From the journal Digital Discovery Peer review history

21-Nov-2023

Dear Dr Back:

Manuscript ID: DD-PER-10-2023-000213
TITLE: Accelerated Chemical Science with AI

Thank you for your submission to Digital Discovery, published by the Royal Society of Chemistry. I sent your manuscript to reviewers and I have now received their reports which are copied below.

After careful evaluation of your manuscript and the reviewers’ reports, I will be pleased to accept your manuscript for publication after revisions.

Please revise your manuscript to fully address the reviewers’ comments. When you submit your revised manuscript please include a point by point response to the reviewers’ comments and highlight the changes you have made. Full details of the files you need to submit are listed at the end of this email.

Digital Discovery strongly encourages authors of research articles to include an ‘Author contributions’ section in their manuscript, for publication in the final article. This should appear immediately above the ‘Conflict of interest’ and ‘Acknowledgement’ sections. I strongly recommend you use CRediT (the Contributor Roles Taxonomy, https://credit.niso.org/) for standardised contribution descriptions. All authors should have agreed to their individual contributions ahead of submission and these should accurately reflect contributions to the work. Please refer to our general author guidelines https://www.rsc.org/journals-books-databases/author-and-reviewer-hub/authors-information/responsibilities/ for more information.

Please submit your revised manuscript as soon as possible using this link :

*** PLEASE NOTE: This is a two-step process. After clicking on the link, you will be directed to a webpage to confirm. ***

https://mc.manuscriptcentral.com/dd?link_removed

(This link goes straight to your account, without the need to log in to the system. For your account security you should not share this link with others.)

Alternatively, you can login to your account (https://mc.manuscriptcentral.com/dd) where you will need your case-sensitive USER ID and password.

You should submit your revised manuscript as soon as possible; please note you will receive a series of automatic reminders. If your revisions will take a significant length of time, please contact me. If I do not hear from you, I may withdraw your manuscript from consideration and you will have to resubmit. Any resubmission will receive a new submission date.

The Royal Society of Chemistry requires all submitting authors to provide their ORCID iD when they submit a revised manuscript. This is quick and easy to do as part of the revised manuscript submission process.   We will publish this information with the article, and you may choose to have your ORCID record updated automatically with details of the publication.

Please also encourage your co-authors to sign up for their own ORCID account and associate it with their account on our manuscript submission system. For further information see: https://www.rsc.org/journals-books-databases/journal-authors-reviewers/processes-policies/#attribution-id

I look forward to receiving your revised manuscript.

Yours sincerely,
Linda Hung
Associate Editor
Digital Discovery
Royal Society of Chemistry

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

Reviewer 1

The paper comes from a reputable scientific group. After reviewing it, I can only recommend adding several more references to the advances in generative chemistry and biology with and without experimental validation that were committed.
Other than that, I have no further comments and do not want to delay the publication.

Reviewer 2

In this perspective, the authors aim to summarize discussion from several panels at the 15th ASLLA symposium on “Accelerated Chemical Science with AI” including: Data, New Applications, Machine Learning (ML) Algorithms, and Education. The article touches on a wide array of topics in each panel that are important for researchers in the field to have at least passing familiarity with. In the section on Data, topics range from generating high quality data with quantified uncertainty to best practices for building databases and how to facilitate data sharing for chemistry as well as fundamental ML work. The discussion on New Applications focused on expanding to transient and multi-scale applications and better integrating experimental with computational data for synthesizability and discovery. The ML Algorithm section focuses on how to help fundamental ML algorithm development tackle domain-specific problems and progress from interpolation to discovery. The last panel on Education focuses on outreach and how best to incorporate these core concepts of AI accelerated chemical science to undergraduate and graduate level science curriculums.
I believe that this perspective article is valuable to the broader community and serves as a useful starting point for approaching some of the current challenges in AI driven chemical science. Overall, it is well written and I would recommend accepting for publication after addressing the following points:
1. Was there any discussion on how the broad data sharing would work with more industrial funding vs general funding for research?
2. How would releasing “negative” results work with broad data standardization? For the most part once a reaction is failed given a specific research context it receives little focus or additional characterization.
3. How much characterization and reaction meta-data would be needed as a baseline for standardization? (e.g. Concentrations, Temp, Heating, Pressure, Mixing, Additions, Structures, Side-Products, NMR, MS, etc.). Across different reaction types and vessels some parameters may be undefined or hard to calculate.

Response letter attached separately.

This text has been copied from the PDF response to reviewers and does not include any figures, images or special characters:


Dear Dr. Linda Hung,

We would like to express our sincere gratitude to you for the time and effort invested in the evaluation of our manuscript entitled “Accelerated Chemical Science with AI” submitted to Digital Discovery (DD-PER-10-2023-000213).

We have carefully revised the manuscript according to the reviewer's comments and attached point-by-point responses in the following pages. Revisions to the manuscript are highlighted in blue.

Thank you again for your valuable time on this work.

Best regards,

Seoin Back
Assistant Professor of Chemical and Biomolecular Engineering
Sogang University




Referee: 1

Comments to the Author
The paper comes from a reputable scientific group. After reviewing it, I can only recommend adding several more references to the advances in generative chemistry and biology with and without experimental validation that were committed.
Other than that, I have no further comments and do not want to delay the publication.

