Assessing the impact of generative AI on medicinal chemistry

Walters, W. Patrick; Murcko, Mark

doi:10.1038/s41587-020-0418-2

HOME
ABOUT
- RESULTS
- differences
- BENEFITS
- HISTORY
- TEAM
- LOCATION
- FACILITIES
- BANKING
- MEMBERSHIPS
- APPROVALS
- LICENCES
- SUPPLIERS
- SPONSORSHIPS
- MEDIA
- PRIVACY
AUCTIONS
SHIPPING
FEES
- TS REWARDS
TOOLS
guides
FAQ
CONTACT
- CONNECT

VEHICLES
BRAND
- JAPANESE CARS
  - DAIHATSU
  - EUNOS
  - FORD
  - HONDA
  - ISUZU
  - LEXUS
  - MAZDA
  - MITSUBISHI
  - MITSUOKA
  - NISSAN
  - SUBARU
  - SUZUKI
  - TOYOTA
- GERMAN CARS
- AMERICAN CARS
- BRITISH CARS
- ITALIAN CARS
- FRENCH CARS
- SWEDISH CARS
- KOREAN CARS
TYPE
- mobility
- VENDING
- instruction
- TAXIS
- AMBULANCES
- FIRE ENGINES
- HEARSES
- LIMOUSINES
- COMMERCIAL
CLASS
FUEL
TRUCKS
minitrucks
- DAIHATSU
- HONDA
- MAZDA
- MITSUBISHI
- NISSAN
- SUBARU
- SUZUKI
- DUMP
- CRANE
- CAMPER
- REFRIGERATED
- 4WD
- NEW
BUSES
MOTORHOMES
- YAHOO!
- RAKUTEN
- DEALER

PARTS
- FREE REPORT
- PARTS CONTAINERS
- PARTS SYSTEMS
- PARTS PROTECTION
- BODY SHELLS
- DISMANTLING
- ONLINE PARTS
- NEW PARTS
- INTERIOR PARTS
- EXTERIOR PARTS
  - BONNETS
  - BUMPERS
  - GRILLES
  - FENDERS
  - DOORS
  - TRUNKS
  - SPOILERS
  - LIGHTS
  - EMBLEMS
  - CAMERAS
- ENGINES
- TRANSMISSIONS
- WHEELS & TYRES
  - WHEELS
  - TYRES
CUTS
PERFORMANCE PARTS
TRUCK PARTS
MOTORBIKE PARTS
- MOTORBIKE ENGINES
- MOTORBIKE ACCESSORIES

MOTORBIKES
MARINE
FORKLIFTS
MACHINERY
AGRICULTURAL
OTHER
COUNTRY
- AUSTRALIA
- CANADA
- KENYA
- MYANMAR
- NEW ZEALAND
- PAKISTAN
- TANZANIA
- UNITED STATES

