Dear Dr. Pan,

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.

Please submit your revised manuscript by May 12 2025 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.

• 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,

Clara Sousa

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, we expect all author-generated code to 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.  We note that the grant information you provided in the ‘Funding Information’ and ‘Financial Disclosure’ sections do not match.

When you resubmit, please ensure that you provide the correct grant numbers for the awards you received for your study in the ‘Funding Information’ section.

4. Thank you for stating the following financial disclosure:

 [This work was sponsored by Natural Science Foundation of Xinjiang Uygur AutonomousRegion((2023D01C158), the "Tianshan Talents" Medical and Health High Level Talent Training Program Project (TSYC202301B068), and the Natural Science Foundation of Xinjiang Uygur Autonomous Region - General Project (2024D01C157)]. 

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.

5. Thank you for stating the following in the Acknowledgments Section of your manuscript:

[This work was sponsored by Natural Science Foundation of Xinjiang Uygur AutonomousRegion(2023D01C158), the "Tianshan Talents" Medical and Health High Level Talent Training Program Project (TSYC202301B068), and the Natural Science Foundation of Xinjiang Uygur Autonomous Region - General Project (2024D01C157)]

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:

[This work was sponsored by Natural Science Foundation of Xinjiang Uygur AutonomousRegion((2023D01C158), the "Tianshan Talents" Medical and Health High Level Talent Training Program Project (TSYC202301B068), and the Natural Science Foundation of Xinjiang Uygur Autonomous Region - General Project (2024D01C157)]. 

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

6. We note that you have indicated that there are restrictions to data sharing for this study. For studies involving human research participant data or other sensitive data, we encourage authors to share de-identified or anonymized data. However, when data cannot be publicly shared for ethical reasons, we allow authors to make their data sets available upon request. For information on unacceptable data access restrictions, please see http://journals.plos.org/plosone/s/data-availability#loc-unacceptable-data-access-restrictions.

Before we proceed with your manuscript, please address the following prompts:

a) If there are ethical or legal restrictions on sharing a de-identified data set, please explain them in detail (e.g., data contain potentially identifying or sensitive patient information, data are owned by a third-party organization, etc.) and who has imposed them (e.g., a Research Ethics Committee or Institutional Review Board, etc.). Please also provide contact information for a data access committee, ethics committee, or other institutional body to which data requests may be sent.

b) If there are no restrictions, please upload the minimal anonymized data set necessary to replicate your study findings to a stable, public repository and provide us with the relevant URLs, DOIs, or accession numbers. Please see http://www.bmj.com/content/340/bmj.c181.long for guidelines on how to de-identify and prepare clinical data for publication. For a list of recommended repositories, please see https://journals.plos.org/plosone/s/recommended-repositories. You also have the option of uploading the data as Supporting Information files, but we would recommend depositing data directly to a data repository if possible.

Please update your Data Availability statement in the submission form accordingly.

7. In the online submission form, you indicated that [The datasets generated and analyzed during the current study are not publicly available, but are available from the corresponding author upon reasonable request.].

All PLOS journals now require all data underlying the findings described in their manuscript to be freely available to other researchers, either 1. In a public repository, 2. Within the manuscript itself, or 3. Uploaded as supplementary information.

This policy applies to all data except where public deposition would breach compliance with the protocol approved by your research ethics board. If your data cannot be made publicly available for ethical or legal reasons (e.g., public availability would compromise patient privacy), please explain your reasons on resubmission and your exemption request will be escalated for approval.

8. Please include a copy of Table 2 which you refer to in your text on page 17.

[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?

Reviewer #1: Yes

Reviewer #2: Partly

**********

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

Reviewer #1: Yes

Reviewer #2: I Don't Know

**********

3. Have the authors made all data underlying the findings in their manuscript fully available??>

The PLOS Data policy

Reviewer #1: No

Reviewer #2: No

**********

4. Is the manuscript presented in an intelligible fashion and written in standard English??>

Reviewer #1: No

Reviewer #2: No

**********

Reviewer #1: The comments are attached as a pdf file, but the PLOS One website cannot accept the attachment only. So, I include all the comments so that I can proceed with submission. As a result, I request the authors to refer to the attachment to have a better understanding of the comments.

