Kernel Methods for Predicting Yields of Chemical Reactions

Haywood, Alexe L.; Redshaw, Joseph; Hanson-Heine, Magnus W.D.; Taylor, Adam; Brown, Alex; Mason, Andrew M.; Gärtner, Thomas; Hirst, Jonathan D.

Abstract

The use of machine learning methods for the prediction of reaction yield is an emerging area. We demonstrate the applicability of support vector regression (SVR) for predicting reaction yields, using combinatorial data. Molecular descriptors used in regression tasks related to chemical reactivity have often been based on time-consuming, computationally demanding quantum chemical calculations, usually density functional theory. Structure-based descriptors (molecular fingerprints and molecular graphs) are quicker and easier to calculate and are applicable to any molecule. In this study, SVR models built on structure-based descriptors were compared to models built on quantum chemical descriptors. The models were evaluated along the dimension of each reaction component in a set of Buchwald-Hartwig amination reactions. The structure-based SVR models outperformed the quantum chemical SVR models, along the dimension of each reaction component. The applicability of the models was assessed with respect to similarity to training. Prospective predictions of unseen Buchwald-Hartwig reactions are presented for synthetic assessment, to validate the generalizability of the models, with particular interest along the aryl halide dimension.

Citation

Haywood, A. L., Redshaw, J., Hanson-Heine, M. W., Taylor, A., Brown, A., Mason, A. M., Gärtner, T., & Hirst, J. D. (2022). Kernel Methods for Predicting Yields of Chemical Reactions. Journal of Chemical Information and Modeling, 62(9), 2077-2092. https://doi.org/10.1021/acs.jcim.1c00699

• Journal Article Type: Article
• Acceptance Date: Oct 11, 2021
• Online Publication Date: Oct 26, 2021
• Publication Date: May 9, 2022
• Deposit Date: Jan 7, 2022
• Publicly Available Date: Oct 27, 2022
• Journal: Journal of Chemical Information and Modeling
• Print ISSN: 1549-9596
• Electronic ISSN: 1549-960X
• Publisher: American Chemical Society
• Peer Reviewed: Peer Reviewed
• Volume: 62
• Issue: 9
• Pages: 2077-2092
• DOI: https://doi.org/10.1021/acs.jcim.1c00699
• Keywords: Library and Information Sciences; Computer Science Applications; General Chemical Engineering; General Chemistry
• Public URL: https://nottingham-repository.worktribe.com/output/6739583
• Publisher URL: https://pubs.acs.org/doi/10.1021/acs.jcim.1c00699
• Additional Information: This document is the Accepted Manuscript version of a Published Work that appeared in final form in Journal of Chemical Information and Modeling, copyright © American Chemical Society after peer review and technical editing by the publisher. To access the final edited and published work see https://pubs.acs.org/doi/10.1021/acs.jcim.1c00699