Multi‐Threshold Analysis for Chemical Space Mapping of Ni‐Catalyzed Suzuki‐Miyaura Couplings

Abstract

AbstractA key challenge in synthetic chemistry is the selection of high‐performing ligands for cross‐coupling reactions. To address this challenge, this work presents a classification workflow to identify physicochemical descriptors that bin monophosphine ligands as active or inactive in Ni‐catalyzed Suzuki‐Miyaura coupling reactions. Using five previously published high‐throughput experimentation datasets for training, we found that a binary classifier using a phosphine's minimum buried volume and Boltzmann‐averaged minimum electrostatic potential is most effective at distinguishing high and low‐yielding ligands. Experimental validations are also presented. Using the two physicochemical descriptors from the binary classifier to represent the chemical space of monophosphine ligands leads to a more predictive guide for structure‐reactivity relationships compared with classic chemical space representations.