PONE-D-24-38371Optimizing chemotherapeutic targets in non-small cell lung cancer with transfer learning for precision medicinePLOS ONE

Dear Dr. kumari,

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 Nov 15 2024 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,

Ruo Wang

Academic Editor

PLOS ONE

Journal Requirements:

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

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: 

The authors extend their appreciation to the Deanship of Scientific Research and Graduate Studies at King Khalid University, KSA, for funding this work through General Research Project under grant number: GRP/4/45.

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: 

The authors extend their appreciation to the Deanship of Scientific Research and Graduate Studies at King Khalid University, KSA, for funding this work through General Research Project under grant number: GRP/4/45.

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: 

The authors extend their appreciation to the Deanship of Scientific Research and Graduate Studies at King Khalid University, KSA, for funding this work through General Research Project under grant number: GRP/4/45.

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

5. We note that your Data Availability Statement is currently as follows: All relevant data are within the manuscript and its Supporting Information files.

Please confirm at this time whether or not your submission contains all raw data required to replicate the results of your study. Authors must share the “minimal data set” for their submission. PLOS defines the minimal data set to consist of the data required to replicate all study findings reported in the article, as well as related metadata and methods (https://journals.plos.org/plosone/s/data-availability#loc-minimal-data-set-definition).

For example, authors should submit the following data:

- The values behind the means, standard deviations and other measures reported;

- The values used to build graphs;

- The points extracted from images for analysis.

Authors do not need to submit their entire data set if only a portion of the data was used in the reported study.

If your submission does not contain these data, please either upload them as Supporting Information files or deposit them to a stable, public repository and provide us with the relevant URLs, DOIs, or accession numbers. For a list of recommended repositories, please see https://journals.plos.org/plosone/s/recommended-repositories.

If there are ethical or legal restrictions on sharing a de-identified data set, please explain them in detail (e.g., data contain potentially sensitive information, data are owned by a third-party organization, etc.) and who has imposed them (e.g., an ethics committee). Please also provide contact information for a data access committee, ethics committee, or other institutional body to which data requests may be sent. If data are owned by a third party, please indicate how others may request data access.

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.

[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: Partly

Reviewer #2: Partly

Reviewer #3: No

**********

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

Reviewer #1: Yes

Reviewer #2: Yes

Reviewer #3: No

**********

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

Reviewer #3: 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: No

Reviewer #3: No

**********

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:  The manuscript presents a novel approach for identifying chemotherapeutic targets in non-small cell lung cancer (NSCLC) using transfer learning models. The proposed method integrates a hybrid UNet transformer for feature extraction and a modified Rime optimization (MRO) algorithm for dimensionality reduction, followed by a deep transfer learning (DTransL) model to improve the accuracy of drug discovery. While the study addresses an important topic in the intersection of machine learning and oncology, several critical issues regarding methodology clarity, data presentation, and interpretation of results need to be addressed to improve the manuscript's rigor and impact.

Major Comments:

1. Introduction and Background:

The introduction provides a good overview of the challenges in NSCLC treatment and the potential for machine learning models in drug discovery. However, the transition to the specific approach used in this study is abrupt. It would be beneficial to provide more context on the limitations of existing models and why the proposed hybrid UNet transformer and DTransL model are expected to address these gaps.

The introduction should better articulate the novelty of the proposed approach compared to existing methods. Currently, it is not clear how the combination of feature extraction and transfer learning represents a significant advancement over prior models.

2. Methods:

The methodology section is quite detailed, but it lacks clarity in several key areas:

The description of the hybrid UNet transformer model for feature extraction is overly technical without sufficient context for readers who may not be familiar with this architecture. A brief explanation of how the hybrid UNet differs from standard UNet models and its relevance to feature extraction in drug discovery would be helpful.

The use of the Modified Rime Optimization (MRO) algorithm for dimensionality reduction needs more justification. The rationale behind selecting this algorithm over other common methods (e.g., Principal Component Analysis, t-SNE) is not well explained. A comparative discussion of its advantages and limitations is necessary.

