PCOMPBIOL-D-25-01998

An Improved Dataset for Predicting Mammal Infecting Viruses from Genetic Sequence Information

PLOS Computational Biology

Dear Dr. Reddy,

Thank you for submitting your manuscript to PLOS Computational Biology. After careful consideration, we feel that it has merit but does not meet PLOS Computational Biology's publication criteria as it currently stands. Therefore, we invite you to submit a revised version of the manuscript that addresses the points raised during the review process.

Briefly, both reviewers thought the manuscript makes a valuable contribution to the field, but both identified substantial issues they wish addressed in terms of statistical methodology, comparisons to state of the art, and dataset provenance and description.  Based on the major changes requested, if you need more time to revise please just let us know.

Please submit your revised manuscript by Jan 26 2026 11:59PM. If you will need more time than this to complete your revisions, please reply to this message or contact the journal office at ploscompbiol@plos.org. When you're ready to submit your revision, log on to https://www.editorialmanager.com/pcompbiol/ and select the 'Submissions Needing Revision' folder to locate your manuscript file.

Please include the following items when submitting your revised manuscript:

* A rebuttal letter that responds to each point raised by the editor and reviewer(s). You should upload this letter as a separate file labeled 'Response to Reviewers'. This file does not need to include responses to formatting updates and technical items listed in the 'Journal Requirements' section below.

* A marked-up copy of your manuscript that highlights changes made to the original version. You should upload this as a separate file labeled 'Revised Manuscript with Track Changes'.

* An unmarked version of your revised paper without tracked changes. You should upload this as a separate file labeled 'Manuscript'.

If you would like to make changes to your financial disclosure, competing interests statement, or data availability statement, please make these updates within the submission form at the time of resubmission. Guidelines for resubmitting your figure files are available below the reviewer comments at the end of this letter

We look forward to receiving your revised manuscript.

Kind regards,

Peter M Kasson

Academic Editor

PLOS Computational Biology

Shaun Mahony

Section Editor

PLOS Computational Biology

Journal Requirements:

1) Please ensure that the CRediT author contributions listed for every co-author are completed accurately and in full.

At this stage, the following Authors/Authors require contributions: Aaron R Hall, Adam Witmer, Nick Hengartner, and Austin Schneider. Please ensure that the full contributions of each author are acknowledged in the "Add/Edit/Remove Authors" section of our submission form.

The list of CRediT author contributions may be found here: https://journals.plos.org/ploscompbiol/s/authorship#loc-author-contributions

2) We ask that a manuscript source file is provided at Revision. Please upload your manuscript file as a .doc, .docx, .rtf or .tex. If you are providing a .tex file, please upload it under the item type u2018LaTeX Source Fileu2019 and leave your .pdf version as the item type u2018Manuscriptu2019.

3) Please provide an Author Summary. This should appear in your manuscript between the Abstract (if applicable) and the Introduction, and should be 150-200 words long. The aim should be to make your findings accessible to a wide audience that includes both scientists and non-scientists. Sample summaries can be found on our website under Submission Guidelines:

https://journals.plos.org/ploscompbiol/s/submission-guidelines#loc-parts-of-a-submission

4) Please upload all main figures as separate Figure files in .tif or .eps format. For more information about how to convert and format your figure files please see our guidelines:

https://journals.plos.org/ploscompbiol/s/figures

Note: If the reviewer comments include a recommendation to cite specific previously published works, please review and evaluate these publications to determine whether they are relevant and should be cited. There is no requirement to cite these works unless the editor has indicated otherwise.

Reviewers' comments:

Reviewer's Responses to Questions

Comments to the Authors:

Please note that one review is uploaded as an attachment.

Reviewer #1: This is an interesting manuscript and represents a lot of work (especially on data curation), but is too brief in key places. More detail about the datasets used, and the curation performed (see below) would help highlight the important contributions of this manuscript.

I do not think our publication (Mollentze et al, 2021, PLOS Biology) should be cited as the source of the data used here – we published a model based on available data, and did not do any curation ourselves apart from picking a representative genome for each entry. Instead, please give credit to the original authors as described in our publication (primarily Olival et al. and Woolhouse & Brierley, with a very small number of updates to these in Mollentze et al. 2020). Note, however, that this applies to the curated data only (N = 861 viruses).

