Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; 90 of the 90 references it cites were found in a registry or an index.

Augmenting large language models with chemistry tools

Open access
M. Bran, Andres, Cox, Sam, Schilter, Oliver, Baldassari, Carlo, White, Andrew D., Schwaller, Philippe · 2024 · Nature Machine Intelligence

Abstract

Large language models (LLMs) have shown strong performance in tasks across domains but struggle with chemistry-related problems. These models also lack access to external knowledge sources, limiting their usefulness in scientific applications. We introduce ChemCrow, an LLM chemistry agent designed to accomplish tasks across organic synthesis, drug discovery and materials design. By integrating 18 expert-designed tools and using GPT-4 as the LLM, ChemCrow augments the LLM performance in chemistry, and new capabilities emerge. Our agent autonomously planned and executed the syntheses of an insect repellent and three organocatalysts and guided the discovery of a novel chromophore. Our evaluation, including both LLM and expert assessments, demonstrates ChemCrow’s effectiveness in automating a diverse set of chemical tasks. Our work not only aids expert chemists and lowers barriers for non-experts but also fosters scientific advancement by bridging the gap between experimental and computational chemistry.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1038/s42256-024-00832-8

Cites

90 of 90 references verified0 citation errors · 0 not checkable

Statistics

Figures

Fig. 1 Overview and toolset. a, An overview of the task-solving process. Using a variety of chemistry-related packages and software, a set of tools is created. These tools and a user input are then given to an LLM. The LLM proceeds through an automatic, iterative chain-of-thought process, deciding on its path, choice of tools and inputs before coming to a final answer. The example shows the synthesis of DEET, a common insect repellent. b, Toolsets implemented in ChemCrow: reaction, molecule, safety, search and standard tools. Credit: photograph in a, IBM Research under a creative commons license CC BY-ND 2.0. Source data
Fig. 1 Overview and toolset. a, An overview of the task-solving process. Using a variety of chemistry-related packages and software, a set of tools is created. These tools and a user input are then given to an LLM. The LLM proceeds through an automatic, iterative chain-of-thought process, deciding on its path, choice of tools and inputs before coming to a final answer. The example shows the synthesis of DEET, a common insect repellent. b, Toolsets implemented in ChemCrow: reaction, molecule, safety, search and standard tools. Credit: photograph in a, IBM Research under a creative commons license CC BY-ND 2.0. Source dataCC BY · PubMed Central
Fig. 2 Experimental validation. a, Example of the script run by a user to initiate ChemCrow. b, Query and synthesis of a thiourea organocatalyst. c, IBM Research RoboRXN synthesis platform on which the experiments were executed (pictures reprinted courtesy of International Business Machines Corporation). d, Experimentally validated compounds. Credit: photographs in c, IBM Research under a creative commons license CC BY-ND 2.0.
Fig. 2 Experimental validation. a, Example of the script run by a user to initiate ChemCrow. b, Query and synthesis of a thiourea organocatalyst. c, IBM Research RoboRXN synthesis platform on which the experiments were executed (pictures reprinted courtesy of International Business Machines Corporation). d, Experimentally validated compounds. Credit: photographs in c, IBM Research under a creative commons license CC BY-ND 2.0.CC BY · PubMed Central
Fig. 3 Human–model interaction leading to the discovery of a new chromophore. Left, human input, actions and observation. Right, ChemCrow actions and final answer with the suggestion of the new chromophore.
Fig. 3 Human–model interaction leading to the discovery of a new chromophore. Left, human input, actions and observation. Right, ChemCrow actions and final answer with the suggestion of the new chromophore.CC BY · PubMed Central
Fig. 4 Evaluation results. Comparative performance of GPT-4 and ChemCrow across a range of tasks. a, Per-task preference. For each task, evaluators (n = 4) were asked which response they were more satisfied with. Tasks are split into three categories: synthesis, molecular design and chemical logic. Tasks are sorted by order of difficulty within the classes. b, Mean chemical accuracy (factuality) of responses across human evaluators (n = 4) in organic synthesis tasks, sorted by synthetic accessibility of targets c, Aggregate results for each metric from human evaluators across all tasks (n = 56) compared to EvaluatorGPT scores (n = 14). The error bars represent the confidence interval (95%). d, The checkboxes highlight the strengths and flaws of each system. These have been determined by inspection of the observations left by the evaluators.
Fig. 4 Evaluation results. Comparative performance of GPT-4 and ChemCrow across a range of tasks. a, Per-task preference. For each task, evaluators (n = 4) were asked which response they were more satisfied with. Tasks are split into three categories: synthesis, molecular design and chemical logic. Tasks are sorted by order of difficulty within the classes. b, Mean chemical accuracy (factuality) of responses across human evaluators (n = 4) in organic synthesis tasks, sorted by synthetic accessibility of targets c, Aggregate results for each metric from human evaluators across all tasks (n = 56) compared to EvaluatorGPT scores (n = 14). The error bars represent the confidence interval (95%). d, The checkboxes highlight the strengths and flaws of each system. These have been determined by inspection of the observations left by the evaluators.CC BY · PubMed Central
Fig. 5 Safety guidelines provided by ChemCrow. Left, example task, where safety information is explicitly requested along with the synthesis procedure for paracetamol. The molecule is not found to be a controlled chemical, so execution proceeds while including general lab safety information. Right, in cases where the input molecule is found to be a controlled chemical, execution stops, with a warning indicating that it is illegal and unethical to propose compounds with properties similar to a controlled chemical.
Fig. 5 Safety guidelines provided by ChemCrow. Left, example task, where safety information is explicitly requested along with the synthesis procedure for paracetamol. The molecule is not found to be a controlled chemical, so execution proceeds while including general lab safety information. Right, in cases where the input molecule is found to be a controlled chemical, execution stops, with a warning indicating that it is illegal and unethical to propose compounds with properties similar to a controlled chemical.CC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

