Key points are not available for this paper at this time.
The conventional approach to developing asymmetric synthetic methods relies heavily on empirical optimization. However, the integration of artificial intelligence (AI) and high-throughput experimentation (HTE) technology presents a paradigm shift with immense potential to revolutionize the discovery and optimization of asymmetric reactions. In this study, we present an efficient workflow for the development of a series of nickel-catalyzed asymmetric cross-coupling reactions, leveraging AI and HTE technology. Many nickel-catalyzed enantioselective cross-coupling reactions share a common Ni(III) intermediate, which dictates the enantioselectivity. To harness this mechanistic insight, we embarked on developing a predictive model for nickel-catalyzed enantioselective coupling reactions, elucidating the general rules governing enantioselectivity. Through the application of data science tools and HTE technology, we curated a data set to construct an AI-based model. This model was subsequently utilized to facilitate the discovery of efficient nickel hydride-catalyzed enantioselective and regioselective cross-coupling reactions. Employing AI-assisted virtual ligand screening and HTE-enabled condition optimization, we successfully identified optimal ligands for eight coupling reactions. Consequently, a series of chiral sp3 C–C bonds were synthesized with high yield and enantioselectivity.
Gao et al. (Tue,) studied this question.