Prof. Dr. Timothy Newhouse, Department of Chemistry, Yale University, New Haven, CT, Timothy Newhouse | Department of Chemistry (yale.edu)

Computationally Augmented Total Synthesis

Efficient syntheses of complex small molecules often involve speculative experimental approaches. The central challenge of such plans is that experimental evaluation of high-risk strategies is resource intensive, as it entails iterative attempts at unsuccessful strategies. Herein, we report a complementary strategy that combines creative human-generated synthetic plans with robust computational prediction of the feasibility of key steps in the proposed synthesis.  A neural network model was trained on a literature-based dataset (from Reaxys^®) to predict the outcome of a generally disfavored transformation, the 6-endo-trig radical cyclization, and applied to synthetic planning of clovan-2,9-dione, resulting in 5-8 step syntheses of three clovane sesquiterpenoids. This work establishes how a machine learning model can guide multistep syntheses of complex small molecules. 

Organised by the Institute of Organic Chemistry