Heuristic-enabled active machine learning: A case study of predicting essential developmental stage and immune response genes in Drosophila melanogaster

Olufemi Tony Aromolaran; Itunu Isewon; Eunice Adedeji; Marcus Oswald; Ezekiel Adebiyi; Rainer Koenig; Jelili Oyelade

doi:10.1371/journal.pone.0288023

Peer Review History

Original SubmissionApril 3, 2023
25 Apr 2023 Decision Letter - Jian Xu, Editor Transfer Alert This paper was transferred from another journal. As a result, its full editorial history (including decision letters, peer reviews and author responses) may not be present. PONE-D-23-10047Heuristic-enabled active machine learning for conditionally essential gene prediction in D. melanogasterPLOS ONE Dear Dr. Oyelade, 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 Jun 09 2023 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, Jian Xu, Ph.D. 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 noticed you have some minor occurrence of overlapping text with the following previous publication(s), which needs to be addressed: https://pubmed.ncbi.nlm.nih.gov/34471501/ https://bmcbioinformatics.biomedcentral.com/articles/10.1186/s12859-017-1745-2 https://ieeexplore.ieee.org/document/7081610 In your revision ensure you cite all your sources (including your own works), and quote or rephrase any duplicated text outside the methods section. Further consideration is dependent on these concerns being addressed. 4. 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. 5. Thank you for stating the following in the Acknowledgments Section of your manuscript: "This work was supported by the Deutsche Forschungsgemeinschaft (https://www.dfg.de/) within the project KO 3678/5-1, and the German Federal Ministry of Education and Research (BMBF, Fkz 01EO1002, 01EO1502 and 13N15711) and funding from the World Bank awarded to Covenant Applied Informatics and Communication Africa Centre of Excellence (CApIC-ACE) through the ACE Impact Project (2019 – 2024)." 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: "1. Deutsche Forschungsgemeinschaft (https://www.dfg.de/) within the project KO 3678/5-1, and the German Federal Ministry of Education and Research (BMBF, Fkz 01EO1002, 01EO1502 and 13N15711) 2. World Bank awarded to Covenant Applied Informatics and Communication Africa Centre of Excellence (CApIC-ACE) through the ACE Impact Project (2019 – 2024) The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript." Please include your amended statements within your cover letter; we will change the online submission form on your behalf. 6. Please include captions for your Supporting Information files at the end of your manuscript, and update any in-text citations to match accordingly. Please see our Supporting Information guidelines for more information: http://journals.plos.org/plosone/s/supporting-information. [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 ******** 2. Has the statistical analysis been performed appropriately and rigorously? Reviewer #1: 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 ****** 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 ****** 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: In the article “Heuristic-enabled active machine learning for conditionally essential gene prediction in D. melanogaster”, Aromolaran and colleagues propose a machine learning approach supported by heuristics to support the annotation and employ the prediction of conditional essential genes. The authors attempt to eliminate the curation of gene essentiality by using an uncertainty-based learning approach. While there is merit in tackling a challenging topic, there are methodological concerns considering the manuscript and data/code availability as they are. -The concepts regarding conditional essentiality were well defined, but there is important literature on the topic that should be reviewed and or discussed: https://www.sciencedirect.com/science/article/abs/pii/S0959437X18301291 https://www.sciencedirect.com/science/article/pii/S0734975021001282 https://pubmed.ncbi.nlm.nih.gov/35939967/ https://pubs.rsc.org/en/content/articlelanding/2009/mb/b905264j -Curation of potentially essential/non-essential and conditional essential genes in D. melanogaster based on FlyBase annotations has been performed here and should be discussed: https://academic.oup.com/nargab/article/2/3/lqaa051/5874956 -It is important to highlight that defining conditional essentiality experimentally is very challenging, requiring functional testing under a range of conditions and accounting for potential bias in the functional techniques employed as well as standard annotations. -The authors should be more clear that they are seeking to automate data labeling (and the curation of genes for essentiality in the end) while still using an active learning approach. Sometimes they suggest they are replacing traditional ML approaches, which is not true or the point is not clear (e.g. 74-79). - For clarity, the Materials and methods should appear before the Results (suggestion) -The authors evaluate the performance of their proposed method using and comparing other selection approaches and data available in the literature. However, the data and source code for the HEAL and for the ML approach are not available at the moment. Only the pseudocode for the HEAL is available. The repository only contains binary files and code related to the website, and the repository is not well documented. ALL the source code (ML/bash commands/software versions) and aLL data used for the manuscript should be public and clearly documented, for scientific reproducibility and scrutiny. Use Github for the code and Figshare/Zenodo for the data (if too big for Github). -The authors should focus the paper on the proposed HEAL approach and validate with solid benchmark datasets, potentially involving gene essentiality data (not only the 5 presented, or justify why these 5 datasets are enough to validate their approach). The authors should present the conditional essentiality application as a use-case, not as the main topic, particularly because it is difficult to validate the results. The structure of the manuscript is confusing as is. -The authors manually define sets of essential/non-essential and conditional genes 377-386. However, the terms used to select/label those genes within FlyBase are not clear. These annotations are critical for the success of the approach and should be well documented. What defines essentiality for embryonic development and/or immune response? This should be supported by scientific literature. How can the authors be sure that they are selecting