The explanation of the deep transfer learning (DTransL) model is also highly technical and lacks clarity. More intuitive descriptions or visual aids (e.g., flowcharts) showing how transfer learning is applied in this context could greatly enhance understanding.

3. Data Presentation and Analysis:

The manuscript presents results across three benchmark datasets (Davis, KIBA, and Binding-DB), demonstrating improvements in predictive accuracy using the proposed MRO+DTransL model. However, the presentation of the results could be more systematic:

Tables summarizing the performance of different models should include standard deviations or confidence intervals to provide a sense of variability and statistical significance.

The manuscript reports various performance metrics (e.g., Concordance Index, Mean Square Error, Regression towards Mean, Pearson Correlation), but the relevance of these metrics to the clinical applicability of the model is not well discussed. The authors should provide more context on why these particular metrics were chosen and how they relate to real-world drug discovery and treatment scenarios.

The ablation studies (e.g., varying epochs) are a good addition to demonstrate the robustness of the model. However, more detailed explanations are needed regarding the implications of these results for practical applications, such as computational costs and model training time.

4. Interpretation of Results:

While the manuscript claims significant improvements over existing models, it does not provide a critical discussion of potential limitations. For instance, how might overfitting or data imbalance impact the reported results? Are there any challenges in replicating these results in a clinical setting?

The authors should also address the generalizability of their findings. The datasets used for validation (Davis, KIBA, and Binding-DB) are standard in the field, but it is unclear whether the model would perform equally well on new, unseen datasets, particularly those that reflect diverse patient populations or drug-target interactions.

5. Discussion and Conclusion:

The discussion section should provide a more balanced view of the study’s strengths and limitations. While the authors emphasize the superiority of their approach, there is little mention of potential drawbacks, such as the computational complexity of the proposed models or the need for large-scale, high-quality data.

The manuscript should propose specific future research directions to address current limitations. For example, are there plans to test the model on other types of cancer, or to explore alternative feature extraction techniques? Such a discussion would help situate the work within the broader field and suggest avenues for further development.

6. Figures and Visual Aids:

The manuscript contains several figures, such as the conceptual structure of the proposed drug discovery model. However, some of these figures are not clearly referenced in the text. Each figure should be explicitly described and referenced to enhance comprehension.

The addition of comparative visualizations (e.g., ROC curves, precision-recall curves) could provide more insights into the model's performance relative to existing methods.

Minor Comments:

Abstract: The abstract should be more concise and directly state the novel contributions of the study. Currently, it contains too much general information and lacks a clear summary of key findings.

Language and Clarity: The manuscript contains numerous grammatical errors and awkward phrasings that affect readability. A thorough proofreading is necessary to improve clarity and coherence.

References: Ensure all references are up-to-date and relevant. Some recent studies on transfer learning and drug discovery in oncology could provide a more comprehensive background.

Reviewer #2:  The authors designed and tested a deep learning algorithm with a feature extraction (integrate hybrid UNet) combined with modified rime optimization (MRO) for dimensionality reduction called MRO+DTransL. The new network was tested on 3 different datasets according to its performance against state of the art networks for datasets for lung cancer with EGFRT790M mutation. Nevertheless, the accuracy of the presented approach is very high for benchmark datasets, there are some points of the presented work the authors should address in more detail.

Authors should fix typing errors:

forNSCLC (last section of introduction)

extrapolativeprocess (2 section)

mutationprediction (Table 1)

andALK (Table 1)

EGFRT790M (2 section)

theoptimal (3.1 section)

removesless (3.1 section)

variedpart (3.1 section)

populaceearlier (3.1 section)

Medicatioinnovation (3.3 section)

ofCT (3.3 section)

,QT (3.3 section)

characteristictrajectories (3.3 section)

markfields (3.3 section)

efficiencymechanism (3.3 section)

Maxpooling (3.3 section)

charcteristicmap (3.3 section)

recordvitalcharacteristics (3.3 section)

maxpooling (3.3 section)

)are (3.3 section)

resultsLastly (4.1 section)

…

The relation of this work to the mentioned networks in the second paragraph of section ‘2. related works’ is not clear to me. Authors do not use this related works in their conclusion. I do not see the importance of mentioning this works.

