Leveraging large language models for predictive chemistry
Open accessPublished version of a preprint
The DOI matches its Crossref record; 82 of the 82 references it cites were found in a registry or an index.
Abstract
Machine learning has transformed many fields and has recently found applications in chemistry and materials science. The small datasets commonly found in chemistry sparked the development of sophisticated machine learning approaches that incorporate chemical knowledge for each application and, therefore, require specialized expertise to develop. Here we show that GPT-3, a large language model trained on vast amounts of text extracted from the Internet, can easily be adapted to solve various tasks in chemistry and materials science by fine-tuning it to answer chemical questions in natural language with the correct answer. We compared this approach with dedicated machine learning models for many applications spanning the properties of molecules and materials to the yield of chemical reactions. Surprisingly, our fine-tuned version of GPT-3 can perform comparably to or even outperform conventional machine learning techniques, in particular in the low-data limit. In addition, we can perform inverse design by simply inverting the questions. The ease of use and high performance, especially for small datasets, can impact the fundamental approach to using machine learning in the chemical and material sciences. In addition to a literature search, querying a pre-trained large language model might become a routine way to bootstrap a project by leveraging the collective knowledge encoded in these foundation models, or to provide a baseline for predictive tasks.
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.
Integrity signals
Registry
Cites
Statistics
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.
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?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“In parallel, chemistry-oriented reviews have shown that large language models can move beyond text generation toward tool use, retrieval, planning, code execution, and multi-agent coordination [5-10].”
From From Scientific Copilots to Tool-Grounded Autonomy: AI Agents in Simulation-Driven Materials Discovery (2026) · cites this paper as [9]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The central challenge is not only to predict a property, but to manage the sequence of reasoning and action that connects a scientific objective to executable computational or experimental steps [2-10].”
From From Scientific Copilots to Tool-Grounded Autonomy: AI Agents in Simulation-Driven Materials Discovery (2026) · cites this paper as [9]
Experimental — accuracy not yet measuredThe check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“The broader literature on autonomous scientific systems has already argued for more rigorous evaluation protocols and transparent tool interfaces [3,5,7-12].”
From From Scientific Copilots to Tool-Grounded Autonomy: AI Agents in Simulation-Driven Materials Discovery (2026) · cites this paper as [9]
Experimental — accuracy not yet measuredThe check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“To the best of our knowledge, no prior review has isolated simulation-driven, toolorchestrating AI agent workflows for materials discovery as a distinct evidence base with study-level extraction of autonomy, validation, and reproducibility [3-14].”
From From Scientific Copilots to Tool-Grounded Autonomy: AI Agents in Simulation-Driven Materials Discovery (2026) · cites this paper as [9]
Experimental — accuracy not yet measured
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
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404
XGBoost: A Scalable Tree Boosting System
Chen, T., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939785 · Cited by 54,569
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., & Liu, P. J. (2019) · arXiv · doi:10.48550/arxiv.1910.10683 · Cited by 10,929
Weininger, D. (1988) · Journal of Chemical Information and Computer Sciences · doi:10.1021/ci00057a005 · Cited by 7,436 · cited 8×
“For machine learning applications, there has been a lot of effort to represent a chemical with unique line encodings (for example, simplified molecular-input line-entry system (SMILES) 30 or self-referencing embedded strings (SELFIES) 31,32 ).”
InfluentialBannwarth, C., Ehlert, S., & Grimme, S. (2019) · Journal of Chemical Theory and Computation · doi:10.1021/acs.jctc.8b01176 · Cited by 4,399
ChEMBL: a large-scale bioactivity database for drug discovery
Gaulton, A., Bellis, L. J., Bento, A. P., Chambers, J., Davies, M., Hersey, A., Light, Y., McGlinchey, S., Michalovich, D., Al-Lazikani, B., et al. (2012) · Nucleic Acids Research · doi:10.1093/nar/gkr777 · Cited by 4,382
Universal Language Model Fine-tuning for Text Classification
Howard, J., & Ruder, S. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p18-1031 · Cited by 4,100 · cited 1×
“Before discussing the different applications in detail, let us first discuss how we fine-tune 23 the GPT-3 model in practice for a simple but highly non-trivial example.”
Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules
Gómez-Bombarelli, R., Wei, J. N., Duvenaud, D., Hernández-Lobato, J. M., Sánchez-Lengeling, B., Sheberla, D., Aguilera-Iparraguirre, J., Hirzel, T. D., Adams, R. P., & Aspuru-Guzik, A. (2018) · ACS Central Science · doi:10.1021/acscentsci.7b00572 · Cited by 3,106
On the Opportunities and Risks of Foundation Models
Bommasani, R., Hudson, D. A., Adeli, E., Altman, R., Arora, S., von Arx, S., Bernstein, M. S., Bohg, J., Bosselut, A., Brunskill, E., et al. (2021) · arXiv · doi:10.48550/arxiv.2108.07258 · Cited by 2,676
Research works printed but not linked: 7
- Goldblum, M., Finzi, M., Rowan, K. & Wilson, A. The no free lunch theorem, Kolmogorov complexity, and the role of inductive biases in machine learning. ICLR 2024 Conference, OpenReview https://openreview.net/forum?id=X7nz6ljg9Y (2023).
