important for developing new pharmacological therapies in autism spectrum disorders (ASDs). Altered sensory perception is one of the hallmarks of autism and has been recently added to DSM-5 as one of the core symptoms of autism. Touch is one of the fundamental sensory modalities, yet it is currently understudied. Furthermore, there seems to be a discrepancy between different studies from different groups focusing on tactile discrimination. It is not clear if this discrepancy can be explained by different experimental setups, inconsistent terminology, or the heterogeneity of sensory processing alterations in ASDs. The authors aim to investigate the interplay between tactile discrimination and cognitive processes during perceptual decisions. They have developed a forepaw-based 2-alternative choice task for mice and investigated tactile perception and learning in Fmr1-/y mice

Strengths:

There are several strengths of this task: translational relevance to human psychophysical protocols, including controlled vibrotactile stimulation. In addition to the experimental setup, there are also several interesting findings: Fmr1-/y mice demonstrated choice consistency bias, which may result in impaired perceptual learning, and enhanced tactile discrimination in low-salience conditions, as well as attentional deficits with increased cognitive load. The increase in the error rates for low salience stimuli is interesting. These observations, together with the behavioral design, may have a promising translational potential and, if confirmed in humans, may be potentially used as biomarkers in ASD.

Weaknesses:

Some weaknesses are related to the lack of the original raster plots and density plots of licks under different conditions, learning rate vs time, and evaluation of the learning rate at different stages of learning. Overall, these data would help to answer the question of whether there are differences in learning strategies or neural circuit compensation in Fmr1-/y mice. It is also not clear if reversal learning is impaired in Fmr1-/y mice.

Author response:

Reviewer #1 (Public review): 

Summary: 

This study addresses the important question of how top-down cognitive processes affect tactile perception in autism - specifically, in the Fmr1-/y genetic mouse model of autism. Using a 2AFC tactile task in behaving mice, the study investigated multiple aspects of perceptual processing, including perceptual learning, stimulus categorization and discrimination, as well as the influence of prior experience and attention.  

We appreciate the reviewer’s statement highlighting the importance of our study. 

Strengths: 

The experiments seem well performed, with interesting results. Thus, this study can/will advance our understanding of atypical tactile perception and its relation to cognitive factors in autism. 

We thank the reviewer for recognizing the quality of our experiments and the relevance of our findings for understanding tactile perception and cognition in autism.

Weaknesses: 

Certain aspects of the analyses (and therefore the results) are unclear, which makes the manuscript difficult to understand. Clearer presentation, with the addition of more standard psychometric analyses, and/or other useful models (like logistic regression) would improve this aspect. The use of d' needs better explanation, both in terms of how and why these analyses are appropriate (and perhaps it should be applied for more specific needs rather than as a ubiquitous measure). 

We thank the reviewer for the helpful comments. We understand that the analyses were difficult to follow, and we will work on the clarity of the Results section. However, we would like to emphasize that every d′ measure is accompanied by analyses of response rates (i.e., correct and incorrect choice rates). In addition, we applied standard psychometric analyses whenever possible. Specifically, psychometric functions were fitted to the data using logistic regression. We will rework the text to clarify these points.

During training, only two stimulus amplitudes were presented, which precluded the construction of psychometric curves. For the categorization task, however, psychometric analyses were feasible and conducted (Figure 2). These analyses revealed no evidence of categorization bias (as measured by threshold) or accuracy (as measured by the slope) across stimulus strengths.

The calculation of d’ is included in the Methods, but we will also report and explain its use in each part of the Results section where it has been included.

Reviewer #2 (Public review): 

Summary: 

This manuscript presents a tactile categorization task in head-fixed mice to test whether Fmr1 knockout mice display differences in vibrotactile discrimination using the forepaw. Tactile discrimination differences have been previously observed in humans with Fragile X Syndrome, autistic individuals, as well as mice with loss of Fmr1 across multiple studies. The authors show that during training, Fmr1 mutant mice display subtle deficits in perceptual learning of "low salience" stimuli, but not "high salience" stimuli, during the task. Following training, Fmr1 mutant mice displayed an enhanced tactile sensitivity under low-salience conditions but not high-salience stimulus conditions. The authors suggest that, under 'high cognitive load' conditions, Fmr1 mutant mouse performance during the lowest indentation stimuli presentations was affected, proposing an interplay of sensory and cognitive system disruptions that dynamically affect behavioral performance during the task. 

Strengths: 

The study employs a well-controlled vibrotactile discrimination task for head-fixed mice, which could serve as a platform for future mechanistic investigations. By examining performance across both training stages and stimulus "salience/difficulty" levels, the study provides a more nuanced view of how tactile processing deficits may emerge under different cognitive and sensory demands. 

We thank the reviewer for emphasizing the strengths of our task design and analysis approach, and we appreciate that the potential of this platform for future mechanistic investigations is recognized.

Weaknesses: 

The study is primarily descriptive. The authors collect behavioral data and fit simple psychometric functions, but provide no neural recordings, causal manipulations, or computational modeling. Without mechanistic evidence, the conclusions remain speculative. 

We thank the reviewer for the careful reading of our manuscript and for the constructive feedback. The reviewer raises a valid point. We agree that our study is primarily descriptive and focused on behavioral data, and we appreciate the opportunity to clarify the scope and interpretation of our findings. Our primary goal was to characterize behavioral patterns during tactile discrimination and categorization, and the psychometric analyses were intended to provide a detailed description of these patterns. We do not claim to provide direct neural, causal, or computational evidence. 

Second, the authors repeatedly make strong claims about "categorical priors," "attention deficits," and "choice biases," but these constructs are inferred indirectly from secondary behavioral measures. Many of the effects are based on non-significant trends, and alternative explanations (such as differences in motivation, fatigue, satiety, stereotyped licking, and/or reward valuation) are not considered. 

Alternative explanations of our findings, such as differences in motivation, fatigue, satiety, stereotyped licking, and reward valuation have indeed been considered. We will revise the manuscript to present these points more clearly. 

Third, the mapping of the behavioral results onto high-level cognitive constructs is tenuous and overstated. The authors' interpretations suggest that they directly tested cognitive theories such as Load Theory, Adaptive Resonance Theory, or Weak Central Coherence. However, the experiments do not manipulate or measure variables that would allow such theories to be tested. More specific comments are included below.

This was not done intentionally. We do not claim to have tested the Load Theory; rather, inspired by it, we assessed behavioral patterns in our tactile categorization task. We agree that referring to the Adaptive Resonance Theory, which is based on artificial neural network models, might be misleading since we focus on behavioral results, and we will revise the text accordingly. However, our task allowed us to examine the impact of categorization on discrimination, confirming that Fmr1^-/yation can amplify perceptual differences between stimuli belonging to different categories and reduce perceived differences within a category in WT mice but not in the mice when low-salience stimuli were experienced. Finally, we do not claim to have tested the Weak Central Coherence theory, although our results suggest reduced use of categories in low-salience tactile discrimination. 

(1) The authors employ a two-choice behavioral task to assess forepaw tactile sensitivity in Fmr1 knockout mice. The data provide an interesting behavioral observation, but it is a descriptive study. Without mechanistic experiments, it is difficult to draw any conclusions, especially regarding top-down or bottom-up pathway dysfunctions. While the task design is elegant, the data remain correlational and do not advance our mechanistic understanding of Fmr1-related sensory and/or cognitive alterations. 

We agree with the reviewer that our current experiments are behavioral in nature and do not provide direct mechanistic evidence for top-down pathway dysfunction. Our goal was to carefully characterize tactile responses and behavioral patterns in Fmr1^-/y mice. The notion of “top-down” is used at the behavioral level, referring to the influence of higher-level cognitive processes (e.g., categorization, attention) on perception, rather than to underlying neural circuits. We will revise the manuscript to more clearly emphasize that our conclusions are based on behavioral observations, and we will frame mechanistic inferences as hypotheses rather than established findings. We will also explicitly note that future work using neural recordings or causal manipulations will be required to directly test these hypotheses.

We also note that identifying the precise top-down circuits involved will require extensive additional experimentation. For example, one would first need to pinpoint the specific top-down pathway that modulates the influence of categorization on discrimination without directly altering categorization itself. After such a circuit is identified, further work would then be needed to rescue or manipulate this pathway in the Fmr1^-/y model. These steps represent a substantial program of mechanistic research that, while important, goes well beyond the scope of the present study.

(2) The conclusions hinge on speculative inferences about "reduced top-down categorization influence" or "choice consistency bias," but no neural, circuit-level, or causal manipulations (e.g., optogenetics, pharmacology, targeted lesions, modeling) are used to support these claims. Without mechanistic data, the translational impact is limited. 

We recognize that “reduced top-down categorization influence” and “choice consistency bias” are based on behavioral observations. However, we respectfully disagree that this makes these constructs inherently speculative. Similar behavioral inferences have been applied in previous clinical studies to characterize cognitive tendencies (Soulières et al., 2007; Feigin et al., 2021). The translational impact of our work lies in the highly translational platform we have developed – and in highlighting the complexity of tactile measures and additional analyses that can be conducted in clinical studies.

We agree with the reviewer that the neural-based experiments would indeed provide valuable mechanistic insight into our observed behavioral alterations, and we believe future studies should therefore focus on their underlying neurobiological substrate.

We will revise the language throughout the manuscript to clarify that all conclusions are based on behavioral measures.  

(3) Statistical analysis: 

(a) Several central claims are based on "trends" rather than statistically significant effects (e.g., reduced task sensitivity, reduced across-category facilitation). Building major interpretive arguments on nonsignificant findings undermines confidence in the conclusions.  

Several trends are evident in complex measures, such as d’ analyses on task sensitivity or responses pooled across different amplitudes. Additional analyses revealed which component of these measures showed a statistically significant difference across genotypes, namely the low-salience incorrect choices accounting for low task sensitivity. We chose to present all analyses to be transparent and to highlight that commonly used complex measures (like d’ analyses) may mask important findings. In the text, we described p-values between 0.05 and 0.1 as observed trends without over-interpreting their significance. 

(b) The n number for both genotypes should be increased. In several experiments (e.g., Figure 1D, 2E), one animal appears to be an outlier. Considering the subtle differences between genotypes, such an outlier could affect the statistical results and subsequent interpretations. 

The number of mice used in each genotype group is consistent with standard practices in behavioral studies using mice and sensory tasks. We have performed effect size measures (e.g., Cohen’s d) alongside some of the statistical comparisons, showing a medium effect size (>0.5). 

As the reviewer correctly noted, no mice were excluded based on outlier analyses, since the observed variability reflects true biological differences rather than experimental or technical errors. We will reexamine our dataset for potential outliers. If any are identified, we will perform analyses both with and without the outlier and report any effects that are sensitive to single animals. These procedures and results will be explicitly described in the Methods and Results sections.

(c) The large number of comparisons across salience levels, categories, and trial histories raises concern for false positives. The manuscript does not clearly state how multiple comparisons were controlled.  

We thank the reviewer for raising this important point and we will include a clear statement on multiple comparisons in the Methods section. 

(d) The data in Figure 5, shown as separate panels per indentation value, are analyzed separately as ttests or Mann-Whitney tests. However, individual comparisons are inappropriate for this type of data, as these are repeated stimulus applications across a given session. The data should be analyzed together and post-hoc comparisons reported. Given the very subtle difference in miss rates across control and mutant mice for 'low-salience' stimulus trials, this is unlikely to be a statistically meaningful difference when analyzed using a more appropriate test. 

We thank the reviewer for raising this point. This was not done intentionally. A repeated-measures ANOVA on miss rates for low-salience stimuli during categorization confirmed that there are statistically significant differences both across stimulus amplitudes and between genotypes. Additional correction for multiple comparisons will be performed and explained in the Methods section.  

(4) Emphasis on theoretical models: The paper leans heavily on theories such as Adaptive Resonance Theory, Load Theory of Attention, and Weak Central Coherence, but the data do not actually test these frameworks in a rigorous way. The discussion should be reframed to highlight the potential relevance of these frameworks while acknowledging that the current data do not allow them to be assessed. 

As mentioned above, our goal was not to directly test these theories but rather to apply them within our translational framework. The Discussion section will be reframed to highlight that our findings are consistent with predictions from certain cognitive theories rather than implying that these frameworks were directly tested.

Reviewer #3 (Public review): 

Summary: 

Developing consistent and reliable biomarkers is critically important for developing new pharmacological therapies in autism spectrum disorders (ASDs). Altered sensory perception is one of the hallmarks of autism and has been recently added to DSM-5 as one of the core symptoms of autism. Touch is one of the fundamental sensory modalities, yet it is currently understudied. Furthermore, there seems to be a discrepancy between different studies from different groups focusing on tactile discrimination. It is not clear if this discrepancy can be explained by different experimental setups, inconsistent terminology, or the heterogeneity of sensory processing alterations in ASDs. The authors aim to investigate the interplay between tactile discrimination and cognitive processes during perceptual decisions. They have developed a forepaw-based 2-alternative choice task for mice and investigated tactile perception and learning in Fmr1-/y mice 

Strengths: 

There are several strengths of this task: translational relevance to human psychophysical protocols, including controlled vibrotactile stimulation. In addition to the experimental setup, there are also several interesting findings: Fmr1-/y mice demonstrated choice consistency bias, which may result in impaired perceptual learning, and enhanced tactile discrimination in low-salience conditions, as well as attentional deficits with increased cognitive load. The increase in the error rates for low salience stimuli is interesting. These observations, together with the behavioral design, may have a promising translational potential and, if confirmed in humans, may be potentially used as biomarkers in ASD. 

We appreciate the reviewer’s positive assessment of our study’s translational value and the importance of our behavioral findings.

Weaknesses: 

Some weaknesses are related to the lack of the original raster plots and density plots of licks under different conditions, learning rate vs time, and evaluation of the learning rate at different stages of learning. Overall, these data would help to answer the question of whether there are differences in learning strategies or neural circuit compensation in Fmr1-/y mice. It is also not clear if reversal learning is impaired in Fmr1-/y mice.  

We thank the reviewer for these helpful suggestions. We agree that visualizing behavioral patterns, such as raster and density plots of licks, as well as learning rate over time, could provide additional insights into learning dynamics. This analysis will be conducted and added into the revised manuscript.

There was no assessment of reversal learning in Fmr1^-/y mice in this study. While it is an interesting and important question based on previous findings in preclinical and clinical studies, it falls outside the scope of the current manuscript.    

Feigin H, Shalom-Sperber S, Zachor DA, Zaidel A (2021) Increased influence of prior choices on perceptual decisions in autism. Elife 10.

Soulières I, Mottron L, Saumier D, Larochelle S (2007) At ypical categorical perception in autism: Autonomy of discrimination? J Autism Dev Disord 37:481–490.

This is how to set it up.

Ddx: 1. Heart Failure 2. PE 3. Aspiration Pneumonia 4. COPD with acute exacerbation 5. Kidney or Liver Failure 6. MI 7. Arrythmia

Fig 3.

This data makes sense, as it would be easier to spot dolphins in lower water levels, paired with the fact that there is the possibility that the dolphin populations are more condensed due to the lessening amount of swimming space.

She limits her claim by supporting that students should embrace coffee to enhance mental functioning unless they have serious side effects.

This is a counterargument with merit

No merit given here by the author

The author bases this suggestion on the idea that black tea provides similar benefits with fewer negative effects than coffee.

They justify this advice by pointing out that studying without coffee encourages responsibility and self-discipline.

The author supports this recommendation by explaining that coffee stimulates and energises the mind.

Claim of Policy

Claim of Value

Claim of fact

Fact

Reviewer #1 (Public review):

Summary:

This study generated 3D cell constructs from endometrial cell mixtures that were seeded in the Matrigel scaffold. The cell assemblies were treated with hormones to induce a "window of implantation" (WOI) state. Although many bioinformatic analyses point in this direction, there are major concerns that must be addressed.

Strengths:

The addition of 3 hormones to enhance the WOI state (although not clearly supported in comparison to the secretory state).

Comments on revisions:

The authors did their best to revise their study according to the Reviewers' comments. However, the study remains unconvincing, incomplete and at the same time still too dense and not focused enough.

Reviewer #1 (Public review):

This manuscript reports a dual-task experiment intended to test whether language prediction relies on executive resources, using surprisal-based measures of predictability and an n-back task to manipulate cognitive load. While the study addresses a question under debate, the current design and modeling framework fall short of supporting the central claims. Key components of cognitive load, such as task switching, word prediction vs integration, are not adequately modeled. Moreover, the weak consistency in replication undermines the robustness of the reported findings. Below unpacks each point.

Cognitive load is a broad term. In the present study, it can be at least decomposed into the following components:

(1) Working memory (WM) load: news, color, and rank.

(2) Task switching load: domain of attention (color vs semantics), sensorimotor rules (c/m vs space).

(3) Word comprehension load (hypothesized against): prediction, integration.

The components of task switching load should be directly included in the statistical models. Switching of sensorimotor rules may be captured by the "n-back reaction" (binary) predictor. However, the switching of attended domains and the interaction between domain switching and rule complexity (1-back or 2-back) were not included. The attention control experiment (1) avoided useful statistical variation from the Read Only task, and (2) did not address interactions. More fundamentally, task-switching components should be directly modeled in both performance and full RT models to minimize selection bias. This principle also applies to other confounding factors, such as education level. While missing these important predictors, the current models have an abundance of predictors that are not so well motivated (see later comments). In sum, with the current models, one cannot determine whether the reduced performance or prolonged RT was due to affecting word prediction load (if it exists) or merely affecting the task switching load.

The entropy and surprisal need to be more clearly interpreted and modeled in the context of the word comprehension process. The entropy concerns the "prediction" part of the word comprehension (before seeing the next word), whereas surprisal concerns the "integration" part as a posterior. This interpretation is similar to the authors writing in the Introduction that "Graded language predictions necessitate the active generation of hypotheses on upcoming words as well as the integration of prediction errors to inform future predictions [1,5]." However, the Results of this study largely ignored entropy (treating it as a fixed effect) and only focus on surprisal without clear justification.

In Table S3, with original and replicated model fitting results, the only consistent interaction is surprisal x age x cognitive load [2-back vs. Reading Only]. None of the two-way interactions can be replicated. This is puzzling and undermines the robustness of the main claims of this paper.

Reviewer #3 (Public review):

Summary:

The manuscript by Shaikh and Assisi addresses a timely and important question related to the neural circuit mechanisms underlying spatial representations during navigation. Concretely, they present a model of the medial entorhinal cortex (MEC) with biophysically detailed conductance-based stellate cells that can perform path integration and reveal two potential mechanisms underlying two forms of predictive coding by grid cells in the MEC. One mechanism uses HCN channels to explain predictive coding in MEC layer II grid cells equivalent to ~5% of the diameter of a grid field, and the other uses asymmetric connections between interneurons and stellate cells, resulting in a ~25% predictive bias of layer III grid cells. The methods and model are technically sound, and the model is expected to be useful for computational neuroscientists studying the neural mechanisms of spatial navigation.