conditional essential genes? Or the authors are focussing on genes that are essential for specific conditions (embryonic development and immune response)? This is quite confusing and should be clarified and consistent in the manuscript. -Why using essentiality for immune response? The focus seems to be essentiality for survival(?). This is not clear and not defined anywhere. If the focus is on essentiality for immune response, this should be raised and discussed in the introduction. -Features were extracted for the genes but the code used for this has not been made available. -Cross-validation results using the selected gene essentiality data should be demonstrated using a figure. The data/code for the cross-validation should be available as well. The validations using the gene essentiality data are weak in the current form. -Only 11 of the 151 predicted to be essential for embryonic development have support from FlyBase. How can the authors be confident about the others? Again, the validation here appears weak. - GO analysis for genes essential for embryonic development should be included in the title (line 577-578) -The authors should register a domain name for http://165.73.223.20. This is because any IP address change would disrupt the availability of the website. -It is clear that some well-defined method for curation of data is still necessary prior to employing HEAL, and this should be acknowledged by the authors (Discussion/Conclusion). -The authors discuss some genes identified by their approach at top-ranked. Were these genes included in the training set or in the test set only? -The authors should clearly discuss the limitations of the present study -If validated, the HEAL method can be used for binary classification approaches beyond conditional essentiality. This can be raised in the Discussion -More information on the HEAL website implementation should be given (Python/Django?) ****** 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 ******** [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.0288023.r001
Revision 1
6 Jun 2023 Author Response Reviewer #1: In the article “Heuristic-enabled active machine learning for conditionally essential gene prediction in D. melanogaster”, Aromolaran and colleagues propose a machine learning approach supported by heuristics to support the annotation and employ the prediction of conditional essential genes. The authors attempt to eliminate the curation of gene essentiality by using an uncertainty-based learning approach. While there is merit in tackling a challenging topic, there are methodological concerns considering the manuscript and data/code availability as they are. -The concepts regarding conditional essentiality were well defined, but there is important literature on the topic that should be reviewed and or discussed: https://www.sciencedirect.com/science/article/abs/pii/S0959437X18301291 https://www.sciencedirect.com/science/article/pii/S0734975021001282 https://pubmed.ncbi.nlm.nih.gov/35939967/ https://pubs.rsc.org/en/content/articlelanding/2009/mb/b905264j -Curation of potentially essential/non-essential and conditional essential genes in D. melanogaster based on FlyBase annotations has been performed here and should be discussed: https://academic.oup.com/nargab/article/2/3/lqaa051/5874956 Response: We thank the reviewer for pointing us to the related literature. We have reviewed these publications in line 23 -41 and 66-74 -It is important to highlight that defining conditional essentiality experimentally is very challenging, requiring functional testing under a range of conditions and accounting for potential bias in the functional techniques employed as well as standard annotations. Response: We appreciate the reviewer for highlighting this fact. We have included this fact in line 72-74. -The authors should be more clear that they are seeking to automate data labeling (and the curation of genes for essentiality in the end) while still using an active learning approach. Sometimes they suggest they are replacing traditional ML approaches, which is not true or the point is not clear (e.g. 74-79). Response: To clarify the statement in line 351-353, the paragraph stated the goal of the study to replace the human component in the Active learning approach and not replace ML approaches. - For clarity, the Materials and methods should appear before the Results (suggestion) Response: The sections have been arranged as suggested by the reviewer. -The authors evaluate the performance of their proposed method using and comparing other selection approaches and data available in the literature. However, the data and source code for the HEAL and for the ML approach are not available at the moment. Only the pseudocode for the HEAL is available. The repository only contains binary files and code related to the website, and the repository is not well documented. ALL the source code (ML/bash commands/software versions) and aLL data used for the manuscript should be public and clearly documented, for scientific reproducibility and scrutiny. Use Github for the code and Figshare/Zenodo for the data (if too big for Github). Response: We appreciate the author for pointing out the packaging of our data and source code, we now provide all the data and source with clear description in github. -The authors should focus the paper on the proposed HEAL approach and validate with solid benchmark datasets, potentially involving gene essentiality data (not only the 5 presented, or justify why these 5 datasets are enough to validate their approach). The authors should present the conditional essentiality application as a use-case, not as the main topic, particularly because it is difficult to validate the results. The structure of the manuscript is confusing as is. Response: We agree with the reviewer as regards the need to present the conditional essentiality as a use case and this is evident in the title modification. We chose not to validate with other gene essentiality data because the focus of the study is modifying active learning for labeling biological when there is limited training data which also helps to focus the paper on the proposed HEAL approach as suggested. -The authors manually define sets of essential/non-essential and conditional genes 377-386. However, the terms used to select/label those genes within FlyBase are not clear. These annotations are critical for the success of the approach and should be well documented. What defines essentiality for embryonic development and/or immune response? This should be supported by scientific literature. How can the authors be sure that they are