A Molecular Stereostructure Descriptor Based On Spherical Projection

Description of molecular stereostructure is critical for the machine learning prediction of asymmetric catalysis. Herein we report a spherical projection descriptor of molecular stereostructure (SPMS), which allows precise representation of the molecular van der Waals (vdW) surface. The key features of SPMS descriptor are presented using the examples of chiral phosphoric acid, and the machine learning application is demonstrated in Denmark's dataset of asymmetric thiol addition to N-acylimines. In addition, SPMS descriptor also offers a color-coded diagram that provides straightforward chemical interpretation of the steric environment.

Automated summary

The description of molecular stereostructure is crucial for the machine learning prediction of asymmetric catalysis. A spherical projection descriptor of molecular stereostructure (SPMS) is introduced to accurately represent the molecular van der Waals surface, demonstrated using chiral phosphoric acid as an example and applied in the asymmetric thiol addition to N-acylimines dataset from Denmark. Additionally, SPMS descriptor features a color-coded diagram for easy chemical interpretation of the steric environment.