Selective functionalization of hindered meta-C-H bond of o-alkylaryl ketones promoted by automation and deep learning

Selective functionalization of the sterically hindered aromatic meta- C-H bond is unprecedented and remains to be a major challenge. Promoted by automation-based high-throughput experimentation (HTE) and deep learning (DL), a novel strategy to functionalize the hindered meta-C-H bond is disclosed. With carbon dioxide as a traceless director, a one-pot three-step protocol was developed to achieve selective arylation of o-alkylaryl ketones at the hindered meta position. This novel strategy involved photo-induced C-H carboxylation, carboxyl group-directed Pd-catalyzed C-H function-alization, and microwave-assisted decarboxylation. With HTE and DL, a broad scope of substrates was explored (1,032 reactions) and a DL-based model (CMPRY) for reaction yield prediction was es-tablished. Two independent tests with unseen o-alkylaryl ketones and/or potassium aryltrifluoroborates were used to evaluate the model. The model gave excellent performances in predicting un-seen reactions; mean absolute errors in yield were only 6.6% and 8.4%, suggesting its potential in synthetic application.