Meta-2OM: A multi-classifier meta-model for the accurate prediction of RNA 2′-O-methylation sites in human RNA

Md. Harun-Or-Roshid; Nhat Truong Pham; Balachandran Manavalan; Hiroyuki Kurata

doi:10.1371/journal.pone.0305406

Peer Review History

Original SubmissionJanuary 17, 2024
14 Feb 2024 Decision Letter - Shahid Akbar, Editor PONE-D-24-02313Meta2-OM: A multi-classifier meta-model for the accurate prediction of RNA 2'-O-methylation sites in human RNAPLOS ONE Dear Dr. Kurata, 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. ============================== ACADEMIC EDITOR: Major Revision/>============================== Please submit your revised manuscript by Mar 30 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, Shahid Akbar, PhD 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, all author-generated code must 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. We note that the grant information you provided in the ‘Funding Information’ and ‘Financial Disclosure’ sections do not match. When you resubmit, please ensure that you provide the correct grant numbers for the awards you received for your study in the ‘Funding Information’ section. 4. Thank you for stating the following in the Acknowledgments Section of your manuscript: “This work was supported by a Grant-in-Aid for Scientific Research (B) (22H03688) from the Japan Society for the Promotion of Science (JSPS), Japan. It was also supported by the National Research Foundation of Korea (NRF) funded by the Ministry of Science and ICT (2021R1A2C1014338), Republic of Korea.” We note that you have provided additional information within the Acknowledgements Section that is not currently declared in your Funding Statement. Please note that 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 author(s) received no specific funding for this work.” Please include your amended statements within your cover letter; we will change the online submission form on your behalf. [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 ******** 2. Has the statistical analysis been performed appropriately and rigorously? Reviewer #1: Yes Reviewer #2: 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 ****** 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: Roshid et al. have created the Meta2OM predictor, employing a meta-learning-based stacking approach. They also conducted a comparative analysis with existing methods, demonstrating superior performance. Additionally, they have made a significant contribution to the research community by providing both a web server and a standalone program. However, I have the following suggestions for further improvement. 1.Improve the overall flow and structure of the manuscript. Ensure all figures are high-quality and meet journal publication standards. 2.Investigate the potential benefits of using NLP-based embeddings and additional feature descriptors beyond those employed in previous studies. Experiment with various feature combinations to optimize performance. 3.Explore diverse classifier architectures beyond those used in previous works. Consider incorporating new algorithms and comparing their effectiveness. 4.Provide details on the parameter search ranges used during model development. Include this information in a dedicated README file for transparency and reproducibility. 5.Utilize all relevant information from baseline models, including probabilistic scores, class labels, and their combinations. Explore different ways of incorporating this information to enhance prediction performance. 6.Use acronyms consistently throughout the manuscript (e.g., always use ML or Machine Learning, ACC or Accuracy). Define acronyms upon first use and avoid unnecessary acronyms. 7.Explain the reasoning behind using a CD-HIT threshold of 0.8. Provide justification for this specific value and its impact on the results. 8.For the user concerns to provide a clear background of training models, authors are advised to cite the recent predictors such as AIPs-SnTCN , iACP-GAEnsC, iACP-GAEnsC, pAtbp-EnC, and cACP-DeepGram 9.Change the title to "Meta-2OM" for consistency and clarity. Reviewer #2: This study presents promising Meta2-OM predictors for identifying 2OM sites using meta-learning techniques. The careful dataset construction and exploration of diverse ML classifiers and encodings suggest a well-considered approach. Given the growing interest in RNA post-transcriptional modification sites within bioinformatics, this work holds significant potential. To further strengthen its impact, I have the following suggestions: 1. The authors should investigate both nucleotide-specific and generic models. Compare their advantages and disadvantages, highlighting the strengths of each approach and justifying the choice of using a generic dataset for this study. 2. Clearly explain how the current dataset differs from the one used in i2OM. This will provide context and allow for a more meaningful comparison of the two methods. 3. Include H2Opred in the comparison table alongside other existing methods. Analyze its performance relative to your proposed tool to provide a more comprehensive evaluation. 4. Comparison of Meta2-OM with existing methods. I have noticed they have used just only one method. It should be revised. 5. Revise Table 5 to ensure a fair comparison with i2OM. If relevant, consider incorporating nucleotide-specific models from both methods as suggested in point 1. 6.In the machine learning section, the authors should incorporate the following predictors such as iMethyl-STTNC,DP-BINDER, and AFP-CMBPred to provide clear understanding of the model. 7. Analyze the optimal sequence length for prediction accuracy. Construct baseline models with varying sequence lengths (e.g., 31-201 bp) and compare their performance to identify the most effective length. ****** 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.] 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. https://doi.org/10.1371/journal.pone.0305406.r001
Revision 1
