Dear Dr. Mengshan,

Thank you very much for submitting your manuscript "Prediction of DNA Methylation based on Multi-dimensional feature encoding and double convolutional fully connected convolutional neural network" for consideration at PLOS Computational Biology.

As with all papers reviewed by the journal, your manuscript was reviewed by members of the editorial board and by several independent reviewers. In light of the reviews (below this email), we would like to invite the resubmission of a significantly-revised version that takes into account the reviewers' comments.

We cannot make any decision about publication until we have seen the revised manuscript and your response to the reviewers' comments. Your revised manuscript is also likely to be sent to reviewers for further evaluation.

When you are ready to resubmit, please upload the following:

[1] A letter containing a detailed list of your responses to the review comments and a description of the changes you have made in the manuscript. Please note while forming your response, if your article is accepted, you may have the opportunity to make the peer review history publicly available. The record will include editor decision letters (with reviews) and your responses to reviewer comments. If eligible, we will contact you to opt in or out.

[2] Two versions of the revised manuscript: one with either highlights or tracked changes denoting where the text has been changed; the other a clean version (uploaded as the manuscript file).

Important additional instructions are given below your reviewer comments.

Please prepare and submit your revised manuscript within 60 days. If you anticipate any delay, please let us know the expected resubmission date by replying to this email. Please note that revised manuscripts received after the 60-day due date may require evaluation and peer review similar to newly submitted manuscripts.

Thank you again for your submission. We hope that our editorial process has been constructive so far, and we welcome your feedback at any time. Please don't hesitate to contact us if you have any questions or comments.

Sincerely,

Piero Fariselli

Academic Editor

PLOS Computational Biology

Sushmita Roy

Section Editor

PLOS Computational Biology

***********************

Reviewer's Responses to Questions

Comments to the Authors:

Please note here if the review is uploaded as an attachment.

Reviewer #1: The authors present a novel machine learning-based model, MEDCNN, for the prediction of DNA methylation modification sites. While the paper is overall interesting, there are several aspects that require further clarification. Please find my specific comments below:

1. In the abstract, the authors mention that "most models have been built in terms of of a single methylation type. To address the above-mentioned issues, a deep learning-based method was proposed in this study for DNA methylation site prediction, termed the MEDCNN model.". However, based on the provided description, it seems that also the MEDCNN model has actually been trained separately on different species to predict a single methylation type. Please clarify this aspect for better understanding.

2. The dataset described in Table 1 appears to differ from the one used by Lv. et al. for training iDNA-MS. Notably, the dataset employed in this study includes a greater amount of training and testing data compared to Lv. et al. Moreover, it remains unclear how the training and testing data were generated. Could you please provide more details regarding the dataset acquisition process and the methodology used to partition the data into training and testing sets? Specifically, does the dataset exhibit any sequence similarity between the training and testing sequences?

3. The limited description of the training/testing data raises concerns regarding the comparison results presented in the section titled "Experimental results compared with other models." Several points deserve clarification:

- Is it possible that the prediction performance of MEDCNN is influenced by the larger training dataset used?

- To ensure a robust comparison with iDNA-MS, it would be better to use precisely its training and testing data. For instance, could there be an overlap between the test set used here and training set of iDNA-MS?

- Overall, figures 6 and 7 appear to exhibit comparable results, without any discernible predictor outperforming the other. It is advisable to conduct statistical significance tests, such as t-tests or Wilcoxon tests, to determine whether there are statistically significant differences in prediction performance.

4. I have some concerns regarding the effectiveness of the NCP features utilized in the model. Do these features genuinely contribute to improved performance? They seem akin, albeit not formally, to a one-hot encoding of the four nucleotides. It is reasonable to assume that a machine learning approach would readily learn a mapping between BFP and NCP, as it represents a one-to-one mapping between binary vectors. Additionally, there appears to be little discrepancy in performance between these two features when used individually, as demonstrated in the "Experimental results of different feature encoding" section. Kindly provide further justification for the necessity of these features. Also in this case, employing a statistical significance test could aid in elucidating whether certain features or their combinations outperform others.

5. Regarding the section titled "Experimental results of cross-species validation," the concluding statement appears unsupported by the experimental tests depicted in Figure 5 since the authors' assertion appears valid solely for C. equisetifolia.

6. The manuscript would benefit from a thorough proofreading to rectify typos. I have compiled a list of some identified errors:

- Page 9, Equation 6: The term "D_i" lacks an explanation. Also, it has been possibly mistyped as "D_I".

- Page 9, line 182: The sentence beginning with "However, since a 2D feature ..." requires revision.

- Page 12, line 254: The meaning of "to identify 17 datasets" is unclear.

