Dear Dr Exner,

Thank you for submitting your revised manuscript via Review Commons entitled "Deep learning predicts tissue outcomes in retinal organoids" for consideration as a Research Article by PLOS Biology.

Your manuscript has now been evaluated by the PLOS Biology editorial staff as well as by an academic editor with relevant expertise and I am writing to let you know that we would like to send your revision back to the original reviewers.

However, before we can send your manuscript back to the reviewers, we need you to complete your submission by providing the metadata that is required for full assessment. To this end, please login to Editorial Manager where you will find the paper in the 'Submissions Needing Revisions' folder on your homepage. Please click 'Revise Submission' from the Action Links and complete all additional questions in the submission questionnaire.

Once your full submission is complete, your paper will undergo a series of checks in preparation for peer review. After your manuscript has passed the checks it will be sent out for review. To provide the metadata for your submission, please Login to Editorial Manager (https://www.editorialmanager.com/pbiology) within two working days, i.e. by Nov 12 2025 11:59PM.

During the process of completing your manuscript submission, you will be invited to opt-in to posting your pre-review manuscript as a bioRxiv preprint. Visit http://journals.plos.org/plosbiology/s/preprints for full details. If you consent to posting your current manuscript as a preprint, please upload a single Preprint PDF.

Feel free to email us at plosbiology@plos.org if you have any queries relating to your submission.

Kind regards,

Ines

--

Ines Alvarez-Garcia, PhD

Senior Editor

PLOS Biology

ialvarez-garcia@plos.org

Dear Dr Exner,

Thank you for your patience while we considered your revised manuscript entitled "Deep learning predicts tissue outcomes in retinal organoids" for publication as a Research Article at PLOS Biology. This revised version of your manuscript has been evaluated by the PLOS Biology editors, the Academic Editor and by two of the original reviewers from Review Commons.

Based on the reviews, we are likely to accept this manuscript for publication, provided you consider the recommendations suggested by Reviewer 3 for future work, which you could discuss in the text. We would also like to change the article type to Methods and Resources, as we do think it fits better that format, thus please select this article type from the dropdown menu when you submit the final revision. Please also make sure to address the data and other policy-related requests stated below my signature.

In addition, we would like you to consider a suggestion to improve the title:

"A deep learning-based computational pipeline predicts developmental outcome in retinal organoids”

As you address these items, please take this last chance to review your reference list to ensure that it is complete and correct. If you have cited papers that have been retracted, please include the rationale for doing so in the manuscript text, or remove these references and replace them with relevant current references. Any changes to the reference list should be mentioned in the cover letter that accompanies your revised manuscript.

In addition to these revisions, you may need to complete some formatting changes, which you will receive in a follow up email. A member of our team will be in touch with a set of requests shortly. If you do not receive a separate email within a few days, please assume that checks have been completed, and no additional changes are required.

We expect to receive your revised manuscript within two weeks.

To submit your revision, please go to https://www.editorialmanager.com/pbiology/ and log in as an Author. Click the link labelled 'Submissions Needing Revision' to find your submission record. Your revised submission must include the following:

- a cover letter that should detail your responses to any editorial requests, if applicable, and whether changes have been made to the reference list

- a Response to Reviewers file that provides a detailed response to the reviewers' comments (if applicable, if not applicable please do not delete your existing 'Response to Reviewers' file.)

- a track-changes file indicating any changes that you have made to the manuscript.

NOTE: If Supporting Information files are included with your article, note that these are not copyedited and will be published as they are submitted. Please ensure that these files are legible and of high quality (at least 300 dpi) in an easily accessible file format. For this reason, please be aware that any references listed in an SI file will not be indexed. For more information, see our Supporting Information guidelines:

https://journals.plos.org/plosbiology/s/supporting-information

*Published Peer Review History*

Please note that you may have the opportunity to make the peer review history publicly available. The record will include editor decision letters (with reviews) and your responses to reviewer comments. If eligible, we will contact you to opt in or out. Please see here for more details:

https://plos.org/published-peer-review-history/

*Press*

Should you, your institution's press office or the journal office choose to press release your paper, please ensure you have opted out of Early Article Posting on the submission form. We ask that you notify us as soon as possible if you or your institution is planning to press release the article.

*Protocols deposition*

To enhance the reproducibility of your results, we recommend that if applicable you deposit your laboratory protocols in protocols.io, where a protocol can be assigned its own identifier (DOI) such that it can be cited independently in the future. Additionally, PLOS ONE offers an option for publishing peer-reviewed Lab Protocol articles, which describe protocols hosted on protocols.io. Read more information on sharing protocols at https://plos.org/protocols?utm_medium=editorial-email&utm_source=authorletters&utm_campaign=protocols

Please do not hesitate to contact me should you have any questions.

