Data Driven Chemistry - representations and regression

Data-Driven Chemistry

We harness machine learning to transform quantum chemical data into predictive models for molecular properties and reactivity. Our methodologies combine density functional theory calculations with graph neural networks and statistical learning to predict bond strengths, spectroscopic properties, and conformational behavior. Key aims include automating thermochemical analysis, developing quantitative structure-selectivity relationships for flexible molecules, and accelerating catalyst optimization through data-driven design. Our tools enable researchers to navigate chemical space efficiently, moving from trial-and-error experimentation toward rational, predictive chemistry.

Collaborators

Scott Denmark, Olexandr Isayev, Seonah Kim, Steven Lopez, Matt Sigman, Olaf Wiest

Recent Papers

Fundamental Study of Density Functional Theory Applied to Triplet State Reactivity: Introduction of the TRIP50 Dataset.

Hughes, W. B.; Popescu, M. V.; Paton, R. S.  J. Chem. Theory Comput. 2026, DOI: 10.1021/acs.jctc.6c00144

Deep learning for asymmetric catalysis.

Paton, R. S.; Kim, S. Nat. Comput. Sci. 2026, 6, 115–116

The Atroposelective Iodination of 2-Amino-6-arylpyridines Catalyzed by Chiral Disulfonimides Actually Proceeds via Brønsted Base Catalysis: A Combined Experimental, Computational, and Machine-Learning Study.

Parmar, K. S.; Bawel, S.; Popescu, M. V.; Mai, B. K.; Timmerman, J. C.; Altundas, B.; Paton, R. S.; Denmark, S. E. J. Am. Chem. Soc. 2026, 148, 2175–2190

 

A Fragment Based Approach Towards Curating, Comparing and Developing Machine Learning Models Applied in Photochemistry.
Pérez-Soto, R.; Popescu, M. V.; Kumar, S.; Adao Gomes, L.; Lee, C.; Shore, E.; Lopez, S. A.; Paton, R. S.; Kim, S. Chem. Sci. 2025, 16, 21874–21886
Conformation Dependent Features of Bisphosphine Ligands.

Stenfors, B.; Cadge, J.; Aikonen, S.; Luchini, G.; Wahlers, J.; Koh, K.; Muuronen, M.; Menche, M.; Pfeifle, M.; Keto, A.; Paton, R. S.; Sigman, M. S.; Wiest, O. J. Org. Chem. 2025, 90, 13874–13884

CASCADE-2.0: Real Time Prediction of 13C-NMR Shifts with sub-ppm Accuracy.

Bhadauria, A.; Feng, Z.; Popescu, M. V.; Paton, R. S.submitted 2025

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. in revision 2026

Computer-Aided Design of Stability Enhanced Nicotinamide Cofactor Biomimetics.

Platt, A.; Klem, H.; Mallinson, S.; Bomble, Y.; Paton, R. S. Green Chem. 2025, 27, 6831–6844