Peer Review History
Original SubmissionJuly 21, 2020 |
---|
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-20-22563 Short k-mer Abundance Profiles Yield Robust Machine Learning Features and Accurate Classifiers for RNA Viruses PLOS ONE Dear Dr. Alam, 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. Authors need to prepare a new version of the manuscript in accordance with the recommendations and significant comments from the reviewers. Otherwise, the manuscript will not be published. Please submit your revised manuscript by Oct 02 2020 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:
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: http://journals.plos.org/plosone/s/submission-guidelines#loc-laboratory-protocols We look forward to receiving your revised manuscript. Kind regards, Ruslan Kalendar, 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 Reviewers' comments: Reviewer's Responses to Questions Comments to the Author 1. Is the manuscript technically sound, and do the data support the conclusions? Reviewer #1: Partly Reviewer #2: No ********** 2. Has the statistical analysis been performed appropriately and rigorously? Reviewer #1: N/A Reviewer #2: Yes ********** 3. Have the authors made all data underlying the findings in their manuscript fully available? Reviewer #1: Yes Reviewer #2: Yes ********** 4. Is the manuscript presented in an intelligible fashion and written in standard English? Reviewer #1: Yes Reviewer #2: Yes ********** 5. Review Comments to the Author Reviewer #1: This manuscript addresses the problem of recognizing sequences of RNA viral origin within a data set of sequences. Their solution is a machine learning one, in which they derive from a sequence a set of features, each of which is a short $k$-mer, either its presence or its frequency, which is not clear. They use and evaluate several machine learning methods built using a Python machine learning package. The evaluation efforts are extensive and sufficient. The authors make their Python software available through Github. Always capitalize Python. There are two major problems with the exposition. First, the authors never clearly define the classification problem they are trying to solve. After reading the entire manuscript, it is clearly a binary classification, but what exactly are the classes? Ask a computer scientist for help with properly defining a computational problem. Second, the mathematical exposition on page 34 is the weakest part of the manuscript. The sentences, starting with the first two, make no mathematical sense. What do "mismatches and gaps" have to do with $k$-mers? Again, consult a computer scientist, preferably a theoretical computer scientist. Also, never use the blackboard abbreviation $\\forall$ in technical writing. That and similar notation is reserved for formal logic expressions. Write it out in English and do not put that in the displayed equation. The entire section needs a complete rewrite with more careful mathematical details. Some minor issues follow. Page 2. "De novo" is not hyphenated. Page 3 and throughout. "numerous[1]" should be "numerous [1]". In general, there must be a space before a citation. Page 3, line 48. "Often completely unbeknownst to us." is not a sentence. Make sure every sentence has a subject and a verb. Page 3, line 49. "are astounding" should be "is astounding". Page 3, line 57. "encoding;" should be "encoding," Page 4, lines 65-67. I verified this claim with a search of Web of Science. Page 5, line 92. Do not use the possessive with inanimate things. So, "Scikit-learn's" should be rephrased "The scikit-learn". Make changes throughout. Page 35, line 465. "dataset" should be "data set". Change throughout. Page 37, lines 508-509. Capitalize Intel. "8GBs" should be "8GB". Figure 1, "Layers of Feature Selection", suffers from poor resolution and poor readability. There is no need for the color. Just use black text in black boxes with white background for maximum readability. Reviewer #2: Summary This study applies a short k-mer sequence scores based machine-learning method for classifying RNA viruses from human transcripts. The short k-mer based features are selected and tested with six different classification models: Logistic Regression, SVM, Kernel SVM, Decision Tree, Random Forest and Gaussian Naïve Bayes Classifiers. The methods were mainly tested on (1) RNA viral genomes and human transcripts (2) de-novo assembled contigs from RNA-seq data, and achieved good AUC results on the first data set and reasonable results on the second one. Major issues 1. The main issue is the experiment results lack comparisons. (1) All the results in this study are not compared with other machine learning based viral sequences classifiers, while there are a lot of those kinds of tools, especially those that are also based on k-mer features, like VirFinder. (2) For the results on RNA viral genomes and human transcripts (pager 7, line 113), while the tested models have good AUCs, the results are not compared with blast results or other machine-learning based methods, which does not prove the superiority of the proposed methods 2. For the models training and testing, while as stated a 25% split of training and testing data set is performed (page 7, line 118), no test metrics are reported. For Figure 3, why report the results of cross-validation but not the testing results? 3. The results on real RNA-seq assemblies seem not to be better than blast. On page 15, line 208, blast “yielded 135 false positives” on Human transcriptome assemblies. However, comparing to the results in Table 3, rbf-SVM68 has much more false positives comparing to blast (7067 even after length filtered) 4. How ssRNA(+) and ssRNA(-) are distinguished is not well explained. Usually contigs assembled from RNA-seq data contain both plus and minus strand sequences for a genome, can these contigs be successfully classified as ssRNA(+) or ssRNA(-)? Minor issues: 1. In page 15, line 208, blast “yielded 135 false positives” on Human transcriptome assemblies, while in Supplementary Table 4, there are actually 243 sequences. 2. In page 8, line 130, AUROC is already used before the text “Area under the receiver operating characteristic curve” 3. In Figure 5, typo “Only humam_filtered” 4. Evaluation metrics need some explanation, like macro-averaged f1-score, binary f1-score, ROC AUC etc. ********** 6. PLOS authors have the option to publish the peer review history of their article (what does this mean?). If published, this will include your full peer review and any attached files. If you choose “no”, your identity will remain anonymous but your review may still be made public. Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our Privacy Policy. Reviewer #1: Yes: Lenwood S. Heath 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. |
Revision 1 |
Short k-mer Abundance Profiles Yield Robust Machine Learning Features and Accurate Classifiers for RNA Viruses PONE-D-20-22563R1 Dear Dr. Alam, 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, Ruslan Kalendar, PhD Academic Editor PLOS ONE |
Formally Accepted |
PONE-D-20-22563R1 Short k-mer Abundance Profiles Yield Robust Machine Learning Features and Accurate Classifiers for RNA Viruses Dear Dr. Alam: 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. Ruslan Kalendar Academic Editor PLOS ONE |
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 .