5 more claims about this paper

Create a free account to see every claim other papers make about this one.

See all claims — free account

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 76 references

Research works printed but not linked: 5

  1. Devlin, J., Chang, M.-W., Lee, K. & Toutanova, K. Bert: pre-training of deep bidirectional transformers for language understanding. In Proc. Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (eds Burstein, J. et al.) 4171–4186 (Association for Computational Linguistics, 2019).
  2. Li, R. et al. Starcoder: may the source be with you! Trans. Mach. Learn. Res. https://openreview.net/pdf?id=KoFOg41haE (2023).
  3. Zelikman, E., Wu, Y., Mu, J. & Goodman, N. Star: bootstrapping reasoning with reasoning. Adv. Neural Inf. Process. Syst. 35, 15476–15488 (2022).
  4. Lowe, D. M. Extraction of Chemical Structures and Reactions from the Literature. PhD thesis, Univ. of Cambridge (2012).
  5. Gao, L., Schulman, J. & Hilton, J. Scaling laws for reward model overoptimization. In Proc. International Conference on Machine Learning (eds Krause, A. et al.) 10835–10866 (PMLR, 2023).

Cited by

See all 1,023

Metadata

Authors
M. Bran, A., Cox, S., Schilter, O., Baldassari, C., White, A. D., & Schwaller, P.
Affiliations
  • Future House, Inc. (US)
  • IBM Research - Zurich (CH)
  • NCCR Catalysis (CH)
Corresponding author
  • White, Andrew D.
  • Schwaller, Philippe
Venue
Nature Machine Intelligence
Published
2024-05-08
Volume
6
Issue
5
Pages
525-535
ISSN
2522-5839 (ISSN-L)
OpenAlex
W4396723768
Cited by
794
References
76
Citations by year
2026: 395 · 2025: 305 · 2024: 83
FWCI
76.42
Type
journal article
Language
en
Open access
Licence
Locations
  • Nature Machine Intelligence (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by-nd)
  • PubMed (publishedVersion)
  • Infoscience (Ecole Polytechnique Fédérale de Lausanne) (submittedVersion, cc-by-nc-nd)
Funders
  • Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung (180544)
  • National Science Foundation (1751471)
Topics
  • Physical Sciences › Materials Science › Materials Chemistry › Machine Learning in Materials Science
  • Life Sciences › Pharmacology, Toxicology and Pharmaceutics › Drug Discovery › Computational Drug Discovery Methods
  • Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence Applications
Keywords
large language models, GPT-4, organic synthesis planning, drug discovery, materials design, organocatalysts

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Augmenting large language models with chemistry tools. https://app.cochat.ai/papers/10.1038/s42256-024-00832-8
The paper
M. Bran, A., Cox, S., Schilter, O., Baldassari, C., White, A. D., & Schwaller, P. (2024). Augmenting large language models with chemistry tools. Nature Machine Intelligence. https://doi.org/10.1038/s42256-024-00832-8

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.