Strengths:

One strength of the model is its use of conductance-based neuron models of stellate cells and interneurons, adding important biophysical constraints and details to existing continuous attractor network models of grid cells. The model fills a gap in the literature by providing mechanisms for predictive coding constrained by biophysical properties of stellate cells and simplified network topology.

Weaknesses:

A weakness of the model is that the neural network is relatively small (five sheets with 71 × 71 neurons each), and the 2-D toroidal topology is further simplified to a 1-D ring attractor consisting of three rings with 192 neurons each. The model incorporates biophysical detail at the single-neuron level, but not at the network level. For example, it includes only stellate cells and a generic interneuron type, and does not implement data-driven connectivity patterns.

The restricted network size and the limited experimental knowledge about connectivity among stellate cells, principal cells, and different interneuron types in the MEC could be addressed in more detail. Moreover, the manuscript lacks a thorough discussion of assumptions common to most continuous attractor network (CAN) models of grid cells, such as the use of "hand-crafted" connections between direction-sensitive conjunctive grid cells and network cells to drive attractor shifts. Including such a discussion would strengthen the manuscript. This is especially relevant given the authors' explicit claim that they have revealed two mechanisms underlying the emergence of a predictive code in the MEC. In this reviewer's view, the work demonstrates a potential mechanism, but one that requires experimental verification. The significance of the model would thus be increased by providing more experimentally testable predictions of the model.

Author response:

The following is the authors’ response to the original reviews.

Reviewer #1 (Public review):

(1) The manuscript is quite dense, with some concepts that may prove difficult for the non-specialist. I recommend spending a few more words (and maybe some pictures) describing the difference between task-relevant and task-irrelevant planes. Nice technique, but not instantly obvious. Then we are hit with "stimulus-related", which definitely needs some words (also because it is orthogonal to neither of the above). 

We agree that the original description of the planes was too terse and have expanded on this in the revised manuscript.

Line 85 - To test the influence of attention, trials were sorted according to two spatial reference planes, based on the location of the stimulus: task-related and task-unrelated (Fig. 1b). The task-related plane corresponded to participants’ binary judgement (Fig 1b, light cyan vertical dashed line) and the task-unrelated plane was orthogonal to this (Fig 1b, dark cyan horizontal dashed line). For example, if a participant was tasked with performing a left-or-right of fixation judgement, then their task-related plane was the vertical boundary between the left and right side of fixation, while their task-unrelated plane was the horizontal boundary. The former (left-right) axis is relevant to their task while the latter (top-bottom) axis is orthogonal and task irrelevant. This orthogonality can be leveraged to analyze the same data twice (once according to the task-related plane and again according to the taskunrelated plane) in order to compare performance when the relative location of an event is either task relevant or irrelevant.

Line 183 - whereas task planes were constant, the stimulus-related plane was defined by the location of the stimulus on the previous trial, and thus varied from trial to trial. That is, on each trial, the target is considered a repeat if it changes location by <|90°| relative to its location on the previous trial, and an alternate if it moves by >|90°|.

(2) While I understand that the authors want the three classical separations, I actually found it misleading. Firstly, for a perceptual scientist to call intervals in the order of seconds (rather than milliseconds), "micro" is technically coming from the raw prawn. Secondly, the divisions are not actually time, but events: micro means one-back paradigm, one event previously, rather than defined by duration. Thirdly, meso isn't really a category, just a few micros stacked up (and there's not much data on this). And macro is basically patterns, or statistical regularities, rather than being a fixed time. I think it would be better either to talk about short-term and long-term, which do not have the connotations I mentioned. Or simply talk about "serial dependence" and "statistical regularities". Or both. 

We agree that the temporal scales defined in the current study are not the only way one could categorize perceptual time. We also agree that by using events to define scales, we ignore the influence of duration. In terms of the categories, we selected these for two reasons: 1) they conveniently group previous phenomena, and 2) they loosely correspond to iconic-, short- and long-term memory. We agree that one could also potentially split it up into two categories (e.g., short- and long-term), but in general, we think any form of discretization will have limitations. For example, Reviewer 1 suggests that the meso category is simply a few micros stacked together. However, there is a rich literature on phenomena associated with sequences of an intermediate length that do not appear to be entirely explained by stacking micro effects (e.g., sequence learning and sequential dependency). We also find that when controlling for micro level effects, there are clear meso level effects. Also, by the logic that meso level effects are just stacked micro effects, one could also argue the same for macro effects. We don’t think this argument is incorrect, rather we think it exemplifies the challenge of discretising temporal scales. Ultimately, the current study was aimed to test whether seemingly disparate phenomena identified in previous work could be captured by unifying principles. To this end we found that these categories were the most useful. However, we have included a “Limitations and future directions” section in the Discussion of the revised manuscript that acknowledges both the alternative scheme proposed by Reviewer 1, and the value of extending this work to consider the influence of duration (as well as events).

Line 488 - Limitations and future directions. One potential limitation of the current study is the categorization of temporal scales according to events, independent of the influence of event duration. While this simplification of time supports comparison between different phenomena associated with each scale (e.g., serial dependence, sequential dependencies, statistical learning), future work could investigate the role of duration to provide a more comprehensive understanding of the mechanisms identified in the current study.

Related to this, while the temporal scales applied here conveniently categorized known sensory phenomena, and partially correspond to iconic-, short-, and long-term memory, they are but one of multiple ways to delineate time. For example, temporal scales could alternatively be defined simply as short- and long-term (e.g., by combining micro and meso scale phenomena). However, this could obscure meaningful differences between phenomena associated with sensory persistence and short-term memory, or qualitative differences in the way that shortsequences of events are processed.

(3) More serious is the issue of precision. Again, this is partially a language problem. When people use the engineering terms "precision" and "accuracy" together, they usually use the same units, such as degrees. Accuracy refers to the distance from the real position (so average accuracy gives bias), and precision is the clustering around the average bias, usually measured as standard deviation. Yet here accuracy is percent correct: also a convention in psychology, but not when contrasting accuracy with precision, in the engineering sense. I suggest you change "accuracy" to "percent correct". On the other hand, I have no idea how precision was defined. All I could find was: "mixture modelling was used to estimate the precision and guess rate of reproduction responses, based on the concentration (k) and height of von Mises and uniform distributions, respectively". I do not know what that means.

In the case of a binary decision, is seems reasonable to use the term “accuracy” to refer to the correspondence between the target state and the response on a task. However, we agree that while our (main) task is binary, the target is not and nor is the secondary task. We thank the reviewer for bringing this to our attention, as we agree that this will be a likely cause of confusion. To avoid confusion we have specifically referred to “task accuracy” throughout the revised manuscript.

With regards to precision, our measure of precision is consistent with what Reviewer 1 describes as such, i.e., the clustering of responses. In particular, the von Mises distribution is essentially a Gaussian distribution in circular space, and the kappa parameter defines the width of the distribution, regardless of the mean, with larger values of kappa indicating narrower (more precise) distributions. We could have used standard deviation to assess precision; however, this would incorrectly combine responses on which participants failed to encode the target (e.g., because of a blink) and were simply guessing. To account for these trials, we applied mixture modelling of guess and genuine responses to isolate the precision of genuine responses, as is standard in the visual working memory literature. However, we agree that this was not sufficiently described in the original manuscript and have elaborated on this method in the revised version.

Line 598 - From the reproduction task, we sought to estimate participant’s recall precision. It is likely that on some trials participants failed to encode the target and were forced to make a response guess. To isolate the recall precision from guess responses, we used mixture modelling to estimate the precision and guess rate of reproduction responses, based on the concentration (k) and height of von Mises and uniform distributions, respectively (Bays et al., 2009). The k parameter of the von Mises distribution reflects its width, which indicates the clustering of responses around a common location.

(4) Previous studies show serial dependence can increase bias but decrease scatter (inverse precision) around the biased estimate. The current study claims to be at odds with that. But are the two measures of precision relatable? Was the real (random) position of the target subtracted from each response, leaving residuals from which the inverse precision was calculated? (If so, the authors should say so..) But if serial dependence biases responses in essentially random directions (depending on the previous position), it will increase the average scatter, decreasing the apparent precision. 

Previous studies have shown that when serial dependence is attractive there is a corresponding increase in precision around small offsets from the previous item (citations). Indeed, attractive biases will lead to reduced scattering (increased precision) around a central attracter. Consistent with previous studies, and this rational, we also found an attractive bias coupled with increased precision. To clarify, for the serial dependency analysis, we calculated bias and precision by binning reproduction responses according to the offset between the current and previous target and then performing the same mixture modelling described above to estimate the mean (bias) and kappa (precision) parameters of the von Mises distribution fit to the angular errors. This was not explained in the original manuscript, so we thank Reviewer 1 for bringing this to our attention and have clarified the analysis in the revised version.

Line 604 - For the serial dependency analysis, we calculated bias and precision by binning reproduction responses according to the angular offset between the current and previous target and then performing mixture modelling to estimate the mean (bias) and k (precision) parameters of the von Mises distribution.

(5) I suspect they are not actually measuring precision, but location accuracy. So the authors could use "percent correct" and "localization accuracy". Or be very clear what they are actually doing. 

As explained in our response to Reviewer 1’s previous comment, we are indeed measuring precision.

Reviewer #2 (Public review):

(1) The abstract should more explicitly mention that conclusions about feedforward mechanisms were derived from a reanalysis of an existing EEG dataset. As it is, it seems to present behavioral data only.

It is not clear what relevance the fact that the data has been analyzed previously has to the results of the current study. However, we do think that it is important to be clear that the EEG recordings were collected separately from the behavioural and eyetracking data, so we have clarified this in the revised abstract.

Line 7 - By integrating behavioural and pupillometry recordings with electroencephalographical recordings from a previous study, we identify two distinct mechanisms that operate across all scales.

(2) The EEG task seems quite different from the others, with location and color changes, if I understand correctly, on streaks of consecutive stimuli shown every 100 ms, with the task involving counting the number of target events. There might be different mechanisms and functions involved, compared to the behavioral experiments reported. 

As stated above, we agree that it is important that readers are aware that the EEG recordings were collected separately to the behavioural and eyetracking data. We were forthright about this in the original manuscript and how now clarified this in the revised abstract. We agree that collecting both sets of data in the same experiment would be a useful validation of the current results and have acknowledged this in a new Limitations and future directions section of the Discussion of the revised manuscript.

Line 501 - Another limitation of the current study is that the EEG recordings were collected in the separate experiment to the behavioural and pupillometry data. The stimuli and task were similar between experiments, but not identical. For example, the EEG experiment employed coloured arc stimuli presented at a constant rate of ~3.3 Hz and participants were tasked with counting the number of stimuli presented at a target location. By contrast, in the behavioural experiment, participants viewed white blobs presented at an average rate of ~2.8 Hz and performed a binary spatial task coupled with an infrequent reproduction task. An advantage of this was that the sensory responses to stimuli in the EEG recordings were not conflated with motor responses; however, future work combining these measures in the same experiment would serve as a validation for the current results.

(3) How is the arbitrary choice of restricting EEG decoding to a small subset of parieto-occipital electrodes justified? Blinks and other artifacts could have been corrected with proper algorithms (e.g., ICA) (Zhang & Luck, 2025) or even left in, as decoders are not necessarily affected by noise. Moreover, trials with blinks occurring at the stimulus time should be better removed, and the arbitrary selection of a subset of electrodes, while reducing the information in input to the decoder, does not account for trials in which a stimulus was missed (e.g., due to blinks).

Electrode selection was based on several factors: 1) reduction of eye movement/blink artifacts (as noted in the original manuscript), 2) consistency with the previous EEG study (Rideaux, 2024) and other similar decoding studies (Buhmann et al., 2024; Harrison et al., 2023; Rideaux et al., 2023), 3) improved signal-to-noise by including only sensors that carry the most position information (as shown in Supplementary Figure 1a and the previous EEG study). We agree that this was insufficiently explained in the original manuscript and have clarified our sensor selection in the revised version.

Line 631 - We only included the parietal, parietal-occipital, and occipital sensors in the analyses to i) reduce the influence of signals produced by eye movements, blinks, and non-sensory cortices, ii) for consistency with similar previous decoding studies (Buhmann et al., 2024; Rideaux, 2024; Rideaux et al., 2025), and iii) to improve decoding accuracy by restricting sensors to those that carried spatial position information (Supplementary Fig. 1a).

(4) The artifact that appears in many of the decoding results is puzzling, and I'm not fully convinced by the speculative explanation involving slow fluctuations. I wonder if a different high-pass filter (e.g., 1 Hz) might have helped. In general, the nature of this artifact requires better clarification and disambiguation.

We agree that the nature of this artifact requires more clarification and disambiguation. Due to relatively slow changes in the neural signal, which are not stimulus-related, there is a degree of temporal autocorrelation in the recordings. This can be filtered out, for example, by using a stricter high-pass filter; however, we tried a range of filters and found that a cut-off of at least 0.7 Hz is required to remove the artifact, and even a filter of 0.2 Hz introduces other (stimulus-related) artifacts, such as above-chance decoding prior to stimulus onset. These stimulus-related artifacts are due to the temporal smearing of data, introduced by the filtering, and have a more pronounced and complex influence on the results and are more difficult to remove through other means, such as the baseline correction applied in the original manuscript.

The temporal autocorrelation is detected by the decoder during training and biases it to classify/decode targets that are presented nearby in time as similar. That is, it learns the neural pattern for a particular stimulus location based on the activity produced by the stimulus and the temporal autocorrelation (determined by slow stimulus unrelated fluctuations). The latter only accounts for a relatively smaller proportion of the variance in the neural recordings under normal circumstances and would typically go undetected when simply plotting decoding accuracy as a function of position. However, it becomes weakly visible when decoding accuracy is plotted as a function of distance from the previous target, as now the bias (towards temporally adjacent targets) aligns with the abscissa. Further, it becomes highly visible when the stimulus labels are shuffled, as now the decoder can only learn from the variance associated with the temporal autocorrelation (and not from the activity produced by the stimulus).

In the linear discriminant analysis, this led to temporally proximal items being more likely to be classified as on the same side. This is why there is above-chance performance for repeat trials (Supplementary Figure 2b), and below-chance performance for alternate trials, even when the labels are shuffled – the temporal autocorrelation produces a general bias towards classifying temporally proximate stimuli as on the same side, which selectively improves the classification accuracy of repeat trials. Fortunately, the bias is relatively constant as a function of time within the epoch and is straightforward to estimate by shuffling the labels, which means that it can be removed through a baseline correction. However, to further demonstrate that the autocorrelation confound cannot account for the differences observed between repeat and alternate trials in the micro classification analysis, we now additionally show the results from a more strictly filtered version of the data (0.7 Hz). These results show a similar pattern as the original, with the additional stimulusrelated artifacts introduced by the strict filter, e.g., above chance decoding prior to stimulus onset.

In the inverted encoding analysis, the same temporal autocorrelation manifests as temporally proximal trials being decoded as more similar locations. This is why there is increased decoding accuracy for targets with small angular offsets from the previous target, even when the labels are shuffled (Supplementary Figure 3c), because it is on these trials that the bias happens to align with the correct position. This leads to an attractive bias towards the previous item, which is most prominent when the labels are shuffled.

To demonstrate the phenomenon, we simulated neural recordings from a population of tuning curves and performed the inverted encoding analysis on a clean version of the data and a version in which we introduced temporal autocorrelation. We then repeated this after shuffling the labels. The simulation produced very similar results to those we observed in the empirical data, with a single exception: while precision in the simulated shuffled data was unaffected by autocorrelation, precision in the unshuffled data was clearly affected by this manipulation. This may explain why we did not find a correlation between the shuffled and unshuffled precision in the original manuscript. 

These results echo those from the classification analysis, albeit in a more continuous space. However, whereas in the classification analysis it was straightforward to perform a baseline correction to remove the influence of general temporal dependency, the more complex nature of the accuracy, precision, and bias parameters over the range of time and delta location makes this approach less appropriate. For example, the bias in the shuffled condition ranged from -180 to 180 degrees, which when subtracted from the bias in the unshuffled condition would produce an equally spurious outcome, i.e., the equal opposite of this extreme bias. Instead for the inverted encoding analysis, we used the data high-pass filtered at 0.7 Hz. As with the classification analysis, this removed the influence of general temporal dependencies, as indicated by the results of the shuffled data analysis (Supplementary Figure 3f), but it also temporally smeared the stimulus-related signal, resulting in above chance decoding accuracy prior to stimulus onset (Supplementary Figure 3d). However, given thar we were primarily interested in the pattern of accuracy, precision, and bias as a function of delta location, and less concerned with the precise temporal dynamics of these changes, which appeared relatively stable in the filtered data. Thus, this was the more suitable approach to removing the general temporal dependencies in the inverted encoding analysis and the one that is presented in Figure 3.

We have updated the revised manuscript in light of these changes, including a fuller description of the artifact and the results from the abovementioned control analyses.

Figure 3 updated.

Figure 3 caption - e) Decoding accuracy for stimulus location, from reanalysis of previously published EEG data (17). Inset shows the EEG sensors included in the analysis (blue dots), and black rectangles indicate the timing of stimulus presentations (solid: target stimulus, dashed: previous and subsequent stimuli). f) Decoding accuracy for location, as a function of time and D location. Bright colours indicate higher decoding accuracy; absolute accuracy values can be inferred from (e). g-i) Average location decoding  (g) accuracy, (h) precision, and (h) bias from 50 – 500 ms following stimulus onset. Horizontal bar in (e) indicates cluster corrected periods of significance; note, all time points were significantly above chance due to temporal smear introduced by strict high-pass filtering (see Supplementary Figure 3 for full details). Note, the temporal abscissa is aligned across (e & f). Shaded regions indicate ±SEM.

Line 218 - To further investigate the influence of serial dependence, we applied inverted encoding modelling to the EEG recordings to decode the angular location of stimuli. We found that decoding accuracy of stimulus location sharply increased from ~60 ms following stimulus onset (Fig. 3e). Note, to reduce the influence of general temporal dependencies, we applied a 0.7 Hz high-pass filter to the data, which temporally smeared the stimulus-related information, resulting in above chance decoding accuracy prior to stimulus presentation (for full details, see Supplementary Figure 3). To understand how serial dependence influences the representation of these features, we inspected decoding accuracy for location as a function of both time and D location (Fig. 3f). We found that decoding accuracy varied depending not only as a function of time, but also as a function of D location. To characterise this relationship, we calculated the average decoding accuracy from 50 ms until the end of the epoch (500 ms), as a function of D location (Fig. 3g). This revealed higher accuracy for targets with larger D location. We found a similar pattern of results for decoding precision (Fig. 3h). These results are consistent with the micro temporal context (behavioural) results, showing that targets that alternated were recalled more precisely. Lastly, we calculated the decoding bias as a function of D location and found a clear repulsive bias away from the previous item (Fig. 3i). While this result is inconsistent with the attractive behavioural bias, it is consistent with recent studies of serial dependence suggesting an initial pattern of repulsion followed by an attractive bias during the response period (20–22).