CARVIEW

MOTORHOMES

Select Language

HTTP/2 301 date: Sun, 18 Jan 2026 10:04:29 GMT content-length: 0 location: https://doi.org/10.1038/S41587-020-0418-2 server: cloudflare vary: Origin expires: Mon, 19 Jan 2026 10:04:29 GMT permissions-policy: interest-cohort=(),browsing-topics=() cf-cache-status: DYNAMIC nel: {"report_to":"cf-nel","success_fraction":0.0,"max_age":604800} strict-transport-security: max-age=31536000; includeSubDomains; preload report-to: {"group":"cf-nel","max_age":604800,"endpoints":[{"url":"https://a.nel.cloudflare.com/report/v4?s=GOedeQ6u3l5CycylyDNK%2Fiu%2F6riHJ3%2BT2sMGJGPmP7Pn6dKO4NWbtEPsrxiauc7jG9Gcw%2FbCmBI6PCc8qrmDiJin9ZAjIw%3D%3D"}]} cf-ray: 9bfd44b92f59741b-BLR alt-svc: h3=":443"; ma=86400 HTTP/2 302 date: Sun, 18 Jan 2026 10:04:29 GMT content-type: text/html;charset=utf-8 location: https://www.nature.com/articles/s41587-020-0418-2 server: cloudflare vary: Origin vary: Accept expires: Sun, 18 Jan 2026 10:11:00 GMT permissions-policy: interest-cohort=(),browsing-topics=() cf-cache-status: DYNAMIC nel: {"report_to":"cf-nel","success_fraction":0.0,"max_age":604800} strict-transport-security: max-age=31536000; includeSubDomains; preload report-to: {"group":"cf-nel","max_age":604800,"endpoints":[{"url":"https://a.nel.cloudflare.com/report/v4?s=yTmkt6NAAoPYOtfewrmNRV53ptoU5uARrf8StnDYU3Flr7572zcoOxn6VCW2t1d52CDIa0oxJ7sRQoj3Gpa%2Fpslsigd9QQ%3D%3D"}]} cf-ray: 9bfd44bac90c741b-BLR alt-svc: h3=":443"; ma=86400 HTTP/2 303 strict-transport-security: max-age=31536000;preload x-vcap-request-id: e828e7bd-01ec-4b64-6567-88013f8a5c1b server: Oscar Platform 0.2039.0 via: 1.1 google, 1.1 varnish content-type: text/html location: https://idp.nature.com/authorize?response_type=cookie&client_id=grover&redirect_uri=https%3A%2F%2Fwww.nature.com%2Farticles%2Fs41587-020-0418-2 accept-ranges: bytes date: Sun, 18 Jan 2026 10:04:29 GMT x-served-by: cache-bom-vanm7210077-BOM, cache-bom-vanm7210064-BOM x-cache: MISS, MISS x-cache-hits: 0, 0 x-timer: S1768730669.375765,VS0,VE402 vary: x-forwarded-host, upgrade-insecure-requests alt-svc: h3=":443";ma=86400,h3-29=":443";ma=86400,h3-27=":443";ma=86400 content-length: 150 HTTP/2 302 cache-control: no-cache, no-store, max-age=0, must-revalidate content-security-policy: frame-ancestors 'none'; expires: 0 location: https://idp.nature.com/transit?redirect_uri=https%3A%2F%2Fwww.nature.com%2Farticles%2Fs41587-020-0418-2&code=11912897-202e-4810-88fc-958f5e7e894f pragma: no-cache set-cookie: idp_session=sVERSION_1f25f3494-a4a4-418f-98eb-3d48f7a2127d; Domain=.nature.com; Path=/; Secure; SameSite=None; HttpOnly set-cookie: idp_session_http=hVERSION_10b7b9b2d-f003-48af-80b5-190680c234b3; Domain=.nature.com; Path=/; HttpOnly set-cookie: idp_marker=cd457c47-c03e-4edd-9828-01490390dcfa; Domain=.nature.com; Path=/; Max-Age=34560000; HttpOnly strict-transport-security: max-age=31536000 ; includeSubDomains traceparent: 00-13e9e8d1aa8048397602b4735d37dc9e-eb3bc0e15057d8f4-01 x-content-type-options: nosniff x-frame-options: DENY x-vcap-request-id: 13e9e8d1-aa80-4839-7602-b4735d37dc9e x-xss-protection: 1; mode=block via: 1.1 google, 1.1 varnish x-cdn-origin: SNPaaS accept-ranges: bytes date: Sun, 18 Jan 2026 10:04:30 GMT x-served-by: cache-bom-vanm7210070-BOM x-cache: MISS x-cache-hits: 0 x-timer: S1768730670.836006,VS0,VE391 vary: x-forwarded-proto alt-svc: h3=":443";ma=86400,h3-29=":443";ma=86400,h3-27=":443";ma=86400 content-length: 0 HTTP/2 302 cache-control: no-cache, no-store, max-age=0, must-revalidate content-language: en-US content-security-policy: frame-ancestors 'none'; expires: 0 location: https://www.nature.com/articles/s41587-020-0418-2 pragma: no-cache strict-transport-security: max-age=31536000 ; includeSubDomains traceparent: 00-2883d1757611498e41618b710ca3417a-23fd4c1c7d516fce-01 x-content-type-options: nosniff x-frame-options: DENY x-vcap-request-id: 2883d175-7611-498e-4161-8b710ca3417a x-xss-protection: 1; mode=block via: 1.1 google, 1.1 varnish x-cdn-origin: SNPaaS accept-ranges: bytes date: Sun, 18 Jan 2026 10:04:30 GMT x-served-by: cache-bom-vanm7210070-BOM x-cache: MISS x-cache-hits: 0 x-timer: S1768730670.240611,VS0,VE365 vary: x-forwarded-proto alt-svc: h3=":443";ma=86400,h3-29=":443";ma=86400,h3-27=":443";ma=86400 content-length: 0 HTTP/2 200 content-encoding: gzip x-b3-sampled: 1 x-content-type-options: nosniff set-cookie: CONTENT_USAGE_SESSIONID="utterlyidle:v1:YWUxZjI1MDctYWRmNC00YTRkLTg3OTItYjY0OTRkMDI0NmEz"; Domain=.nature.com; Path=/; Secure=; HttpOnly= set-cookie: user.uuid.v2="f0975416-8290-4e2e-89d8-a7ce5c46abad"; Expires=Sat, 18 Apr 2026 10:04:30 GMT; Path=/; secure; HttpOnly content-type: text/html; charset="UTF-8" x-frame-options: DENY x-sn-servicetimems: 272 x-b3-traceid: 8ea3e6ed7a605448 x-forwarded-host: www.nature.com x-xss-protection: 1; mode=block server: Oscar Platform 0.2039.0 tracestate: gorouter=c15350db3198f9cf tracestate: gorouter=c15350db3198f9cf x-b3-spanid: 24aea0012afd6f73 x-dump-request-bodies: 0 x-vcap-request-id: 3d23e26e-96db-4db8-6531-51ad95c25967 cache-control: private, must-revalidate via: 1.1 google, 1.1 varnish accept-ranges: bytes traceparent: 00-3d23e26e96db4db8653151ad95c25967-455c0df10b96eaff-01 traceparent: 00-3d23e26e96db4db8653151ad95c25967-05bd8bd17a2d3b0d-01 strict-transport-security: max-age=31536000;preload age: 0 date: Sun, 18 Jan 2026 10:04:31 GMT x-served-by: cache-bom-vanm7210077-BOM, cache-bom-vanm7210064-BOM x-cache: MISS, MISS, MISS x-cache-hits: 0, 0 x-timer: S1768730671.619415,VS0,VE725 vary: X-Frame-Options,X-Oscar-Cache-Mode, Accept-Encoding alt-svc: h3=":443";ma=86400,h3-29=":443";ma=86400,h3-27=":443";ma=86400 Assessing the impact of generative AI on medicinal chemistry | Nature Biotechnology

