PONE-D-24-06894Analyzing scRNA-seq data by CCP-assisted UMAP and tSNEPLOS ONE

Dear Dr. Wei,

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.

The reviewers’ comments pointed out that a significant revision is required to improve and strengthen the current version of the manuscript. A better literature review should be incorporated into the manuscript. The mathematical formalism used in the manuscript needs to be carefully revised. The bibliography should be carefully revised and unified. A flowchart should be added to the manuscript to better explain the whole process. Larger datasets should be tested to show the scalability and general performance of the proposed approach. Please refer to the reviewers’ reports and the Reviewer’s Responses to Questions section for detailed comments, which could help you improve your manuscript. Please carefully address (and reply to) all the comments raised by all reviewers (this is mandatory).

Please submit your revised manuscript by Jun 27 2024 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,

Andrea Tangherloni

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. Thank you for stating the following financial disclosure: "NIH grants R01GM126189, R01AI164266, and R35GM148196

NSF grants DMS-2052983, DMS-1761320, and IIS-1900473

NASA grant 80NSSC21M0023

MSU Foundation

Bristol-Myers Squibb 65109

Pfizer"

Please state what role the funders took in the study.  If the funders had no role, please state: ""The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript."" 

If this statement is not correct you must amend it as needed. 

Please include this amended Role of Funder statement in your cover letter; we will change the online submission form on your behalf. 

4. Please expand the acronym “NIH, NSF, NASA and MSU” (as indicated in your financial disclosure) so that it states the name of your funders in full.

This information should be included in your cover letter; we will change the online submission form on your behalf.

5. Thank you for stating the following in the Acknowledgments Section of your manuscript: "This work was supported in part by NIH grants R01GM126189, R01AI164266, and R35GM148196 , NSF grants DMS-2052983, DMS-1761320, and IIS-1900473, NASA grant 80NSSC21M0023, MSU Foundation, Bristol-Myers Squibb 65109, and Pfizer."

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: "NIH grants R01GM126189, R01AI164266, and R35GM148196

NSF grants DMS-2052983, DMS-1761320, and IIS-1900473

NASA grant 80NSSC21M0023

MSU Foundation

Bristol-Myers Squibb 65109

Pfizer"

Please include your amended statements within your cover letter; we will change the online submission form on your behalf.

6. Please remove your figures from within your manuscript file, leaving only the individual TIFF/EPS image files, uploaded separately. These will be automatically included in the reviewers’ PDF.

Additional Editor Comments :

The reviewers’ comments pointed out that a significant revision is required to improve and strengthen the current version of the manuscript. A better literature review should be incorporated into the manuscript. The mathematical formalism used in the manuscript needs to be carefully revised. The bibliography should be carefully revised and unified. A flowchart should be added to the manuscript to better explain the whole process. Larger datasets should be tested to show the scalability and general performance of the proposed approach. Please refer to the reviewers’ reports and the Reviewer’s Responses to Questions section for detailed comments, which could help you improve your manuscript. Please carefully address (and reply to) all the comments raised by all reviewers (this is mandatory).

[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: Yes

Reviewer #2: Yes

Reviewer #3: Yes

Reviewer #4: Yes

Reviewer #5: Yes

Reviewer #6: Yes

**********

2. Has the statistical analysis been performed appropriately and rigorously?

Reviewer #1: Yes

Reviewer #2: Yes

Reviewer #3: Yes

Reviewer #4: I Don't Know

Reviewer #5: Yes

Reviewer #6: 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: Yes

Reviewer #2: Yes

Reviewer #3: Yes

Reviewer #4: Yes

Reviewer #5: Yes

Reviewer #6: Yes

**********

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

Reviewer #2: Yes

Reviewer #3: Yes

Reviewer #4: Yes

Reviewer #5: Yes

Reviewer #6: 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: Authors utilize the proposed method CCP as an initialization tool for uniform manifold approximation and projection (UMAP) and t-distributed stochastic neighbor embedding (tSNE) and reported enhancement of CCP assisted UMAP and tSNE over UMAP and tSNE. The paper is well written, organised and I believe the propose method may be good alternative for scRNA-seq data visulaization. I have some suggestions and comments givn below:

1. Nowadays, many deep learning-based dimensionality reduction methods are introduced and they show promising results. It is not clear what are the advantages of the proposed methods over those deep learning-based methods apart from CCP has the ability to work on small size datsets. Some comparison results of CCP assisted UMAP and tSNE, along with PCA and NMF and deep learning assisted UMAP and tSNE may be reported.