Line 726 - As shown in Supplementary Figure 3, we found the same general temporal dependencies in the decoding accuracy computed using inverted encoding that were found using linear discriminant classification. However, as a baseline correction would not have been appropriate or effective for the parameters decoded with this approach, we instead used a high-pass filter of 0.7 Hz to remove the confound, while being cautious about interpreting the timing of effects produced by this analysis due to the temporal smear introduced by the filter.

Supplementary Figure 2 updated.

Supplementary Figure 2 caption - Removal of general micro temporal dependencies in EEG responses. We found that there were differences in classification accuracy for repeat and alternate stimuli in the EEG data, even when stimulus labels were shuffled. This is likely due to temporal autocorrelation within the EEG data due to low frequency signal changes that are unrelated to the decoded stimulus dimension. This signal trains the decoder to classify temporally proximal stimuli as the same class, leading to a bias towards repeat classification. For example, in general, the EEG signal during trial one is likely to be more similar to that during trial two than during trial ten, because of low frequency trends in the recordings. If the decoder has been trained to classify the signal associated with trial one as a leftward stimulus, then it will be more likely to classify trial two as a leftward stimulus too. These autocorrelations are unrelated to stimulus features; thus, to isolate the influence of stimulus-specific temporal context, we subtracted the classification accuracy produced by shuffling the stimulus labels from the unshuffled accuracy (as presented in Figure 2e, f). We confirmed that using a stricter high-pass filter (0.7 Hz) removes this artifact, as indicated by the equal decoding accuracy between the two shuffled conditions. However, the stricter high-pass filter temporally smears the stimulus-related signal, which introduces other (stimulus-related) artifacts, e.g., above-chance decoding accuracy prior to stimulus presentation, that are larger and more complex, i.e., changing over time. Thus, we opted to use the original high pass filter (0.1 Hz) and apply a baseline correction. a) The uncorrected classification  accuracy along task related and unrelated planes. Note that these results are the same as the corrected version shown in Figure 2e, because the confound is only apparent when accuracy is grouped according to temporal context.

b) Same as (a), but split into repeat and alternate stimuli, along (left) task-related and (right) unrelated planes. Classification  accuracy when labels are shuffled is also shown. Inset in (a) shows the EEG sensors included in the analysis (blue dots). (c, d) Same as (a, b), but on data filtered using a 0.7 Hz high-pass filter. Black rectangles indicate the timing of stimulus presentations (solid: target stimulus, dashed: previous and subsequent stimuli). Shaded regions indicate ±SEM.

Supplementary Figure 3 updated.

Supplementary Figure 3 caption - Removal of general temporal dependencies in EEG responses for inverted encoding analyses. As described in Methods - Neural Decoding, we used inverted encoding modelling of EEG recordings to estimate the decoding accuracy, precision, and bias of stimulus location. Just as in the linear discriminant classification analysis, we also found the influence of general temporal dependencies in the results produced by the inverted encoding analysis. In particular, there was increased decoding accuracy for targets with low D location. This was weakly evident in the period prior to stimulus presentation, but clearly visible when the labels were shuffled. These results are mirror those from the classification analysis, albeit in a more continuous space. However, whereas in the classification analysis it was straightforward to perform a baseline correction to remove the influence of general temporal dependency, the more complex nature of the accuracy, precision, and bias parameters over the range of time and D location makes this approach less appropriate. For example, the bias in the shuffled condition ranged from -180° to 180°, which when subtracted from the bias in the unshuffled condition would produce an equally spurious outcome, i.e., the equal opposite of this extreme bias. Instead for the inverted encoding analysis, we used the data high-pass filtered at 0.7 Hz. As with the classification analysis, this significantly reduced the influence of general temporal dependencies, as indicated by the results of the shuffled data analysis, but it also temporally smeared the stimulus-related signal, resulting in above chance decoding accuracy prior to stimulus onset. However, we were primarily interested in the pattern of accuracy, precision, and bias as a function of D location, and less concerned with the precise temporal dynamics of these changes. Thus, this was the more suitable approach to removing the general temporal dependencies in the inverted encoding analysis and the one that is presented in Figure 3. (a) Decoding accuracy as a function of time for the EEG data filtered using a 0.1 Hz high-pass filter. Inset shows the EEG sensors included in the analysis (blue dots), and black rectangles indicate the timing of stimulus presentations (solid: target stimulus, dashed: previous and subsequent stimuli). (b, c) The same as (a), but as a function of time and D location for (b) the original data and (c) data with shuffled labels. (d-f) Same as (a-c), but for data filtered using a 0.7 Hz high-pass filter. Shaded regions in (a, d) indicate ±SEM. Horizontal bars in (a, d) indicate cluster corrected periods of significance; note, all time points in (d) were significantly above chance. Note, the temporal abscissa is vertically aligned across plots (a-c & d-f).

In the process of performing these additional analyses and simulations, we became aware that the sign of the decoding bias in the inverted encoding analyses had been interpreted in the wrong direction. That is, where we previously reported an initial attractive bias followed by a repulsive bias relative to the previous target, we have in fact found the opposite, an initial repulsive bias followed by an attractive bias relative to the previous target. Based on the new control analyses and simulations, we think that the latter attractive bias was due to general temporal dependencies. That is, in the filtered data, we only observe a repulsive bias. While the bias associated with serial dependence was not a primary feature of the study, this (somewhat embarrassing) discovery has led to reinterpretation of some results relating to serial dependence. However, it is encouraging to see that our results now align with those of recent studies (Fischer et al., 2024; Luo et al., 2025; Sheehan et al. 2024).

Line 385 - Our corresponding EEG analyses revealed better decoding accuracy and precision for stimuli preceded by those that were different and a bias away from the previous stimulus. These results are consistent with finding that alternating stimuli are recalled more precisely. Further, while the repulsive pattern of biases is inconsistent with the observed behavioural attractive biases, it is consistent with recent work on serial dependence indicating an initial period of repulsion, followed by an attractive bias during the response period (20–22). These findings indicate that serial dependence and first-order sequential dependencies can be explained by the same underlying principle.

(5) Given the relatively early decoding results and surprisingly early differences in decoding peaks, it would be useful to visualize ERPs across conditions to better understand the latencies and ERP components involved in the task.

A rapid presentation design was used in the EEG experiment, and while this is well suited to decoding analyses, unfortunately we cannot resolve ERPs because the univariate signal is dominated by an oscillation at the stimulus presentation frequency (~3 Hz). We agree that this could be useful to examine in future work.

(6) It is unclear why the precision derived from IEM results is considered reliable while the accuracy is dismissed due to the artifact, given that both seem to be computed from the same set of decoding error angles (equations 8-9).

This point has been addressed in our response to point (4).

(7) What is the rationale for selecting five past events as the meso-scale? Prior history effects have been shown to extend much further back in time (Fritsche et al., 2020). 

We used five previous items in the meso analyses to be consistent with previous research on sequential dependencies (Bertelson, 1961; Gao et al., 2009; Jentzsch & Sommer, 2002; Kirby, 1976; Remington, 1969). However, we agree that these effects likely extend further and have acknowledged this in the revied version of the manuscript.

Line 240 - Higher-order sequential dependences are an example of how stimuli (at least) as far back as five events in the past can shape the speed and task accuracy of responses to the current stimulus (9, 10); however, note that these effects have been observed for more than five events (20).

(8) The decoding bias results, particularly the sequence of attraction and repulsion, appear to run counter to the temporal dynamics reported in recent studies (Fischer et al., 2024; Luo et al., 2025; Sheehan & Serences, 2022). 

This point has been addressed in our response to point (4).

(9) The repulsive component in the decoding results (e.g., Figure 3h) seems implausibly large, with orientation differences exceeding what is typically observed in behavior. 

As noted in our response to point (4), this bias was likely due to the general temporal dependency confound and has been removed in the revised version of the manuscript.

(10) The pattern of accuracy, response times, and precision reported in Figure 3 (also line 188) resembles results reported in earlier work (Stewart, 2007) and in recent studies suggesting that integration may lead to interference at intermediate stimulus differences rather than improvement for similar stimuli (Ozkirli et al., 2025).

Thank you for bringing this to our attention, we have acknowledged this in the revised manuscript.

Line 197 - Consistent with our previous binary analysis, and with previous work (19), we also found that responses were faster and more accurate when D location was small (Fig. 3b, c).

(11) Some figures show larger group-level variability in specific conditions but not others (e.g., Figures 2b-c and 5b-c). I suggest reporting effect sizes for all statistical tests to provide a clearer sense of the strength of the observed effects. 

Yes, as noted in the original manuscript, we find significant differences between the variance task-related and -unrelated conditions. We think this is due to opposing forces in the task-related condition: 

“The increased variability of response time differences across the taskrelated plane likely reflects individual differences in attention and prioritization of responding either quickly or accurately. On each trial, the correct response (e.g., left or right) was equally probable. So, to perform the task accurately, participants were motivated to respond without bias, i.e., without being influenced by the previous stimulus. We would expect this to reduce the difference in response time for repeat and alternate stimuli across the taskrelated plane, but not the task-unrelated plane. However, attention may amplify the bias towards making faster responses for repeat stimuli, by increasing awareness of the identity of stimuli as either repeats or alternations (17). These two opposing forces vary with task engagement and strategy and thus would be expected produce increased variability across the task-related plane.” We agree that providing effect sizes may provided a clearer sense of the observed effects and have done so in the revised version of the manuscript.

Line 739 - For Wilcoxon signed rank tests, the rank-biserial correlation (r) was calculated as an estimate of effect size, where 0.1, 0.3, and 0.5 indicate small, medium, and large effects, respectively (54). For Friedman’s ANONA tests, Kendal’s W was calculated as an estimate of effect size, where 0.1, 0.3, and 0.5 indicate small, medium, and large effects, respectively (55).

(12) The statement that "serial dependence is associated with sensory stimuli being perceived as more similar" appears inconsistent with much of the literature suggesting that these effects occur at post-perceptual stages (Barbosa et al., 2020; Bliss et al., 2017; Ceylan et al., 2021; Fischer et al., 2024; Fritsche et al., 2017; Sheehan & Serences, 2022). 

In light of the revised analyses, this statement has been removed from the manuscript.

(13) If I understand correctly, the reproduction bias (i.e., serial dependence) is estimated on a small subset of the data (10%). Were the data analyzed by pooling across subjects?

The dual reproduction task only occurred on 10% of trials. There were approximately 2000 trials, so ~200 reproduction responses. For the micro and macro analyses, this was sufficient to estimate precision within each of the experimental conditions (repeat/alternate, expected/unexpected). However, it is likely that we were not able to reproduce the effect of precision at the meso level across both experiments because we lacked sufficient responses to reliably estimate precision when split across the eight sequence conditions. Despite this, the data was always analysed within subjects.

(14) I'm also not convinced that biases observed in forced-choice and reproduction tasks should be interpreted as arising from the same process or mechanism. Some of the effects described here could instead be consistent with classic priming. 

We agree that the results associated with the forced-choice task (response time task accuracy) were likely due to motor priming, but that a separate (predictive) mechanism may explain the (precision) results associated with the reproduction task. These are two mechanisms we think are operating across the three temporal scales investigated in the current study.

Reviewing Editor Comments:

(1) Clarify task design and measurement: The dense presentation makes it difficult to understand key design elements and their implications. Please provide clearer descriptions of all task elements, and how they relate to each other (EEG vs. behaviour, stimulus plane vs. TR and TU plane, reproduction vs. discrimination and role of priming), and clearly explain how key measures were computed for each of these (e.g., precision, accuracy, reproduction bias).

In the revised manuscript, we have expanded on descriptions of the source and nature of the data (behavioural and EEG), the different planes analyzed in the behavioural task, and how key metrics (e.g., precision) were computed.

(2) Offer more insight into underlying data, including original ERP waveforms to aid interpretation of decoding results and the timing of effects. In particular, unpack the decoding temporal confound further.

In the revised manuscript, we have considerably offered more insight into the decoding results, in particular, the nature of the temporal confound. We were unable to assess ERPs due to the rapid presentation design employed in the EEG experiment.

(3) Justify arbitrary choices such as electrode selection for EEG decoding (e.g., limiting to parieto-occipital sensors), number of trials in meso scale, and the time terminology itself.

In the revised manuscript, we have clarified the reasons for electrode selection.

(3) Discuss deviations from literature: Several findings appear to contradict or diverge from previous literature (e.g., effects of serial dependence). These discrepancies could be discussed in more depth. 

Upon re-analysis of the serial dependence bias and removal of the temporal confound, the results of the revised manuscript now align with those from previous literature, which has been acknowledged.

Reviewer #1 (Recommendations for the authors):

(1) would like to use my reviewer's prerogative to mention a couple of relevant publications. 

Galluzzi et al (Journal of Vision, 2022) "Visual priming and serial dependence are mediated by separate mechanisms" suggests exactly that, which is relevant to this study.

Xie et al. (Communications Psychology, 2025) "Recent, but not long-term, priors induce behavioral oscillations in peri-saccadic vision" also seems relevant to the issue of different mechanisms. 

Thank you for bringing these studies to our attention. We agree that they are both relevant have referenced both appropriately in the revised version of the manuscript.

Reviewer #2 (Recommendations for the authors): 

(1) I find the discussion on attention and awareness (from line 127 onward) somewhat vague and requiring clarification.

We agree that this statement was vague and referred to “awareness” without operationation. We have revised this statement to improve clarity.

Line 135 - However, task-relatedness may amplify the bias towards making faster responses for repeat stimuli, by increasing attention to the identity of stimuli as either repeats or alternations (17).

(2) Line 140: It's hard to argue that there are expectations that the image of an object on the retina is likely to stay the same, since retinal input is always changing. 

We agree that retinal input is often changing, e.g., due to saccades, self-motion, and world motion. However, for a prediction to be useful, e.g., to reduce metabolic expenditure or speed up responses, it must be somewhat precise, so a prediction that retinal input will change is not necessarily useful, unless it can specify what it will change to. Given retinal input of x at time t, the range of possible values of x at time t+1 (predicting change) is infinite. By contrast, if we predict that x=x at time t+1 (no change), then we can make a precise prediction. There is, of course, other information that could be used to reduce the parameter space of predicted change from x at time t, e.g., the value of x at time t-1, and we think this drives predictions too. However, across the infinite distribution of changes from x, zero change will occur more frequently than any other value, so we think it’s reasonable to assert that the brain may be sensitive to this pattern.

(3) Line 564: The gambler's fallacy usually involves sequences longer than just one event.

Yes, we agree that this phenomenon is associated with longer sequences. This section of the manuscript was in regards to previous findings that were not directly relevant to the current study and has been removed in the revised version.

(4) In the shared PDF, the light and dark cyan colors used do not appear clearly distinguishable. 

I expect this is due to poor document processing or low-quality image embeddings. I will check that they are distinguishable in the final version.

References: 

Barbosa, J., Stein, H., Martinez, R. L., Galan-Gadea, A., Li, S., Dalmau, J., Adam, K. C. S., Valls-Solé, J., Constantinidis, C., & Compte, A. (2020). Interplay between persistent activity and activity-silent dynamics in the prefrontal cortex underlies serial biases in working memory. Nature Neuroscience, 23(8), Articolo 8. https://doi.org/10.1038/s41593-020-0644-4

Bliss, D. P., Sun, J. J., & D'Esposito, M. (2017). Serial dependence is absent at the time of perception but increases in visual working memory. Scientific reports, 7(1), 14739. 

Ceylan, G., Herzog, M. H., & Pascucci, D. (2021). Serial dependence does not originate from low-level visual processing. Cognition, 212, 104709. https://doi.org/10.1016/j.cognition.2021.104709

Fischer, C., Kaiser, J., & Bledowski, C. (2024). A direct neural signature of serial dependence in working memory. eLife, 13. https://doi.org/10.7554/eLife.99478.1

Fritsche, M., Mostert, P., & de Lange, F. P. (2017). Opposite effects of recent history on perception and decision. Current Biology, 27(4), 590-595. 

Fritsche, M., Spaak, E., & de Lange, F. P. (2020). A Bayesian and efficient observer model explains concurrent attractive and repulsive history biases in visual perception. eLife, 9, e55389. https://doi.org/10.7554/eLife.55389

Gekas, N., McDermott, K. C., & Mamassian, P. (2019). Disambiguating serial effects of multiple timescales. Journal of vision, 19(6), 24-24. 

Luo, M., Zhang, H., Fang, F., & Luo, H. (2025). Reactivation of previous decisions repulsively biases sensory encoding but attractively biases decision-making. PLOS Biology, 23(4), e3003150. https://doi.org/10.1371/journal.pbio.3003150

Ozkirli, A., Pascucci, D., & Herzog, M. H. (2025). Failure to replicate a superiority effect in crowding. Nature Communications, 16(1), 1637. https://doi.org/10.1038/s41467025-56762-5

Sheehan, T. C., & Serences, J. T. (2022). Attractive serial dependence overcomes repulsive neuronal adaptation. PLoS biology, 20(9), e3001711. 

Stewart, N. (2007). Absolute identification is relative: A reply to Brown, Marley, and

Lacouture (2007).  Psychological  Review, 114, 533-538. https://doi.org/10.1037/0033-295X.114.2.533

Treisman, M., & Williams, T. C. (1984). A theory of criterion setting with an application to sequential dependencies. Psychological review, 91(1), 68. 

Zhang, G., & Luck, S. J. (2025). Assessing the impact of artifact correction and artifact rejection on the performance of SVM- and LDA-based decoding of EEG signals. NeuroImage, 316, 121304. https://doi.org/10.1016/j.neuroimage.2025.121304

Reviewer #3 (Public review):

Summary:

This study provides the Drosophila community with a large collection of new split-Gal4 descending neuron genetic lines. They extend previous efforts to characterize and identify genetic lines for this important class of neurons by providing images of descending neurons and a metric for genetic lines based on specificity and consistency. Their discussion highlights several applications of this collection, for example, to understand the function of new descending neurons through optogenetic and/or physiological characterization. They also helpfully discuss caveats, encouraging users of this collection to validate expression patterns and to be careful when interpreting optogenetic experimental results, considering potential off-target labeling in the lines. Overall, members of the Drosophila community interested in understanding the function of descending neurons and their role in behavior will find this a helpful resource.

Strengths:

(1) The authors extend the previous genetic access of descending neurons in Drosophila to over 800 split-Gal4 lines and 190 cell types (nearly half of the known population of descending neurons). The authors update and at times correct the previous identification of descending neurons from a previous, large-scale analysis. The authors extend and, at times, correct previous efforts at characterizing these neurons.

