Designing Target-Specific Datasets for Regioselectivity Predictions on Complex Substrates

The development of machine learning models to predict the regioselectivity of C(sp3)–H functionalization reactions is reported. A dataset for dioxirane oxidations was curated from the literature and used to generate a model to predict the regioselectivity of C–H oxidation. To assess whether smaller, intentionally designed datasets could provide ac-curacy on complex targets, a series of acquisition functions were developed to select the most informative mole-cules for the specific target. Active learning-based acquisition functions that leverage predicted reactivity and model uncertainty were found to outperform those based on molecular and site similarity alone. The use of acquisition functions for dataset elaboration significantly reduced the number of datapoints needed to perform accurate predic-tion, and it was found that smaller, machine-designed datasets can give accurate predictions when larger, randomly selected datasets fail. Finally, the workflow was experimentally validated on five complex substrates and shown to be applicable to predicting the regioselectivity of arene C–H radical borylation. These studies provide a quantitative alternative to the intuitive extrapolation from “model substrates” that is frequently used to estimate reactivity on complex molecules.