The manuscript presents an innovative approach to the quantitative analysis of Tilianin using Raman spectroscopy combined with deep learning. This work proposes an approach for Tilianin quantification and seems likely to compare the proposed deep learning model with other traditional and machine learning models; however, there are some weaknesses that should be addressed before being considered for publication.

The readability of the manuscript is rather low. Particularly, the introduction is poorly written. Please take a careful consideration to revise the text to improve the readability.

The authors are requested to cross check the references to ensure they are placed properly. For instance, in Introduction section, the reference 22 discusses CNN and not VAE. Please verify.

The last paragraph of Introduction is poorly written, and the novelties are very unclear. The authors need to spend some time to improve the quality of writing and describe all the contributions of the work clearly.

There are other works in the literature that have addressed similar challenges with either a greater number of data or data augmentation techniques. Some of these works are:

Rashedi, M., Khodabandehlou, H., Wang, T., Demers, M., Tulsyan, A., Garvin, C., and Undey, C. (2024). Integration of just-in-time learning with variational autoencoder for cell culture process monitoring based on Raman spectroscopy. Biotechnol. Bioeng, 121, 1–20. doi:10.1002/bit.28713

Min, R., Wang, Z., Zhuang, Y., and Yi, X. (2023). Application of semi-supervised convolutional neural network regression model based on data augmentation and process spectral labeling in Raman predictive modeling of cell culture processes. Biochemical Engineering Journal, 191(108774), ISSN 1369–703X.

Khodabandehlou, H., Rashedi, M., Wang, T., Tulsyan, A., Schorner, G., Garvin, C., and Undey, C. (2024). Cell culture product quality attribute prediction using convolutional neural networks and raman spectroscopy. Biotechnol. Bioeng, 121, 1231–1243. doi:10.1002/bit.28646.

The authors are requested to describe the contributions of their work compared to the mentioned references.

In many places in the text, the word “And” is used right after the end of a finished sentence. Please correct/remove them throughout the manuscript.

In section 2.1 it is written “Weigh the desired mass of Tilianin powder on a balance and transfer it to a beaker. Using a pipette measure less than the target volume of methanol into the beaker. Heat gently and stir well using a glass rod until Tilianin is completely dissolved. Transfer the dissolved Tilianin solution to a volumetric flask. Use a standard volumetric flask to finalize the volume and rinse the residual material several times to ensure that all Tilianin enters the solution system.” This type of writing is not a common practice in academic writing and needs a major revision. Please revise these sentences throughout the text accordingly.

In section 2.2, the authors are needed to explain how the offline measurements are labeled with the Raman spectra in the training dataset.

Section 2.3, de-meaned � detrended

In section 2.3 appropriate references are required for the baseline removal. Some of those references are:

Eilers, P., & Boelens, H. F. M. (2005). Baseline correction with asymmetric least squares smoothing (Leiden University Medical Centre Report).

Cai, Y., Yang, C., Xu, D., & Gui, W. (2018). Baseline correction for Raman spectra using penalized spline smoothing based on vector transformation. Analytical Methods, 10, 3525–3533.

Please consider providing comparison with these references to validate your approach.

In figure 1, the wave numbers are shown from 550 cm^(-1) to 2000 cm^(-1). Is this the ultimate range of wavenumbers? What happens to the spectra before or after this range? How many wavenumbers does the Raman machine provide?

In second paragraph of section 2.4, the authors have mentioned a classification model can be made between Raman spectra and concentrations. Do the authors mean a regression model? Otherwise, please clearly explain what the classes are in the classification. Then, please explain why classification is needed?

In the caption of figure 2, please type in what preprocessing steps are implemented on the Raman spectra.

In section 3.1, what do the authors mean by 1×1 convolutional channel compression? Please clarify. Also, please show where this is applied on Figure 4.

In the third paragraph of section 3.1, the authors discuss residual blocks. They say “the input features are directly added to a series of transformed outputs”. They need to clarify which output they are talking about. I don’t see any residual block for the output of the model in Figure 4.