(2) Clear images of descending neurons labeled by new genetic lines are presented in the main figure papers for reference.

(3) This study classifies lines labeling descending neurons using a quality score to indicate specificity and consistency. They provide this for the entire set of genetic lines, a valuable assessment for researchers interested in targeting these neurons for optogenetic or physiological characterization.

Weaknesses:

Although this paper represents a substantial effort and useful contribution to the Drosophila community, a few weaknesses, primarily regarding the specificity and reliability of genetic lines, remain:

(1) The authors state that optogenetic activation of DN types using the new split-GAL4 lines is expected to reliably activate the target neurons with virtually no off-target effects in the rest of the central nervous system. More data supporting this conclusion, including both qualitative and quantitative anatomical evidence, would strengthen this claim.

(2) The authors do recommend that researchers using these lines examine expression patterns themselves to evaluate line cleanliness and consistency, but some analysis by the authors would be useful, for example, providing guidelines for best practices to perform this evaluation.

(3) Changes in expression patterns after several generations are noted by the authors, weakening confidence somewhat in the long-term usefulness of this collection of genetic lines.

DOI: 10.1101/2025.09.03.673940

Resource: RRID:BDSC_63184

Curator: @scibot

SciCrunch record: RRID:BDSC_63184

What is this?

Pólya's book "How to Solve IT" came out, translated by Imre Lakator into Hungarian

my high school Teacher Boreczky Elemer translted Lakaotos's PhD thesis published as a book with the title Proofs and Refutations

into Hungarian and my best friend

and close collaborators over the past 3 years Andras Benedek assisted the translation with his knowledge of Mathematics.

Document de Synthèse : L'Emprise du Numérique et les Dangers des Réseaux Sociaux

Introduction : Une Lutte "David contre Goliath"

Ce briefing expose la problématique alarmante de l'impact des réseaux sociaux sur la santé mentale et la sécurité des enfants et adolescents.

Il met en lumière les témoignages poignants de victimes et de leurs familles, les actions en justice, le manque de régulation et les tactiques des géants de la technologie.

La lutte est présentée comme un combat "David contre Goliath" entre des familles endeuillées et des entreprises multimillionnaires.

Thèmes Principaux et Faits Importants :

1. Addiction et Impact sur la Santé Mentale des Adolescents :

Témoignage d'Alexis Spence : Alexis a développé de l'anorexie, de la dépression et s'est scarifiée à partir de 11 ans après avoir téléchargé Instagram.

L'algorithme l'a submergée de contenus sur la minceur, puis de photos de personnes anorexiques, de contenus tristes et déprimants.

Elle décrit comment elle s'est enfermée dans sa souffrance, devenant "une personne qu'on ne reconnaissait plus".

Citation : "J'avais 11 ans quand j'ai téléchargé Instagram pour la première fois et c'est là que tout a commencé. [...]

À force de regarder de la fitness, l'application a commencé à me montrer des mannequins. [...] Les mannequins étaient de plus en plus minces jusqu'à ce que ce ne soient plus des mannequins mais des personnes anorexiques."

Citation : "Mon compte est devenu rempli de ces contenus. C'était des photos tristes en noir et blanc avec des textes déprimants."

Citation : "Je pense vraiment qu'Instagram a une grande part de responsabilité dans les problèmes de santé mentale dont j'ai souffert, surtout si on prend en compte mon Je n'avais que 13 ans."

Idées Suicidaires et Automutilation : Plusieurs témoignages de parents évoquent les scarifications et les tentatives de suicide de leurs enfants, directement liées aux contenus diffusés par les algorithmes.

Citation : "J'ai posté une photo qui disait que j'avais l'intention de me suicider ce soir-là. [...] J'ai reçu un appel de l'assistante sociale. Vous devez venir à l'école immédiatement. Votre fille a tenté de se suicider."

Citation : "On avait mis en place des scarifications un peu contrôlées. Donc lorsqu'il allait pas bien, il me demandait ses lames. J'attendais derrière la porte de sa chambre et voir se scarifier."

Déni des Plateformes : Les dirigeants des Big Tech ont longtemps nié le lien entre leurs plateformes et les problèmes de santé mentale.

Citation d’un sénateur interrogeant Mark Zuckerberg : "everyone knows that kids who spend a lot of time too much time on your platforms are at risk and it's not just the mental health issues. I mean let me ask you a question is your platform safe for kids I believe it is but there's a difference between country if we don't start honest."

2. Cyberpédocriminalité et Manque de Sécurité :

Prolifération de Contenus Dangereux : Les plateformes sont des vecteurs de cyberpédocriminalité, avec des prédateurs sexuels qui exploitent les algorithmes et les fonctionnalités pour cibler les enfants. Interpol Europe est "débordé par la cyberpédocriminalité".

Citation : "on est quand même un moment assez crucial où Interpol Europe on est débordé par la cyberpédocriminalité et les plateformes elles sont vraiment utilisées par les prédateurs sexuels."

Citation : "Plus de 80 % des cas de sextorsion, c'est sur Instagram et Snapchat. Urgence à ce qu'elles fassent le ménage."

Algorithmes Complices : Une expérience avec un avatar de 13 ans, "Lili", démontre que les algorithmes proposent très rapidement des contenus sombres, des scènes d'automutilation, du vampirisme, des scènes sexualisées, et même l'apologie du suicide, même sans recherche préalable de l'utilisateur.

Citation : "Sur TikTok, l'algorithme est encore plus rapide. En moins de 5 minutes, la plateforme met en avant des vidéos faisant l'apologie du suicide."

Citation : "En quelques clics, la petite Lili se retrouve témoin de plusieurs viols sur mineurs."

Techniques de Manipulation des Prédateurs : Des modes d'emploi pour piéger les enfants sont disponibles en ligne. Les prédateurs utilisent des tactiques psychologiques comme le "love bombing" et la sexualisation progressive des conversations, détournant des codes familiers (personnages de dessins animés) pour normaliser des comportements abusifs.

Citation : "Ils vont vraiment jouer sur plein de ressorts psychologiques différents au niveau des enfants."

Citation : "Le fait de reprendre des codes par exemple de la Reine des Neiges, enfin des des différents personnages comme ça, il y a il y a des choses qui sont familières qui font pas forcément heurté comme un cohite frontal de de pornographie."

Réponse Insuffisante des Plateformes : Malgré les signalements, les plateformes ne suppriment pas toujours les contenus illicites et les comptes de prédateurs. Leurs efforts de sécurité sont jugés insuffisants.

Citation d’un sénateur : "Mr. Zuckerberg, what the hell were you thinking? [...] In what I understand get resources in what saying universe is there a link for se results anyway?" (concernant un message d'avertissement offrant l'option "voir les résultats quand même" pour des contenus problématiques).

Citation d’un représentant de l’office de lutte contre la cyberpédocriminalité : "On a très très peu de signalement qui parviennent par exemple WhatsApp."

3. Le Rôle des Entreprises de Technologie et leur Responsabilité :

Le "Business Model" des Big Tech : Les documents internes de Meta révélés par Frances Haugen (une lanceuse d'alerte) montrent que l'entreprise était consciente des vulnérabilités des enfants et des impacts négatifs, mais a privilégié les profits.

Citation : "Ces documents montrent que depuis 20 ans mett à enquête sur les vulnérabilités des enfants."

Citation : "Facebook repeatedly encounter conflicts between its own profits and our safety."

Citation d’un sénateur : "Children are not your priority. Children are your product. Children you see as a way to make money."

L'Article 230 comme Bouclier : Les entreprises se cachent derrière l'article 230 du droit américain, qui leur confère une immunité en tant qu'hébergeurs de contenu, les protégeant des poursuites judiciaires pour le contenu publié par leurs utilisateurs.

Citation : "Ces entreprises se cachent derrière l'article 230 qui est vraiment archaïque. Ils utilisent cette loi comme bouclier pour dire vous ne pouvez pas nous attaquer."

Citation d’un sénateur : "It's an astonishing benefit that your industry has that no other industry has. They just don't have to worry about being held in court if they're negligent."

Lobbying Intense : Pour contrer les projets de loi visant à lever leur immunité et à les responsabiliser, les Big Five ont dépensé près de 100 millions de dollars en lobbying, plus de la moitié provenant du groupe Meta.

Citation : "Ils ont dépensé près de 100 millions de dollars pour faire renoncer les députés et les sénateur, plus de la moitié de cette somme provient du seul groupe métablill."

4. Mobilisation Collective et Actions en Justice :

Mouvement Mondial des Parents : Des parents et des familles du monde entier se mobilisent pour exiger des changements et une meilleure protection des enfants.

Citation d’un père : "Nous en tant que père Tant que mer nous ne faisons rien, personne ne le fera à notre place. C'est notre lutte."

Citation d’une mère : "Nous sommes des milliers de pères et de mères qui pensons que les smartphones et les réseaux sociaux ne sont pas bons pour nos fils et nos filles."

Collectif Algos Victima : Fondé par l'avocate Maître Laure Bouttron Marmion, ce collectif rassemble des familles d'adolescents dont le suicide est lié aux réseaux sociaux, notamment l'affaire de Marie, une jeune fille décédée en 2021.

Le collectif vise à faire reconnaître la responsabilité des entreprises.

Citation de Maître Bouttron Marmion : "On souhaite la régulation cette plateforme qui aujourd'hui est au degré zéro de la régulation."

Citation de Maître Bouttron Marmion : "On ne peut pas ne pas considérer que le réseau social n'a pas sa part de responsabilité dans le suicide de Marie."

Actions Judiciaires aux États-Unis et en Europe : Plus de 1000 familles et 44 États américains sur 50 poursuivent les géants de la technologie. Des avocats cherchent des bases juridiques solides pour les attaquer.

Citation d’Alexis : "Depuis, plus de 1000 familles nous ont rejoint et maintenant 44 États américains sur 50 attaquent en justice les grandes entreprises technologiques pour qu'ils soient tenu responsable." Initiatives de Réglementation : Des projets de loi comme le "Kids Online Safety Act", le "EARN IT Act" et le "STOP CSAM Act" visent à rendre les entreprises responsables de l'exploitation des enfants et à supprimer leur immunité.

Citation d’un sénateur : "We have bills that have passed through this incredibly diverse committee when it comes to our political views. Kids online safety act earned act stopam act."

5. Solutions et Espoirs :

Interdiction des Smartphones avant un certain âge : En Espagne, un mouvement de parents a réussi à réglementer l'utilisation des téléphones portables dans les collèges et milite pour une interdiction totale avant 16 ans.

Citation d’une mère : "Nous souhaitons que les smartphones ne puissent pas être utilisés avant 16 ans."

Citation : "Maintenant, dans les classes et dans la cour, ils ne peuvent plus utiliser leur téléphone portable, sauf si le professeur le demande à un moment précis."

Désactivation des Algorithmes pour les Mineurs : Une demande clé est la désactivation des algorithmes pour les mineurs afin de les protéger des contenus inappropriés.

Citation : "Nous devons veiller à ce que l'algorithme soit désactivé pour les mineurs."

Espoir dans la Lutte "d'en bas" : L'espoir réside dans la mobilisation des familles et des citoyens face à l'inaction des entreprises et des législateurs.

Citation : "J'ai beaucoup plus d'espoir dans les familles, dans la lutte qui vient d'en bas plutôt que d'en haut."

L'excuse de Zuckerberg : Lors d'une audition au Sénat, Mark Zuckerberg a été contraint de s'excuser devant les victimes, bien que ses excuses aient été perçues comme insincères et non liées à la nature de son produit.

Citation de Mark Zuckerberg : "I'm sorry for everything that you all gone through terrible. No one should have to go through the things that your families have have suffered."

Citation d’Alexis : "Ses excuses n'étaient pas sincères. Il s'est excusé mais il ne s'est pas excusé à cause de son produit qu'il appelle lui-même un produit et qui fait du mal."

Conclusion : Un Monde Post-Écran pour les Enfants ?

Le briefing souligne que le consensus sur la menace profonde que représentent les réseaux sociaux pour la santé mentale et la sécurité des enfants est désormais établi.

La persévérance des victimes et des familles est cruciale pour obliger les entreprises et les législateurs à agir, avec l'espoir qu'un jour, "ça nous semblera tout aussi horrible qu'un enfant possède un téléphone portable et soit déconnecté de la vie".

I experience this daily with my 2.5 year old sister, she's working on her speech and learning how to pronounce things such as "yes" which she says "yeth" or when somebody asks how she's doing, she says "two n half" because she misunderstands what they're asking

You can compare this to Yoda's speech pattern, literally out of order. "Do or do not. There is no try." or "The greatest teacher. Failure is." - Yoda

The English language is also a complicated one. It's very patchworked and built by different languages and also doesn't follow consistent rules like other languages do. sometimes I believe the only consistent rule of the english language is that it's inconsistent.

Briefing : L'Alcoolisme au Féminin – Briser le Tabou

Objectif : Ce briefing vise à synthétiser les principaux thèmes, idées et faits marquants concernant l'alcoolisme au féminin, tels qu'abordés dans les extraits sonores de "Alcool au féminin, elles brisent le tabou".

Résumé Exécutif

L'alcoolisme au féminin est une maladie complexe, souvent invisible et entourée d'une honte et d'une culpabilité profondes, rendant sa détection et sa prise en charge plus difficiles que chez les hommes.

Les femmes sont physiologiquement plus vulnérables à l'alcool et l'utilisent souvent comme une "béquille" pour gérer un mal-être, une anxiété, une dépression, ou des traumatismes passés, notamment des violences sexuelles.

L'industrie de l'alcool cible activement les femmes avec des produits et des stratégies marketing spécifiques.

Le chemin vers la sobriété est long, marqué par des rechutes possibles, et nécessite un soutien indispensable de l'entourage, des groupes de parole, et des structures spécialisées.

Briser le tabou et reconnaître l'alcoolisme comme une maladie est crucial pour aider les femmes à s'en sortir.

Thèmes et Idées Principales

1. L'Alcoolisme Féminin : Une Réalité Invisible et Sous-Estimée

Prévalence incertaine : Le nombre de femmes dépendantes à l'alcool est difficile à estimer, oscillant entre 100 000 et 1,5 million, en raison du silence imposé par la honte et la culpabilité.

Honte et Culpabilité Accrues pour les Femmes : "Une femme qui boit tout d'un coup, c'est une honte. C'est deux fois plus dur qu'un homme.

Une femme alcoolique, c'est vraiment on nous le pardonne pas." Ce jugement social conduit à l'isolement et au déni, retardant la consultation de 10 ans en moyenne par rapport aux hommes.

Stratégies de Dissimulation : Les femmes mettent souvent en place des stratagèmes pour cacher leur consommation, comme planquer des bouteilles dans des endroits inattendus (ex: "planquer la bouteille dans le landau de ma fille").

2. Vulnérabilité Physiologique et Conséquences Spécifiques

Métabolisme et Dilution : "Quand on donne la même quantité d'alcool à un homme et une femme du même poids, l'alcoolémie sera plus élevée chez la femme."

Cela est dû à un métabolisme plus lent et une moindre proportion d'eau dans le corps féminin.

Impacts Accrus sur la Santé : Les maladies (cirrhose, maladies cardiovasculaires, troubles cognitifs comme la mémoire et la concentration) se développent plus rapidement et sont plus violentes chez les femmes.

Un lien fort existe avec le risque de cancer du sein, "quelque chose qui est très peu connu".

Signes Visibles : L'alcool "abîme énormément et chez les femmes, ça se voit. Une femme alcoolique, ça se voit au visage, aux yeux. Les yeux sont tristes souvent. La peau est abîmée."

3. Les Racines Psychologiques de l'Addiction chez les Femmes

Alcool comme Béquille ou Auto-Médication : Contrairement aux hommes dont la consommation "part d'une consommation plus festive qui dérape", les femmes "le plus souvent consomment pour traiter quelque chose, pour traiter un mal-être, une dépression, une anxiété."

Noémilovski témoigne : "j'ai bu de l'alcool comme j'aurais pris des médicaments pour pour apaiser et l'angoisse et la dépression."

Traumatismes d'Enfance et Violences Sexuelles : Derrière l'addiction se cachent souvent des "traumatismes d'enfance, des drames intimes".

Le vécu d'une agression sexuelle peut multiplier "jusqu'à 36 le risque de développer une addiction".

L'alcool permet "d'économiser, d'avoir à se confronter à ces horreurs". Laurence, par exemple, a découvert que son alcoolisme masquait un inceste.

Sentiment de Solitude et Différence : Muriel Robin a ressenti : "je me sentais tellement différente que j'étais très seule. Donc j'étais en souffrance."

L'alcool est alors apparu comme une solution pour "masquer tout", "penser à rien" et "se perdre".

L'Illusion du Plaisir et du "Soi-Même" : Beaucoup croient que l'alcool est une source de plaisir ou qu'il permet d'être "soi-même".

Noémilovski réfute cette idée : "on n'est pas soi-même. On est l'alcool, on est l'effet de l'alcool."

L'alcool crée une "chaleur, une douceur, un calme", mais mène à un "cercle vicieux" où l'on est "encore plus déprimé que la veille, encore plus angoissé".

4. L'Influence de la Société et du Marketing de l'Alcool

Normalisation de la Consommation Féminine : Boire est devenu "courant" pour les femmes, une manière de "s'intégrer", de décompresser, ou de faire la fête.

Lucille Woodward souligne : "on a toujours eu l'impression que c'était cool de boire et normal et plutôt une démonstration de force de la femme et on se rend pas compte en fait que finalement ça nous affaiblit."

Ciblage Marketing Spécifique : L'industrie de l'alcool cible les femmes avec des produits et des packagings "ultra girly" (ex: "tube de rouge à lèvres géant qui en fait contient une bouteille de champagne") et des saveurs aromatisées (mangue, litchi, cerise, pamplemousse) pour des alcools "moins forts".

Ces stratégies "associent un univers positif à un produit qui est quand même problématique pour la santé."

La "Zone Grise" : De nombreuses femmes se situent dans une "zone grise" où elles dépassent les limites recommandées (10 verres/semaine) sans se considérer comme dépendantes.

Le critère n'est pas le nombre de verres, mais "quand on ne peut pas s'en séparer et quand on a le sentiment d'avoir perdu la liberté de s'abstenir" et l'impact sur la santé et l'environnement.

5. Le Chemin vers la Sobriété : Un Combat Difficile mais Possible

Reconnaître la Maladie : L'alcoolisme est une maladie, non un manque de volonté.

C'est "une maladie que l'on peut soigner à condition d'oser la regarder en face."

L'Importance du Soutien : "L'alcool, on ne peut pas s'en sortir seul. Il faut demander de l'aide."

Groupes de parole : Les Alcooliques Anonymes ont été une "révélation" pour Noémilovski grâce à l'absence de jugement.