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

View all journals
Search
Log in

Content Explore content
About the journal
Publish with us
Subscribe

Sign up for alerts
RSS feed

nature
nature biotechnology
correspondence
article

Correspondence
Published: 30 January 2020

Assessing the impact of generative AI on medicinal chemistry

W. Patrick Walters ORCID: orcid.org/0000-0002-1235-2869¹ &
Mark Murcko¹

Nature Biotechnology volume 38, pages 143–145 (2020)Cite this article

19k Accesses
186 Citations
89 Altmetric
Metrics details

Subjects

Computational biology and bioinformatics
Drug discovery

Access through your institution

Buy or subscribe

To the Editor — The profound challenges of drug discovery, coupled with the societal importance of the task, make it imperative that we investigate novel, creative methods that improve our abilities to design new medicines. In recent years, attempts at developing and deploying a wide range of computational methods to support drug discovery have accelerated—sometimes with extraordinary claims made about their significance. Novel computational approaches require rigorous evaluation to determine their true utility in real-world drug discovery settings. Sadly, novel methods often are disclosed without sufficient documentation, making it difficult or impossible to carry out such an objective evaluation.

Over the past few years, interest has grown in the application of artificial intelligence (AI) techniques to drug discovery^1,2. One active branch of AI that has been the focus of a tremendous amount of recent activity is the field of generative modeling^{3,4,5,6,7,8,9}. In this technique, a deep learning model is trained based on a corpus of existing molecules. The model typically ‘encodes’ a higher-dimensional representation, such as a SMILES (simplified molecular-input line-entry system)¹⁰, into a lower-dimensional representation, often referred to as a latent space. This latent space can then be ‘decoded’ back to the higher-dimensional representation to create new molecules. The exploration of this latent space can be coupled with a predictive model with the aim of discovering novel, active molecules. In a sense, generative models can be seen as a variation on the de novo design¹¹ programs that were in vogue during the 1990s and early 2000s. As with de novo design, evaluating the significance of the output of these models is not straightforward. Although two groups have made initial efforts at developing methods for benchmarking generative models^12,13, evaluating the novelty, and ultimately the significance, of the molecules generated by these methods remains an open question. Such benchmarks provide a common ground for evaluation and comparison, but the ultimate value of generative models will be demonstrated through the synthesis and biological evaluation of the novel molecules they identify.

This is a preview of subscription content, access via your institution

Relevant articles

Open Access articles citing this article.

