Machine-learning-assisted development of a fast mechanochemical reaction

Summary

Herein, we combine Bayesian Optimization and mechanochemistry to develop a rapid, solvent-free protocol for the Johnson–Corey–Chaykovsky (JCC) cyclopropanation and epoxidation. By prioritizing efficiency and sustainability, Machine Learning quickly identified a new set of reaction conditions for this venerable reaction that diverge from established paradigms (explosive NaH/DMSO system), revealing that these transformations can proceed efficiently under air-equilibrated, mild conditions using an inexpensive and safe base (KOH). The method is broadly applicable, scalable, and tolerant to diverse functional groups and enabled the preparation of a wide variety of three-membered homo- and heterocycles. Overall, this work pioneers the synergy between Machine Learning and mechanochemistry to design industrially relevant transformations that prioritize safety and sustainability.