Radical C-H functionalization provides a useful strategy to elaborate heteroarenes. The success of this transformation relies on the control and prediction of regioselectivty. In this talk, we will discuss a machine learning strategy that allows the quantified and efficient approach for regioselectivity prediction. The usage of physical orgnaic descriptors and random forest model achieved satisfying performance in the out-of-sample test set. This strategy in principle can serve for the machine learning-prediction of chemo- and regioselectivities of a wide array of organic transformations.

Regioselectivity prediction of radical C-H functionalization of heteroarenes through machine learning and physical orgnaic descriptors

ACS Spring Meeting 2021

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