The authors have tried to report the hyper parameters of the model structure in section 3.1, however, there are some missing details like the structure of fully connected layer.

In section 3.3 where the models are compared, a detailed description of all models is required. The competitive models lack detailed information regarding their hyper-parameters. Please revise this section appropriately.

Is this VAE model generated by the authors or has been used in other works? There are some curiosities about this model since a regenerated input in the decoder is used in fully connected layers. This provides a question why a regeneration of input improves the performance of compared with regular ANN. Please comment on this and clarify.

The authors are requested to discuss what specific challenges in Raman spectral analysis the proposed model is designed to overcome compared to prior models.

Why was SGD found to perform better than Adam? Could this be due to batch size or learning rate settings?

The self-attention mechanism is mentioned but not well explained in the context of spectral analysis. A brief mathematical or visual representation of how self-attention aids in feature extraction from Raman spectra would be beneficial.

The model performs well in lower concentration ranges but exhibits fluctuations at 0.2 mg/ml. What might be causing this? Is this due to saturation effects in Raman spectral intensities, or does the deep learning model struggle with higher concentration ranges?

While the paper shows strong performance metrics, a discussion on how RSAQN could be integrated into real pharmaceutical quality control workflows would be useful. Were any misclassification or prediction errors analyzed qualitatively? What types of spectra did the model struggle with?

Consider discussing potential applications beyond Tilianin (e.g., broader pharmaceutical compounds, food safety, biomedical diagnostics). Could transfer learning be applied to enhance model generalization across different Raman spectroscopy datasets?

Reviewer #2: This study presents a novel Raman-based deep learning model (RSAQN) for non-destructive Tilianin quantification. In contrast to conventional destructive HPLC/MS techniques, RSAQN employs self-attention mechanisms to analyze spectral features from six concentration levels (120 samples total). The model demonstrates superior performance over five benchmark ML/DL approaches, achieving an R² value of 0.9144, thereby enabling rapid and accurate drug quality assessment. However, several issues require attention:

1. The current English expression needs improvement - the descriptions are unnecessarily complex, sentences are overly long, and the overall organization lacks clarity. A more concise and straightforward presentation would significantly enhance readability.

2. The Introduction section disproportionately focuses on HPLC, which is not the manuscript's primary focus. The HPLC discussion should be condensed, while more emphasis should be placed on Tilianin measurement techniques and relevant machine learning methods. A comparative analysis of key parameters would better highlight the advantages of the proposed method.

3. In the Data Acquisition section: The characteristic peak at 520.7 cm-1 - which molecular component does this correspond to?

4. For the Spectral Data Analysis section: Including a reference table assigning various Raman peaks would significantly improve data interpretation.

5. In the Model Testing and Analysis section: The meaning of "fluctuations controlled within 0.02" is unclear - does this refer to an absolute value of 0.02 or 2% variation? Additionally, the claim regarding the model's accuracy and robustness in low-concentration ranges (based solely on Figure 2) requires stronger validation. Additional methods such as cross-validation and noise injection testing should be incorporated to substantiate these conclusions.

**********

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

**********

[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.

Attachments

Attachment

Submitted filename: Raman review.pdf

<p>Study on the quantitative analysis of Tilianin based on Raman spectroscopy combined with deep learning

PONE-D-24-58474R1

Dear Dr. Pan,

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,

Clara Sousa

Academic Editor

PLOS ONE

Reviewers' comments:

Reviewer's Responses to Questions

Comments to the Author

Reviewer #1: All comments have been addressed

**********

2. Is the manuscript technically sound, and do the data support the conclusions??>

Reviewer #1: Yes

**********

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

Reviewer #1: Yes

**********

4. Have the authors made all data underlying the findings in their manuscript fully available??>

The PLOS Data policy

Reviewer #1: Yes

**********

5. Is the manuscript presented in an intelligible fashion and written in standard English??>

Reviewer #1: Yes

**********

Reviewer #1: I believe the authors have addressed the comments appropriately and this manuscript can be considered for publication.

**********

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

**********