High-throughput experimentation (HTE) has enabled the rapid exploration of large expanses of chemical reaction space to accelerate key synthetic steps in pharmaceutical development. However, the dimensionality of reaction parameters, desire to use minimal starting material, and need to thoroughly analyze reaction outcomes still requires the judicious selection of which experiments to perform. To satisfy these challenges, we have quantified phosphine ligand diversity with computational featurization and applied multivariate linear regression modeling to analyze reaction outcomes holistically. We describe our process to establish a computational featurization platform for phosphine ligands used in Pd-catalyzed cross-coupling reactions at GSK. We also demonstrate that the choice of computational method has implications for phosphine feature values, ligand selection for HTE, and the development of linear regression models of reaction outcomes.

HTE in 3D: Implication of phosphine featurization methods on HTE design and analysis of reaction outcomes

ACS Spring Meeting 2021

The official archive and repository for all ACS Meetings & Expositions abstracts and select posters or presentations.