Identification of nanomolar adenosine A2A receptor ligands using reinforcement learning and structure-based drug design
- Morgan Thomas
- , Pierre G. Matricon
- … Chris de Graaf
Nature Communications Open Access 01 July 2025
Accelerating discovery of bioactive ligands with pharmacophore-informed generative models
- Weixin Xie
- , Jianhang Zhang
- … Jianfeng Pei
Nature Communications Open Access 10 March 2025
Generative Artificial Intelligence: Evolving Technology, Growing Societal Impact, and Opportunities for Information Systems Research
- Veda C. Storey
- , Wei Thoo Yue
- … Roman Lukyanenko
Information Systems Frontiers Open Access 25 February 2025

Access options

Access through your institution

Access Nature and 54 other Nature Portfolio journals

Get Nature+, our best-value online-access subscription

27,99 € / 30 days

cancel any time

Learn more

Subscribe to this journal

Receive 12 print issues and online access

251,40 € per year

only 20,95 € per issue

Learn more

Buy this article

Purchase on SpringerLink
Instant access to the full article PDF.

39,95 €

Prices may be subject to local taxes which are calculated during checkout

Additional access options:

Log in
Learn about institutional subscriptions
Read our FAQs
Contact customer support

**Fig. 1: Comparison of compound 1 and two related inhibitors.**

References

Griffen, E. J., Dossetter, A. G., Leach, A. G. & Montague, S. Drug Discov. Today 18, 725–731 (2018).
Google Scholar
Vamathevan, J. et al. Nat. Rev. Drug Discov. 18, 463–477 (2019).
Article CAS Google Scholar
Putin, E. et al. Mol. Pharm. 15, 4386–4397 (2018).
Article CAS Google Scholar
Segler, M. H. S., Kogej, T., Tyrchan, C. & Waller, M. P. ACS Cent. Sci. 4, 120–131 (2018).
Article CAS Google Scholar
Jørgensen, P. B., Schmidt, M. N. & Winther, O. Mol. Inform. 37, 1700133 (2018).
Article Google Scholar
Schneider, G. Mol. Inform. 37, 1880131 (2018).
Article Google Scholar
Kadurin, A., Nikolenko, S., Khrabrov, K., Aliper, A. & Zhavoronkov, A. Mol. Pharm. 14, 3098–3104 (2017).
Article CAS Google Scholar
Dimitrov, T., Kreisbeck, C., Becker, J. S., Aspuru-Guzik, A. & Saikin, S. K. ACS Appl. Mater. Interfaces 11, 24825–24836 (2019).
Article CAS Google Scholar
Gómez-Bombarelli, R. et al. ACS Cent. Sci. 4, 268–276 (2018).
Article Google Scholar
Weininger, D. J. Chem. Inf. Comput. Sci. 28, 31–36 (1988).
Article CAS Google Scholar
Schneider, G. & Fechner, U. Nat. Rev. Drug Discov. 4, 649–663 (2005).
Article CAS Google Scholar
Brown, N., Fiscato, M., Segler, M. H. S. & Vaucher, A. C. J. Chem. Inf. Model. 59, 1096–1108 (2019).
Article CAS Google Scholar
Polykovskiy, D. et al. Preprint at https://arxiv.org/abs/1811.12823v3 (2018).
Merk, D., Friedrich, L., Grisoni, F. & Schneider, G. Mol. Inform. 37, 1700153 (2018).
Article Google Scholar
Zhavoronkov, A. et al. Nat. Biotechnol. 37, 1038–1040 (2019).
Article CAS Google Scholar
Colangelo, M. LinkedIn https://www.linkedin.com/pulse/pharmas-alphago-moment-first-time-ai-has-designed-new-colangelo/ (3 September 2019).
Silver, D. et al. Nature 529, 484–489 (2016).
Article CAS Google Scholar
Gao, M. et al. J. Med. Chem. 56, 3281–3295 (2013).
Article CAS Google Scholar
Tan, F. H., Putoczki, T. L., Stylli, S. S. & Luwor, R. B. Oncotargets Ther. 12, 635–645 (2019).
Article CAS Google Scholar
Canning, P. et al. J. Mol. Biol. 426, 2457–2470 (2014).
Article CAS Google Scholar
Stewart, K. D., Shiroda, M. & James, C. A. Bioorg. Med. Chem. 14, 7011–7022 (2006).
Article CAS Google Scholar
Hessler, G. & Baringhaus, K. Drug Discov. Today Technol. 7, e263–e269 (2010).
Article CAS Google Scholar
Leach, A. R. & Lewis, R. A. J. Comput. Chem. 15, 233–240 (1994).
Article CAS Google Scholar
Stahl, M. & Bajorath, J. J. Med. Chem. 54, 1–2 (2011).
Article CAS Google Scholar

Download references

Author information

Authors and Affiliations

Relay Therapeutics, Cambridge, MA, USA
W. Patrick Walters & Mark Murcko

Authors

W. Patrick Walters
View author publications
Search author on:PubMed Google Scholar
Mark Murcko
View author publications
Search author on:PubMed Google Scholar

Corresponding author

Correspondence to W. Patrick Walters.