21 May 2024 Author Response Dear Academic Editor PLOS ONE Reviewer #1 Roshid et al. have created the Meta2OM predictor, employing a meta-learning-based stacking approach. They also conducted a comparative analysis with existing methods, demonstrating superior performance. Additionally, they have made a significant contribution to the research community by providing both a web server and a standalone program. However, I have the following suggestions for further improvement. 1. Improve the overall flow and structure of the manuscript. Ensure all figures are high-quality and meet journal publication standards. Author’s response: As per your suggestion, we revised the flow and structure of the manuscript. We ensured that the figure files met journal publication standards for quality. Additionally, we confirmed the figure quality using the PLOS-ONE journal ‘PAGE’ tool. 2. Investigate the potential benefits of using NLP-based embeddings and additional feature descriptors beyond those employed in previous studies. Experiment with various feature combinations to optimize performance. Author’s response: We updated the development process by incorporating eight additional feature descriptors, including the NLP-based Word2Vec. Subsequently, we selected the optimal baseline models for the final model construction. (Please see Word2Vec subsection of Encoding and feature extraction strategy section. See Baseline models: construction and evaluation in the Results section) 3. Explore diverse classifier architectures beyond those used in previous works. Consider incorporating new algorithms and comparing their effectiveness. Author’s response: As per your suggestion, we utilized additional classifiers (CBC, NB, KNN, LR) that were not employed in the original manuscript. We demonstrated the effectiveness of the additional methods in predicting 2-OM sites. Please see CBC, NB, and KNN subsection of Materials and methods. Furthermore, we compared the proposed method with the existing methods in independent dataset in the subsection of Comparison of Meta-2OM with existing methods. 4. Provide details on the parameter search ranges used during model development. Include this information in a dedicated README file for transparency and reproducibility. Author’s response: Thanks for your suggestion. We have included a table in the supplementary materials that details the search ranges for hyperparameters across all machine-learning methods. Additionally, we have added all these information in the README file. (See S1 Table) 5. Utilize all relevant information from baseline models, including probabilistic scores, class labels, and their combinations. Explore different ways of incorporating this information to enhance prediction performance. Author’s response: Thanks for your suggestion. Initially, we explored all the approaches mentioned and found that features based on probabilistic scores demonstrated a superior discriminative ability. Hence, we developed the final meta-predictor using LR. In the revised manuscript, we also explored six different classifiers to evaluate their effectiveness in meta-prediction. Our results indicate that the LR-based meta-predictor is particularly robust. These details are included in the revised manuscript (Please see the subsection of Impact of meta-learning on the development of Meta-2OM). 6. Use acronyms consistently throughout the manuscript (e.g., always use ML or Machine Learning, ACC or Accuracy). Define acronyms upon first use and avoid unnecessary acronyms. Author’s response: Thanks for pointing out the above issue. We have carefully revised the manuscript to ensure consistent use of acronyms throughout. We revised the manuscript according to your comments. (Main Manuscript) 7. Explain the reasoning behind using a CD-HIT threshold of 0.8. Provide justification for this specific value and its impact on the results. Author’s response: At this time, we revised the datasets and updated the manuscript accordingly. The main dataset was collected from the latest methods i2OM, where they constructed the datasets by applying CD-HIT analysis with a threshold of 0.8 to control the redundancy. CD-HIT (0.8) indicates the sequence datasets have less than 80% similarity among the sample units. The researcher tried to make a less homogeneous sample for training the model where the datasets can provide unique information to characterize the class. Also, a good-quality dataset can contribute to the training process by producing consistent prediction performance. Due to the lack of biological data samples and considering the overfitting issue, researchers mostly considered an 80% or 90% threshold for developing datasets. (Please see the subsection of Benchmark datasets construction of Methods). 8. For the user concerns to provide a clear background of training models, authors are advised to cite the recent predictors such as AIPs-SnTCN, iACP-GAEnsC, iACP-GAEnsC, pAtbp-EnC, and cACP-DeepGram. Author’s response: We certainly agree with the reviewer. We have cited these methods to provide a clear background of model training and the importance of ensemble learning. 9. Change the title to "Meta-2OM" for consistency and clarity. Author’s response: We revised and updated the title according to your suggestion. (Title and Main Manuscript) Reviewer #2 This study presents promising Meta2-OM predictors for identifying 2OM sites using meta-learning techniques. The careful dataset construction and exploration of diverse ML classifiers and encodings suggest a well-considered approach. Given the growing interest in RNA post-transcriptional modification sites within bioinformatics, this work holds significant potential. To further strengthen its impact, I have the following suggestions: 1. The authors should investigate both nucleotide-specific and generic models. Compare their advantages and disadvantages, highlighting the strengths of each approach and justifying the choice of using a generic dataset for this study. Author’s response: As per your suggestion, we have constructed both nucleotide-specific datasets and generic dataset models. The performance comparison showed that the generic model has an advantage over nucleotide-specific models. Therefore, we have selected the generic model. Moreover, the advantages and strengths of the generic model are highlighted in the revised manuscript (Please see the subsection of Comparison of performance based on generic and nucleotide-specific modifications). 