2. Nowadays, scRNA-seq datasets contain millions of cells. Authors have considered datasets size less than 10000 cells. I suggest to incorporate results on some large datasets.

3. Authors have reported some impressive results. However, apart from average NMI and ARI reported in Fig 7, detailed results on each of the methods in terms of ARI, NMI on each datasets is expected in tabular format may be in supplementary.

4. In scRNA-seq data analysis running time is also another issue. It would be helpful for reader if authors can report a comparison of the proposed method in terms of running time and memory usage. I also suggest to incorporate systems specification on which the method was tested.

5. The result reported in Fig 8 can be extended by considering a datset of much larger size.

6. I wanted access to the method online. But the link is not working.

7. Typos: line number 236

8. Need captions in supporting figures in supplementary.

Reviewer #2: The authors proposed to utiliza correlated clustering and projection to analyze scRNA-seq data. The work may have been a laborious one that I should appreciate the authors' time and patient to come up with some results. However, there are several problems that deduct from the quality of this manuscript. Below are several comments on this work.

1. The article does not reflect the time consumption performance of this method. Is it suitable for large-scale data sets (Data of more than 10,000 cells)? Are there any disadvantages compared to standard UMAP or t-SNE?

2. Is it scientific that the Urothelial in the Qx Bladder data set in Figure 2 is divided into three sub-clusters? Is it biologically significant?

3. Is it scientific for Mesenchymal in the Qx Trachea data set in Figure 2 to cluster two sub-clusters into one category?

4. Ductal in the Human4 data set in Figure 4 is divided into two clusters in CCP-assisted. Is this biologically meaningful?

Reviewer #3: 1.English expressions need to be edited more careful and more native, in this manuscript, there are some mistakes. For example, “The The samples were colored according to the true cell type” in line 205 on page 13.

2. I suggest the authors should add a flowchart in the manuscript to show the process very well.

3. Important computational models about dimensionality reduction and feature selection in scRNA-seq analysis should be cited. Some recommended studies are helpful (PMIDs: 36642414, 36924730, and 37660567).

4. The authors should carefully check and unify the information of references. Some references lack the information of volume or contain the wrong page number.

Reviewer #4: Correlated Clustering and Projection (CCP) is a data dimensionality reduction method previously designed by the authors. During the dimensionality reduction process, CCP separately processed the low variance (LV) genes.

In this manuscript, the authors found that the reduced data obtained from CCP dimensionality reduction can improve the visualization effect of UMAP and tSNE. From the authors’ experiments, the effect is good.

Major concerns:

1. CCP first clusters genes, which may mask the importance of different genes. Some clusters may be sets of low expression genes, while some others may be sets of high expression genes. Some marker genes are originally unique, but they may be in the same cluster as other non-marker genes, or there may be many marker genes in a certain cluster, or some clusters may not have any marker genes. That is, during the gene clustering process, the uniqueness of marker genes may be reduced? Please reply if there are any possibilities that I mentioned here.

2. It is best to draw a flowchart or an example diagram for the method. Solely using descriptions and formulas can confuse us on subtle differences, such as whether x_m ^ n in line 105 and x_i ^ n in formula (5) represent the same thing.

3. The authors set the number of super-genes to 300 for all datasets, but the number of genes in the original datasets used in the paper is different. Why not dynamically adjust the number of super-genes based on the number of genes?

4. P5, line 118, What weights are these w_ {im} and how to set?

Minor comments:

P4 line 104, Does z_m ^ {S ^ n} represent the expression vector of the corresponding cluster?

Typos: Page10 Line 167, dataa -->data

Reviewer #5: 1. Provide a more detailed explanation of how CCP partitions genes and identifies super-genes to enhance understanding.

2. Include specific details about CCP implementation and parameter settings for reproducibility.

3. Compare CCP with other dimensionality reduction techniques such as PCA or autoencoders to contextualize its performance.

4. Detail the statistical tests used to claim improvements in UMAP and tSNE, including p-values, to substantiate your results.

5. Describe the 18 datasets used, including their sources and characteristics, to assess the generalizability of the findings.

6. Discuss how CCP specifically handles the sparsity in scRNA-seq data, a critical challenge in the field.

7. Explain the biological relevance of the improvements made by CCP to highlight its impact on the field.

8. Provide information about any software available for implementing CCP to aid in adoption and further research.

9. Identify limitations of CCP and suggest areas for future research to guide subsequent studies.

10. Improve the quality of graphical representations of UMAP and tSNE results to better communicate your findings.

11. Incorporate recent literature to position CCP within the current research landscape and ensure the study is up-to-date.

