Dear Dr Cocco,

Thank you very much for submitting your manuscript "Probing T-cell response by sequence-based probabilistic modeling" 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.

Both reviewers liked the paper. As pointed out by both reviewers and reviewer 2 in particular making it more accessible to math biologists not expert in machine learning might greatly enhance its impact. I know this could take quite a lot of work and time but I think it would be worth the effort.

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,

Rustom Antia

Associate 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]

Both reviewers liked the paper. As pointed out by both reviewers and reviewer 2 in particular making it more accessible to math biologists not expert in machine learning might greatly enhance its impact. I know this could take quite a lot of work and time but I think it would be worth the effort. So while a minor revision would make it acceptable for publication ...

Reviewer's Responses to Questions

Comments to the Authors:

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

Reviewer #1: In this work the Authors present a family of new probabilistic strategies to

analyze T cell receptor (TCR) repertoire. The underlying idea is to construct

probabilistic models on the base of clone abundances to extract TCR sequence

motifs.

The Authors present 3 methods: Restricted Boltzmann Machines (RBM) on previously

aligned TCR sequences, a selection-factor based model (SONIA), and a new RPM

strategy that does not require previous alignment of the sequences. The

application ground of the method consists of TRB CDR3 regions sequences of

7 patient repertoire sequences taken at different times (21 days apart).

The manuscript is scientifically sound and I find particularly interesting the

fact that overall the RBM results used on the not-aligned dataset provides

analogous results compared to the RBM on aligned sequences and SONIA. Moreover,

the lower dimensional "projection" of the RBM on the latent variable space

present sequence motives that were previously found in other works (notably Dash

et al. [17], and Glanville et al [21]).

The manuscript is well written (apart from some issues that I will report

below), and it is scientifically sound. Previous work in the field has been

fairly taken into account in the bibliography.

In the following I will present a series of minor comments that the Author should

address for the sake of clarity.

1. Datasets: I personally find the description of Balachandran et al [16]

dataset in Section Results - Dataset Structure a bit too unforgiving for those

computational biologists which do not have a solid background in immunology. In

particular, without referring to the original paper, it was not clear to me the

preliminary discussion on the neoantigen model. The first paragraph (lines

79-90) is really dense, and would benefit from a critical rewriting.

2. Presentation of the results: Although the discussion is nice and thorough I

found a bit hard to figure out eventually which one of the three strategies was

better suited for this kind of studies. Perhaps a final table (or another

histogram) comparing the global and per patient AUROC for the 3 methods,

expanding somehow Fig.3 D would be helpful.

3. By construction (iterative alignment strategy) the structure of the aligned

sequences have gaps in the center and letter at the extremities. Could the LR

strategies be used (I do not know how) to prove or disprove this structure?

Reviewer #2: Bravi et al. proposes to use a machine-learning approach known as Restricted Boltzmann Machine (RBM) to identify antigen-specific TCRs with a sequence-based inference approach. Several improvements and clarifications are needed so that biologists/immunologists (and people outside the field of machine learning) could appreciate the results of the paper.

1. Figure 1 shows the schematic of the approach. I found Figure 1A and its description in the text to be confusing as it is missing some important immunological details and may be misleading. First, not only antigen but also cytokines should be added to maintain the T cells during 21 days. Second, peptides decay quickly, so T cells probably were restimulated several times between day 0 and day 21, and it should be indicated on the schematic. Third, you need to say how long the cells were stimulated at day 21 before they were taken for analysis.

2. It looks like the patterns (“constraints”) for antigen recognition are very specific for each person/antigen. Do you need the individual person/antigen data for PBMCs expansion in vitro to obtain these patterns for a new patient or already analyzed patients and single time point data from a new patient would be sufficient? It is not clear from the description of the results how it could be generalized. For example, how much can be inferred from a single patient’s blood draw (analog of PBMCs at day 0 in Figure 1A)? Will it be possible to infer the number of neoantigens (important prognostic factor) from a single blood draw? What determines the percentage of well-clustered and expanded sequences in different individuals? Please, describe the practical use of the results for the biologists/immunologists more clearly in the main text, discussion, and abstract.

3. Please describe the limitations: what the method could and could not do in terms of answering the related biological questions.

4. The last sentence in the abstract is unclear. I suggest replacing it with a more specific example(s) of practical use of the RBM approach (see point 2).

**********

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: 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

**********

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 #2: No: no code

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

References:

Review your reference list to ensure that it is complete and correct. If you have cited papers that have been retracted, please include the rationale for doing so in the manuscript text, or remove these references and replace them with relevant current references. Any changes to the reference list should be mentioned in the rebuttal letter that accompanies your revised manuscript.

If you need to cite a retracted article, indicate the article’s retracted status in the References list and also include a citation and full reference for the retraction notice.

Dear Dr Cocco,

We are pleased to inform you that your manuscript 'Probing T-cell response by sequence-based probabilistic modeling' 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,

Rustom Antia

Associate Editor

PLOS Computational Biology

Rob De Boer

Deputy Editor

PLOS Computational Biology

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