Sincerely,

Ines

--

Ines Alvarez-Garcia, PhD

Senior Editor

PLOS Biology

ialvarez-garcia@plos.org

------------------------------------------------------------------------

DATA POLICY:

You may be aware of the PLOS Data Policy, which requires that all data be made available without restriction: http://journals.plos.org/plosbiology/s/data-availability. For more information, please also see this editorial: http://dx.doi.org/10.1371/journal.pbio.1001797

Note that we do not require all raw data. Rather, we ask that all individual quantitative observations that underlie the data summarized in the figures and results of your paper be made available in one of the following forms:

1) Supplementary files (e.g., excel). Please ensure that all data files are uploaded as 'Supporting Information' and are invariably referred to (in the manuscript, figure legends, and the Description field when uploading your files) using the following format verbatim: S1 Data, S2 Data, etc. Multiple panels of a single or even several figures can be included as multiple sheets in one excel file that is saved using exactly the following convention: S1_Data.xlsx (using an underscore).

2) Deposition in a publicly available repository. Please also provide the accession code or a reviewer link so that we may view your data before publication.

Regardless of the method selected, please ensure that you provide the individual numerical values that underlie the summary data displayed in the following figure panels as they are essential for readers to assess your analysis and to reproduce it:

Fig. 1B, C; Fig. 2C, D; Fig. S1A-E; Fig. S2B, C; Fig. S3A-F; Fig. S4Am B; Fig. S5A, B; Fig. S6A, B; Fig. S11; Fig. S15A, B; Fig. S16A, B; Fig. S17A, B; Fig. S22; Fig. S26; Fig. S27; Fig. S28; Fig. S29; Fig. S34; Fig. S35; Fig. S36 and Fig. S37

For the figures that have predictions, please make sure that you add to the figure legend the link to the code used to generate the data. Apologies if I have missed some from the list above.

NOTE: the numerical data provided should include all replicates AND the way in which the plotted mean and errors were derived (it should not present only the mean/average values).

Please also ensure that figure legends in your manuscript include information on WHERE THE UNDERLYING DATA CAN BE FOUND, and ensure your supplemental data file/s has a legend.

Please ensure that your Data Statement in the submission system accurately describes where your data can be found.

------------------------------------------------------------------------

CODE POLICY

Per journal policy, if you have generated any custom code during the course of this investigation, please make it available without restrictions. Please ensure that the code is sufficiently well documented and reusable, and that your Data Statement in the Editorial Manager submission system accurately describes where your code can be found.

Please note that we cannot accept sole deposition of code in GitHub, as this could be changed after publication. However, you can archive this version of your publicly available GitHub code to Zenodo. Once you do this, it will generate a DOI number, which you will need to provide in the Data Accessibility Statement (you are welcome to also provide the GitHub access information). See the process for doing this here: https://docs.github.com/en/repositories/archiving-a-github-repository/referencing-and-citing-content

------------------------------------------------------------------------

Reviewers' comments

Rev. 1: Constantin Pape - note that this reviewer has signed the review.

The revised manuscript addresses all my previous comments. I recommend it for publication in PLOS Biology

Rev. 3:

I would like to thank the authors for their thorough and transparent response to the previous round of review. The revised manuscript serves as a rigorous proof-of-concept for the application of deep learning in predicting organoid developmental trajectories. The authors have significantly strengthened the technical foundations of the work, addressed concerns regarding statistical rigor, and expanded the scope of their predictive framework.

While I am recommending acceptance based on the methodological soundness and the potential utility of the "Latent Determination Horizon" framework, I must note that the revision was unable to fully resolve two major limitations regarding generalizability and biological interpretability. These remaining issues do not preclude publication of this technical advance, but they do define the clear boundaries of the current study. Below, I outline the improvements that underpin my decision to accept, followed by specific recommendations for addressing the lingering limitations in future work.

1. Improvements and Rationale for Acceptance

The authors have successfully addressed several critical technical concerns raised in my initial report, significantly improving the robustness of the study:

Expansion of Predictive Scope (Figure 4C): The inclusion of the analysis predicting abstract morphological clusters at the final timepoint is a substantial improvement. This demonstrates that the model is not limited to recognizing specific tissue structures (like lens or RPE) but can capture global developmental trajectories early in the culture period. This generalization elevates the work from a simple binary classifier to a broader morphological forecasting tool.

Correction of Dimensionality Issues: I commend the authors for addressing the critique regarding Euclidean distances in high-dimensional space. The shift to calculating distances within a PCA-reduced space, validated by the Nearest Neighbor Jaccard analysis (Supplementary Figure S3), provides a much more mathematical sound basis for the claims regarding morphological divergence.