- Dettmers, T., Lewis, M., Belkada, Y. & Zettlemoyer, L. GPT3.int8(): 8-bit matrix multiplication for transformers at scale. Adv. Neural Inf. Process. Syst. 35, 30318–30332 (2022).
- Dettmers, T., Lewis, M., Shleifer, S. & Zettlemoyer, L. 8-bit optimizers via block-wise quantization. in The Tenth International Conference on Learning Representations (2022).
- Hu, E. J. et al. LoRA: low-rank adaptation of large language models. in International Conference On Learning Representations (2021).
- Griffiths, R.-R. et al. Gauche: a library for Gaussian processes in chemistry. in ICML 2022 2nd AI for Science Workshop https://openreview.net/forum?id=i9MKI7zrWal (2022)
- Radford, A. et al. Language models are unsupervised multitask learners. OpenAI blog 1, 9 (2019).
- Kawazoe, Y., Yu, J.-Z., Tsai, A.-P. & Masumoto, T. (eds) Nonequilibrium Phase Diagrams of Ternary Amorphous Alloys Landolt-Börnstein: Numerical Data and Functional Relationships in Science and Technology—New Series (Springer, 2006).
Cited by
Autonomous chemical research with large language models
Boiko, D. A., MacKnight, R., Kline, B., & Gomes, G. (2023) · Nature · doi:10.1038/s41586-023-06792-0 · Cited by 1,050
“These models have been successfully applied to various domains, including natural language 1–5 , biological 6,7 and chemical research 8–10 as well as code generation 11,12 .”
Augmenting large language models with chemistry tools
M. Bran, A., Cox, S., Schilter, O., Baldassari, C., White, A. D., & Schwaller, P. (2024) · Nature Machine Intelligence · doi:10.1038/s42256-024-00832-8 · Cited by 794
Self-citationArtificial intelligence in drug development
Zhang, K., Yang, X., Wang, Y., Yu, Y., Huang, N., Li, G., Li, X., Wu, J. C., & Yang, S. (2025) · Nature Medicine · doi:10.1038/s41591-024-03434-4 · Cited by 498
A Comprehensive Survey on Deep Graph Representation Learning
Ju, W., Fang, Z., Gu, Y., Liu, Z., Long, Q., Qiao, Z., Qin, Y., Shen, J., Sun, F., Xiao, Z., et al. (2024) · Neural Networks · doi:10.1016/j.neunet.2024.106207 · Cited by 341
Empowering biomedical discovery with AI agents
Gao, S., Fang, A., Huang, Y., Giunchiglia, V., Noori, A., Schwarz, J. R., Ektefaie, Y., Kondic, J., & Zitnik, M. (2024) · Cell · doi:10.1016/j.cell.2024.09.022 · Cited by 315
Metadata
- Authors
- Jablonka, K. M., Schwaller, P., Ortega-Guerrero, A., & Smit, B.
- Affiliations
- Helmholtz Institute Jena (DE)
- École Polytechnique Fédérale de Lausanne (CH)
- Corresponding author
- Smit, Berend
- Venue
- Nature Machine Intelligence
- Published
- 2024-02-06
- Volume
- 6
- Issue
- 2
- Pages
- 161-169
- ISSN
- 2522-5839 (ISSN-L)
- OpenAlex
- W4391561379
- Cited by
- 378
- References
- 75
- Citations by year
- 2026: 121 · 2025: 178 · 2024: 77
- FWCI
- 36.62
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- creativecommons.org/licenses/by/4.0 (tdm)
- creativecommons.org/licenses/by/4.0 (vor)
- Locations
- Nature Machine Intelligence (publishedVersion, cc-by)
- ChemRxiv (acceptedVersion, cc-by)
- HZB Repository (Helmholtz-Zentrum Berlin für Materialien und Energie GmbH (HZB)) (submittedVersion, other-oa)
- Infoscience (Ecole Polytechnique Fédérale de Lausanne) (submittedVersion, cc-by-nc-nd)
- Funders
- National Science Foundation
- Carl-Zeiss-Stiftung
- Grantham Foundation for the Protection of the Environment
- École Polytechnique Fédérale de Lausanne
- Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung (180544, 51NF40, 182892, (51NF40-182892).)
- NCCR Catalysis
- Topics
- Physical Sciences › Materials Science › Materials Chemistry › Machine Learning in Materials Science
- Life Sciences › Pharmacology, Toxicology and Pharmaceutics › Drug Discovery › Computational Drug Discovery Methods
- Social Sciences › Arts and Humanities › History and Philosophy of Science › History and advancements in chemistry
- Keywords
- large language models, GPT-3, fine-tuning, inverse design, molecular property prediction, reaction yield prediction, foundation models, literature searching
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: Leveraging large language models for predictive chemistry. https://app.cochat.ai/papers/10.1038/s42256-023-00788-1
- The paper
- Jablonka, K. M., Schwaller, P., Ortega-Guerrero, A., & Smit, B. (2024). Leveraging large language models for predictive chemistry. Nature Machine Intelligence. https://doi.org/10.1038/s42256-023-00788-1
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.