-->PONE-D-25-64588-->-->Interpretable Drug Discovery Across Medical Knowledge Graphs Based on Graph Embedding Models: A Case Study of Type 2 Diabetes-->-->PLOS One

Dear Dr. Zhou,

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 Mar 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 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 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,

Zeheng Wang

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. PLOS requires an ORCID iD for the corresponding author in Editorial Manager on papers submitted after December 6th, 2016. Please ensure that you have an ORCID iD and that it is validated in Editorial Manager. To do this, go to ‘Update my Information’ (in the upper left-hand corner of the main menu), and click on the Fetch/Validate link next to the ORCID field. This will take you to the ORCID site and allow you to create a new iD or authenticate a pre-existing iD in Editorial Manager.

3. 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.

4. Please include your tables as part of your main manuscript and remove the individual files. Please note that supplementary tables (should remain/ be uploaded) as separate "supporting information" files.

5. Please provide a complete Data Availability Statement in the submission form, ensuring you include all necessary access information or a reason for why you are unable to make your data freely accessible. If your research concerns only data provided within your submission, please write "All data are in the manuscript and/or supporting information files" as your Data Availability Statement.

6. When completing the data availability statement of the submission form, you indicated that you will make your data available on acceptance. We strongly recommend all authors decide on a data sharing plan before acceptance, as the process can be lengthy and hold up publication timelines. Please note that, though access restrictions are acceptable now, your entire data will need to be made freely accessible if your manuscript is accepted for publication. This policy applies to all data except where public deposition would breach compliance with the protocol approved by your research ethics board. If you are unable to adhere to our open data policy, please kindly revise your statement to explain your reasoning and we will seek the editor's input on an exemption. Please be assured that, once you have provided your new statement, the assessment of your exemption will not hold up the peer review process.

7. We notice that your supplementary figures are uploaded with the file type 'Figure'. Please amend the file type to 'Supporting Information'. Please ensure that each Supporting Information file has a legend listed in the manuscript after the references list.

8. 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.

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

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: Partly

**********

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

Reviewer #1: Yes

Reviewer #2: N/A

**********

-->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: No

Reviewer #2: No

**********

-->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

**********

-->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: This study proposes a framework for interpretable drug discovery in T2DM by constructing a gene-bridged knowledge graph integrating Traditional Chinese Medicine (TCM) and Modern Medicine (MM). The interdisciplinary approach is commendable. However, several major issues must be addressed before the manuscript can be considered for publication: 1) a critical need to clarify the novel contribution of its dataset, which appears heavily reliant on and derivative of existing resources like SymMap, 2) a more precise articulation of its methodological novelty beyond prior integrative studies, and 3) full compliance with PLOS ONE's data availability policy.

1. Substantiation of Novelty: Dataset and Methodological Contribution

The manuscript currently overstates its novelty. A major concern is that the core integrated dataset does not appear to constitute a significant new contribution.

Lack of Novelty in Data Integration: The authors state their knowledge graph is built from multiple sources including SymMap. However, SymMap is itself a major, publicly available resource specifically designed to integrate TCM and modern biomedical entities (herbs, ingredients, targets, diseases). The description suggests the authors' work primarily involves extending SymMap by incorporating additional disease data and other complementary sources (e.g., Hetionet, STRING). This is an incremental data curation effort, not the creation of a fundamentally new integrative resource. The authors must:

Provide a transparent comparison: A table or quantitative analysis should detail exactly what new entities and relations were added beyond what is available in SymMap or similar integrated databases. What percentage of the final graph's triples are uniquely sourced from non-SymMap databases?

Reframe the contribution: The manuscript's narrative should shift from "constructing a cross-medicine KG" (which SymMap already is) to "constructing an extended and application-specific KG for T2DM, based on augmenting SymMap with additional modern biomedical relations and disease-specific data, to enable a novel interpretable prediction workflow." The novelty lies in the application and analytical framework, not the foundational data layer.

Clarification of Methodological Advancement: Beyond data, the authors must more clearly distinguish their interpretability framework from prior work that combines embeddings with rule learning or path finding. What is new about the unified path scoring scheme? How does it improve upon or differ from related mechanisms in literature?

2. Mandatory Compliance with PLOS ONE Data Availability Policy

The submission does not meet the journal's requirement for unconditional data and code sharing, which is essential for verifying claims about dataset construction and model performance.

Current Statement is Non-Compliant: The authors selected "Yes - all data are fully available without restriction" but provided no access details. The processed, integrated knowledge graph used in this study is the key output of the data preparation phase and should be shared or submit the Supplementary material.

3. Other Necessary Revisions

Experimental Rigor: Justify the choice of embedding models and evaluation metrics more thoroughly.

Figure Clarity: Ensure all figures (especially the conceptual diagram Fig. 1 and the Venn diagram Fig. 2) are high-resolution, legible, and contain self-explanatory legends.

