Proc Natl Acad Sci U S A. 2022 Apr 19;119(16):e2118451119. doi: 10.1073/pnas.2118451119. Epub 2022 Apr 11.
ABSTRACT
SignificanceGiven the ubiquity of amide coupling reactions, understanding the factors which influence the success of the reaction and having means to predict the reaction rate would streamline synthetic efforts. This study outlines a data science-based workflow for effective statistical modeling with sparse experimental data. We demonstrated informed substrate selection, collection of rate data and interpretable molecular descriptors, and statistical model development for amide coupling rates. The resulting statistical models illuminate substrate features that impact rate and allow for the prediction of untested amide coupling rates.
PMID:35412905 | DOI:10.1073/pnas.2118451119
