Concise Total Synthesis of (+)-Shearilicine: A Machine Learning-Assisted Strategy for Ligand Optimization of an Enantioselective Palladium-Catalyzed α-Arylation.

Herein, we report the short enantioselective total synthesis of (+)-shearilicine, facilitated by a machine learning-empowered design of novel ligands for Pd-catalyzed α-arylation. The enantioselectivity resulting from the arylation of a highly functionalized cyclohexanone with a carbazole was predicted using a support vector regression (SVR) model. More than 120 BI-DIME-type ligands were virtually screened to identify promising candidates for experimental validation, yielding a great improvement in the enantioselectivity of this problematic arylation. Additional notable features of the synthesis include a mild silane-directed intramolecular allylative cyclization to build the final six-membered carbon framework and a singlet oxygen-mediated Achmatowicz-Ali rearrangement to construct the 6,8-dioxabicyclo[3.2.1]octane ring system.