Discussion of Limitations: Expand the limitations section to explicitly discuss the dependency on existing integrated resources, potential biases introduced by the fusion strategy, and the subjective component in designing the scoring scheme.

Reviewer #2: The manuscript presents an integrated cross-medicine biomedical knowledge graph built from multiple public sources and a link-prediction–plus–rule-based path-explanation framework (ComplEx/RotatE with AnyBURL+DFS and unified path scoring) to identify drug candidates and return the highest-scoring mechanistic semantic paths for interpretability.

The authors have conducted substantial work in the area of drug discovery; however, several key aspects require further improvement:

1. The motivation in both the abstract and the introduction should be strengthened, and the methodological description needs to be more logically structured. In particular, the presentation should shift from merely stating what has been done to clearly articulating what problem is being addressed and solved.

2. Regarding related works, many recently published papers working on discovering novel drugs for complex diseases were missed, such as 10.1109/JBHI.2025.3600045, 10.1109/JBHI.2025.3585290, and 10.1109/JBHI.2024.3383591. Authors should cite and discuss these works to present a more comprehensive literature review.

3. The authors are encouraged to include an overview figure illustrating the main workflow of the proposed framework, highlighting the roles and relative importance of the individual components.

4. In the case studies section, methodological descriptions and experimental results should be presented separately to improve clarity and readability.

5. Regarding the weighting scheme and hyperparameter settings, the current choices appear to be largely heuristic. It is recommended to conduct lightweight sensitivity analyses to demonstrate the robustness of the method with respect to these parameters.

6. The authors should add comparative experiments to justify the selection of ComplEx and RotatE as the primary models, for example by including additional representative baselines.

7. Ablation studies are necessary to demonstrate the necessity and contribution of each major design component in the proposed approach.

8. For future works, authors should discuss the possibility of applying advanced graph learning techniques (10.1038/s41551-024-01312-5 and 10.1109/TSMC.2025.3572738) for improved performance of the proposed model.

**********

-->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: 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.]

To ensure your figures meet our technical requirements, please review our figure guidelines: https://journals.plos.org/plosone/s/figures

You may also use PLOS’s free figure tool, NAAS, to help you prepare publication quality figures: https://journals.plos.org/plosone/s/figures#loc-tools-for-figure-preparation.

NAAS will assess whether your figures meet our technical requirements by comparing each figure against our figure specifications.

-->PONE-D-25-64588R1-->-->Interpretable Drug Discovery Across Medical Knowledge Graphs Based on Graph Embedding Models: A Case Study of Type 2 Diabetes-->-->PLOS One

Dear Dr. Zhou,

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 May 14 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 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 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.

As the corresponding author, your ORCID iD is verified in the submission system and will appear in the published article. PLOS supports the use of ORCID, and we encourage all coauthors to register for an ORCID iD and use it as well. Please encourage your coauthors to verify their ORCID iD within the submission system before final acceptance, as unverified ORCID iDs will not appear in the published article. Only the individual author can complete the verification step; PLOS staff cannot verify ORCID iDs on behalf of authors.

We look forward to receiving your revised manuscript.

Kind regards,

Zeheng Wang

Academic Editor

PLOS One

Journal Requirements:

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.

Please 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 rebuttal letter that accompanies your revised manuscript. If you need to cite a retracted article, indicate the article’s retracted status in the References list and also include a citation and full reference for the retraction notice.

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

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 #1: All comments have been addressed

Reviewer #2: All comments have been addressed

Reviewer #3: (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 #1: Yes

Reviewer #2: Yes

Reviewer #3: Partly

**********

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

Reviewer #1: Yes

Reviewer #2: N/A

Reviewer #3: No

**********

-->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 #1: Yes

Reviewer #2: Yes

Reviewer #3: No

**********

-->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 #1: Yes

Reviewer #2: Yes

Reviewer #3: No

**********

-->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 #1: This manuscript presents a comprehensive and well-structured study on the construction of a cross-medical knowledge graph (CMKG) for Type 2 Diabetes Mellitus (T2DM), integrating data from multiple biomedical sources. The authors propose a novel unified path scoring framework that combines graph embedding models (notably ComplEx) with rule-based reasoning (AnyBURL) and a domain-specific Ingredient Specificity Index (ISI) to enhance interpretability in drug discovery. The study is rigorous in methodology, rich in data, and provides biologically meaningful insights into potential drug mechanisms from both Traditional Chinese Medicine (TCM) and modern medicine.

The author has addressed all my concerns and I have no other questions

Reviewer #2: All of my concerns have been addressed in this revised manuscript, and I recommend to accept this work.

Reviewer #3: This manuscript addresses an interesting and potentially useful topic: using a cross-medicine knowledge graph to support interpretable candidate drug discovery for type 2 diabetes by integrating Traditional Chinese Medicine and modern medicine resources. The attempt to combine graph embeddings with rule learning and path-based explanation is a worthwhile direction. My main concerns are outlined below.

