Skip Navigation

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.

NLM Colloquia: Integrating Generative AI with Statistical Mechanics for Predicting Biomolecular Structure and Properties Across Temperature, Pressure, Chemical Potentials

Air date: Wednesday, January 29, 2025, 11:00:00 AM
Time displayed is Eastern Time, Washington DC Local
iCalendar: Add event to iCalendar Add an upcoming event to your calendar.
Description: The National Library of Medicine (NLM) Division of Intramural Research (DIR) is pleased to welcome Pratyush Tiwary, PhD, the Millard and Lee Alexander Professor at the University of Maryland, College Park for his lecture entitled, "Integrating Generative AI with Statistical Mechanics for Predicting Biomolecular Structure and Properties Across Temperature, Pressure, Chemical Potentials". Structure prediction tools using Generative Artificial Intelligence (AI) have significantly advanced, offering rapid predictions of the most stable structure for generic proteins/RNA and even generating ensembles with dynamics. This might suggest that molecular dynamics (MD) and statistical mechanics are now maybe obsolete. However, I will demonstrate why these methods remain critical for ensuring AI approaches are both predictive and reliable for biophysics. I'll discuss how current AI predictions can sometimes result from memorization or hallucination and show how integrating Generative AI with enhanced MD and statistical mechanics provides a more predictive, though slower, alternative to using AI alone. Examples will include kinases and RNA, revealing thermodynamic and dynamic properties such as drug residence times, conformational populations, mutation effects, and melting curves derived from chemical identity and force fields. Lastly, I’ll illustrate how these integrated methods enable predictions of biomolecular properties under thermodynamic conditions far from training data, including temperature, pressure, and chemical potential. Questions during the presentation can be sent to NLMColloquia@nih.gov.


For more information go to https://www.nlm.nih.gov/research/lectures.html
Author: Pratyush Tiwary, PhD
Runtime: 1 hour