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
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, accepted
A Fragment Based Approach Towards Curating, Comparing and Developing Machine Learning Models Applied in Photochemistry.
Stenfors, B.; Cadge, J.; Aikonen, S.; Luchcini, G.; Wahlers, J.; Koh, K.; Muuronen, M.; Menche, M.; Pfeifle, M.; Keto, A.; Paton, R.; Sigman, M.; 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.; Paton, R. submitted 2025
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. in revision 2025
Transferable Machine Learning Interatomic Potential for Pd Catalyzed Cross-Coupling Reactions.Anstinea, D. M.; Zubatyuka, R.; Gallegos, L. C.; Paton, R. S.; Wiest, O.; Nebgen, B.; Jones, T.; Gomes, G.; Tretiak, S.; Isayev, O. ChemRxiv 2025, DOI: 10.26434/chemrxiv-2025-n36r6
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
Rapid Prediction of Conformationally-Dependent DFT-Level Descriptors using Graph Neural Networks for Carboxylic Acids and Alkyl Amines.Haas, B. C.; Hardy, M. A.; Sowndarya S. V., S.; Adams, K.; Coley, C. W.; Paton, R. S.; Sigman, M. S. Digit. Discov. 2025, 4, 222–233
