As artificial intelligence (AI) proliferates, synthetic chemistry stands to benefit from its progress. Despite hidden variables and ‘unknown unknowns’ in datasets that may impede the realization of a digital twin for the laboratory flask, there are many opportunities to leverage AI and large datasets to advance synthesis science.
References
Burger, B. et al. Nature 583, 237–241 (2020).
Coley, C. W. et al. Science 365, eaax1566 (2019).
Abolhasani, M. & Kumacheva, E. Nat. Synth. https://doi.org/10.1038/s44160-022-00231-0 (2023).
Lowe, D. Chemical Reactions From US Patents (1976-Sep2016) (Figshare, 2017); https://doi.org/10.6084/m9.figshare.5104873.v1
Kearnes, S. M. et al. J. Am. Chem. Soc. 143, 18820–18826 (2021).
Tshitoyan, V. et al. Nature 571, 95–98 (2019).
Olivetti, E. et al. Materials synthesis insights from scientific literature via text extraction and machine learning. Chem. Mater. 29, 9436–9444 (2017).
Kononova, O. et al. Sci. Data 6, 203 (2019).
Wang, Z. et al. Sci. Data 9, 231 (2022).
Kim, E., Huang, K., Kononova, O., Ceder, G. & Olivetti, E. Matter 1, 8–12 (2019).
Fitzner, M. et al. Chem. Sci. 11, 13085–13093 (2020).
Kim, E. et al. Chem. Mater. 29, 9436–9444 (2017).
Segler, M. H. S., Preuss, M. & Waller, M. P. Nature 555, 604–610 (2018).
Szymanski, N. J. et al. Mater. Horiz. 8, 2169–2198 (2021).
MacLeod, B. P. et al. Sci. Adv. 6, eaaz8867 (2020).
Xu, L. et al. Nat. Catal. 4, 71–78 (2021).
Novák, Z. et al. Nat. Catal. 4, 991–993 (2021).
McQueen, T., Xu, Q., Andersen, E. N., Zandbergen, H. W. & Cava, R. J. J. Solid State Chem. 180, 2864–2870 (2007).
Raccuglia, P. et al. Nature 533, 73–76 (2016).
Coley, C. W., Barzilay, R., Jaakkola, T. S., Green, W. H. & Jensen, K. F. ACS Cent. Sci. 3, 434–443 (2017).
Wang, Z. et al. Optimal thermodynamic conditions to minimize kinetic byproducts in aqueous materials synthesis. Preprint at https://doi.org/10.21203/rs.3.rs-2398824/v1 (2023).
Bergman, R. G. & Danheiser, R. L. Angew. Chem. Int. Ed. 55, 12548–12549 (2016).
Acknowledgements
N.D. and W.S. acknowledge support through the Dreyfus Program for Machine Learning in the Chemical Sciences and Engineering. C.W.C. thanks the National Science Foundation under grant no. CHE-2144153 and the AI2050 program at Schmidt Futures (grant G-22-64475) for financial support. We thank P.F. Poudeu, J. Neilson, and A. Miura for stimulating conversations.
Author information
Authors and Affiliations
Contributions
N.D., W.S. and C.W.C. jointly prepared the manuscript.
Corresponding authors
Ethics declarations
Competing interests
The authors declare no competing interests.
Rights and permissions
About this article
Cite this article
David, N., Sun, W. & Coley, C.W. The promise and pitfalls of AI for molecular and materials synthesis. Nat Comput Sci 3, 362–364 (2023). https://doi.org/10.1038/s43588-023-00446-x
Published:
Issue Date:
DOI: https://doi.org/10.1038/s43588-023-00446-x
- Springer Nature America, Inc.
This article is cited by
-
Optimal thermodynamic conditions to minimize kinetic by-products in aqueous materials synthesis
Nature Synthesis (2024)
-
The increasing potential and challenges of digital twins
Nature Computational Science (2024)
-
Navigating phase diagram complexity to guide robotic inorganic materials synthesis
Nature Synthesis (2024)