Ethics declarations

Competing interests

W.P.W. is employed by, and M.M. is a member of the Board of Diretors of, Relay Therapeutics.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Walters, W.P., Murcko, M. Assessing the impact of generative AI on medicinal chemistry. Nat Biotechnol 38, 143–145 (2020). https://doi.org/10.1038/s41587-020-0418-2

Download citation

Published: 30 January 2020
Version of record: 30 January 2020
Issue date: February 2020
DOI: https://doi.org/10.1038/s41587-020-0418-2

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

This article is cited by

Accelerating discovery of bioactive ligands with pharmacophore-informed generative models
- Weixin Xie
- Jianhang Zhang
- Jianfeng Pei
Nature Communications (2025)
Identification of nanomolar adenosine A2A receptor ligands using reinforcement learning and structure-based drug design
- Morgan Thomas
- Pierre G. Matricon
- Chris de Graaf
Nature Communications (2025)
Leveraging generative models with periodicity-aware, invertible and invariant representations for crystalline materials design
- Zhilong Wang
- Fengqi You
Nature Computational Science (2025)
Large language models for reticular chemistry
- Zhiling Zheng
- Nakul Rampal
- Omar M. Yaghi
Nature Reviews Materials (2025)
AI-enabled individual learning strategies and scientific innovation: a case from the field of computer science
- Runhui Lin
- Yalin Li
- Biting Li
Scientometrics (2025)

Access through your institution

Buy or subscribe

Associated content

Reply to ‘Assessing the impact of generative AI on medicinal chemistry’

Alex Zhavoronkov
Alán Aspuru-Guzik

Nature Biotechnology Correspondence 30 Jan 2020

Explore content

Research articles
Reviews & Analysis
News & Comment
Podcasts
Videos
Current issue
Collections

Follow us on Facebook
Follow us on Twitter
Subscribe
Sign up for alerts
RSS feed

About the journal

Aims & Scope
Journal Information
Journal Metrics
About the Editors
Research Cross-Journal Editorial Team
Reviews Cross-Journal Editorial Team
Our publishing models
Editorial Values Statement
Editorial Policies
Content Types
Web Feeds
Posters
Contact

Publish with us

Submission Guidelines
For Reviewers
Language editing services
Open access funding
Submit manuscript

Search

Search articles by subject, keyword or author

Show results from

Advanced search

Quick links

Explore articles by subject
Find a job
Guide to authors
Editorial policies

Nature Biotechnology (Nat Biotechnol)

ISSN 1546-1696 (online)

ISSN 1087-0156 (print)

nature.com sitemap

About Nature Portfolio

About us
Press releases
Press office
Contact us

Discover content

Journals A-Z
Articles by subject
protocols.io
Nature Index

Publishing policies

Nature portfolio policies
Open access

Author & Researcher services

Reprints & permissions
Research data
Language editing
Scientific editing
Nature Masterclasses
Research Solutions

Libraries & institutions

Librarian service & tools
Librarian portal
Open research
Recommend to library

Advertising & partnerships

Advertising
Partnerships & Services
Media kits
Branded content

Professional development

Nature Awards
Nature Careers
Nature Conferences

Regional websites

Nature Africa
Nature China
Nature India
Nature Japan
Nature Middle East

Privacy Policy
Use of cookies
Legal notice
Accessibility statement
Terms & Conditions
Your US state privacy rights

Sign up for the Nature Briefing: Translational Research newsletter — top stories in biotechnology, drug discovery and pharma.

Email address

I agree my information will be processed in accordance with the Nature and Springer Nature Limited Privacy Policy.

Get what matters in translational research, free to your inbox weekly. Sign up for Nature Briefing: Translational Research

HOME
ABOUT
AUCTIONS
SHIPPING
FEES
TOOLS
HOW
FAQ
CONTACT

Original Source | Taken Source