On a related note, I was more than half way through the manuscript before the link between the “training” and “testing” datasets mentioned here and any of the data we used in Mollentze et al. became clear (and then only by comparing dataset sizes) – I think for general readers this task will be impossible currently. We had 1000 randomly split datasets called “test” and “train”, and a completely independent set of viruses which were treated as an additional ad hoc “holdout” dataset – it appears this is what is being referred to as our “testing” data here, even though none of our model performance metrics were based on these data. Given the importance of dataset splits uncovered in this manuscript, I think it is important to provide readers with more context – these were not formal data splits as is being implied here, but two completely independent datasets from different sources, as explained in Mollentze et al. Only one of these datasets had high quality labels suitable for model training and testing (an amalgamation of data curated in various other studies, as described above; the other dataset being all remaining viruses), so adding this additional context would also help highlight that by curating the data in the “holdout” dataset, the authors have nearly doubled the amount of available data - a pretty significant change for the entire field.

Other comments

Abstract:

It is unclear what is meant by models having a different “baseline” in this context.

It remains unclear from the abstract whether the improved performance is from the data improvements, a different data splitting scheme, or a different model (since 8 models are mentioned).

I would suggest an additional sentence explaining why the broader host labels might be useful (and any results suggesting that they are). I was also missing a general conclusion sentence.

Page 1:

First paragraph: We can predict many (most?) virus protein structures from the sequence already, so this is no longer a good example of a virus feature that is hard to obtain. I would agree that there are many phenotypic measures which do fit this description however.

Final paragraph: More detail is needed here - what are these new labels for / what is the reasoning behind adding them? This is currently only explained in the discussion.

Page 3:

Is this accuracy measure for the Mollentze et al. holdout data based on curation of these data done in the present work? If so that should be made clear. In the original manuscript, we quoted the number of viruses first detected in humans that were correctly predicted as human-infecting (70.8%), but noted that many of the other viruses likely are capable of human infection too, even if first detected in another host.

Page 4:

In addition to the need for more context about these datasets mentioned above, note that simply using a keyword search for “partial” is a very strict filter for full genomes. At least in the curated part of our data, genomes that still contain that keyword are “near complete”, with all required ORFs and nearly the right length – generally what is missing is simply the hard-to-sequence terminals. I’d be surprised if this filter makes much of a difference (for the curated data), but agree that for a formal dataset intended for future comparisons it is simpler to remove such sequences. However, I would not consider their inclusion in Mollentze et al. an “inaccuracy”.

Page 11:

First paragraph: If it is true that features inherent to mammalian hosts make their viruses easy to distinguish from non mammal-infecting viruses, this would suggest a hierarchical approach would be even more accurate - first predict which viruses can infect mammals, then predict which of those can infect primates/humans. This seems like a future direction worth discussing.

Second paragraph: Given that the previous division of datasets was entirely arbitrary, I’m not convinced there needs to be any effort to maintain these sizes when re-balancing. To me it would be far more interesting to see how much models improved when using the large amount of additional data to it’s fullest extent, to have a model based on much more training data.

Page 12:

The first part of this page does a good job of making the case for the less resolved host labels – I would move this much earlier in the manuscript to make this reasoning clearer from the start.

As the dataset is repeatedly highligted as the main point of this manuscript, much more information on the curation process and evidence standards considered will be needed. For example, what methods of confirmation of virus presence were considered sufficient (e.g. sequencing only, PCR- based, etc.)? Further, what source(s) of evidence were used? All I could find was the comments in retarget.py, but comments in a python script is not a very accessible format. Based on the comments on that script however, I am concerned – there seems to be extensive use of secondary sources like ICTV reports or virushostdb. Were the ultimate sources of such entries checked for accuracy?

Page 15:

Data availability – I could not find a list of citations to support the labels added here. Please provide these in a human-readable format to allow verification and extension by others.

Reviewer #2: See attachment

**********

Have the authors made all data and (if applicable) computational code underlying the findings in their manuscript fully available?

The PLOS Data policy requires authors to make all data and code underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data and code should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data or code —e.g. participant privacy or use of data from a third party—those must be specified.requires authors to make all data and code underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data and code should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data or code —e.g. participant privacy or use of data from a third party—those must be specified.