Statistical Rigor: The addition of formal statistical testing (paired Wilcoxon signed-rank tests with Holm-Bonferroni correction) provides the necessary quantitative evidence that the CNN ensemble significantly outperforms classical machine learning baselines.

Reproducibility: The public release of the full code repository and raw data on Zenodo/GitHub is a vital step. Given the niche nature of the experimental model, ensuring the community can inspect and adapt the code is essential for the method's translation to other systems.

2. Remaining Limitations and Recommendations for Future Work

While the revisions justify publication, the response indicates that Major Issues 1 (Generalizability) and 2 (Biological Interpretability) from my previous report remain largely unsolved due to inherent constraints of the study design.

A. Generalizability (The "Single-Lab" Constraint) The authors have acknowledged that they cannot validate the model on external datasets because the specific Oryzias latipes differentiation protocol is unique to their laboratory. Consequently, the model technically remains overfitted to a single laboratory’s specific experimental conditions, species, and imaging setup.

Future Recommendation: To transition this from a "single-lab demonstration" to a community tool, future work must prioritize domain adaptation. I strongly suggest establishing collaborations to generate parallel datasets using mammalian (mouse/human) organoids. Even small "few-shot" learning experiments—where a model pre-trained on Medaka data is fine-tuned with a small number of human organoid images—would be a powerful way to demonstrate true utility to the broader biomedical community.

B. Biological Interpretability (The "Black Box" Issue) The authors performed an exhaustive computational analysis using eight different attribution methods across three CNN architectures. However, the results were largely "negative" in terms of biological insight: the methods showed low consistency and failed to identify stable, human-interpretable features (e.g., specific texture patterns or precursor structures) driving the predictions.

Future Recommendation: It is clear that standard saliency maps (e.g., Grad-CAM, DeepLIFT) are insufficient for this type of diffused biological signal. For future studies, I recommend moving beyond pixel-attribution methods. Generative Approaches: Techniques involving Generative Adversarial Networks (GANs) or Variational Autoencoders (VAEs) could be used to "dream" or synthesize images that maximize the "RPE-positive" class score. Visualizing these exaggerated synthetic features might reveal the texture or shape cues the model is reacting to, which are likely too subtle or distributed for saliency maps to capture. Correlative Approaches: Correlating activation vectors from intermediate network layers with transcriptomic data (if available in the future) could help link the "black box" features to specific molecular programs, bridging the gap between pixel data and biological mechanisms. To conclude, this manuscript successfully establishes a robust computational framework for predicting organoid fate and defines a valuable "determination window" for future experimentation. Despite the "black box" nature of the predictions and the species-specific limitations, the methodological rigor of the revised analysis warrants acceptance.

Attachments

Attachment

Submitted filename: Referee_report_v2.pdf

Dear Dr Exner,

Thank you for the submission of your revised Methods and Resources entitled "A deep learning-based computational pipeline predicts developmental outcome in retinal organoids" for publication in PLOS Biology. On behalf of my colleagues and the Academic Editor, Bon-Kyoung Koo, I am delighted to let you know that we can in principle accept your manuscript for publication, provided you address any remaining formatting and reporting issues. These will be detailed in an email you should receive within 2-3 business days from our colleagues in the journal operations team; no action is required from you until then. Please note that we will not be able to formally accept your manuscript and schedule it for publication until you have completed any requested changes.

Please take a minute to log into Editorial Manager at http://www.editorialmanager.com/pbiology/, click the "Update My Information" link at the top of the page, and update your user information to ensure an efficient production process.

PRESS

We frequently collaborate with press offices. If your institution or institutions have a press office, please notify them about your upcoming paper at this point, to enable them to help maximise its impact. If the press office is planning to promote your findings, we would be grateful if they could coordinate with biologypress@plos.org. If you have previously opted in to the early version process, we ask that you notify us immediately of any press plans so that we may opt out on your behalf.

We also ask that you take this opportunity to read our Embargo Policy regarding the discussion, promotion and media coverage of work that is yet to be published by PLOS. As your manuscript is not yet published, it is bound by the conditions of our Embargo Policy. Please be aware that this policy is in place both to ensure that any press coverage of your article is fully substantiated and to provide a direct link between such coverage and the published work. For full details of our Embargo Policy, please visit http://www.plos.org/about/media-inquiries/embargo-policy/.

Many congratulations and thanks again for choosing PLOS Biology for publication and supporting Open Access publishing. We look forward to publishing your study.

Sincerely,

Ines

--

Ines Alvarez-Garcia, PhD

Senior Editor

PLOS Biology

ialvarez-garcia@plos.org