The Paton Research Group

Computational chemistry, machine learning, and open-source tools for chemical discovery

We develop quantum chemical workflows and machine learning models to predict reactivity and selectivity in organic and organometallic reactions. A substantial part of our effort goes into open-source software, including AQME, GoodVibes, ALFABET, and CASCADE, which are used by research groups worldwide. We collaborate closely with experimental groups, who test our predictions and provide much of the data on which our models are trained and benchmarked.

Research

Data-Driven Chemistry

Catalyst Discovery and Design

Reaction Mechanism and Selectivity

Lab Photos

Recent Publications

The generation of five-membered hetarynes balanced on the edge of accessibility.

Hindson, M. J.; Popescu, M. V.; Alisauskas, E.; Fresia, M.; Holmes, S.; Petropavloskikh, D.; Paton, R. S.; Burton, J. W.; Smith, M. D. Nat. Commun. 2026, accepted

Transferable Machine Learning Interatomic Potential for Pd Catalyzed Cross-Coupling Reactions.

Anstine, D. M.; Zubatyuk, R.; Gallegos, L. C.; Paton, R. S.; Wiest, O.; Nebgen, B.; Jones, T.; Gomes, G.; Tretiak, S.; Isayev, O. Nat. Comput. Sci. 2026, accepted

Designing Artificial Cofactors and Their Enzymes Together.

Platt, A. P.; Bomble, Y. J.; Paton, R. S. Trends in Biotech. 2026, 44, 2821–2823.

Programmable Regiodivergent Cyclization of Acyclic 1,5-Dienes Unlocks Rigid Bicyclic Architectures.

Zhang, Z.-X.; Shu, K.; Popescu, M. V.; Guo, Y.; Tyler, J.; Paton, R. S.; Aggarwal, V. K. Nat. Chem. 2026, DOI: 10.1038/s41557-026-02238-y

Phosphine-mediated azine C–H couplings with water and ammonia.

Nottingham, K. G.; Brunner, D. A.; Dalmau, D.; Melanese, A. K.; Alegre-Requena, J. V.; Paton, R. S.; McNally, A. Nature 2026, 657, 957–963

Selectivity Emerges from Indiscriminate Photoreduction.

Edgecomb, J. M.; Sau, A.; Manoj, N.; Resmini, M. D.; Meyer, A. F.; Paton, R. S.; Damrauer, N. H.; Wickens, Z. K. Nature 2026, 656, 630–637