Des groupes spécifiques aux femmes permettent de reconnaître une "consommation autothérapeutique" commune.

Entraide et Témoignages : Des initiatives comme celle de Sylvie, qui aide d'autres femmes via internet, sont cruciales. "À force d'en parler, de déculpabiliser, d'avoir moins honte, j'ai pu tomber le masque en fait."

L'Entourage Aimant : Le soutien du conjoint est fondamental, comme pour Fiona Géin et Muriel Robin. Leurs partenaires ont cessé de boire et ont posé des limites claires pour leur relation.

La Reconstruction Personnelle :Deuil de l'Alcool :

L'arrêt peut être vécu comme un deuil, "comme si ma meilleure amie était morte", laissant un sentiment de vide.

Accepter les Rechutes : Les rechutes sont fréquentes et "ne remettent pas tout en cause". La mémoire de l'alcool reste présente ("l'image de Pac-Man dans mon cerveau").

Se Réconcilier avec Soi-Même : Le processus de reconstruction inclut la réappropriation de son image, de son corps, et de son estime de soi, souvent perdus pendant l'addiction.

Des ateliers d'art-thérapie ou de socio-esthétique aident à "se redonner une dignité" et à "adoucir le regard sur soi-même".

Trouver de Nouveaux Plaisirs : Remplacer l'alcool par d'autres sources de joie, comme le thé pour Sylvie, est une stratégie efficace.

6. L'Impact sur l'Entourage, en Particulier les Enfants

Souffrance Familiale : Pour chaque personne alcoolique, "en moyenne sept personnes qui souffrent autour d'elle", les enfants étant souvent en première ligne.

Les Enfants Observateurs : Charlotte, fille d'une mère alcoolique, mesurait le niveau des bouteilles et comprenait l'ambiance "sordide" de la maison.

Le Paradoxe de l'Amour et de la Haine : Les enfants d'alcooliques doivent gérer un paradoxe : "Je pouvais beaucoup l'aimer mais je pouvais la haïr en même temps parce que je ne la reconnaissais pas quand elle était ivre."

Nécessité de se Sauver Soi-Même : Malgré les tentatives de "réparer" le parent, le chemin est souvent de "sauver notre peau" et "abandonner cette famille dysfonctionnelle".

Citations Clés

"J'ai senti que dans mon disque dur, il y avait quelque chose qui était là et que et boire était normal." – Muriel Robin, sur l'installation de sa dépendance.

"Moi je buvais je buvais un litre de champagne quand je quand j'étais dehors. Je buvais un litre de champagne tous les soirs minimum." – Muriel Robin, sur la quantité consommée.

"L'alcool, j'allais dire c'est la récompense. Ce n'est pas une récompense. C'est quelque c'est c'est quelque chose qui qui vous veut du mal." – Muriel Robin, sur la nature trompeuse de l'alcool.

"Oui, j'étais alcoolique. Ouais, j'étais alcoolique pendant 30 ans." – Muriel Robin, sur la durée de son addiction. "L'alcool dérobe des années de vie de manière insidieuse et pour les femmes en particulier de façon invisible. C'est un poison qui s'instille à l'abri des regards." – Narratrice.

"Une femme qui boit tout d'un coup, c'est une honte. C'est deux fois plus dur qu'un homme. Une femme alcoolique, c'est vraiment on nous le pardonne pas." – Témoignage.

"Les hommes, ça part d'une consommation plus festive qui dérape. Les femmes le plus souvent consomment pour traiter quelque chose, pour traiter un mal-être, une dépression, une anxiété." – Experte.

"J'ai commencé à boire suite à un viol." – Anaïs. "Mon engagement, j'ai un problème avec l'alcool. Je bois, je bois trop." – Lucille Woodward, brisant le tabou en ligne.

"On a un problème d'alcool lorsqu'on ne peut pas s'en séparer et quand on a le sentiment d'avoir perdu la liberté de s'abstenir." – Définition de l'addiction.

"J'ai pris de l'alcool comme on prendrait des anxiolytiques." – Noémilovski.

"Tu n'es pas toi-même quand tu bois et moi je veux être avec toi quand tu es toi-même." – Proche de Noémilovski. "L'alcool, c'est sans faim. Vous voyez le matin, vous vous dites, je vais arrêter de boire et puis le soir, vous remettez ça." – Sylvie.

"Le pire que j'ai fait, je crois que c'était dans le landau de ma fille. J'avais planqué la bouteille dans le landau de ma fille." – Sylvie, sur la dissimulation.

"Il y a un gros pourcentage de risque de cancer du sein lié à l'alcool et ça vraiment c'est quelque chose qui est très peu connu." – Dr. Sarah Coscas, psychiatre addictologue. "Ma petite me disait : 'Maman, tu sens la bière ?'" – Témoignage d'une mère.

"Le vécu d'une agression sexuelle par une femme pouvait multiplier jusqu'à 36 le risque de développer une addiction." – Dr. Sarah Coscas.

"La personne, elle préfère préfère dire non, j'ai pas bu pour ne pas passer la soirée à se disputer avec son conjoint ou sa conjointe alors que elle peut pas aligner trois mots parce que elle a passé sa soirée ou sa journée à à boire." – Richard Baudouin, compagnon de Fiona Géin.

"Écoute moi si tu veux boire une bouteille de champagne tous les soirs c'est ta vie mais moi je j'ai trop peur de te perdre et entre la cigarette et l'alcool je peux pas voir quelqu'un qui se détruit donc on arrête l'histoire." – Anne Le Nen à Muriel Robin, un ultimatum salvateur.

Conclusion

Le document met en lumière la spécificité de l'alcoolisme au féminin, caractérisé par une invisibilité sociale, une vulnérabilité physiologique accrue, et des origines souvent liées à des traumatismes ou un mal-être profond.

Il souligne l'importance cruciale de la reconnaissance de cette maladie, de la brisure du tabou, et du soutien collectif pour permettre aux femmes de se reconstruire et de retrouver une vie digne et sobre.

Le chemin est long, mais le témoignage de ces femmes courageuses montre que la sortie est possible.

Briefing Détaillé : La Relation des Français à l'Alcool – Entre Héritage Culturel et Lutte Personnelle

Ce document de briefing explore la relation complexe et souvent paradoxale des Français à l'alcool, à partir d'un enregistrement audio riche en témoignages et analyses.

Il met en lumière comment l'alcool est profondément ancré dans la culture française, ses différentes fonctions sociales et personnelles, les dangers sous-estimés, les défis de la sobriété et l'influence des lobbies.

Thèmes Principaux

L'Alcool comme Héritage Culturel et Art de Vivre Français : L'alcool est présenté comme une tradition séculaire, un "art de vivre" fait de rituels et de moments de convivialité.

L'Alcool, Rite de Passage et Quête d'Identité : De l'enfance à l'âge adulte, l'alcool marque les étapes de la vie, offrant un sentiment de liberté, de socialisation et de performance.

Les Illusions et Dangers de l'Alcool : Malgré sa valorisation, l'alcool est une drogue qui masque les problèmes, conduit à des comportements risqués (violences, blackouts) et a des conséquences dévastatrices sur la santé et les relations.

La Lutte pour la Sobriété : Le parcours vers l'abstinence est semé d'embûches, confronté à la pression sociale, au déni et à la nécessité d'une reconstruction profonde.

L'Influence des Lobbies et les Croyances Tenaces : Les campagnes de santé publique se heurtent à la puissante influence des lobbies de l'alcool et à des mythes persistants comme le "French Paradoxe".

Idées et Faits Importants

1. L'Alcool comme Héritage Culturel et Art de Vivre Français

Ancrage Profond : L'alcool est "une histoire profondément ancrée dans nos mémoires. C'est la France, une bonne bouteille." Il est omniprésent lors des rencontres entre amis ("on va boire un coup"), symbolisant la convivialité.

Rituels Sociaux : L'expression "il y a toujours une bonne bouteille sur la table" souligne l'aspect ritualisé de la consommation.

Initiation Précoce : De nombreux témoignages révèlent une initiation à l'alcool dès la petite enfance, souvent en famille.

Charlotte se souvient d'avoir "fini la soupe avec le vin" avec son grand-père à 6 ans, et David d'un "fond de Sauternes" à un repas de Noël. Cette initiation est vécue avec fierté, comme un partage du "patrimoine".

Traditions Institutionnelles : Jusqu'en novembre 1956, les écoles primaires servaient de l'eau coupée au vin à la cantine, ce qui témoigne de la normalisation de l'alcool dès le jeune âge.

2. L'Alcool, Rite de Passage et Quête d'Identité

Adolescence et Transgression : Pour les adolescents, "boire est alors un rite de passage pour rentrer dans l'âge adulte." C'est une manière de "faire comme les grands", de "faire partie d'un groupe", même si le goût n'est pas apprécié au début.

Libération et Communication : Le premier verre est un "déclic" qui permet de "vivre différemment", de "se libérer de quelque chose", de "communiquer avec les autres et avec soi-même".

Sentiment de Puissance et de Liberté : Baptiste décrit l'alcool comme des "super pouvoirs", de "l'essence dans [son] moteur", le "breuvage magique qui va [lui] permettre d'être pleinement [lui]-même".

Il procure un sentiment de "liberté" et de "rébellion", où "la nuit nous appartient, on est les rois du monde."

Performance et Compétition : L'ivresse est associée à des notions de "performance" et de "compète" : "bien tenir l'alcool", "accepter les défis", "pas savoir dire non". Le "binge drinking" (cinq verres en moins de deux heures) est courant chez les jeunes.

Séduction et Désirabilité : L'alcool est perçu comme un moyen de devenir "quelqu'un", de "plaire", d'avoir des "premières expériences avec les filles". Charlotte buvait "pour me sentir désirable.

Draguer sans alcool me paraissait inconcevable." Près d'un jeune sur trois confie avoir besoin de boire avant un rapport sexuel.

Valorisation de l'Excès : "Boire c'est rentrer dans la norme, boire c'est s'émanciper." La "valorisation de l'ivresse et de la transgression et des excès" est perçue comme faisant "partie de la jeunesse."

Désinhibition et Faux Courage : L'alcool "désinhibe les timides", "décoince les coincés" et sert de "petite dose de courage liquide" pour Charlotte, qui a du mal à aborder des inconnus sobre.

3. Les Illusions et Dangers de l'Alcool

Une "Drogue Plaisir" aux Conséquences Néfastes : L'alcool est une "molécule plaisir qui va dès le premier verre agir dans le cerveau et puis euh donner un petit peu d'effets euphorisant, plaisant, relaxant", mais il conduit à l'illusion. Perte de Mémoire et Blackouts :

L'alcool peut "détruire mes souvenirs" ("Je sais où je suis allé mais je me rappelle plus de ce que j'y ai fait"). Marie décrit des "trous noirs" fréquents où elle ne se souvenait de rien, y compris comment elle était rentrée chez elle.

Violences et Agressions Sexuelles : L'alcool est impliqué dans 40% des condamnations pour violence familiale en France. Plus d'un jeune sur cinq (18-24 ans) déclare avoir eu un rapport sexuel non consenti à cause de l'alcool.

Le témoignage de Marie, violée par un ami de son père pendant un confinement alcoolisé, est particulièrement frappant.

Elle affirme : "pour moi, le problème c'est pas l'alcool, c'est qu'il faut éduquer les garçons". Son père, dévasté, reconnaît : "Et l'alcool a une part de une part de responsabilité là-dedans".

Baptiste raconte son propre viol, "J'aurais aussi aimé qu'on me dise que qu'on peut me faire du mal quand je suis bourré. On peut aussi me faire du mal parce que je suis bourré."

La discussion met en évidence la culture du viol persistante : "encore aujourd'hui, si une femme a bu trop, qu'elle a perdu le contrôle, qu'en plus elle avait mis une mini jupe, bah s'il lui arrive quelque chose, elle a un petit peu cherché." Le responsable est l'agresseur.

Impact sur la Santé : L'alcool multiplie les risques de cancer, d'AVC hémorragique et de troubles du rythme cardiaque.

Il cause 41 000 décès par an en France, étant la deuxième cause de mort évitable après le tabac.

Détérioration des Relations : David explique comment l'alcool a détruit son couple et son lien avec ses enfants. Sa femme décrit son regard "dans le vide, fuyant, vitreux" et le sentiment qu'il ne faisait "pas d'efforts pour moi."

L'alcool le rend agressif et manipulateur verbalement, au point d'une altercation physique avec sa femme devant leurs enfants.

L'Alcool comme Béquille face à l'Ennui et l'Angoisse : Jean-François a commencé à boire seul après sa carrière sportive, pour combler "la petite mort du sportif" et "accompagner l'ennui".

Il buvait ses "émotions", son "salaire", "tout". Rose utilisait l'alcool pour "tuer l'ennui et défier la mort".

4. La Lutte pour la Sobriété Pression Sociale et Jugement : Refuser de boire, surtout jeune, expose à des jugements : "tu te crains", "celle qui l'emmerdeuse", "celle qui n'est pas marrante".

Pour Lou, qui ne boit pas du tout à 21 ans, la pression sociale est "quasiment en permanence sur [ses] épaules". Arrêter de boire suscite la réaction "Ah, vous êtes devenu chiant", ou "tu es malade".

Le Déni : Les personnes dépendantes sont souvent dans le déni, se croyant capables de contrôler leur consommation. Jean-François et Baptiste décrivent des "pauses" pour se rassurer, avant de reprendre de plus belle.

L'addiction est une "pathologie de la liberté", la "perte de la liberté de s'abstenir."

Le Chemin Difficile de la Reconstruction : La sobriété n'est pas un "glamour instantané". C'est un processus long et douloureux, car le système de plaisir est "endormi". Il faut "apprendre à vivre sans cette béquille là".

Le Rôle du Soutien : Le soutien des proches est crucial. La lettre des amis de Baptiste l'a aidé à "ouvrir les yeux". Coluche soulignait l'importance d'"avoir des copains qui vous aident".

Bénéfices de la Sobriété : Pour David, la sobriété lui a permis de "redevenir acteur de [sa] vie", d'"être présent" pour ses enfants et sa femme, de "répondre au téléphone quand les gens [l']appellent".

C'est une source de fierté et de bonheur retrouvé.

5. L'Influence des Lobbies et les Croyances Tenaces Publicités et Mythes : Pendant des décennies, l'alcool a été promu comme un bienfait, voire un médicament ("le bon grog picon chaud tue la grippe", "soignez-vous par le vin"). Un livre de 1974 "Soignez-vous par le vin" a connu un immense succès.

Le "French Paradoxe" : La croyance que le vin rouge protège des maladies cardiaques, popularisée par le "French Paradoxe" dans les années 90, a "fait du mal" car elle est "restée très ancrée".

Cette "corrélation" n'a jamais été réellement prouvée comme un lien de causalité.

Le slogan "consommer avec modération" a été judicieusement introduit par les lobbies pour atténuer les messages de prévention.

Loi Evain (1991) : Cette loi a marqué un tournant en interdisant la publicité à la télévision et au cinéma et en imposant un message de prévention. Cependant, elle a été rapidement "attaquée" par les lobbies.

Influence Politique : Le président de la République est "sous influence des lobbies de l'alcool", ce qui se traduit par des annulations de campagnes de prévention jugées trop "prohibitionnistes" par l'industrie.

La campagne de 2023 "C'est pas un peu absurde de se souhaiter une bonne santé avec de l'alcool ?" a provoqué une réaction virulente des lobbies.

L'attitude des hommes politiques, comme le président qui "va boire une bière avec les joueurs", "brouille vraiment tous les messages."

En conclusion, l'alcool en France est un phénomène culturel complexe, intriqué dans l'histoire, les rituels sociaux et les parcours individuels.

Si son rôle dans la convivialité et la libération est souvent mis en avant, les témoignages révèlent les dangers profonds sur la santé physique et mentale, les relations humaines, et la dignité individuelle.

La lutte pour la sobriété est un combat personnel et collectif, exacerbé par la pression sociale et la puissante influence des lobbies qui perpétuent des mythes favorables à la consommation.

Le défi est de reconsidérer une culture où "boire était aussi naturel que respirer" pour une société plus consciente et en meilleure santé.

**Poor visual hierarchy/ chaotic layout

• POUR: The cluttered layout lacks clear structure, making it hard to focus or find information. This violates the Understandable principle.
• The page is cluttered with multiple blue boxes and sections with little visual distinction.
• Users with cognitive impairments may struggle to distinguish important from unimportant information.

SKREEEEEEEEEEE <3

pg. 189 the 3 examples that were giving were god to me, i would use something around those lines myself

I never realized that the reasoning behind the typical lesson plan template was science/research backed.

Finished here will continue tomorrow.

1. Clear Link In Footer - This link text is very clear and describes exactly where the link takes you to. It doesn't just say "click here", which is helpful for everyone particularly screen reader users.

• ADI 7688 MC-Ref
• Órgão julgador: Tribunal Pleno
• Relator(a): Min. FLÁVIO DINO
• Julgamento: 19/08/2024
• Publicação: 16/10/2024

DIREITO CONSTITUCIONAL. AÇÃO DIRETA DE INCONSTITUCIONALIDADE. ART 166-A, INCISO I E PARÁGRAFOS DA CONSTITUIÇÃO. DISPOSITIVOS QUE TRATAM DAS TRANSFERÊNCIAS ESPECIAIS CONHECIDAS COMO “EMENDAS PIX”. INADEQUAÇÃO DOS MECANISMOS DE TRANSPARÊNCIA E RASTREABILIDADE DAS TRANSFERÊNCIAS ESPECIAIS. RISCO DE GRAVE DANO AO ERÁRIO. CAUTELAR DEFERIDA EM PARTE.

• 1. A transparência requer a ampla divulgação sobre a origem e o destino dos recursos públicos, conforme decidido pelo STF na ADPF 854. Imperativo assegurar o controle institucional e social sobre o orçamento público. A probabilidade do direito está demonstrada mediante dados que apontam para a inexistência dos instrumentos de planejamento, bem como para a inadequação de mecanismos de controle quanto às transferências especiais (“emendas PIX”).

• 2. Há risco de dano ao erário e à ordem constitucional caso a realização das transferências especiais (“emendas PIX”), previstas no art. 166-A da Constituição, continue a ocorrer sem mecanismos que assegurem a transparência e a rastreabilidade dos dados (art. 163-A da Constituição).

• 3. Decisão liminar obriga a existência prévia de planos de trabalho, com o registro em plataforma eletrônica sobre a destinação e aplicação de parcela muito expressiva do Orçamento da União. No mesmo sentido de obediência à Constituição Federal, a decisão liminar dispõe sobre a incidência plena dos controles externo e interno constantes dos artigos 70, 71 e 74 da Carta Magna.

• 4. Tutela liminar deferida não é impeditiva de realização de transferências especiais (“emendas PIX”), desde que observados os trilhos constantes da Constituição Federal.

• 5. Medida cautelar referendada.

