Toward data-science-guided prediction of enantiomeric excess in amines—A workflow method

Abstract

Potential bottlenecks in high-throughput determination of enantiomeric excess in chiral primary amines is being addressed, by Howard et al. in this issue of Chem, by developing a data-driven methodology that replaces extensive calibration measurements and the corresponding calibration curves through a combination of machine learning methods and computations that produces a theoretical model and predicted calibration curves.