Predicting the Stereoselectivity of Chemical Transformations by Machine Learning
This addresses the challenge of predicting stereoselectivity for chemical and enzymatic reactions, which is crucial for fields like medicine and industrial catalysis, though it appears incremental relative to prior work.
The authors tackled the problem of quantitatively predicting stereoselectivity in chemical reactions, which is difficult due to small energetic differences and qualitative understanding. Their novel machine learning technique combining LASSO, Random Forest, and Gaussian Mixture models significantly outperformed a recent groundbreaking approach on a published dataset.
Stereoselective reactions (both chemical and enzymatic reactions) have been essential for origin of life, evolution, human biology and medicine. Since late 1960s, there have been numerous successes in the exciting new frontier of asymmetric catalysis. However, most industrial and academic asymmetric catalysis nowadays do follow the trial-and-error model, since the energetic difference for success or failure in asymmetric catalysis is incredibly small. Our current understanding about stereoselective reactions is mostly qualitative that stereoselectivity arises from differences in steric effects and electronic effects in multiple competing mechanistic pathways. Quantitatively understanding and modulating the stereoselectivity of for a given chemical reaction still remains extremely difficult. As a proof of principle, we herein present a novel machine learning technique, which combines a LASSO model and two Random Forest model via two Gaussian Mixture models, for quantitatively predicting stereoselectivity of chemical reactions. Compared to the recent ground-breaking approach [1], our approach is able to capture interactions between features and exploit complex data distributions, which are important for predicting stereoselectivity. Experimental results on a recently published dataset demonstrate that our approach significantly outperform [1]. The insight obtained from our results provide a solid foundation for further exploration of other synthetically valuable yet mechanistically intriguing stereoselective reactions.