1. The prediction and validation design is not rigorous enough to support the drug discovery claims.

The manuscript reports overall link prediction metrics for ComplEx and RotatE on a random triple split of the full graph, but this does not adequately validate the downstream task of discovering candidate therapeutics for T2DM. It is unclear whether known T2DM-related drug or herb associations were removed from training before candidate ranking, and therefore it is difficult to determine whether the model is discovering novel candidates or simply recovering information already encoded in the graph. The manuscript should define a clear benchmark for the actual target task, for example recovery of held-out known T2DM therapeutics, and should explain how leakage from known disease-drug, herb-disease, or gene-disease relations was prevented.

2. The conclusions overstate what the current evidence supports.

At present, the study demonstrates that the framework can rank candidate entities and produce literature-supported semantic paths. That is a useful hypothesis-generation result, but it is not sufficient to claim interpretable drug discovery in a strong sense. No experimental validation, expert evaluation, retrospective benchmark against known antidiabetic drugs, or comparison of top-k candidate precision is provided. The manuscript should substantially tone down the claims and frame the method as a candidate prioritization and explanation framework unless stronger validation is added.

3. The interpretability framework is largely heuristic and is not itself validated.

The unified path scoring formula relies on manually assigned weights, length penalties, bonuses, and a fixed 0.7 discount for DFS-only paths, but there is no empirical justification, sensitivity analysis, or ablation study showing that these choices improve explanation quality. This is especially important because some of the reported top paths do not appear strongly mechanistic. For example, paths involving “irritability” or “bipolar disorder” as intermediate nodes are difficult to interpret as convincing biological explanations for antidiabetic effects. If the paper claims interpretability, the authors should evaluate whether the top-ranked paths are actually considered meaningful by domain experts or at least show that alternative weighting schemes do not materially change the conclusions.

4. The manuscript contains a major internal inconsistency in the model comparison.

Earlier sections and Table 5 indicate that ComplEx outperforms RotatE on MRR and Hits@K and is therefore selected as the final model. However, the conclusion states that “RotatE performs better on Hits@10 and MRR,” which directly contradicts the reported results. This needs to be corrected, and the full manuscript should be carefully checked for similar inconsistencies.

5. There is insufficient rigor in the quantitative evaluation.

Only single-point metric values are reported for the embedding models. There are no repeated runs, confidence intervals, variance estimates, or statistical tests, despite the stochastic nature of embedding training. The manuscript also gives no evidence that the chosen hyperparameters are robust. At minimum, the authors should repeat training with multiple random seeds and report mean ± standard deviation for MRR and Hits@K. If model selection is based on these metrics, uncertainty should be reported.

6. Entity alignment and relation fusion need validation.

The graph construction step relies heavily on entity name-based reassignment and rule-based relation fusion using Jaccard and overlap thresholds. These steps are central to the contribution, yet no evaluation is provided for alignment accuracy or relation fusion quality. Because cross-system integration between TCM and MM is a major claim of the manuscript, the authors should report manual validation on a representative sample or otherwise quantify the error rate introduced by entity merging and relation consolidation.

7. Data and code availability are not yet adequate for reproducibility.

The submission metadata says that all data are fully available, but the reviewer PDF does not provide a concrete data availability statement with repository links, accession numbers, or downloadable processed outputs. The source databases are public, but the actual integrated graph, processed triples, entity mappings, relation fusion tables, candidate rankings, and path-scoring outputs appear not to be shared. Reproducibility also requires code or at least detailed scripts for graph construction, training, and interpretability analysis. These materials should be deposited in a public repository.

8. The writing requires substantial editing before publication.

The manuscript contains many grammatical and stylistic problems, including incorrect verb forms, inconsistent capitalization, awkward phrasing, punctuation issues, and numerous typos. Examples include “we generates,” “Traditional chinese medicine,” “burnden,” “Mediacal Insurance,” missing spaces after periods, and inconsistent use of full-width punctuation. The English is understandable overall, but it is not yet at the standard expected for publication without substantial revision.

**********

-->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 #1: No

Reviewer #2: No

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.]

To ensure your figures meet our technical requirements, please review our figure guidelines: https://journals.plos.org/plosone/s/figures

You may also use PLOS’s free figure tool, NAAS, to help you prepare publication quality figures: https://journals.plos.org/plosone/s/figures#loc-tools-for-figure-preparation.

NAAS will assess whether your figures meet our technical requirements by comparing each figure against our figure specifications.

-->

Interpretable Candidate Drug Prioritization and Explanation Framework Across-Medical Knowledge Graphs Based on Graph Embedding Models: A Case Study of Type 2 Diabetes

PONE-D-25-64588R2

Dear Dr. Zhou,

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. For questions related to billing, please contact billing support.

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,

Zeheng Wang

Academic Editor

PLOS One

Additional Editor Comments (optional):

Reviewers' comments: