PONE-D-24-57420iProtDNA-SMOTE: Enhancing Protein-DNA Binding Sites Prediction through Imbalanced Graph Neural NetworksPLOS ONE

Dear Dr. Lin,

Thank you for submitting your manuscript to PLOS ONE. After careful consideration, we feel that it has merit but does not fully meet PLOS ONE’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 Feb 19 2025 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 plosone@plos.org . When you're ready to submit your revision, log on to https://www.editorialmanager.com/pone/ 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 academic editor and reviewer(s). You should upload this letter as a separate file labeled 'Response to Reviewers'.
• 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, please include your updated statement in your cover letter. Guidelines for resubmitting your figure files are available below the reviewer comments at the end of this letter.

If applicable, we recommend that you deposit your laboratory protocols in protocols.io to enhance the reproducibility of your results. Protocols.io assigns your protocol its own identifier (DOI) so that it can be cited independently in the future. For instructions see: https://journals.plos.org/plosone/s/submission-guidelines#loc-laboratory-protocols . 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 .

We look forward to receiving your revised manuscript.

Kind regards,

Syed Nisar Hussain Bukhari

Academic Editor

PLOS ONE

Journal Requirements:

When submitting your revision, we need you to address these additional requirements.

1. Please ensure that your manuscript meets PLOS ONE's style requirements, including those for file naming. The PLOS ONE style templates can be found at 

https://journals.plos.org/plosone/s/file?id=wjVg/PLOSOne_formatting_sample_main_body.pdf and 

https://journals.plos.org/plosone/s/file?id=ba62/PLOSOne_formatting_sample_title_authors_affiliations.pdf

2. Please note that PLOS ONE has specific guidelines on code sharing for submissions in which author-generated code underpins the findings in the manuscript. In these cases, we expect all author-generated code to be made available without restrictions upon publication of the work. Please review our guidelines at https://journals.plos.org/plosone/s/materials-and-software-sharing#loc-sharing-code and ensure that your code is shared in a way that follows best practice and facilitates reproducibility and reuse.

3. Thank you for stating the following financial disclosure: This research was funded by the National Natural Science Foundation of China, 62162032 and 32260154, and Technology Projects of the Education Department of Jiangxi Province of China, GJJ2201040 and GJJ2201004.

Please state what role the funders took in the study.  If the funders had no role, please state: ""The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript."" 

If this statement is not correct you must amend it as needed. 

Please include this amended Role of Funder statement in your cover letter; we will change the online submission form on your behalf.

4. Thank you for stating the following in the Acknowledgments Section of your manuscript: This research was funded by the National Natural Science Foundation of China, 62162032 and 32260154, and Technology Projects of the Education Department of Jiangxi Province of China, GJJ2201040 and GJJ2201004.

We note that you have provided funding information that is not currently declared in your Funding Statement. However, funding information should not appear in the Acknowledgments section or other areas of your manuscript. We will only publish funding information present in the Funding Statement section of the online submission form. 

Please remove any funding-related text from the manuscript and let us know how you would like to update your Funding Statement. Currently, your Funding Statement reads as follows: This research was funded by the National Natural Science Foundation of China, 62162032 and 32260154, and Technology Projects of the Education Department of Jiangxi Province of China, GJJ2201040 and GJJ2201004.

Please include your amended statements within your cover letter; we will change the online submission form on your behalf.

5. Your abstract cannot contain citations. Please only include citations in the body text of the manuscript, and ensure that they remain in ascending numerical order on first mention.

[Note: HTML markup is below. Please do not edit.]

Reviewers' comments:

Reviewer's Responses to Questions

Comments to the Author

1. Is the manuscript technically sound, and do the data support the conclusions?

The manuscript must describe a technically sound piece of scientific research with data that supports the conclusions. Experiments must have been conducted rigorously, with appropriate controls, replication, and sample sizes. The conclusions must be drawn appropriately based on the data presented.

Reviewer #1: Yes

Reviewer #2: Yes

Reviewer #3: Yes

Reviewer #4: Yes

Reviewer #5: Partly

**********

2. Has the statistical analysis been performed appropriately and rigorously?

Reviewer #1: Yes

Reviewer #2: Yes

Reviewer #3: N/A

Reviewer #4: No

Reviewer #5: Yes

**********

3. Have the authors made all data underlying the findings in their manuscript fully available?

The PLOS Data policy requires authors to make all data 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 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—e.g. participant privacy or use of data from a third party—those must be specified.

Reviewer #1: Yes

Reviewer #2: Yes

Reviewer #3: Yes

Reviewer #4: Yes

Reviewer #5: Yes

**********

4. Is the manuscript presented in an intelligible fashion and written in standard English?

PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous. Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here.

Reviewer #1: Yes

Reviewer #2: Yes

Reviewer #3: Yes

Reviewer #4: Yes

Reviewer #5: Yes

**********

5. Review Comments to the Author

Please use the space provided to explain your answers to the questions above. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics. (Please upload your review as an attachment if it exceeds 20,000 characters)

Reviewer #1: 1. The manuscript studies an important area in understanding the biological process and the cellular functions arising out of these interactions.

2. The manuscript is well written, the literature is thoroughly reviewed and the study has been organized in a systematic fashion.

3. The language of the manuscript is good, but needs a little proof reading to fix some language and grammatical errors.

4. The working of ESM2 and Graph SMOTE should have been elaborated within the manuscript, so that it becomes easy for the reader to understand the class balancing and the embeddings generated by ESM2. Although the raw data files on GitHub contain sequence and encoding, but the graph data and ESM2 embedding are in binary format which is beyond comprehension. It would be beneficial for this study to explain the output of ESM2 and the graph structure derived from such embeddings.

5. The authors are also advised to perform some downstream analysis for the novel predictions generated by their model if any to show its relevance in predicting biological functions associated with this DNA binding protein.

Reviewer #2: Considering the use of graph-based neural network structure, it is necessary to discuss and examine more research studies. Also, with further explanations about the innovation presented in the article, the strengths of the presented model can be strengthened.

Reviewer #3: he study is methodologically sound, innovative, and impactful. Addressing the identified weaknesses would further elevate its contributions to the field.

Recommendation: Accept with minor revisions.

Reviewer #4: I find the idea of using graph neural networks and SMOTE to predict protein-DNA binding sites quite intriguing. The experiments on the TR646, TE46, and TR573 datasets, and the comparisons to strong baselines like CLAPE-DB and DNAPred, show promising results with AUC values between 0.850 and 0.896. However, I think the current version needs some serious work before it's ready for a top-tier journal like PLOS ONE.

The first thing that struck me was the huge gap between the method section and the data visualization. The method section felt like a dense wall of text, making it hard to follow. More diagrams or figures to illustrate the model and the results would make it much easier to understand.

I was also disappointed by the lack of discussion about the model's limitations. The authors briefly mention potential issues with long sequences, but that's it. I'd really like to see a more in-depth analysis of things like computational cost, training time, and how well the model scales to larger datasets. This would give a more balanced perspective.

The writing style also felt a bit… robotic. It looks a bit too polished and maybe even a bit salesy. I think a simpler, more direct writing style would be much better.

From a technical standpoint, I was concerned about the lack of ablation studies. The model combines several components, like the ESM2 pre-trained model and GraphSMOTE. It would be really helpful to see how much each of these components actually contributes to the final performance.

Reproducibility is another key issue. The authors provide code and datasets, which is good, but they're missing crucial training details like learning rates, batch sizes, and the number of epochs. This makes it hard for other researchers to independently verify the results.

Finally, the paper doesn't fully address the impact of data imbalance. Even with GraphSMOTE, the recall on the TE46 dataset is quite low (0.363), suggesting that this remains a challenge. I think a deeper discussion on how imbalance affects performance, especially recall, is needed.

Overall, I think the approach has a lot of potential. But the paper needs some significant revisions to make it more readable, transparent, and convincing. I recommend restructuring the paper, simplifying the language, adding more visuals, and conducting more experiments to fully evaluate the model.

Reviewer #5: This paper introduces iProtDNA-SMOTE, a novel model for predicting protein-DNA binding sites. The proposed method addresses the significant class imbalance problem in such datasets by combining the Graph SMOTE algorithm (designed for class imbalance issues) with protein-DNA language models and Graph Neural Networks (GNNs). The model was trained and tested on five protein-DNA binding benchmarks from the literature and demonstrates superior performance compared to other existing models on the same benchmarks.

Given the large class imbalance between the number of residues that bind to DNA and those that do not, the use of the SMOTE algorithm to account for this imbalance is highly relevant. The authors tackle this problem by framing it within a graph-based framework, utilizing embeddings from the ESM model and constructing a graph based on pairwise distances computed from the AlphaFold 3 (AF3) protein structure. The authors then train the Graph Neural Network on datasets curated from prior publications. It is worth noting that these training and test datasets are themselves predictions of protein-DNA interactions derived from previous models (GraphBind, GraphPred, and DBPred). During training, the Graph SMOTE algorithm is employed to upsample examples from the minority class (DNA-binding residues).

Comments:

I find the overall approach of the paper compelling, and it is reasonable to assume that a SMOTE-type algorithm would be beneficial in addressing class imbalance. The results on their independent benchmarks appear promising compared to other models in the literature. Overall, this is an interesting and innovative approach to a biologically significant problem characterized by substantial class imbalance.

However, I would like the following questions addressed before publication:

1. Why are the three models—GraphBind, GraphPred, and DBPred—not included in the benchmarks? The paper does not explain their absence. Is it because their predictions on these benchmarks are already very high, given that the benchmarks (labels) are essentially derived from the predictions of these models? This needs to be clarified, and their performances should be reported, possibly in a supplementary table if necessary.

2. I observed that iProtDNA-SMOTE consistently achieves very high precision but often has the lowest recall across benchmarks. Could the authors address why this trade-off occurs systematically? Is it due to the problem setup of oversampling the minority class, which might make the model adept at identifying a specific type of positive example (protein-DNA binding) while missing others? Some insights or discussion on this issue are crucial. I recommend examining the worst mistakes in the false negatives (i.e., binding sites missed by the model) to better understand the underlying reasons for the low recall and potentially improve it.

**********

6. 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: Yes:  Nisar Iqbal Wani PhD

Reviewer #2: No

Reviewer #3: Yes:  Dr. Syed Mutahar Aaqib

Reviewer #4: No

Reviewer #5: Yes:  Abhimanyu Banerjee

**********

[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.]

While revising your submission, please upload your figure files to the Preflight Analysis and Conversion Engine (PACE) digital diagnostic tool, https://pacev2.apexcovantage.com/ . PACE helps ensure that figures meet PLOS requirements. To use PACE, you must first register as a user. Registration is free. Then, login and navigate to the UPLOAD tab, where you will find detailed instructions on how to use the tool. If you encounter any issues or have any questions when using PACE, please email PLOS at figures@plos.org . Please note that Supporting Information files do not need this step.

Attachments

Attachment

Submitted filename: Review Comments iPROTDNA-smote.docx

Attachment

Submitted filename: comments.docx

Attachment

Submitted filename: Suggestions for Improvement.docx

iProtDNA-SMOTE: Enhancing Protein-DNA Binding Sites Prediction through Imbalanced Graph Neural Networks

PONE-D-24-57420R1

Dear Dr. Lin,

We’re pleased to inform you that your manuscript has been judged scientifically suitable for publication and will be formally accepted for publication once it meets all outstanding technical requirements.

Within one week, you’ll receive an e-mail detailing the required amendments. When these have been addressed, you’ll receive a formal acceptance letter and your manuscript will be scheduled for publication.

An invoice will be generated when your article is formally accepted. Please note, if your institution has a publishing partnership with PLOS and your article meets the relevant criteria, all or part of your publication costs will be covered. Please make sure your user information is up-to-date by logging into Editorial Manager at Editorial Manager®  and clicking the ‘Update My Information' link at the top of the page. If you have any questions relating to publication charges, please contact our Author Billing department directly at authorbilling@plos.org.

If your institution or institutions have a press office, please notify them about your upcoming paper to help maximize its impact. If they’ll be preparing press materials, please inform our press team as soon as possible -- no later than 48 hours after receiving the formal acceptance. Your manuscript will remain under strict press embargo until 2 pm Eastern Time on the date of publication. For more information, please contact onepress@plos.org.

Kind regards,

Syed Nisar Hussain Bukhari

Academic Editor

PLOS ONE

Additional Editor Comments (optional):

Reviewers' comments:

Reviewer's Responses to Questions

Comments to the Author

1. If the authors have adequately addressed your comments raised in a previous round of review and you feel that this manuscript is now acceptable for publication, you may indicate that here to bypass the “Comments to the Author” section, enter your conflict of interest statement in the “Confidential to Editor” section, and submit your "Accept" recommendation.

Reviewer #2: (No Response)

**********

2. Is the manuscript technically sound, and do the data support the conclusions?

The manuscript must describe a technically sound piece of scientific research with data that supports the conclusions. Experiments must have been conducted rigorously, with appropriate controls, replication, and sample sizes. The conclusions must be drawn appropriately based on the data presented.

Reviewer #2: (No Response)

**********

3. Has the statistical analysis been performed appropriately and rigorously?

Reviewer #2: (No Response)

**********

4. Have the authors made all data underlying the findings in their manuscript fully available?

The PLOS Data policy requires authors to make all data 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 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—e.g. participant privacy or use of data from a third party—those must be specified.

Reviewer #2: (No Response)

**********

5. Is the manuscript presented in an intelligible fashion and written in standard English?

PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous. Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here.

Reviewer #2: (No Response)

**********

6. Review Comments to the Author

Please use the space provided to explain your answers to the questions above. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics. (Please upload your review as an attachment if it exceeds 20,000 characters)

Reviewer #2: (No Response)

**********

7. 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

**********

Attachments

Attachment

Submitted filename: comments_declet_1.docx