Machine Learning Meets Mechanistic Modelling for Accurate Prediction of Experimental Activation Energies

Abstract

Accurate prediction of chemical reactions in solution is challenging for current state-of-the-art approaches based on transition state modelling with density functional theory. Models based on machine learning have emerged as a promising alternative to address these problems, but these models currently lack the precision to give crucial information on the magnitude of barrier heights, influence of solvents and catalysts and extent of regio- and chemoselectivity. Here, we construct hybrid models which combine the traditional transition state modelling and machine learning to accurately predict reaction barriers. We train a Gaussian Process Regression model to reproduce high-quality experimental kinetic data for the nucleophilic aromatic substitution reaction and use it to predict barriers with a mean absolute error of 0.77 kcal/mol for an external test set. The model was further validated on regio- and chemoselectivity prediction on patent reaction data and achieved a competitive top-1 accuracy of 86%, despite not being trained explicitly for this task. Importantly, the model gives error bars for its predictions that can be used for risk assessment by the end user. Hybrid models emerge as the preferred alternative for accurate reaction prediction in the very common low-data situation where only 100–150 rate constants are available for a reaction class. With recent advances in deep learning for quickly predicting barriers and transition state geometries from density functional theory, we envision that hybrid models will soon become a standard alternative to complement current machine learning approaches based on ground-state physical organic descriptors or structural information such as molecular graphs or fingerprints.

Machine Learning Validation via Rational Dataset Sampling with astartes

“…Train the model on some clusters and then evaluate performance on unseen clusters that should be dissimilar to the clusters used for training. Although measuring performance on chemically dissimilar compounds/clusters is not a new concept (Bilodeau et al, 2023;Durdy et al, 2022;Heinen et al, 2021;Jorner et al, 2021;Meredig et al, 2018;Stuyver & Coley, 2022;Terrones et al, 2023;Tricarico et al, 2022), there are a myriad of choices for the first two steps; our software incorporates many popular representations and similarity metrics to give users freedom to easily explore which combination is suitable for their needs.…”