Quantum mechanical models of chemical reactivity provide detailed insights into organic mechanism and selectivity, although these calculations come at a relatively high cost, making predictive applications challenging. The use of statistical and machine learning models offers advantages in terms of speed and efficiency, although accessing the right amount and quality of chemical data has hindered widespread adoption. Here I describe our efforts to bridge this gap through the curation of large quantum chemistry datasets relevant to the stability and reactivity of organic molecules, which are then used to train high-quality machine learning models that can be deployed very quickly. Applications to the prediction of site-selectivity of C-H oxidations and the design of new stable radical structures will be discussed.

Predictions of organic reactivity & selectivity enabled by QM datasets and machine learning models

Fall 2022 abstracts, posters, and presentations will launch in mid-September.

ACS Fall 2022

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