Rega: A Platform for the Prediction of the Regioselectivity of C–H Functionalization Reactions

Sulfinate-mediated radical C-H functionalization reactions are widely used for the modification and diversification of scaffolds in drug discovery. There may be multiple sites of reaction, each with a unique steric and electronic environment. Here we present Rega, an automated transition state searching program for the prediction of regioselectivity from inexpensive HF/6-31G* activation energies, enabling the generation of a synthetic dataset of 490 compounds comprising 2744 sites with labeled reactivity for use in machine learning.