Advancing single-cell RNA-seq data analysis through the fusion of multi-layer perceptron and graph neural network.

iDNA-OpenPrompt: OpenPrompt learning model for identifying DNA methylation

Reviewer #6: In this manuscript, the authors propose the usage of the Correlated Clustering and Projection (CCP) method as an initiation step for t-SNE and UMAP. They have presented results which show substantial improvement over ordinary t-SNE and UMAP when CCP is used as a preprocessing step. However, there are a few concerns.

Major concerns:

--------------------

1. The CCP algorithm used in this work cannot be considered as a benchmark since it is not yet published as a peer-reviewed journal or as a part of any conference proceedings.

2. The authors have not mentioned what values of parameters they have used for t-SNE and UMAP. As it is quite well known that these parameters (for e.g. perplexity in t-SNE or n_neighbors and min-dist in UMAP) are very sensitive, probably fine-tuning them could have achieved the same result, which is not clear.

Infact, the codebase https://github.com/hozumiyu/CCP-scRNAseq-UMAP-TSNE/blob/main/main.py reveals the usage of one pair of values for the dataset GSE57249 and another pair of values for others. No particular guideline for setting these values have been provided.

3. Again, based on the tutorial notebook provided in github, it is not clear why a z-score normalization is required before running UMAP, even when the dataset is preprocessed using CCP. The authors have not presented any discussion about it in the manuscript.

4. The comparative results shown in this manuscript are mainly qualitative. For quantitative comparison, the authors have used only three measures, namely ARI, NMI and ECM. However, they have reported an average over 18 datasets (Figures 7 and S7). This is not an acceptable result at all. Should we assume that results for the 18 datasets have a large variation?

Also, how to access performance in situations where ground truth labels are not available? In addition to ARI, NMI, ECM, pairwise distance preservation before and after CCP-UMAP or CCP-tSNE could be measured.

5. In section 4, the authors mention "Large" datasets. However, the largest dataset used in this study does not have more than 10k cells. Considering technological advancements in the field of scRNA-seq, a million cells is now a reality. So, questions remain as to what is a really large amount? The authors should give an estimate of the running time requirement for the subsample-based strategy for such a dataset.

Minor:

--------

1. ECM - Please change "Element-centeric" to "Element-Centric"

2. Page 16 - $ instead of %

3. "Section ??" - Section reference missing in S1.2 in supporting material

4. Page 8 - S1.3 - $ instead of %

**********

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

Reviewer #2: No

Reviewer #3: No

Reviewer #4: No

Reviewer #5: No

Reviewer #6: Yes: Rajat K. de

**********

[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.

Analyzing scRNA-seq data by CCP-assisted UMAP and tSNE

PONE-D-24-06894R1

Dear Dr. Wei,

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 will be generated when your article is formally accepted. Please note, if your institution has a publishing partnership with PLOS and your article meets the relevant criteria, all or part of your publication costs will be covered. Please make sure your user information is up-to-date by logging into Editorial Manager at Editorial Manager® and clicking the ‘Update My Information' link at the top of the page. If you have any questions relating to publication charges, 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,

Andrea Tangherloni

Academic Editor

PLOS ONE

Comments from PLOS Editorial Office:

We note that one or more reviewers has recommended that you cite specific previously published works in an earlier round of revision. As always, we recommend that you please review and evaluate the requested works to determine whether they are relevant and should be cited. It is not a requirement to cite these works and you may remove them before the manuscript proceeds to publication. We appreciate your attention to this request.

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

Reviewer #3: (No Response)

Reviewer #5: 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

Reviewer #3: (No Response)

Reviewer #5: Yes

**********

3. Has the statistical analysis been performed appropriately and rigorously?

Reviewer #1: Yes

Reviewer #3: (No Response)

Reviewer #5: 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

Reviewer #3: (No Response)

Reviewer #5: 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

Reviewer #3: (No Response)

Reviewer #5: 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 my comments and I believe quality of the paper improved a lot. I don't have any further comments.

Reviewer #3: (No Response)

Reviewer #5: All comments have been thoroughly addressed, and my recommendations have been accepted and implemented.

**********

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: Yes: Hussain Ahmed Chowdhury

Reviewer #3: No

Reviewer #5: No

**********