2. Clearly explain how the current dataset differs from the one used in i2OM. This will provide context and allow for a more meaningful comparison of the two methods. Author’s response: Our original dataset shared 66% similarity with those used by the existing methods, making comparisons unreliable and meaningless. Following your suggestion, we significantly revised the manuscript. We now used the same dataset as i2OM and H2Opred, enabling a direct and meaningful assessment of our method’s performance (Please see Benchmark dataset subsection). 3. Include H2Opred in the comparison table alongside other existing methods. Analyze its performance relative to your proposed tool to provide a more comprehensive evaluation. Author’s response: As per your suggestion, we have compared the performance of the proposed method with H2Opred (Please see Figure 6 and Table 5). 4. Comparison of Meta2-OM with existing methods. I have noticed they have used just only one method. It should be revised. Author’s response: In the revised manuscript, we have used two existing methods, which are the most recent. We have provided the reason for excluding several existing methods in the revised manuscript (Please see Comparison of Meta-2OM with existing methods subsection, pages 27-28). 5. Revise Table 5 to ensure a fair comparison with i2OM. If relevant, consider incorporating nucleotide-specific models from both methods as suggested in point 1. Author’s response: As per your suggestion, we have revised Table 5 to directly compare our proposed method and existing methods based on the nucleotide-specific datasets (Please see Table 5, page 47). We revised the comparison results as shown in Table 5, where the results were compared based on nucleotide-specific cases for i2OM and H2Opred methods. (Please see Comparison of Meta-2OM with existing methods of the Results subsection, Fig 6 and Table 5). 6. In the machine learning section, the authors should incorporate the following predictors such as iMethyl-STTNC, DP-BINDER, and AFP-CMBPred to provide clear understanding of the model. Author’s response: Thanks for your suggestion. We have mentioned the above predictors in the method section of the revised manuscript (Please see pages 17-19 and 23-25). 7. Analyze the optimal sequence length for prediction accuracy. Construct baseline models with varying sequence lengths (e.g., 31-201 bp) and compare their performance to identify the most effective length. Author’s response: Thank you for your excellent suggestion. In the original manuscript, we carried out the preliminary analysis with multiple lengths using random forest. The result showed that a 41 bp fragment achieved the best result. We therefore carried out computational analysis using this fragment. Notably, several other studies also support the effectiveness of a similar fragment size for different RNA modification site prediction (iR5hmcSC, iRNAD, Deepm5C, m5U-GEPred, TS-m6A-DL, PseU-Pred). Attachments Attachment Submitted filename: Response to Reviewers_R1.docx https://doi.org/10.1371/journal.pone.0305406.r002
30 May 2024 Decision Letter - Shahid Akbar, Editor Meta-2OM: A multi-classifier meta-model for the accurate prediction of RNA 2'-O-methylation sites in human RNA PONE-D-24-02313R1 Dear Dr. Kurata, 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, Shahid Akbar, PhD 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 #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: Yes Reviewer #2: Yes ****** 3. Has the statistical analysis been performed appropriately and rigorously? Reviewer #1: Yes 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: Yes 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: Yes 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 #1: The required comments are successfully incorporated and paper is significantly improved. The paper can be published from my side. Reviewer #2: The required comments are successfully incorporated and now the paper is significant improved and should be published from my side ****** 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 ******** https://doi.org/10.1371/journal.pone.0305406.r003
Formally Accepted
17 Jun 2024 Acceptance Letter - Shahid Akbar, Editor PONE-D-24-02313R1 PLOS ONE Dear Dr. Kurata, I'm pleased to inform you that your manuscript has been deemed suitable for publication in PLOS ONE. Congratulations! Your manuscript is now being handed over to our production team. At this stage, our production department will prepare your paper for publication. This includes ensuring the following: * All references, tables, and figures are properly cited * All relevant supporting information is included in the manuscript submission, * There are no issues that prevent the paper from being properly typeset If revisions are needed, the production department will contact you directly to resolve them. If no revisions are needed, you will receive an email when the publication date has been set. At this time, we do not offer pre-publication proofs to authors during production of the accepted work. Please keep in mind that we are working through a large volume of accepted articles, so please give us a few weeks to review your paper and let you know the next and final steps. Lastly, if your institution or institutions have a press office, please let them know about your upcoming paper now to help maximize its impact. If they'll be preparing press materials, please inform our press team within the next 48 hours. 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. If we can help with anything else, please email us at customercare@plos.org. Thank you for submitting your work to PLOS ONE and supporting open access. Kind regards, PLOS ONE Editorial Office Staff on behalf of Dr. Shahid Akbar Academic Editor PLOS ONE https://doi.org/10.1371/journal.pone.0305406.r004

Open letter on the publication of peer review reports

PLOS recognizes the benefits of transparency in the peer review process. Therefore, we enable the publication of all of the content of peer review and author responses alongside final, published articles. Reviewers remain anonymous, unless they choose to reveal their names.

We encourage other journals to join us in this initiative. We hope that our action inspires the community, including researchers, research funders, and research institutions, to recognize the benefits of published peer review reports for all parts of the research system.

Learn more at ASAPbio .