Reviewer #1: Yes

Reviewer #2: Yes

**********

PLOS authors have the option to publish the peer review history of their article (what does this mean?). If published, this will include your full peer review and any attached files.). If published, this will include your full peer review and any attached files.

If you choose “no”, your identity will remain anonymous but your review may still be made public.

Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our For information about this choice, including consent withdrawal, please see our Privacy Policy..

Reviewer #1: No

Reviewer #2: No

[NOTE: If reviewer comments were submitted as an attachment file, they will be attached to this email and accessible via the submission site. Please log into your account, locate the manuscript record, and check for the action link "View Attachments". If this link does not appear, there are no attachment files.]

Figure resubmission:

While revising your submission, we strongly recommend that you use PLOS’s NAAS tool (https://ngplosjournals.pagemajik.ai/artanalysis) to test your figure files. NAAS can convert your figure files to the TIFF file type and meet basic requirements (such as print size, resolution), or provide you with a report on issues that do not meet our requirements and that NAAS cannot fix.

After uploading your figures to PLOS’s NAAS tool - https://ngplosjournals.pagemajik.ai/artanalysis, NAAS will process the files provided and display the results in the "Uploaded Files" section of the page as the processing is complete. If the uploaded figures meet our requirements (or NAAS is able to fix the files to meet our requirements), the figure will be marked as "fixed" above. If NAAS is unable to fix the files, a red "failed" label will appear above. When NAAS has confirmed that the figure files meet our requirements, please download the file via the download option, and include these NAAS processed figure files when submitting your revised manuscript.

Reproducibility:

To enhance the reproducibility of your results, we recommend that authors of applicable studies deposit 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 to publish peer-reviewed clinical study protocols. Read more information on sharing protocols at https://plos.org/protocols?utm_medium=editorial-email&utm_source=authorletters&utm_campaign=protocols

Attachments

Attachment

Submitted filename: Review-PLoSCB2025.pdf

PCOMPBIOL-D-25-01998R1

An Improved Dataset for Predicting Mammal Infecting Viruses from Genetic Sequence Information

PLOS Computational Biology

Dear Dr. Reddy,

Thank you for submitting your manuscript to PLOS Computational Biology. Both reviewers thought that the majority of their comments were well addressed.  One reviewer has an additional suggestion to improve the robustness of the conclusions.  I would recommend addressing this recommendation; if the authors believe it would require an infeasible amount of computational effort, please justify that and and concomitantly soften the conclusions relating to that analysis.  If the more robust analysis is feasible, though, it would lead to a stronger paper.  We look forward to receiving your response and moving this manuscript forward--whichever path you choose, it's pretty close.

Please submit your revised manuscript by May 02 2026 11:59PM. If you will need more time than this to complete your revisions, please reply to this message or contact the journal office at ploscompbiol@plos.org. When you're ready to submit your revision, log on to https://www.editorialmanager.com/pcompbiol/ and select the 'Submissions Needing Revision' folder to locate your manuscript file.

Please include the following items when submitting your revised manuscript:

* A letter that responds to each point raised by the editor and reviewer(s). You should upload this letter as a separate file labeled 'Response to Reviewers'. This file does not need to include responses to formatting updates and technical items listed in the 'Journal Requirements' section below.

* A marked-up copy of your manuscript that highlights changes made to the original version. You should upload this as a separate file labeled 'Revised Manuscript with Track Changes'.

* An unmarked version of your revised paper without tracked changes. You should upload this as a separate file labeled 'Manuscript'.

If you would like to make changes to your financial disclosure, competing interests statement, or data availability statement, please make these updates within the submission form at the time of resubmission. Guidelines for resubmitting your figure files are available below the reviewer comments at the end of this letter.

We look forward to receiving your revised manuscript.

Kind regards,

Peter M Kasson

Academic Editor

PLOS Computational Biology

Shaun Mahony

Section Editor

PLOS Computational Biology

Reviewers' comments:

Reviewer's Responses to Questions

Comments to the Authors:

Please note here if the review is uploaded as an attachment.

Reviewer #1: The authors have addressed all of my previous comments.

Reviewer #2: Thank you for the revised manuscript. The revision addresses many of my previous concerns,

and the paper is substantially improved. In particular, the authors now clarify that the

performance gain on the rebalanced split is likely driven by reduced phylogenetic distance

(rather than a stronger model), remove earlier significance claims based on the sign test, add

preliminary k-mer ablation analysis, and improve data transparency by providing clearer

curation criteria and a human-readable label/citation table.

I have the remaining suggestion that could further strengthen the paper:

• Strengthen the ablation evidence with multi-seed or repeated resampling runs. The new kmer

ablation in Section 2.2.1 is helpful, but it is currently presented as preliminary and singleseed.

Because this result is central to the interpretation (k-mers appearing harmful on the

harder split), please repeat the same ablation across multiple random seeds and, if feasible,

repeated resampling/split repeats. Reporting averaged results (with uncertainty) would

make this conclusion much more robust.

**********

Have the authors made all data and (if applicable) computational code underlying the findings in their manuscript fully available?

The PLOS Data policy requires authors to make all data and code underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data and code should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data or code —e.g. participant privacy or use of data from a third party—those must be specified.requires authors to make all data and code underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data and code should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data or code —e.g. participant privacy or use of data from a third party—those must be specified.

Reviewer #1: Yes

Reviewer #2: Yes

**********

PLOS authors have the option to publish the peer review history of their article (what does this mean?). If published, this will include your full peer review and any attached files.). If published, this will include your full peer review and any attached files.

If you choose “no”, your identity will remain anonymous but your review may still be made public.

Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our For information about this choice, including consent withdrawal, please see our Privacy Policy..

Reviewer #1: No

Reviewer #2: No

[NOTE: If reviewer comments were submitted as an attachment file, they will be attached to this email and accessible via the submission site. Please log into your account, locate the manuscript record, and check for the action link "View Attachments". If this link does not appear, there are no attachment files.]

Figure resubmission:

While revising your submission, we strongly recommend that you use PLOS’s NAAS tool (https://ngplosjournals.pagemajik.ai/artanalysis) to test your figure files. NAAS can convert your figure files to the TIFF file type and meet basic requirements (such as print size, resolution), or provide you with a report on issues that do not meet our requirements and that NAAS cannot fix.

After uploading your figures to PLOS’s NAAS tool - https://ngplosjournals.pagemajik.ai/artanalysis, NAAS will process the files provided and display the results in the "Uploaded Files" section of the page as the processing is complete. If the uploaded figures meet our requirements (or NAAS is able to fix the files to meet our requirements), the figure will be marked as "fixed" above. If NAAS is unable to fix the files, a red "failed" label will appear above. When NAAS has confirmed that the figure files meet our requirements, please download the file via the download option, and include these NAAS processed figure files when submitting your revised manuscript.

Reproducibility:

To enhance the reproducibility of your results, we recommend that authors of applicable studies deposit 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 to publish peer-reviewed clinical study protocols. Read more information on sharing protocols at https://plos.org/protocols?utm_medium=editorial-email&utm_source=authorletters&utm_campaign=protocols

Dear Dr. Reddy,

We are pleased to inform you that your manuscript 'An Improved Dataset for Predicting Mammal Infecting Viruses from Genetic Sequence Information' has been provisionally accepted for publication in PLOS Computational Biology.  Thanks so much for the thoughtful response to the final reviewer query.

Before your manuscript can be formally accepted you will 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.

Please note that your manuscript will not be scheduled for publication until you have made the required changes, so a swift response is appreciated.

IMPORTANT: The editorial review process is now complete. PLOS will only permit corrections to spelling, formatting or significant scientific errors from this point onwards. Requests for major changes, or any which affect the scientific understanding of your work, will cause delays to the publication date of your manuscript.

Should you, your institution's press office or the journal office choose to press release your paper, you will automatically be opted out of early publication. We ask that you notify us now if you or your institution is planning to press release the article. All press must be co-ordinated with PLOS.

Thank you again for supporting Open Access publishing; we are looking forward to publishing your work in PLOS Computational Biology.

Best regards,

Peter M Kasson

Academic Editor

PLOS Computational Biology

Shaun Mahony

Section Editor

PLOS Computational Biology

***********************************************************