selecting conditional essential genes? Or the authors are focussing on genes that are essential for specific conditions (embryonic development and immune response)? This is quite confusing and should be clarified and consistent in the manuscript. Response: Again, we thank the reviewer for pointing this out. This study is focusing on predicting conditionally essential genes given 2 specific conditions. The data collected from Flybase relates to lethality during the 2 conditions. More description about the flybase annotation for the two conditions in focus has been added in line 142-147. -Why using essentiality for immune response? The focus seems to be essentiality for survival(?). This is not clear and not defined anywhere. If the focus is on essentiality for immune response, this should be raised and discussed in the introduction. Response: As stated above, the essentiality relates to immune response condition. This is now discussed in the introduction section on line 43-49. -Features were extracted for the genes but the code used for this has not been made available. Response: Publicly available tools were used for feature generation and these tools were described in the Feature generation section line 156 of the manuscript. -Cross-validation results using the selected gene essentiality data should be demonstrated using a figure. The data/code for the cross-validation should be available as well. The validations using the gene essentiality data are weak in the current form. Response: We acknowledge the concerns of the reviewer. We would like to point out that Fig. 1 is a figure that graphically presents the cross-validation results as requested by the reviewer however, the same cannot be graphically presented for the Drosophila data because we only know the label for about 10% of the data unlike ML approach where the label for both training and test data is available prior to the analysis. Attempting to use ML performance metrics like precision-recall or accuracy will give a false representation of the model performance. To ensure the HEAL model performance is comparable to existing models, we used the UCI data for validation of the model. -Only 11 of the 151 predicted to be essential for embryonic development have support from FlyBase. How can the authors be confident about the others? Again, the validation here appears weak. Response: We thank the reviewer for pointing us in this direction. After careful observation of the result, we discovered that predictions with probability score lower than 0.6 were erroneously reported. We did describe the reason for using the decision boundary of 0.6 in line 559-561. We now excluded genes with probability score lower than 0.6 thereby reducing the number of predictions from 151 to 53 with 5 genes validated in Flybase (Table S1). We thereafter search the literature to find the link between the top 10 predicted genes and developmental stage condition. Our findings are found in the discussion section. A potential limitation of the HEAL model is also mentioned in the discussion section. - GO analysis for genes essential for embryonic development should be included in the title (line 577-578) Response: The Title has been modified to reflect the scope of the study -The authors should register a domain name for http://165.73.223.20. This is because any IP address change would disrupt the availability of the website. Response: We thank the reviewer for this suggestion, the domain name is now registered. -It is clear that some well-defined method for curation of data is still necessary prior to employing HEAL, and this should be acknowledged by the authors (Discussion/Conclusion). Response: The methods for data curation were presented with relevant references in the methods section -The authors discuss some genes identified by their approach at top-ranked. Were these genes included in the training set or in the test set only? Response: The identified genes were not included in the training set. -The authors should clearly discuss the limitations of the present study Response: We thank the reviewer for this comment. A paragraph about the limitation has been included in the discussion section line 485-494 -If validated, the HEAL method can be used for binary classification approaches beyond conditional essentiality. This can be raised in the Discussion -More information on the HEAL website implementation should be given (Python/Django?) Response: We have now included more information on the website implementation on line 414-418. Attachments Attachment Submitted filename: Response to Reviewers.docx https://doi.org/10.1371/journal.pone.0288023.r002
19 Jun 2023 Decision Letter - Jian Xu, Editor Heuristic-enabled active machine learning: A case study of predicting essential developmental stage and immune response genes in Drosophila melanogaster PONE-D-23-10047R1 Dear Dr. Oyelade, 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 for payment will follow shortly after the formal acceptance. To ensure an efficient process, please log into Editorial Manager at http://www.editorialmanager.com/pone/, click the 'Update My Information' link at the top of the page, and double check that your user information is up-to-date. If you have any billing related questions, 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, Jian Xu, Ph.D. 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 ******** 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 ****** 3. Has the statistical analysis been performed appropriately and rigorously? Reviewer #1: 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 ****** 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 ****** 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 authors have addressed all comments and concerns carefully. I consider that the manuscript is now suitable for publication. ****** 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 ******** https://doi.org/10.1371/journal.pone.0288023.r003
Formally Accepted
31 Jul 2023 Acceptance Letter - Jian Xu, Editor PONE-D-23-10047R1 Heuristic-enabled active machine learning: A case study of predicting essential developmental stage and immune response genes in Drosophila melanogaster Dear Dr. Oyelade: I'm pleased to inform you that your manuscript has been deemed suitable for publication in PLOS ONE. Congratulations! Your manuscript is now with our production department. 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 plosone@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. Jian Xu Academic Editor PLOS ONE https://doi.org/10.1371/journal.pone.0288023.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 .