02 JUNE 2021 | 11AM (EDT) / 5PM (CEST)
Machine learning and statistical inference techniques to describe intrinsically disordered protein ensembles
We present our recent work in building ML/AI approaches to describe conformational transitions within intrinsically disordered protein ensembles (IDPs). IDPs challenge the traditional protein structure–function paradigm by adapting their conformations in response to specific binding partners leading them to mediate diverse, and often complex cellular functions such as biological signaling, self-organization and compartmentalization. Obtaining mechanistic insights into their function can therefore be challenging for traditional structural determination techniques. Often, scientists have to rely on piecemeal evidence drawn from diverse experimental techniques to characterize their functional mechanisms. Multi-scale simulations can help bridge critical knowledge gaps about IDP structure-function relationships — however, these techniques also face challenges in resolving emergent phenomena within IDP conformational ensembles. We posit that ML/AI techniques can effectively integrate information gleaned from multiple experimental techniques as well as from simulations in obtaining quantitative insights into complex/ emergent phenomena within these biological systems. We highlight three different aspects of ML/AI approaches: (1) in building biophysically meaningful collective variables that describe conformational transitions in IDP ensembles; (2) using AI-driven approaches to sample rare conformational fluctuations in IDP conformational landscapes; and (3) integrating small angle scattering and nuclear magnetic resonance experiments to probe conformational states accessed and to refine force-field parameters based on their collective descriptions. Together, our approaches highlight how ML/AI could be an integrated aspect for probing IDP-mediated biological phenomena.
Arvind Ramanathan is a computational biologist in the Data Science and Learning Division at Argonne National Laboratory and a senior scientist at the University of Chicago Consortium for Advanced Science and Engineering (CASE). His research interests are at the intersection of data science, high performance computing and biological/biomedical sciences. His research focuses on developing principled and scalable statistical inference techniques for analysis and development of adaptive multi-scale molecular simulations for studying complex biological phenomena (such as how intrinsically disordered proteins self assemble, or how small molecules modulate disordered protein ensembles). He obtained his Ph.D. in computational biology from Carnegie Mellon University, and was the team lead for integrative systems biology team within the Computational Science, Engineering and Division at Oak Ridge National Laboratory. More information about his group and research interests can be found at here.