We’ll discuss the application and development of machine learning models to QM/MM simulations and the analysis of protein allostery. For QM/MM simulations, the discussions include the use of reinforcement learning to construct high-dimensional free energy surfaces and two distinct approaches for improving the accuracy of semi-empirical QM/MM free energy simulations by learning different aspects of how a semi-empirical QM/MM potential function differs from a high-level QM/MM model. For protein allostery, we will discuss different ways that machine learning and Bayesian interference approaches can be combined with deep mutational scanning experiments to probe the mechanism of allostery and to predict activities of mutants.

Machine learning in QM/MM simulations and the analysis of protein allostery

Where thousands of chemistry professionals meet to share ideas and advance scientific and technical knowledge. Spring 2023 abstracts, posters, and presentations will launch at the end of March.

ACS Spring 2023

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