Project Grant 2152521

The National Science Foundation Division of Chemistry awarded a $387,874 Project Grant to the University of Chicago to develop new theoretical and computational tools for efficiently estimating long-time molecular thermodynamics and kinetics. Under the Mathematical and Physical Sciences (CFDA 47.049) federal grant program, Andrew Ferguson of the University of Chicago will establish novel simulation approaches enabled by machine learning and new mathematical theorems to simulate biomolecules millions of times faster than currently possible. Specifically, Ferguson will develop the theoretical and algorithmic foundations of an approach known as Latent Space Simulators to generate ultra-long atomistic molecular simulation trajectories of biomolecules that are continuous in space and time. This approach is trained on short, discontinuous simulation data and then produces continuous all-atom simulation trajectories obeying correct structural, thermodynamic, and kinetic statistics at significantly lower computational cost than conventional molecular dynamics. The grant began April 1, 2022 and ends March 31, 2025.