- Page 12, Figure 4(a): The labels BFP, NCP, and DPCP are probably a typo. If not, please clarify their meaning.

- Page 13, line 176: Add a period before "Five datasets."

- Page 13, line 279: Please revise the sentence starting with "predict whether the weather."

- Page 15, line 304: Please revise the sentence beginning with "iDNA-AB and iDNA-ABT, ..."

Reviewer #2: The authors proposed a deep learning-based method for DNA methylation site prediction, termed the MEDCNN model. The MEDCNN model extracted feature information from gene sequences in three dimensions (i.e., positional information, biological information, and chemical information). The proposed method employs a convolutional neural network model with double convolutional layers and double fully connected layers while iteratively updating the gradient descent algorithm. Besides, the MEDCNN model can predict different types of DNA methylation. The deep learning method based on coding from multiple dimensions outperformed single coding methods.

There are some major concerns:

1) In Fig3 abcde, the authors illustrated the profiles or distributions for each measure, but the readers cannot understand what they mean by the profiles. Explain why the figures have profiles clearly. They should explain details in the figures intelligibly in the figure legends.

2) The authors employed convolutional block attention module after the convolutional layer to gain insights into the important features and their locations along the channels and spatial axes by reasoning about their attention images. However, they did not show the attention map and did not explain the insights on the important features. Does the addition of the attention module contribute to the improvement in prediction performance?

3) It may be hard to understand that MDECNN outperformed the existing methods, because the authors did not investigate the latest methods for the respective methylation site prediction in DNA.

4) https://github.com/gnnumsli/DNA-Methylation is immature. This URL site must be prepared so that the users can execute the program and obtain the same results as provided by the manuscript.

**********

Have the authors made all data and (if applicable) computational code underlying the findings in their manuscript fully available?

The PLOS Data policy requires authors to make all data and code 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 and code 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 or code —e.g. participant privacy or use of data from a third party—those must be specified.

Reviewer #1: Yes

Reviewer #2: No: Thier URL site must be prepared so that the users can execute the program and obtain the same results as provided by the manuscript.

**********

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

Figure 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. 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 us at figures@plos.org.

Data Requirements:

Please note that, as a condition of publication, PLOS' data policy requires that you make available all data used to draw the conclusions outlined in your manuscript. Data must be deposited in an appropriate repository, included within the body of the manuscript, or uploaded as supporting information. This includes all numerical values that were used to generate graphs, histograms etc.. For an example in PLOS Biology see here: http://www.plosbiology.org/article/info%3Adoi%2F10.1371%2Fjournal.pbio.1001908#s5.

Reproducibility:

To enhance the reproducibility of your results, we recommend that you deposit your laboratory protocols in protocols.io, where a protocol can be assigned its own identifier (DOI) such that it can be cited independently in the future. Additionally, PLOS ONE offers an option to publish peer-reviewed clinical study protocols. Read more information on sharing protocols at https://plos.org/protocols?utm_medium=editorial-email&utm_source=authorletters&utm_campaign=protocols

Dear Dr. Li,

We are pleased to inform you that your manuscript 'Prediction of DNA Methylation based on Multi-dimensional feature encoding and double convolutional fully connected convolutional neural network' has been provisionally accepted for publication in PLOS Computational Biology.

Before your manuscript can be formally accepted you will need to complete some formatting changes, which you will receive in a follow up email. A member of our team will be in touch with a set of requests.

Please note that your manuscript will not be scheduled for publication until you have made the required changes, so a swift response is appreciated.

IMPORTANT: The editorial review process is now complete. PLOS will only permit corrections to spelling, formatting or significant scientific errors from this point onwards. Requests for major changes, or any which affect the scientific understanding of your work, will cause delays to the publication date of your manuscript.

Should you, your institution's press office or the journal office choose to press release your paper, you will automatically be opted out of early publication. We ask that you notify us now if you or your institution is planning to press release the article. All press must be co-ordinated with PLOS.

Thank you again for supporting Open Access publishing; we are looking forward to publishing your work in PLOS Computational Biology. 

Best regards,

Piero Fariselli

Academic Editor

PLOS Computational Biology

Sushmita Roy

Section Editor

PLOS Computational Biology

***********************************************************

Reviewer's Responses to Questions

Comments to the Authors:

Please note here if the review is uploaded as an attachment.

Reviewer #1: All my previous concerns have been addressed by the authors in the revised version of the manuscript. I have no further remarks this time

Reviewer #2: It is improved according to my comments

**********

Have the authors made all data and (if applicable) computational code underlying the findings in their manuscript fully available?

The PLOS Data policy requires authors to make all data and code 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 and code 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 or code —e.g. participant privacy or use of data from a third party—those must be specified.

Reviewer #1: Yes

Reviewer #2: Yes

**********

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