• ADPF 854 Ref
• Órgão julgador: Tribunal Pleno
• Relator(a): Min. FLÁVIO DINO
• Julgamento: 04/12/2024
• Publicação: 14/03/2025

DIREITO CONSTITUCIONAL. ARGUIÇÃO DE DESCUMPRIMENTO DE PRECEITO FUNDAMENTAL E AÇÕES DIRETAS DE INCONSTITUCIONALIDADE. TRANSPARÊNCIA E RASTREABILIDADE NO PROCESSO ORÇAMENTÁRIO. ARTS. 163 E SEGUINTES DA CF. SUPERVENIÊNCIA DA LC Nº. 210/2024. INEXISTÊNCIA DE BLOQUEIO GENERALIZADO À EXECUÇÃO DE EMENDAS PARLAMENTARES. MEDIDA CAUTELAR REFERENDADA.

• 1. A execução de recursos oriundos de emendas parlamentares exige o cumprimento dos pressupostos constitucionais da transparência e da rastreabilidade (163-A da CF).
• 2. A LC nº. 210/2024 constitui avanço no cumprimento das determinações do Plenário desta Corte, ao estabelecer regras acerca da proposição e execução de emendas parlamentares. A referida lei complementar deve ser aplicada em consonância com a Constituição, interpretada pelas decisões do Plenário do STF.
• 3. Inexiste bloqueio generalizado à execução de emendas parlamentares, cabendo ao ordenador de despesas competente a análise e deliberação motivada, caso a caso, acerca do cumprimento das determinações desta Corte e da LC nº. 210/2024 para a continuidade da execução das emendas.
• 4. Medida cautelar referendada.

I'm curious how this rumor came to be. Was it just a easy explanation to finding out the language, or who decided this to be a rumor.

1. He believes that if he discredits all belief, he can disregard falsified beliefs and mitigate their influence on the “good” or true beliefs that he strived for.
2. The action of doubting demonstrates that there is a doubter, therefore because he thinks, he is.
3. Substance dualism, that his mind and body that differentiate as a thinking substance and a physical substance.
4. After going through methodological doubt, ensuring that any idea depredations as true has already passed the test of being clear.
5. Yes, as senses are notorious for misleading individuals, Descartes reasoning is more trustworthy.
6. Rationalism and Empiricism differ by justifying existence in two very different ways- one using sensory experiences and the other using reasoning as the basis of understanding.

Reviewer #3 (Public review):

Summary:

The authors were trying to validate SARS-CoV-2 Mac1 as a drug discovery target and by extension other viral macrodomains.

Strengths:

The medicinal chemistry and structure based optimization is exemplary. Macrodomains and ADPribosyl hydrolases have the reputation for being undruggable, yet the authors managed to optimize hits from a fragment screen using structure based approaches and fragment linking to make a 20nM inhibitor as a tool compound to validate the target.<br /> In addition, the in vivo work is also a strength. The ability to reduce the viral count at a rate comparable to nirmatrelvir is impressive. Tracking the cytokine expression levels also supports much of the genetic data and mechanism of action for macrodomains.

Weaknesses:

The main compound AVI-4206, while being very potent and selective is not appreciably orally bioavailable. The fact that they have to use high doses of the compound IP to see in vivo effects may lead to questions regarding off target effects. The authors acknowledge this and point it out as a potential avenue for further optimization.

The cellular models are not as predictive of antiviral activity as one would expect. However, the authors had enough chutzpah to test the compound in vivo knowing that cellular models might not be an accurate representation of a living system with a fully functional immune system all of which is most likely needed in an antiviral response to test the importance of Mac1 as a target.

Comments on revisions:

All previous suggestions were addressed. I am satisfied with the author's modifications.

Author response:

The following is the authors’ response to the previous reviews.

Reviewer #1 (Recommendations for the authors):

Although this study is rigorous and the paper is well-written, I have a few concerns that the authors should address before publication.

(1) Cellular levels of protein ADP-ribosylation should be analyzed using anti-ADPR antibodies following infection, both with and without Mac1 and AVI-4206 treatment. While the authors have provided impressive in vivo data, these experiments could ideally be conducted in mice. However, I would be amenable to these analyses being performed in human airway organoids, as they demonstrate clear phenotypes following AVI-4206 treatment post-infection. For a more in-depth exploration, the authors could consider affinity purifying ADP-ribosylated proteins and identifying them via mass spectrometry. I would find it particularly compelling if this approach revealed components of the NF-kB signaling pathway, given the intriguing results presented in Fig. 5. I am also curious if there are differences in ADP ribosylated proteins when comparing Mac1 KO SARS-C0V-2 to AVI-4206 treatment.

We note that despite the recent flurry of activity around Mac1, there is a surprising lack of public data on overall ADPr levels or targets. While we will address the literature precedence for PARP14 signals specifically below (Reviewer 2 point (h)) by immunofluorescence, we note that overall levels have not been characterized biochemically previously. Recent PARP14 papers and the ASAP AViDD preprint show changes by immunofluorescence only: and the evidence in that preprint is quite modest - see Figure 7B - https://pmc.ncbi.nlm.nih.gov/articles/PMC11370477/.

We suspect the difficulty in tracking changes biochemically is due to multiple factors that influence the overall detectability and reproducibility. First, with regard to detectability - it is quite possible that only a small change in the ADPr status of a small number of targets is responsible for the phenotypes in vivo. Virus levels are very low in the organoid system and the variability in ADPr levels from tissue samples from in vivo experiments is high. Given the difficulty in translating back to cellular models, this problem is therefore magnified further. Second, with regard to reproducibility - we observe a great deal of reagent dependence on ADPr signals by Western blot+/- Mac1 expression in both cellular and tissue lysates (including when stimulated with H2O2, interferon, or during viral infection). Similarly, we do not observe reproducible proteins that pulldown with Mac1 when assayed by mass spectrometry. It is quite likely that these issues are a result of tissue/sample preparation that results in a loss of the ADPr modification during preparation (especially for acidic residue modifications). This also explains the reliance on IF assays in the PARP14 literature. A very good discussion of these issues is also contained in this paper: https://doi.org/10.1042/BSR20240986.

Nonetheless we have attempted one final experiment. Here, we have measured ADPr modification of cellular lysates upon uninfected conditions as well as upon infection with either WT or N40D mutant virus. For all conditions, this was done with or without treatment of cells with 100 μM of AVI-4206. Measurement of ADPr modifications by western blot using a  pan-ADPr antibody revealed a single prominent band with a molecular weight of ~130kDa, that showed a uniform increase in signal upon treatment of cells with AVI-4206 regardless of infection status. While this general trend was also observed with the mono-ADPr antibody, it was not statistically significant in its regulation upon AVI-4206 treatment. We suspect that the major band observed in these western blots is PARP1, as upon enrichment of ADPr proteins from these lysates by Af1521 immunoprecipitation, we find PARP1 to be among the most abundant proteins detected within this molecular weight range. We note that there is a baseline increase in polyADPr detection upon infection of virus with WT Mac1 (relative to uninfected and virus with N40D) and further increase when treated with AVI-4206. This compound-dependent increase is paralleled in the uninfected and N40D conditions. The counterintuitive increase upon WT Mac1 virus infection, which should erase ADPr marks, and the compound-dependent increase in the uninfected condition suggest that there are many indirect effects on ADPr signalling dynamics in this experiment. These results are difficult to reconcile with the specificity profiling of AVI-4206 (Supplementary Figure5: Thermal proteome profiling in A549 cellular lysates). As mentioned above, the lack of consistent signal across reagents for ADPr detection and the timing of monitoring ADPr levels are additional complicating factors.

We added to the results:

“However, we observed no strong consistent signals of global pan-ADP-ribose (panADPr) or mono-ADP-ribose (monoADPr) accumulation in infected cells treated with AVI-4206 in immunoblot analyses (Supplementary Figure 8).”

Methods for experiment:

Calu3 cells were obtained from ATCC and cultured in Advanced DMEM (Gibco) supplemented with 2.5% FBS, 1x GlutaMax, and 1x Penicillin-Streptomycin at 37°C and 5% CO₂. 5x10⁶ cells were plated in 15-cm dishes and media was changed every 2-3 days until the cells were 80% confluent. The cells were treated with INFy 50 ng/mL (R&D Systems) w/without AVI-4206 100 μM. After 6 hours, the cells were infected with WA1 or WA1 NSP3 Mac1 N40D at a multiplicity of infection (MOI) of 1 for 36 hours. The cells were washed with PBS x 3 and scraped in Pierce IP Lysis Buffer (ThermoFisher) containing 1x HALT protease and phosphatase inhibitor mix (ThermoFisher) on ice. The lysate was stored at -80C until further processing.

The cell lysate was incubated for 5 minutes at room temperature with recombinant benzonase. Following incubation, the lysate was centrifuged at 13,000 rpm at 4°C for 20 minutes, and the supernatant was collected. The samples were then boiled for 5 minutes at 95°C in 1x NuPAGE LDS sample buffer (Invitrogen) with a final concentration of 1X NuPAGE sample reducing agent (Invitrogen). For the detection of ADPr levels in whole-cell lysates, the samples were subjected to SDS-PAGE and Immunoblotting. All primary and secondary antibodies (pan-ADP-ribose antibody (MABE1016, Millipore), Mono-ADP-ribose antibody (AbD33204, Bio-Rad), HRP-conjugated (Cell signaling), used at a 1:1000 dilution were diluted in 5% non-fat dry milk in TBST. Signals were detected by chemiluminescence (Thermo) and visualized using the ChemiDoc XRS+ System (Bio-Rad). Densitometric analysis was performed using Image Lab (Bio-Rad). Quantification was normalized to Actin. The data are expressed as mean ± SD. Statistical differences were determined using an unpaired t-test in GraphPad Prism 10.3.1.

(2) SARS-CoV-2 escape mutants for AVI-4206 should be generated, sequenced, and evaluated for both ADP-ribosyl hydrolase activity and their susceptibility to inhibition by AVI-4206.

We thank the reviewer for this suggestion. These are indeed key experiments which are currently hampered by the lack of a cell line that is fully responsive to drug treatment. Although infected organoids and macrophages show an effect in response to AVI-4206, viral levels are ~3 logs lower than in cell lines and difficult to sequence. In the absence of a system that would allow meaningful screening for outgrowth of resistant viruses, we have conducted mass spectrometry studies that showed that Mac1 is the only significant hit for AVI-4206 (SupplementaryFigure 5). The suggested outgrowth experiments will be conducted once a responsive cell line model has been established.

(3) Given that Mac1 is found in several coronaviruses, it would be insightful for the authors to test a selection of Mac1 homologs from divergent coronaviruses to assess whether AVI-4206 can inhibit their activity in vitro.

As mentioned above, inconsistencies in ADPr staining limit our ability to directly measure cellular activity. As an alternative approach to measure AVI-4206 selectivity in cells, we have adapted our CETSA assay for SARS-1 and MERs macrodomain proteins and find evidence that AVI-4206 can shift the melting temperature of both proteins, albeit to a lesser degree than that seen for Mac1. In line with MERS being more structurally divergent than SARS-1 from SARS CoV2, the ΔTagg for SARS-1 and MERS are 4℃ and 1℃, respectively, compared to 9℃ for Mac1.  These data have been added as Supplementary Fig S3C. Development of broader spectrum pan-inhibitors is on our radar for future work which will more thoroughly assess homologs from divergent coronaviruses.

We added the following sentence to the main results:

“Encouragingly, we were also able to adapt our CETSA assay for SARS-1 and MERs macrodomain proteins and find that AVI-4206 can shift the melting temperature of both proteins, albeit to a lesser degree than that seen for Mac1 (Supplementary Figure 3C).”

We also added this supplementary figure 3:

Minor

(1) Line 88, "respectively.heir potency"

Fixed, thank you!

(2) Line 149 add a period after proteome

Fixed, thank you!

Reviewer #2 (Recommendations for the authors):

(a) The authors assess inhibition of MacroD2 and Targ1 as of-targets for AVI-4206. However, Mac1 belongs to the MacroD-type class of macrodomains of which MacroD1, MacroD2 and MOD1s of PARP9 and PARP14 are the human members. In contrast Targ1 belongs to the ALC1-like class, which is only very distantly related to Mac1. Furthermore, recent studies have shown that the first macrodomains of PARP9 and PARP4 (MOD1 of PARP9/14) are much closer related to Mac1 and PARP9/14 were implicated in antiviral immunity. As such the authors should include assays showing the activity of their compounds against MacroD1 and MOD1s of PARP9/14.

We emphasize that we detect no significant shift for any protein other than Mac1 in A549 cells by CETSA-MS (Supplementary Figure 6). For Mac1 CESTA, we see an average of 6 PARP14 spectral counts across conditions and did not detect PARP9.  In addition, for separate work in MPro, we ran similar CETSA experiments where we observed an average of 2 PARP9 and 15 PARP14 spectral counts across conditions. Although PARP9 and PARP14 massively increase expression upon IFN treatment in A549 cells, both proteins have been detected by Western Blot in A549 cells previously at baseline.

Nonetheless, we have included modeling of more diverse macrodomains as a supplemental figure and added to the text:

Modeling of other diverse macrodomains, including those within human PARP9 and PARP14 further suggests that AVI-4206 is selective for Mac1 (Supplementary Figure 4)

(b) In the context of SARS-CoV-2 superinfection are a known major complication of infections. These superinfections are associated with lung damage and therefore it would be good if the authors could assess lung damage, e.g. by histology, to see if their treatment has a positive impact on lung damage and thus may help to suppress complications.

We performed histology and the results are inconclusive, but suggest that AVI-4206 treatment could lower apoptosis.There is no difference in pathology between the N40D cohort and vehicle with these markers. This could suggest that AVI-4206 provides an additional mechanism that results in protection.  We added to the results:

Caspase 3 staining shows that AVI-4206 treatment reduces apoptosis in the lungs compared to vehicle controls. Additionally, Masson's Trichrome staining reveals  a significant reduction in collagen deposition, a surrogate for lung pathology, in the lungs of AVI-4206 treated animals.(Supplementary Figure 9).

Histology:

Mouse lung tissues were fixed in 4% PFA (Sigma Aldrich, Cat #47608) for 24 hours, washed three times with PBS and stored in 70% ethanol. All the stainings were performed at Histo-Tec Laboratory (Hayward, CA). Samples were processed, embedded in paraffin, and sectioned at 4μm. The slides were dewaxed using xylene and alcohol-based dewaxing solutions. Epitope retrieval was performed by heat-induced epitope retrieval (HIER) of the formalin-fixed, paraffin-embedded tissue using citrate-based pH 6 solution (Leica Microsystems, AR9961) for 20 mins at 95°C. The tissues were stained for H&E, caspase-3 (Biocare #CP229c 1:100), and trichrome, dried, coverslipped (TissueTek-Prisma Coverslipper), and visualized using Axioscan 7 slide scanner (ZEISS) at 40X. Image quantification was performed with Image J software and GraphPad Prism.

(c) Fig. 1D labelling is wrong

Thank you - fortunately the data were plotted correctly and it was just the inset table of values that was incorrect. This is now fixed!

(d) Line 88: "T" missing at start of sentence

Fixed, thank you!

(e) Line 118: NudT5/AMP-Glo assay was developed in https://doi.org/10.1021/acs.orglett.8b01742

We have added this foundational reference, thank you!

(f) Line 147ff: It would be good if the authors could highlight that the TPP methodology has known limitations (e.g. detection of low abundance proteins and low thermal shift of some binders) and thus is not an absolute proof that AVI-4206 "engage with high specificity for Mac1"

We added this important context to the concluding sentence of this paragraph:

“While this assay may not be sensitive to detection of proteins with low abundance proteins or low thermal shift upon ligand binding, collectively, these results indicate that AVI-4206 can cross cellular membranes and engage with high specificity for Mac1.”

(g) The authors use their well established in vitro Mac1 model as well as the SARS-CoV-2 WA strain. Given the ongoing diversification of SARS-CoV-2 and the current prevalence of the Omicron VOC it would be good if the authors could investigate whether alteration in Mac1 occurred or are detected which could influence the efficacy of their inhibitor. Similarly, it would be interesting to know how effective their drug is on other clinically relevant beta-CoV Mac1, e.g. from MERS or SARS1.

We thank the reviewer for the suggestion. Mac1 is one of the more conserved areas of the SARS-CoV-2 genome as there has only been one nonsynonymous mutation V34L (Orf1a:V1056L) that recently emerged in the BA.2.86 lineage and is now in all of the JN.1 derivatives. Currently, the mutation is only ~80% penetrant in circulating SARS-CoV-2 sequences suggesting that it might revert to wild-type and is not associated with a fitness benefit. Based on our structural analysis (shown in Supplementary Figure4D above), we do not believe this mutation affects AVI-4206 binding, but we are including this variant in our future in vitro and in vivo studies as well as other beta-CoV.  For SARS and MERS, see response to Reviewer 1 using CETSA to show that these targets are engaged by AVI-4206.

(h) As methods to detect PARP14-derived ADP-ribosylation are available and it was shown that Mac1 can reverse this modification in cells. It would be good if the authors could investigate the impact of AVI-4206 on ADP-ribosylation in vivo.

To test this idea we adapted the IF assay used by others in the field and show an effect of AVI-4206. We have added to the text:

Although the IFN response was not sufficient to control viral replication, it is possible that the changes in ADP-ribosylation, in particular marks catalyzed by PARP14, downstream of IFN treatment could serve as a marker for Mac1 efficacy  (Ribeiro et al. 2025). To investigate whether downstream signals from PARP14 were specifically erased by Mac1, we used an immunofluorescence assay that showed that Mac1 could remove IFN-γ-induced ADP-ribosylation that is mediated by PARP14 (Kar et al. 2024).  We stably expressed wild-type Mac1 and the N40D mutant Mac1 in A549 cells. The data showed that Mac1 expression decreased IFN-γ-induced ADP-ribosylation, whereas the Mac1-N40D mutant did not (Figure 3E, F), indicating that Mac1 mediates the hydrolysis of IFN-γ-induced ADP-ribosylation. The PARP14 inhibitor RBN012759 completely blocked IFN-γ-induced ADP-ribosylation (Figure 3E, F), further confirming that IFN-γ-induced ADP-ribosylation is mediated by PARP14. AVI-4206 reversed the Mac1-induced hydrolysis of ADP-ribosylation and enhanced the ADP-ribosylation signal in Mac1-overexpressing cells (Figure 3E, F), further demonstrating its ability to inhibit the hydrolase activity of Mac1. We further validated this result using different ADP-ribosylation antibodies for immunofluorescence (Supplementary Figure 7). However, we observed no strong consistent signals of global pan-ADP-ribose (panADPr) or mono-ADP-ribose (monoADPr) accumulation in infected cells treated with AVI-4206 in immunoblot analyses (Supplementary Figure 8). Collectively, these results provide further evidence that simple cellular models are insufficient to explore the effects of Mac1 inhibition and that monitoring specific PARP14-mediated ADP-ribosylation patterns can provide an accessible biomarker for the efficacy of Mac1 inhibition.