We greatly appreciate your careful review and feedback. In the revised manuscript, we have added the following references related to generative chemistry and biology.

Alex Zhavoronkov et al., ACS Med. Chem. Lett.2023,14, 901−915
Alán Aspuru-Guzik et al., Acc.Chem.Res.2021, 54, 849−860
Alán Aspuru-Guzik et al., Nat. Mach. Intell., volume 3, pages 76–86 (2021)




 
Referee: 2

Comments to the Author
In this perspective, the authors aim to summarize discussion from several panels at the 15th ASLLA symposium on “Accelerated Chemical Science with AI” including: Data, New Applications, Machine Learning (ML) Algorithms, and Education. The article touches on a wide array of topics in each panel that are important for researchers in the field to have at least passing familiarity with. In the section on Data, topics range from generating high quality data with quantified uncertainty to best practices for building databases and how to facilitate data sharing for chemistry as well as fundamental ML work. The discussion on New Applications focused on expanding to transient and multi-scale applications and better integrating experimental with computational data for synthesizability and discovery. The ML Algorithm section focuses on how to help fundamental ML algorithm development tackle domain-specific problems and progress from interpolation to discovery. The last panel on Education focuses on outreach and how best to incorporate these core concepts of AI accelerated chemical science to undergraduate and graduate level science curriculums.

I believe that this perspective article is valuable to the broader community and serves as a useful starting point for approaching some of the current challenges in AI driven chemical science. Overall, it is well written and I would recommend accepting for publication after addressing the following points:
We greatly appreciate your thorough review and feedback. Although the following points were not addressed during the panel discussion, I have included a conversation with some of co-authors below. We acknowledge your constructive feedback, but we did not include it in the manuscript as it comprises non-official discussions.

1. Was there any discussion on how the broad data sharing would work with more industrial funding vs general funding for research?
Our discussion did not explicitly delve into the dynamics of data sharing for diverse funding sources. While the U.S. funding agency advocates, and often mandates data sharing to the level that reproduces the results, the industrial funding comes with the binding contractual agreements to protect the proprietary information within the bounds of the law. We need to continue to foster the culture of data sharing both within academic communities and industrial settings. Encouraging robust data sharing practices in industrial funding agreements is a crucial area for future AI development to align research endeavors with the collaboration across academia and industry.

2. How would releasing “negative” results work with broad data standardization? For the most part once a reaction is failed given a specific research context it receives little focus or additional characterization.
A viable approach to handling negative results involves systematically collecting and utilizing data generated during the experiment or measurement steps of failed experiments. This process excludes data that require synthesized materials, such as performance indicators or X-ray diffraction (XRD).

Given the significant differences in synthesis and measurement methods across various application areas, a practical strategy would be to identify and define the predominant synthesis methods used in each area. One way to facilitate this identification is by answering standard questions on experiments when submitting manuscripts to journals. Once identified, this information, along with the associated metadata, should be systematically stored. This approach not only preserves data from failed experiments but also aligns with the principles of broad data standardization, potentially offering valuable insights for future research endeavors.

Another practice involves uploading lab notebooks related to the synthesis and employing text mining on these notebooks. The policies of journals that necessitate this process could be important.

3. How much characterization and reaction meta-data would be needed as a baseline for standardization? (e.g. Concentrations, Temp, Heating, Pressure, Mixing, Additions, Structures, Side-Products, NMR, MS, etc.). Across different reaction types and vessels some parameters may be undefined or hard to calculate.
Establishing a generalized standardization applicable across all application areas is challenging. Therefore, it is preferable to define the necessary conditions based on the synthesis methods or performance measurement methods primarily used in each application area. Information about experimental conditions can be systematically collected by defining a unified set of rules, as illustrated in https://www.nature.com/articles/s41560-021-00941-3.

06-Dec-2023

Dear Dr Back:

Manuscript ID: DD-PER-10-2023-000213.R1
TITLE: Accelerated Chemical Science with AI

Thank you for submitting your revised manuscript to Digital Discovery. I am pleased to accept your manuscript for publication in its current form. I have copied any final comments from the reviewer(s) below.

You will shortly receive a separate email from us requesting you to submit a licence to publish for your article, so that we can proceed with the preparation and publication of your manuscript.

You can highlight your article and the work of your group on the back cover of Digital Discovery. If you are interested in this opportunity please contact the editorial office for more information.

Promote your research, accelerate its impact – find out more about our article promotion services here: https://rsc.li/promoteyourresearch.

If you would like us to promote your article on our Twitter account @digital_rsc please fill out this form: https://form.jotform.com/213544038469056.

We are offering all corresponding authors on publications in gold open access RSC journals who are not already members of the Royal Society of Chemistry one year’s Affiliate membership. If you would like to find out more please email membership@rsc.org, including the promo code OA100 in your message. Learn all about our member benefits at https://www.rsc.org/membership-and-community/join/#benefit

By publishing your article in Digital Discovery, you are supporting the Royal Society of Chemistry to help the chemical science community make the world a better place.

With best wishes,

Linda Hung
Associate Editor
Digital Discovery
Royal Society of Chemistry

Reviewer 2

The authors have properly addressed the questions/concerns raised by the reviewer.