Dear Dr Chang,

Thank you very much for submitting your manuscript 'Differentiation of Cytopathic Effects (CPE) Induced by Influenza Virus Infection Using Deep Convolutional Neural Networks (CNN)' for review by PLOS Computational Biology. Your manuscript has been fully evaluated by the PLOS Computational Biology editorial team and in this case also by independent peer reviewers. The reviewers appreciated the attention to an important problem, but raised some substantial concerns about the manuscript as it currently stands. While your manuscript cannot be accepted in its present form, we are willing to consider a revised version in which the issues raised by the reviewers have been adequately addressed. We cannot, of course, promise publication at that time.

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.

Your revisions should address the specific points made by each reviewer. Please return the revised version within the next 60 days. If you anticipate any delay in its return, we ask that you let us know the expected resubmission date by email at ploscompbiol@plos.org. Revised manuscripts received beyond 60 days may require evaluation and peer review similar to that applied to newly submitted manuscripts.

In addition, when you are ready to resubmit, please be prepared to provide the following:

(1) A detailed list of your responses to the review comments and the changes you have made in the manuscript. We require a file of this nature before your manuscript is passed back to the editors.

(2) A copy of your manuscript with the changes highlighted (encouraged). We encourage authors, if possible to show clearly where changes have been made to their manuscript e.g. by highlighting text.

(3) A striking still image to accompany your article (optional). If the image is judged to be suitable by the editors, it may be featured on our website and might be chosen as the issue image for that month. These square, high-quality images should be accompanied by a short caption. Please note as well that there should be no copyright restrictions on the use of the image, so that it can be published under the Open-Access license and be subject only to appropriate attribution.

Before you resubmit your manuscript, please consult our Submission Checklist to ensure your manuscript is formatted correctly for PLOS Computational Biology: http://www.ploscompbiol.org/static/checklist.action. Some key points to remember are:

- Figures uploaded separately as TIFF or EPS files (if you wish, your figures may remain in your main manuscript file in addition).

- Supporting Information uploaded as separate files, titled Dataset, Figure, Table, Text, Protocol, Audio, or Video.

- Funding information in the 'Financial Disclosure' box in the online system.

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.

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. For instructions see here. 

We are sorry that we cannot be more positive about your manuscript at this stage, but if you have any concerns or questions, please do not hesitate to contact us.

Sincerely,

Amber M Smith

Guest Editor

PLOS Computational Biology

Rob De Boer

Deputy Editor

PLOS Computational Biology

A link appears below if there are any accompanying review attachments. If you believe any reviews to be missing, please contact ploscompbiol@plos.org immediately:

[LINK]

Reviewer's Responses to Questions

Comments to the Authors:

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

Reviewer #1: The authors Chang et al. described a CNN that classifies samples into two categories (infected with flu vs not infected with flu) based on images of cells cultured with sample after various times. Two training/validation sets have been constructed and results were similar. The results appear to be robust and have clinical application.

Major issues:

The training data set (images, and their labels) are not provided.

It would be better if the code and trained model is also available.

When images of cells infected with other viruses are used as the input, what is the output? The data in Table 4 indicated that for RSV, training 2, 1200 epochs, accuracy is 1 but the best one is 0.35. What does the column "best one" indicate? Why is the best one is 0.35 and 1200 epoc is 1? Should the best one be better than 1200 epochs (most of the rows are but not always)?

Based on the images provide for the other virus-infected cells, some of them have apparent changes in cell morphology. If they are not classified as influenza damage, are they classified as no damage? (because the CNN only has two outputs).

The manuscript can use some better organization regarding the introduction of training1 vs. training2. Training 2 data appeared before they were introduced, I suspect this was a response to a prior review of some sort.

Minor issues

The manuscript could use some editing of the English Language.

For example:

Page 10: line 145: were differentiated correctly: Do the author mean identified?

Page 19: line 220: resigned training data? What is "resigned" referring to?

Reviewer #2: The manuscript by Want et al. describes a deep convolutional neural network (CNN) approach to detect influenza induced cytopathic effects from microscopic images of influenza infected MDCK cells. The aim is to develop a fast and accurate tool for rapid influenza diagnoses in clinics. Deep learning approaches have been proven to be extremely powerful for identifying objects of interests from images in the past decade. Thus, the approach to the problem was well chosen in the study. The authors showed that trained model can achieve a very high percentage of correct recognition (99.75%). Although the results look convincing, my enthusiasm about the study is dampened by a couple of major concerns and some minor concerns.