A549 Mac1 expression cell construction

Mac1 wild-type (Mac1) and N1062D mutant (Mac1 N1062D) gene fragments were loaded into pLVX-EF1α-IRES-Puro (empty vector, EV) using Gibson cloning kit (NEB E5510). Lentivirus was prepared as previously described (PMID: 30449619; DOI: 10.1016/j.cell.2018.10.024). Briefly, 15 million HEK293T cells were grown overnight on 15 cm poly-L-Lysine coated dishes and then transfected with 6 ug pMD2.G (Addgene plasmid # 12259 ; http://n2t.net/addgene:12259 ; RRID:Addgene_12259), 18 ug dR8.91 (since replaced by second generation compatible pCMV-dR8.2, Addgene plasmid #8455) and 24 ug pLVX-EF1α-IRES-Puro (EV, Mac1, Mac1-N1062D) plasmids using the lipofectamine 3000 transfection reagent per the manufacturer’s protocol (Thermo Fisher Scientific, Cat #L3000001). pMD2.G and dR8.91 were a gift from Didier Trono. The following day, media was refreshed with the addition of viral boost reagent at 500x as per the manufacturer’s protocol (Alstem, Cat #VB100). Viral supernatant was collected 48 hours post transfection and spun down at 300 g for 10 minutes, to remove cell debris. To concentrate the lentiviral particles, Alstem precipitation solution (Alstem, Cat #VC100) was added, mixed, and refrigerated at 4°C overnight. The virus was then concentrated by centrifugation at 1500 g for 30 minutes, at 4°C. Finally, each lentiviral pellet was resuspended at 100x of original volume in cold DMEM+10%FBS+1% penicillin-streptomycin and stored until use at -80°C. To generate Mac1 overexpressing cells, 2 million A549 cells were seeded in 10 cm dishes and transduced with lentivirus in the presence of 8 μg/mL polybrene (Sigma, TR-1003-G). The media was changed after 24h and, after 48 hours, media containing 2μg/ml puromycin was added. Cells were selected for 72 hours and then expanded without selection. The expression of Mac1 was confirmed by Western Blot.

Immunofluorescence assay:

To assess the effect of Mac1 on IFN-induced ADP-ribosylation. A549-pLVX-EV, A549-pLVX-Mac1 and A549-pLVX-Mac1-N1062D cells were seeded in 96-well plate (10,000 cells/well). Cells were pre-treated with medium or 100 unit/mL IFN-γ (Sigma, SRP3058) for 24 hours to induce the expression of ADP-ribosylation. These 3 cell lines were then treated the next day with the indicated concentrations of AVI-4206 or RBN012759 (Medchemexpress, HY-136979). After 24 hours of exposure to drugs, treated cells were fixed in pre-cooled methanol at -20°C for 20 min, blocked in 3% bovine serum albumin for 15 min, incubated with Poly/Mono-ADP Ribose (E6F6A) Rabbit mAb (CST, 83732S) or Poly/Mono-ADP Ribose (D9P7Z) Rabbit mAb (CST, 89190S) antibodies for 1 h, and then incubated with Goat anti-Rabbit IgG Secondary Antibody, Alexa Fluor 488 (ThermoFisher, A-11008) secondary antibodies for 30 min and stained with DAPI for 10 minutes. Fluorescent cells were imaged with an IN Cell Analyzer 6500 System (Cytiva) and analyzed using IN Carta software (Cytiva).

Reviewer #3 (Recommendations for the authors):

Just a couple of observations/details that might help strengthen the article:

(1) The caco-1 data for AVI4206 would suggest that there is some sort of efflux going on, yet there is no mention of it in the paper. This might be useful in the optimization paradigm moving forward.

We thank the reviewer for this observation and suggestion.  Indeed, we believe that efflux is behind the low oral bioavailability of AVI-4206.  We are working specifically to remove this liability in next-generation analogs, using the caco2 assay to guide this ongoing effort. Keep an eye out for a preprint on this soon!  We have added to the discussion:

“In addition to dissecting such molecular mechanisms of macrodomain function and inhibition, future efforts will focus on improving pharmacokinetic properties, including a cellular efflux liability that results in low oral bioavailability of AVI-4206. ”

(2) There are some spectroscopic anomalies/mistakes in the NMR data. The carbon NMR for 1-((8-amino-9H-pyrimido[4,5-b]indol-4-yl)amino)pyrrolidin-2-one should only have 14 unique carbons, but the authors report 15. The HNMR for AVI1500 should only have 19 H's, but the authors list 20. The HNMR data for AVI3762/3763 should have 16 H's, but the authors only report 13. The CNMR for AVI4206 should only have 19 unique carbons, but the authors report 20.

Thank you for noting these inconsistencies regarding the reported NMR spectra. We have rectified them by more closely examining the spectra and in some cases acquiring new data. We identified one peak (47.9) in the 13C NMR of 1-((8-amino-9H-pyrimido[4,5-b]indol-4-yl)amino)pyrrolidin-2-one that is apparently an artifact of the automated peak picking in the data analysis software.  In the 1H NMR of AVI-1500, the triplet peak at 7.20 integrates to 1H, but was erroneously reported as 2H in the original manuscript.  This error has been corrected.  Spectra were re-acquired for AVI-3762, AVI-3763, and AVI-4206 with longer acquisition times, and/or on a 600 MHz spectrometer to afford the complete line lists now reported in the revised manuscript. Please note AVI-4206 has 18 distinct 13C resonances due to the equivalence of the gem-dimethyl methyl groups.

3 stages each child go through them alone

Reviewer #3 (Public review):

Summary:

This study addressed the TCR pairing types and CDR3 characteristics of Treg cells. By analyzing scRNA and TCR-seq data, it claims that 10-20% of dual TCR Treg cells exist in mouse lymphoid and non-lymphoid tissues and suggests that dual TCR Treg cells in different tissues may play complex biological functions.

Strengths:

The study addresses an interesting question of how dual-TCR-expressing Treg cells play roles in tissues.

Weaknesses:

This study is inadequate, particularly regarding data interpretation, statistical rigor, and the discussion of the functional significance of Dual TCR Tregs.

Comments on revisions:

Although the authors have provided brief explanations in response to the reviewers' comments, they do not present any additional analyses that would address the fundamental concerns in a convincing manner.

Moreover, the in silico analyses presented in the manuscript alone are insufficient to support the conclusions, and the functional experiments requested by the reviewers have not been conducted.

In the current rebuttal, while some textual additions have been made to the manuscript, the only substantial revision to the figures appears to be the inclusion of statistical significance annotations (e.g., Fig. 1G, Fig. 3G). These changes do not adequately strengthen the overall data or address the core issues raised.

Author response:

The following is the authors’ response to the previous reviews

Reviewer #1 (Public review):

(1) The use of single-cell RNA and TCR sequencing is appropriate for addressing potential relationships between gene expression and dual TCR.

Thank you for your detailed review and suggestions. The main advantages of scRNA+TCR-seq are as follows: (1) It enables comparative analysis of features such as the ratio of single TCR paired T cells to dual TCR paired T cells at the level of a large number of individual T cells, through mRNA expression of the α and β chains. In the past, this analysis was limited to a small number of T cells, requiring isolation of single T cells, PCR amplification of the α and β chains, and Sanger sequencing; (2) While analyzing TCR paired T cell characteristics, it also allows examination of mRNA expression levels of transcription factors in corresponding T cells through scRNA-seq.

(2) The data confirm the presence of dual TCR Tregs in various tissues, with proportions ranging from 10.1% to 21.4%, aligning with earlier observations in αβ T cells.

Thank you very much for your detailed review and suggestions. Early studies on dual TCR αβ T cells have been very limited in number, with reported proportions of dual TCR T cells ranging widely from 0.1% to over 30%. In contrast, scRNA+TCR-seq can monitor over 5,000 single and paired TCRs, including dual paired TCRs, in each sample, enabling more precise examination of the overall proportion of dual TCR αβ T cells. It is important to note that our analysis focuses on T cells paired with functional α and β chains, while T cells with non-functional chain pairings and those with a single functional chain without pairing were excluded from the total cell proportion analysis. Previous studies generally lacked the ability to determine expression levels of specific chains in T cells without dual TCR pairings.

(3) Tissue-specific patterns of TCR gene usage are reported, which could be of interest to researchers studying T cell adaptation, although these were more rigorously analyzed in the original works.

Thank you very much for your detailed review and suggestions. T cell subpopulations exhibit tissue specificity; thus, we conducted a thorough investigation into Treg cells from different tissue sites. This study builds upon the original by innovatively analyzing the differences in VDJ rearrangement and CDR3 characteristics of dual TCR Treg cells across various tissues. This provides new insights and directions for the potential existence of “new Treg cell subpopulations” in different tissue locations. The results of this analysis suggest the necessity of conducting functional experiments on dual TCR Treg cells at both the TCR protein level and the level of effector functional molecules.

(4) Lack of Novelty: The primary findings do not substantially advance our understanding of dual TCR expression, as similar results have been reported previously in other contexts.

Thank you for your detailed review and suggestions. Early research on dual TCR T cells primarily relied on transgenic mouse models and in vitro experiments, using limited TCR alpha chain or TCR beta chain antibody pairings. Flow cytometry was used to analyze a small number of T cells to estimate dual TCR T cell proportion. No studies have yet analyzed dual TCR Treg cell proportion, V(D)J recombination, and CDR3 characteristics at high throughput in physiological conditions. The scRNA+TCR-seq approach offers an opportunity to conduct extensive studies from an mRNA perspective. With high-throughput advantages of single-cell sequencing technology, researchers can analyze transcriptomic and TCR sequence characteristics of all dual TCR Treg cells within a study sample, providing new ideas and technical means for investigating dual TCR T cell proportions, characteristics, and origins under different physiological and pathological states.

(5) Incomplete Evidence: The claims about tissue-specific differences lack sufficient controls (e.g., comparison with conventional T cells) and functional validation (e.g., cell surface expression of dual TCRs).

Thank you for your detailed review and suggestions. This study indeed only analyzed dual  TCR Treg cells from different tissue locations based on the original manuscript, without a comparative analysis of other dual TCR T cell subsets corresponding to these tissue locations. The main reason for this is that, in current scRNA+TCR-seq studies of different tissue locations, unless specific T cell subsets are sorted and enriched, the number of T cells obtained from each subset is very low, making a detailed comparative analysis impossible. In the results of the original manuscript, we observed a relatively high proportion of dual TCR Treg cell populations in various tissues, with differences in TCR composition and transcription factor expression. Following the suggestions, we have included additional descriptions in R1, citing the study by Tuovinen et al., which indicates that the proportion of dual TCR Tregs in lymphoid tissues is higher than other T cell types. This will help understand the distribution characteristics of dual TCR Treg cells in different tissues and provide a basis for mRNA expression levels to conduct functional experiments on dual TCR Treg cells in different tissue locations.

(6) Methodological Weaknesses: The diversity analysis does not account for sample size differences, and the clonal analysis conflates counts and clonotypes, leading to potential misinterpretation.

We thank you for your review and suggestions. In response to your question about whether the diversity analysis considered the sample size issue, we conducted a detailed review and analysis. This study utilized the inverse Simpson index to evaluate TCR diversity of Treg cells. A preliminary analysis compared the richness and evenness of single TCR Treg cell and dual TCR Treg cell repertoires. The two datasets analyzed were from four mouse samples with consistent processing and sequencing conditions. However, when analyzing single TCR Tregs and dual TCR Tregs from various tissues, differences in detected T cell numbers by sequencing cannot be excluded from the diversity analysis. Following recommendations, we provided additional explanations in R1: CDR3 diversity analysis indicates TCR composition of dual TCR Treg cells exhibits diversity, similar to single TCR Treg cells; however, diversity indices of single TCR Tregs and dual TCR Tregs are not suitable for statistical comparison. Regarding the "clonal analysis" you mentioned, we define clonality based on unique TCR sequences; cells with identical TCR sequences are part of the same clone, with ≥2 counts defined as expansion. For example, in Blood, there are 958 clonal types and 1,228 cells, of which 449 are expansion cells. In R1, we systematically verified and revised clonal expansion cells across all tissue samples according to a unified standard.

(7) Insufficient Transparency: The sequence analysis pipeline is inadequately described, and the study lacks reproducibility features such as shared code and data.

Thank you for your review and suggestions. Based on the original manuscript, we have made corresponding detailed additions in R1, providing further elaboration on the analysis process of shared data, screening methods, research codes, and tools. This aims to offer readers a comprehensive understanding of the analytical procedures and results.

(8) Weak Gene Expression Analysis: No statistical validation is provided for differential gene expression, and the UMAP plots fail to reveal meaningful clustering patterns.

Thank you very much for your review and suggestions. Based on your recommendations, we conducted an initial differential expression analysis of the top 10 mRNA molecules in single TCR Treg and dual TCR Treg cells using the DESeq2 R package in R1, with statistical significance determined by Padj < 0.05. Regarding the clustering patterns in the UMAP plots, since the analyzed samples consisted of isolated Treg cell subpopulations that highly express immune suppression-related genes, we did not perform a more detailed analysis of subtypes and expression gene differences. This study primarily aims to explore the proportions of single TCR and dual TCR Treg cells from different tissue sources, as well as the characteristics of CDR3 composition, with a focus on showcasing the clustering patterns of samples from different tissue origins and various TCR pairing types.

(9) A quick online search reveals that the same authors have repeated their approach of reanalysing other scientists' publicly available scRNA-VDJ-seq data in six other publications,In other words, the approach used here seems to be focused on quick re-analyses of publicly available data without further validation and/or exploration.

Thank you for your review and suggestions. Most current studies utilizing scRNA+TCR-seq overlook analysis of TCR pairing types and related research on single TCR and dual TCR T cell characteristics. Through in-depth analysis of shared scRNA+TCR-seq data from multiple laboratories, we discovered a significant presence of dual TCR T cells in high-throughput T cell research results that cannot be ignored. In this study, we highlight the higher proportion of dual TCR Tregs in different tissue locations, which exhibits a certain degree of tissue specificity, suggesting these cells may participate in complex functional regulation of Tregs. This finding provides new ideas and a foundation for further research into dual TCR Treg functions. However, as reviewers pointed out, findings from scRNA+TCR-seq at the mRNA level require additional functional experiments on dual TCR T cells at the protein level. We have supplemented our discussion in R1 based on these suggestions.

Reviewer #2 (Public review):

(1) The existence of dual TCR expression by Tregs has previously been demonstrated in mice and humans (Reference #18 and Tuovinen. 2006. Blood. 108:4063; Schuldt. 2017. J Immunol. 199:33, both omitted from references). The presented results should be considered in the context of these prior important findings.

Thank you very much for your review and suggestions. Based on the original manuscript, we have supplemented our reading, understanding, and citation of closely related literature (Tuovinen, 2006, Blood, 108:4063 (line 44,line175 in R1); Schuldt, 2017, J Immunol, 199:33 (line 44,line178 in R1)). We once again appreciate the valuable comments from the reviewers, and we will refer to these in our subsequent dual TCR T cell research.

(2) This demonstration of dual TCR Tregs is notable, though the authors do not compare the frequency of dual TCR co-expression by Tregs with non-Tregs. This limits interpreting the findings in the context of what is known about dual TCR co-expression in T cells.

Thank you very much for your review and suggestions. This analysis is primarily based on the scRNA+TCR-seq study of sorted Treg cells, where we found the proportions and distinguishing features of dual TCR Treg cells in different tissue sites. Given the diversity and complexity of Treg function, conducting a comparative analysis of the origins of dual TCR Treg cells and non-T cells with dual TCRs will be a meaningful direction. Currently, peripheral induced Treg cells can originate from the conversion of non-Treg cells; however, little is known about the sources and functions of dual TCR Treg cell subsets in both central and peripheral sites. In R1, we have supplemented the discussion regarding the possible origins and potential applications of the "novel dual TCR Treg" subsets.

(3) Comparison of gene expression by single- and dual TCR Tregs is of interest, but as presented is difficult to interpret. Statistical analyses need to be performed to provide statistical confidence that the observed differences are true.

Thank you very much for your review and suggestions. Based on your recommendations, we performed an initial differential expression analysis of the top 10 mRNA molecules in single TCR Treg and dual TCR Treg cells using the DESeq2 R package in R1, with a statistical significance threshold of Padj<0.05 for comparisons.

(4) The interpretations of the gene expression analyses are somewhat simplistic, focusing on the single-gene expression of some genes known to have a function in Tregs. However, the investigators miss an opportunity to examine larger patterns of coordinated gene expression associated with developmental pathways and differential function in Tregs (Yang. 2015. Science. 348:589; Li. 2016. Nat Rev Immunol. Wyss. 2016. 16:220; Nat Immunol. 17:1093; Zenmour. 2018. Nat Immunol. 19:291).

Thank you for your review and suggestions. This study is based on publicly available scRNA+TCR-seq data from different organ sites generated by the original authors, focusing on sorted and enriched Treg cells within each tissue sample. However, there was no corresponding research on other cell types in each tissue sample, preventing analysis of other cells and factors involved in development and differentiation of single TCR Treg and dual TCR Treg. The literature suggested by the reviewer indicates that development, differentiation, and function of Treg cells have been extensively studied, resulting in significant advances. It also highlights complexity and diversity of Treg origins and functions. This research aims to investigate "novel dual TCR Treg cell subpopulations" that may exhibit tissuespecific differences found in the original authors' studies of Treg cells across different organ sites. This suggests further experimental research into their development, differentiation, origin, and functional gene expression as an important direction, which we have supplemented in the discussion section of R1.

Reviewer #3 (Public review):

(1) Definition of Dual TCR and Validity of Doublet Removal:This study analyzes Treg cells with Dual TCR, but it is not clearly stated how the possibility of doublet cells was eliminated. The authors mention using DoubletFinder for detecting doublets in scRNA-seq data, but is this method alone sufficient?We strongly recommend reporting the details of doublet removal and data quality assessment in the Supplementary Data.