Authors should correct typing errors in Table 1.

In Table 1 authors mention MAE, NDCG, CNN and RNN as well as much more abbreviations. I would suggest writing the meaning of the abbreviations in the caption or directly in the table, so that the reader can better follow the logic of the table.

The ratio of training, validation and testing should be mentioned in the caption of Figure 1.

The caption of Figure 2 should help to understand the Figure itself. More info is needed.

The statement ‘a huge optimal solution is printed as follow’ in section 3.1. The word printed is confusing.

Algorithm 1: Step 1 and 8 are needed to be mentioned?

‘M Agent Place’ is not clear to me. (after equation 16)

‘ln’, ‘un’ in the paragraph before equation 17 are not corresponding to formula 17.

Algorithm 2: step 9 to 12 are not clear to me.

‘which is one of the most common and deadly forms of lung cancer’, this statement was mentioned several times before and is redundant.

Also, all the paragraph after this statement is a repetition of previous statements.

Algorithm 3: 3. … converged do, what means ‘do’?

Also, here step 9 to 11 are not clear to me?

Section 3 show a lot of information about the suggested deep learning approach, which are never mentioned in the results section. It is not clear for me why such a detailed explanation is needed. I would suggest reducing the mentioned formula to the most important ones and shift the other formula in the supporting information section. In general, the section 3 is very long and should be reduced.

In the result section authors present very similar outcome for each investigated dataset. I would suggest combining the findings in a single statement without repeating sever times the same findings. Also, the table 2,3 and 4 can be moved to the supporting information section.

Figures 3, 4 and 5 are looking quite the same. I would suggest compacting the outcome in a single figure, which better show the differences between the datasets. The legend has no sense if the axes label shows the same labels.

The findings are presented 3 times in nearly the same way. I would suggest summarizing the findings in one single statement.

How the authors avoid overfitting? A very high accuracy was reached already with 200 epochs. Why the authors suggest making 1000 epochs with such a small increment of accuracy compared to the high calculation costs.

The authors did not mention the calculation environment and the times needed to obtain the presented outcome.

In Figure 6, 7 and 8 Training time for the iteration is confusing.

In figure 7, why the loss does not oscillate after a certain point?

Table 5 and Figure 9-11 are showing the same. What is the sense to present 2 times the same findings? Figure 9-11 are redundant.

In the conclusion as well as abstract it should be clear what is new in this work. The algorithm was developed by the authors? What are the structural difference to the state of the art algorithm? The feature reduction is different to the presented state of the art algorithm? Main differences and new findings should be more clear.

Reviewer #3:  The paper introduces an approach to finding new therapeutic agents for non-small cell lung cancer (NSCLC) by means of a machine learning (neural) model augmented with an optimisation technique for dimensionality reduction. While the goal of the paper is related to very relevant problem, the presented description of the solution is not very convincing, leading to severe doubts about the actual contribution of the work, as elaborated in detail in the following paragraphs.

Perhaps most importantly, the code and any data pertinent to the presented work is missing in the submission, and there is no link to an online resource (e.g., GitHub or paperswithcode). This makes it impossible to cross-reference the authors' claims with the actual implementation, let alone reproduce the whole approach.

The other general problem is that the authors claim to improve identification of chemotherapeutic targets that could improve outcome in NSCLC patients, but they do not show any results demonstrating success in this specific tasks - all the experiments are done on general drug binding and/or target datasets, which is a rather long shot from actual treatment response. Also, the datasets contain all sorts of drugs, while a more focused approach motivated, for instance, by the specific biology of NSCLC, would make more sense. Last but not least, the authors mention kinase inhibitors in the text, which is inconsistent with what the title of the paper says, not contributing to credibility of the approach.

