PCOMPBIOL-D-25-00988

PAIRNet: Predicting PIWI cleavage specificity via position-aware RNA interaction modeling

PLOS Computational Biology

Dear Dr. Tu,

Thank you for submitting your manuscript to PLOS Computational Biology. After careful consideration, we feel that it has merit but does not fully 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.

Please submit your revised manuscript by Jan 07 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,

Nir Ben-Tal

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: Lin Zeng, Zhenzhen Li, Enzhi Shen, Shikui Tu, and Lei Xu. 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 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

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 manuscript by Zeng et al describes a new deep learning framework that captures targeting rules by PIWI proteins. This is an important unaddressed question and the authors were able to create a model that mostly recapitulates the biochemical experiments. However, several key questions remain unanswered.

1) Can authors' model explain why there is difference between different guide piRNAs?

2) Cleave-n-Seq data also exists for Ago2, and authors could use their approach to create a second model for AGO proteins and compare the two.

3) Ideally, authors model should be accessible not only as a raw code, but also a convenient tool for prediction of targeting rules for a specific piRNA sequence.

Reviewer #2: This is a study by Shikui Tu and Enzhi Shen’s groups. They build a deep-learning model to investigate the piRNA cleavage rule, trained on Cleave-N’-Seq data. This is the first study using deep learning models to investigate piRNA cleavage rule as I know. The model has two main innovations: 1. It encodes interaction information instead of typical one-hot sequence encode. This enables the corporation of mismatches and indels. 2. The model uses a hybrid CNN-transformer architecture, which captures both the local motifs (consecutive pairing) and the global effect of mismatch/indel. The model overall achieves good performance. The authors also interpreted the model and the results are consistent with known knowledges.

Overall, this work is solid and important for the small RNA silencing field. The manuscript is well-written. However, I have several suggestions concerning the feature encoding below:

Major comments:

1. In Fig 1D. Mismatches are encoded as “A|T|C|G”, how does it performs comparing to simply encode mismatches as “mismatches”? In my opinion, different base pairs has different physical affinity (e.g. C-A are more stable than T-T), encoding mismatches into base pairs would be a better way. The same for insertions and deletions.

2. The last paragraph of Introduction seems to be heavily AI edited, and the impact of PAIRNet is exaggerated.

3. Fig 3 and 4. I am wondering how PAIRNet compares to other encoding methods + the CNN-transformer hybrid architecture. It is no wonder typical tree-based models (random forest etc.) cannot decode sequences into interactions, which is why they all perform bad in Fig 3.

Minor comments:

1. Fig 1A. Mismatch and indel are not present intuitively. I would suggest a dark dot as mismatch, a “–” indicates deletions, and a “-AT-” as insertions.

2. line 61. “When revisiting MILI/MIWI data in paper” should be “When revisiting MILI/MIWI data in Gainetdinov et al.”.

3. line 62-64. It would be better to put Fig S1–4 as different panels, as they support the same conclusion.

4. Fig S1 is clipped.

5. line 64. “we still observed variations 63 between different guide RNA both for MILI (S3 Fig) and MIWI (S4 Fig).” Do you mean Fig S1–2?

6. line66. Cite Figures.

7. Fig. 1C. What is the difference between concatenation- and CNN-based embeddings?

8. line95. Typo: “initeraction”.

9. Fig 6. “NoPosition” and “Position Embedding” should be clearly indicated in the figure title or legend.

Reviewer #3: The manuscript describes a new ML approach to predict rates for piRNA-guided cleavage. Small RNA sequence influences AGO/PIWI-catalyzed cleavage rates (PMID: 39025072 and PMID: 37344600). The important goal of this work appears to be finding a unifying rule set for piRNAs of different sequences. It is a useful study, but several major concerns need to be addressed:

1. If authors hold out one piRNA (e.g., L1MC) and train the model without it, will the 3-piRNA (piRNA#1, piRNA#2, Kctd7) model predict how the fourth piRNA cleaves? The hold-out experiment should be repeated for each of the four piRNAs.

2. Do figures 6 and 7 show data from all models (four datasets and two proteins as well as mixed)? If so, it would be important to highlight the data from the mixed model, as such a model would reflect more general rules

3. Authors could test how their model predicts data from another cleave'n'seq experiment described in PMID: 40912244

**********

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.

Reviewer #1: No: https://github.com/CMACH508/PAIRNet is not reachable

Reviewer #2: Yes

Reviewer #3: 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 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 Privacy Policy.

Reviewer #1: No

Reviewer #2: Yes: Tianxiong Yu

Reviewer #3: 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 Prof Tu,

We are pleased to inform you that your manuscript 'PAIRNet: Predicting PIWI cleavage specificity via position-aware RNA interaction modeling' has been provisionally accepted for publication in PLOS Computational Biology.

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,

Nir Ben-Tal

Section Editor

PLOS Computational Biology

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

Reviewer's Responses to Questions

Comments to the Authors:

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

Reviewer #2: The authors has addressed all my comments.

Reviewer #3: The authors put great effort to address all comments from all three reviewers and the manuscript has improved significantly. I strongly recommend accepting it and accompanying its publication with the peer review comments and responses as well.

**********

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.

Reviewer #2: Yes

Reviewer #3: 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 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 Privacy Policy.

Reviewer #2: No

Reviewer #3: Yes: Ildar Gainetdinov