Thank you very much for your review and suggestions. In the analysis of the shared scRNA+TCR-seq data across multiple laboratories, as you mentioned, this study employed the DoubletFinder R package to exclude suspected doublets. Additionally, we used the nCount values of individual cells (i.e., the total sequencing reads or UMI counts for each cell) as auxiliary parameters to further optimize the assessment of cell quality. Generally, due to the possibility that doublet cells may contain gene expression information from two or more cells, their nCount values are often abnormally high. In this study, all cells included in the analysis had nCount values not exceeding 20,000. Among the five tissue sample datasets, we further utilized hashtag oligonucleotide (HTO) labeling (where HTO labeling provides each cell with a unique barcode to differentiate cells from different tissue sources. By analyzing HTO labels, doublets and negative cells can be accurately identified) to eliminate doublets and negative cells.After the removal of chimeric cells, all samples exhibited T cells that possessed two or more TCR clones. This phenomenon validates the reliability of the methodological approach employed in this study and indicates that the analytical results accurately reflect the proportion of dual TCR T cells. Based on the recommendations of the reviewers, we have supplemented and clarified the methods and discussion sections in the manuscript. It is particularly noteworthy that in our analysis, the discussed dual TCR Treg cells and single TCR Treg cells specifically refer to those T cells that possess both functional α and β chains, which are capable of forming TCR. We have excluded from this analysis any Treg cells that possess only a single functional α or β chain and do not form TCR pairs, as well as those Treg cells in which the α or β chains involved in TCR pairing are non-functional.

(2) In Figure 3D, the proportion of Dual TCR T cells (A1+A2+B1+B2) in the skin is reported to be very high compared to other tissues. However, in Figure 4C, the proportion appears lower than in other tissues, which may be due to contamination by non-Tregs. The authors should clarify why it was necessary to include non-Tregs as a target for analysis in this study. Additionally, the sensitivity of scRNA-seq and TCR-seq may vary between tissues and may also be affected by RNA quality and sequencing depth in skin samples, so the impact of measurement bias should be assessed.

We deeply appreciate your review and constructive comments. Based on the original manuscript, we have further supplemented and elaborated on the uniqueness and relative proportions of double TCR T cell pairs in skin tissue samples in Section R1. Due to the scarcity of T cells in skin samples, we included some non-Treg cells during single-cell RNA sequencing and TCR sequencing to obtain a sufficient number of cells for effective analysis. The presence of non-regulatory T cells may indeed impact the statistical representation of double TCR T cells as well as the related comparative analyses, as noted by the reviewer. T cells with A1+A2+B1+B2 type double TCR pairings are primarily found within the non-regulatory T cell population in the skin. In response to this point, we have provided a detailed explanation of this analytical result in the revised manuscript R1. Furthermore, concerning the two datasets included in the study, we conducted a comparative analysis in R1, exploring how factors such as sequencing depth at different tissue sites might introduce biases in our findings, which we have thoroughly elaborated upon in the discussion section. We thank you once again for your valuable suggestions. 

(3) Issue of Cell Contamination:In Figure 2A, the data suggest a high overlap between blood, kidney, and liver samples, likely due to contamination. Can the authors effectively remove this effect? If the dataset allows, distinguishing between blood-derived and tissue-resident Tregs would significantly enhance the reliability of the findings. Otherwise, it would be difficult to separate biological signals from contamination noise, making interpretation challenging.

We thank you for your review and suggestions. We have carefully verified data sources for tissues such as blood, kidneys, and liver. In the study by Oliver T et al., various techniques were employed to differentiate between leukocytes from blood and those from tissues, ensuring accurate identification of leukocytes from tissue samples. First, anti-CD45 antibody was injected intravenously to label cells in the vasculature, verifying that analyzed cells were indeed resident in the tissue. Second, prior to dissection and cell collection, authors performed perfusion on anesthetized mice to reduce contamination of tissue samples by leukocytes from the vasculature. Additionally, during single-cell sequencing, authors utilized HTO technology to avoid overlap between cells from different tissues.

Analysis of the scRNA+TCR-seq data shared by the original authors revealed highly overlapping TCR sequences in blood, kidney, and liver, despite distinct cell labels associated with each tissue. While these techniques minimize overlap of cells from different sources, they cannot completely rule out the potential impact of this technical issue. As suggested, we have provided additional clarification in R1 of the manuscript regarding this phenomenon of high overlap in the kidney, liver, and blood, indicating that the possibility of Treg migration from blood to kidney and liver cannot be entirely excluded.

(4) Inconsistency Between CDR3 Overlap and TCR Diversity:The manuscript states that Single TCR Tregs have a higher CDR3 overlap, but this contradicts the reported data that Dual TCR Tregs exhibit lower TCR diversity (higher 1/DS score). Typically, when TCR diversity is low (i.e., specific clones are concentrated), CDR3 overlap is expected to increase. The authors should carefully address this discrepancy and discuss possible explanations.

Thank you for your review and suggestions. Regarding the potential relationship between CDR3 overlap and TCR diversity, in samples with consistent sequencing depth, lower diversity indeed corresponds to a higher proportion of CDR3 overlap. In our analysis of scRNA+TCR-seq data, we found that single TCR Tregs exhibit both higher diversity and CDR3 overlap, seemingly presenting contradictory analytical results (i.e., dual TCR Tregs show lower TCR diversity and CDR3 overlap). In R1, we supplemented the analysis of possible reasons: the presence of multiple TCR chains in dual TCR Treg cells may lead to a higher uniqueness of CDR3 due to multiple rearrangements and selections, resulting in lower CDR3 overlap; the lower diversity of dual TCR Tregs may be related to the number of T cells sequenced in each sample. The CDR3 diversity analysis in this study merely suggests that the TCR composition of dual TCR Treg cells is diverse, similar to that of single TCR Tregs. However, the diversity indices of single TCR Tregs and dual TCR Tregs are not suitable for statistical comparative analysis. A more in-depth and specific analysis of the diversity and overlap of the VDJ recombination mechanisms and CDR3 composition in dual TCR Tregs during development will be an important technical means to elucidate the function of dual TCR Treg cells.

(5) Functional Evaluation of Dual TCR Tregs:This study indicates gene expression differences among tissue-resident Dual TCR T cells, but there is no experimental validation of their functional significance. Including functional assays, such as suppression assays or cytokine secretion analysis, would greatly enhance the study's impact.

We sincerely appreciate your review and suggestions: In this analysis of scRNA+TCR-seq data, we innovatively discovered a higher proportion of dual TCR Treg cells in different tissue sites, which exhibited differences in tissue characteristics. Furthermore, we conducted a comparative analysis of the homogeneity and heterogeneity between single TCR Treg and dual TCR Treg cells. This result provides a foundation for further research on the origin and characteristics of dual TCR Treg cells in different tissue sites, offering new insights for understanding the complexity and functional diversity of Treg cells. Based on your suggestions, we have supplemented R1 with the feasibility of further exploring the functions of tissue-resident dual TCR T cells and the necessity for potential application research.

(6) Appropriateness of Statistical Analysis:When discussing increases or decreases in gene expression and cell proportions (e.g., Figure 2D), the statistical methods used (e.g., t-test, Wilcoxon, FDR correction) should be explicitly described. They should provide detailed information on the statistical tests applied to each analysis.

Thank you for your review and suggestions: Based on the original manuscript, we have supplemented the specific statistical methods for the differences in cell proportions and gene expression in R1.

Author response:

The following is the authors’ response to the original reviews.

Reviewer #1 (Public review):

“Alternative possibilities are discussed regarding the prior and likelihood of the model. Given that the second case study inspired the introduction of the zero-inflation likelihood, it is not clear how applicable the general methodology is to various datasets. If every unique dataset requires a tailored prior or likelihood to produce the best results, the methodology will not easily replace more traditional statistical analyses that can be applied in a straightforward manner. Furthermore, the differences between the results produced by the two Bayesian models in case study 2 are not discussed. In specific regions, the models provide conflicting results (e.g., regions MH, VPMpc, RCH, SCH, etc.), which are not addressed by the authors. A third case study would have provided further evidence for the generalizability of the methodology.”

We hope in this paper to propose a ‘standard workflow’ for these data; this standard workflow uses the horseshoe prior and we propose that this is the approach used to describe cell count data instead of the better established, but to our thinking, inefficient, t-testing approach.

The horseshoe prior is robust and allows a partially-pooled model to used while weighing-up the contribution of different data points. This is an analogue of excluding outliers and, in any analysis it is normal to investigate further if there are points being excluded as outliers. Often this reveals a particular challenge with the data, in the case of the data here, there are a lot of zeros, indicating that some samples should be excluded because the preparation failed to tag cells rather than because there were no cells to tag. This idea behind the ZIP example is to show that the Bayesian method can allow for this sort of further investigation and, indeed, as the reviewer notes this sort of extended analysis is often bespoke, tailored to the data.

We have clearly failed to explain that the ‘standard workflow’ we propose replace the more traditional methods is the first one we describe, with the horseshoe prior; this produces better results on both datasets than the traditional approach. However, we also feel it is useful to show how a more tailored follow-on can be useful; we need to make it clear that this is intended as an illustration of an ‘optional extra’ rather than a part of the more straightforward ‘standard workflow’.

To make this clearer we have made altered the text in several locations:

• end of Introduction: added clarifying sentence “Here, our aim is to introduce a ‘standard’ Bayesian model for cell count data. We illustrate the application of this model to two datasets, one related to neural activation and the other to developmental lineage. For the second dataset, we also demonstrate a second example extension Bayesian model.”

• Section Hierarchical modeling: “Our goal in both cases is to quantify group differences in the data. We present a ‘standard’ hierarchical model. This model reflects the experimental features common to cell count experiments and reflects the hierarchical structure of cell count data; the standard model is designed to deal robustly and efficiently with noise. On some occasions, to reflect a specific hypotheses, the structure of a particular experiment or an observed source of noise, this model can be further refined or changed to target the analysis. We will give an example of this for our second dataset.”

• Section Horseshoe prior: “The alternative is via a flexible prior such as the horseshoe Carvalho et al., 2010; Piironen and Vehtari, 2017. This more generic option may be suitable as a default ‘standard’ approach in the typical case where outliers are poorly understood.”

• Discussion: word ‘standard’ added to sentence: “Our standard workflow uses a horseshoe prior, along with the partial pooling, this allows our model to deal effectively with outliers.”

• Discussion: modified sentence “The horseshoe prior model workflow we have exhibited here is intended as a standard approach.”

Indeed, because the horseshoe prior deals robustly with outliers, whereas the ZIP is intended to model the outliers, any substantial difference between the two should be examined carefully. The referee is right to point out that we have not explained this in any detail and has helpfully listed a few brain regions were there are differences. This is useful, particularly since the examples listed illustrate in a useful way the opportunities and hazards this sort of data presents. To address this, we have added a new version of Figure 6 to the revised manuscript

Previously Figure 6 showed two example brain regions: MPN and TMd. We have now added MH and SCH to the figure, and new text commenting on the insights the plots provide, both in the Results and Discussion.

Reviewer #2 (Public review):

“A clearer link between the experimental data and model-structure terminology would be a benefit to the non-expert reader.”

This is a very good point and we are acutely aware through our own work how difficult it can be moving between fields with different research goals, different scientific cultures and different technical vocabularies. Just as it can be difficult translating from one language to another without losing nuance and meaning, it can be a real challenge finding technical terms that are useful for the non-expert reader while retaining the precision the application requires! In the long run, we hope that, just as some of the very specialized vocabulary that surrounds frequentist statistics has become familiar to to the working experimental scientists, the precise terminology involved in Bayesian modelling will become familiar and transparent. However, in advance of that day, we have included a glossary of terms at the end of the main text, and have made numerous small tweaks to make sure that link between data and model terminology is clearer and better explained.

Reviewer #1 (Recommendations fro the authors):

(1) “I would strongly recommend that the authors include more case studies in the manuscript, and address the qualitative differences between the different versions of the model.”

We agree that our method will only become established when it is applied to more datasets, we hope to contribute to further analysis and we know other people are already using the approach on their own data. We do, however, feel that adding more datasets to this paper will make it longer and more complex; the plan, instead, is to use the method on novel datasets to test specific hypotheses, so that the results will include novel scientific findings as well as adding another illustration of the Bayesian approach applied to data that is already well studied.

(2) “Figure 6 is not discussed in the main text.”

We had discussed the results presented in Figure 6 in the second paragraph of the section “Case study two – Ontogeny of inhibitory interneurons of the mouse thalamus”, however the reviewer is right in that we did not directly refer to the Figure – this was an oversight. In any case, in the revised manuscript we present a new version of Figure 6 (in response to above comment), which is now explicitly cited in the text.

Revised Figure 6: Example data and inferences highlighting model discrepancies. On the left under ‘data’: boxplots with medians and interquartile ranges for the raw data for four example brain regions. The shape of each point pairs left and right hemisphere readings in each of the five animals. On the right under ‘inference’: HDIs and confidence intervals are plotted. Purple is the Bayesian horseshoe model, pink is the Bayesian ZIP model, and orange is the sample mean. The Bayesian estimates are not strongly influenced by the zero-valued observations (MPN, SCH, TMd) or large-valued outliers (MH) and have means close to the data median. This explains the advantage of the Bayesian results over the confidence interval.

Reviewer #2 (Recommendations from the authors):

(1) “This is a generally well-written methodology paper that also provides the underlying code as a resource. As a reviewer outside both cell-count modelling and hierarchical-Bayesian approaches (though with a general interest in the topics) I found the method a little difficult to follow and would have liked to have been left with a better understanding of how the method is applied to the data. For example, in Figure 1 we are introduced to brain region count, animal count, and “items”. Then in the next line: pooling, model, structure, population and etc in subsequent lines. It is not clear what the subscripts (the pools?) are referring to: are they different regions R or animals N? These terms need to be better linked to the data and/or trimmed. Having said that, the later results look like a solid contribution to the field with a significant reduction in uncertainty from the Bayesian approach over the frequentist one. A future version of the manuscript, therefore, would benefit from greater precision of language as well as an economy and greater focus of terms linking the method to the biology. This is particularly the case around the exposition parts in Figure 1, Figure 2, and the “Hierarchical modelling” section.”

This is another important point. We have now made numerous small changes to tighten up the text in the paper, in response to both this point and the next point.

(2) “Language throughout could be sharpened. Subjectivity like “surprising outliers” could be removed and quirky grammar like “often small, ten is a typical” improved. There are also typos “an rate” etc that should be tidied up.”

As per previous response, we have made numerous tweaks and small improvements and feel that the paper is stronger in this respect.

(3) “Figure 1 caption. “It is a spectrum that depends” Is spectrum the right word here? Also, “thicker stroke” what does this refer to? Wasn’t immediately clear. In A, why is the whole animal within the R bracket that signifies brain regions, and then the brain regions are within the N bracket that signifies whole animals? Apart from the teal colouring, what are the other coloured regions in the image referring to? Improving this first figure would greatly help a reader unfamiliar with the context of the approach.”

We have replaced the word “spectrum” with “continuum”. We have replaced “ Observed quantities have been highlighted with a thicker stroke in the graphical model.” with “The observed data quantities, y_i to y_n, are highlighted with a thick line in the model diagrams”. We have added the following text to describe the red and green lines in panel A: “green and red lines indicate regions labeled as damaged”.

(4) “On P2 there is no discussion of priors when running through the advantage of the Bayesian approach. Is this a choice or an oversight? Priors do have a role in the later analysis.”

A short additional paragraph has been added to the introduction outlining the advantage of having a prior, but also noting that the obligation to pick a prior can be intimidating and that suggesting priors is one of the contributions of our paper: “A Bayesian model also includes a set of probability distributions, referred to as the prior, which represent those beliefs it is reasonable to hold about the statistical model parameters before actually doing the experiment. The prior can be thought of as an advantage, it allows us to include in our analysis our understanding of the data based on previous experiments. The prior also makes explicit in a Bayesian model assumptions that are often implicit in other approaches. However, having to design priors is often considered a challenge and here we hope to make this more straightforward by suggesting priors that are suitable for this class of data.”

(5) “On P4 more explanation would help greatly. Formulas like 23*10*4 or 50*6+50*4 are presented without explanation. What are the various numbers being multiplied? Regions, animals? Again, a clearer link between biological data and model structure would be advantageous.”

We have now modified this line to clearly state the numbers’ sources: “The index i runs over the full set of samples, which in this case comprises 23 brain regions ×10 animals ×4 groups ≈920 datapoints in the first study, and 50 brain regions × 6 HET animals + 50 brain regions × 4 KO animals ≈500 datapoints in the second.”

(6) “P6 and Results. Is it possible to show examples of the data set sampled from? Perhaps an image or two for the two experiments. Both Figures 4 and 5 as they currently are could be made slightly smaller to provide space for a small explanatory sub-panel. This would help ground the results.”

This is a good idea. We have now added heatmap visualisations of both entire datasets to revised versions of Figures 4 and 5 (assuming that this is what the reviewer was suggesting).

DOI: 10.21203/rs.3.rs-7313638/v1

Resource: Mutant Mouse Regional Resource Center (RRID:SCR_002953)

Curator: @AleksanderDrozdz

SciCrunch record: RRID:SCR_002953

What is this?

DOI: 10.21203/rs.3.rs-7313638/v1

Resource: (MMRRC Cat# 037156-JAX,RRID:MMRRC_037156-JAX)

Curator: @AleksanderDrozdz

SciCrunch record: RRID:MMRRC_037156-JAX

What is this?

DOI: 10.21203/rs.3.rs-7313638/v1

Resource: (Thermo Fisher Scientific Cat# A-11034, RRID:AB_2576217)

Curator: @scibot

SciCrunch record: RRID:AB_2576217

What is this?

DOI: 10.21203/rs.3.rs-7313638/v1

Resource: (DSHB Cat# nc82, RRID:AB_2314866)

Curator: @scibot

SciCrunch record: RRID:AB_2314866

What is this?

DOI: 10.21203/rs.3.rs-7313638/v1

Resource: (Thermo Fisher Scientific Cat# A-11004, RRID:AB_2534072)

Curator: @scibot

SciCrunch record: RRID:AB_2534072

What is this?

DOI: 10.21203/rs.3.rs-7313638/v1

Resource: (Thermo Fisher Scientific Cat# A10262, RRID:AB_2534023)

Curator: @scibot

SciCrunch record: RRID:AB_2534023

What is this?

DOI: 10.21203/rs.3.rs-7313638/v1

Resource: RRID:Addgene_104109

Curator: @scibot

SciCrunch record: RRID:Addgene_104109

What is this?

DOI: 10.21203/rs.3.rs-7313638/v1

Resource: (Takara Bio Cat# 632496, RRID:AB_10013483)

Curator: @scibot

SciCrunch record: RRID:AB_10013483

What is this?

DOI: 10.21203/rs.3.rs-7313638/v1

Resource: RRID:Addgene_99280

Curator: @scibot

SciCrunch record: RRID:Addgene_99280

What is this?

DOI: 10.21203/rs.3.rs-7313638/v1

Resource: RRID:Addgene_26220

Curator: @scibot

SciCrunch record: RRID:Addgene_26220

What is this?

DOI: 10.21203/rs.3.rs-7313638/v1

Resource: RRID:Addgene_111068

Curator: @scibot

SciCrunch record: RRID:Addgene_111068

What is this?

DOI: 10.21203/rs.3.rs-7313638/v1

Resource: RRID:Addgene_121922

Curator: @scibot

SciCrunch record: RRID:Addgene_121922

What is this?