Room 209 Havemeyer, 3000 Broadway, New York, NY 10027
Can artificial intelligence help understand and predict chemical dynamics
Presented by Pratyush Tiwary, University of Maryland
The ability to rapidly learn from high-dimensional data to make reliable predictions about the future is crucial in many contexts. This could be a fly avoiding predators, or the retina processing terabytes of data guiding complex human actions. Modern day artificial intelligence (AI) aims to mimic this fidelity and has been successful in many domains of life. It is tempting to ask if AI could also be used to understand and predict the emergent mechanisms of complex molecules with millions of atoms. In this colloquium I will show that certain flavors of AI can indeed help us understand generic molecular and chemical dynamics and also predict it even in situations with arbitrary long memories. However this requires close integration of AI with old and new ideas in statistical mechanics. I will talk about such methods developed by my group using different flavors of generative AI such as information bottleneck, recurrent neural networks and denoising diffusion probabilistic models. I will demonstrate the methods on different problems, where we predict mechanisms at timescales much longer than milliseconds while keeping all-atom/femtosecond resolution. These include ligand dissociation from flexible protein/RNA and crystal nucleation with competing polymorphs. I will conclude with an outlook for future challenges and opportunities.
Pratyush Tiwary is an Assistant Professor at the University of Maryland, College Park, jointly appointed in the Department of Chemistry & Biochemistry and the Institute for Physical Science & Technology. His lab studies rare events in biology, chemistry and materials science by developing computational tools that integrate statistical mechanics with artificial intelligence. He received his undergraduate degree in Metallurgical Engineering from IIT-Varanasi and PhD in Materials Science from Caltech working with Axel van de Walle. He then did two postdocs at ETH and Columbia University working with Michele Parrinello and Bruce Berne respectively. He is the recipient of NSF CAREER award, NIH Maximizing Investigators’ Research Award (MIRA), ACS OpenEye Outstanding Junior Faculty Award and ACS PRF Doctoral New Investigator Award.