First of all, the images used to train the model are images of cells infected by a single virus strain (PR8). While the authors tested the model against a variety of other non-influenza viruses, I think it is critical/essential to test how the model works with other influenza strains. This is because we usually do not know the virus strain that a person is infected with as a priori. The model is useful only when it can correctly predict the presence of influenza virus irrespective of the strain a cell is infected with.

Second, it is not clear to me how this method is compared with other method in terms of accuracy and time needed for diagnoses. Although the authors discussed and compared the performance of their model with the performance of R-mix, the comparison does not seem to be fair, because the tests were done using different sets of data and images collected from different experiment with different protocols. Furthermore, the CNN model may be an automation method and a useful alternative to visual examination, for example by a medical technologist. However, it is not clear to me how much (quantitative) benefit one gains as compared to visual examination, e.g. how much more accurate the CNN model performs compared to visual examination and how much time it saves. Overall, the advantages and significance of this approach in terms of clinical use is not clearly discussed and highlighted. This really limit the enthusiasm about the proposed approach.

Third, in Fig 4, the authors used the model to test against non-influenza viruses and concluded that ’no cytopathic effect was observed in MDCK cells infected by other viruses’. It is not clear to me what analysis was exactly performed. Did the author use the model trained on influenza infected and mock MDCK cells to classify images of cells infected by non-influenza viruses; or the authors retrained the model including the images of cells infected by non-influenza viruses? In the images with other virus infections, is that indeed ‘there is no cytopathic effects’; or other viruses cause cytopathic effects that are different from influenza? I also notice that the images were all taken at 40phi (for other viruses). What about other time points?

Some minor points below:

Lines 186- 201, it is not clear to me how the accuracy of prediction of images taken at different time points were done. Did the authors retrain the model; or just used the model trained on the Training dataset described in the earlier text?

Line 194-195, Can the authors test why the accuracy drops at 40hpi? It is not sufficient to speculate the cause.

Line 198, typo ‘act’ -> ‘fact’?

**********

Have all data underlying the figures and results presented in the manuscript been provided?

Large-scale datasets should be made available via a public repository as described in the PLOS Computational Biology data availability policy, and numerical data that underlies graphs or summary statistics should be provided in spreadsheet form as supporting information.

Reviewer #1: No: The training data set (images and labels) are not provided.

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

Dear Dr. Chang,

Thank you very much for submitting your manuscript "Differentiation of Cytopathic Effects (CPE) Induced by Influenza Virus Infection Using Deep Convolutional Neural Networks (CNN)" 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. The reviewers appreciated the attention to an important topic. Based on the reviews, we are likely to accept this manuscript for publication, providing that you modify the manuscript according to the review recommendations. 

Please prepare and submit your revised manuscript within 30 days. If you anticipate any delay, please let us know the expected resubmission date by replying to this email. 

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

[1] A letter containing a detailed list of your responses to all 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.

Thank you again for your submission to our journal. 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,

Amber M Smith

Guest Editor

PLOS Computational Biology

Rob De Boer

Deputy Editor

PLOS Computational Biology

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

A link appears below if there are any accompanying review attachments. If you believe any reviews to be missing, please contact ploscompbiol@plos.org immediately:

[LINK]

Reviewer's Responses to Questions

Comments to the Authors:

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

Reviewer #1: The authors need to incorporate the reply to reviewer's question in the revised manuscript. Most of the answers to Reviewer 1 were not reflected in the revision. The authors stated that they changed "best one" to "saved weights". But in table 2, they still used "best one". Also although the code is provided in github (much appreciated), the data is provided through a link. The link time out when I tried to download the data.

Reviewer #2: All my concerns are appropriately addressed. I appreciate the author's efforts to collected additional data (images) of cells infected by other strains. This added a lot of robustness to the model.

**********

Have all data underlying the figures and results presented in the manuscript been provided?

Large-scale datasets should be made available via a public repository as described in the PLOS Computational Biology data availability policy, and numerical data that underlies graphs or summary statistics should be provided in spreadsheet form as supporting information.

Reviewer #1: No: As stated, the data were not available.

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: Yes: Ruian Ke

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, PLOS recommends that you deposit 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. For instructions see http://journals.plos.org/ploscompbiol/s/submission-guidelines#loc-materials-and-methods

Dear Dr. Chang,

We are pleased to inform you that your manuscript 'Differentiation of Cytopathic Effects (CPE) Induced by Influenza Virus Infection Using Deep Convolutional Neural Networks (CNN)' 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,

Amber M Smith

Guest Editor

PLOS Computational Biology

Rob De Boer

Deputy Editor

PLOS Computational Biology

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