Predicting Reaction Feasibility and Selectivity of Aromatic C–H Thianthrenation with a QM-ML Hybrid Approach

The direct thianthrenation of aromatic C–H bonds is a valuable late-stage functionalization strategy that can assist, for example, the development of new drugs. We herein present a predictive computational model for this reaction, denoted PATTCH, which is based on semi-empirical quantum mechanics and machine learning. It classifies each aromatic C–H unit either as reactive or not with an accuracy of above 90%. It can address both the site-selectivity and reaction feasibility question associated with the thianthrenation protocol. First, this was achieved by selecting carefully engineered features, which take into account the electronic and steric influence on the site-selectivity. Second, parallel experimentation was used to supplement the available literature data with 54 new negative reactions (unsuccessful thianthrenation), which we show was instrumental for developing the PATTCH tool. Ultimately, we successfully applied the model to a challenging test set encompassing the differentiation between carbocycle vs. heterocycle functionalization, the identification of substrates that were reported to result in a mixture of isomeric products, and to molecules that could not be thianthrenated. The computational predictions were experimentally validated. The PATTCH tool can be obtained free of charge from https://github.com/MolecularAI/thianthrenation_prediction.