The approach itself is rather poorly motivated - why a U-net architecture? This is designed for image processing, and the authors do not show any specific input preprocessing that would let them treat drug and protein target representations as image data (which they seem to use, since when describing that part of the solution, they seem to be working with voxel data). The Rime optimisation part then seems totally disconnected - why is it needed at all? (neural models typically deal with feature extraction well enough on their own; that's one of their key advantages, after all) And how does it process the drug and target features, exactly? None of this is clear at all from the sort of boilerplate, disconnected description in the paper. The exact use of transfer learning is not clear either - what is the original domain where the neural model is trained, and what is the new one? And these are only the selected major questions related to the technical soundness of the approach, unfortunately...

In the validation part, we are shown some impressive numbers, but without context, and without any relationship whatsoever to the goal of the paper (i.e., improving existing NSCLC treatment regimes). Furthermore, comparison with approaches that also target this particular diagnosis is missing. This makes it very hard to see exactly how the data support the hypothesis of the authors.

Finally, in terms of presentation and scientific rigor, the paper does not score too high, either. The level of English is rather low, with grammar issues already in the abstract, lots of typos (especially merged words) and some sentences and even whole paragraphs barely understandable (e.g., the sentences after eq. (8) in the Rime part). Lots of references that are supposed to support claims made in the paper are about totally irrelevant research (e.g., ref [37] in the transfer learning part that is about remote sensing).

This assessment unfortunately leads to the only possible conclusion - this work is by far not ready for publication.

**********

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: Yes:  David Dannhauser

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.]

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.

PONE-D-24-38371R1Optimizing chemotherapeutic targets in non-small cell lung cancer with transfer learning for precision medicinePLOS ONE

Dear Dr. kumari,

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 Dec 13 2024 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,

Ruo Wang

Academic Editor

PLOS ONE

[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

**********

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: (No Response)

Reviewer #2: Partly

**********

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

Reviewer #1: (No Response)

Reviewer #2: Yes

**********

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: (No Response)

Reviewer #2: Yes

**********

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: (No Response)

Reviewer #2: 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: (No Response)

Reviewer #2: The Authors did not review and edit the conclusion of their work. Most of the figures/tables are unchanged. In the current version the figures do not highlight the findings of the authors. I suggest to edit the repeated findings for better readability. A reduction of section 3 (supporting Information) should be considerate by the authors.

**********

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: Yes:  David Dannhauser

**********

[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.

PONE-D-24-38371R2Optimizing chemotherapeutic targets in non-small cell lung cancer with transfer learning for precision medicinePLOS ONE

Dear Dr. kumari,

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 Jan 24 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,

Ruo Wang

Academic Editor

PLOS ONE

[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 #2: All comments have been addressed

**********

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: Partly

**********

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: Yes

**********

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: The authors modified the conclusion of the manuscript and updated the colors of the last three figures.

The figures 3-5 are still unchanged. The reader does not get any information out of these figures. I strongly suggest to modify figure 3-5.

The table 5 and figure 9-11 show the same data. The authors should combine or reduce repeated information.

The conclusion section repeat the values of table 5 against an average value, which is not indicated in the figures or table.

The caption of all figures should be revised. The reader should be able to understand a figure without reading the whole manuscript.

The conlcusion does not comment any reason for the higher performance or differences between the datasets.

**********

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: Yes:  David Dannhauser

**********

[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.

PONE-D-24-38371R3Optimizing chemotherapeutic targets in non-small cell lung cancer with transfer learning for precision medicinePLOS ONE

Dear Dr. kumari,

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 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,

Ruo Wang

Academic Editor

PLOS ONE

[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 #2: All comments have been addressed

**********

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: Yes

**********

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

Reviewer #2: Yes

**********

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: Yes

**********

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: Yes

**********

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: The authors modifed the figures of the manuscript. The findings of the authors are now clear to the reader. I would only suggest to remove from figure 3-5 the percentage values in the graph, because some of the values overlap, which makes it difficult to read them.

**********

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: Yes:  David Dannhauser

**********

[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.

Optimizing chemotherapeutic targets in non-small cell lung cancer with transfer learning for precision medicine

PONE-D-24-38371R4

Dear Dr. kumari,

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,

Ruo Wang

Academic Editor

PLOS ONE

Additional Editor Comments (optional):

Reviewers' comments: