Upcoming Event: Oden Institute & Dept. of Molecular Biosciences

System-Level Understanding of Disease at Atomic Resolution Using Physics-Aware Deep Learning

Dima Kozakov, Professor, Stony Brook University

Abstract

Understanding cellular processes at atomic resolution is  the current frontier in molecular systems biology. Resolving these processes will enable the elucidation of life’s mechanisms, disease progression, and therapeutic development. This progress relies on two major factors: the exponential growth of data on molecular sequences, structures, and interactions through high-throughput experimental techniques, and the development and application of physics-informed machine learning approaches to harness this vast body of knowledge.In this work, I present novel physics- and geometry-informed deep learning architectures for modeling various classes of macromolecular interactions. I discuss their applications to therapeutic design and systems-level biological challenges, including the systematic exploration of differential protein interactions in diseases, large-scale mapping of native protein-metabolite interactions in E. coli, and the design of new therapeutic modalities such as PROTACs

Biography

Dima Kozakov received an MS in Applied Mathematics and Physics at the Moscow Institute of Physics and Technology, and PhD in Biomedical Engineering at Boston University. Currently he is the Professor in the Department of Applied Mathematics, Laufer Center for Physical and Quantitative Biology, and Institute of Advance Computational Sciences at Stony Brook University. Dr. Kozakov is applying approaches from machine learning and physics to understand and model biological macromolecules, with emphasis on molecular interactions and drug design, and its application to understanding mechanisms of life and disease processes. Methods developed by Dr. Kozakov are heavily used in the pharmaceutical industry and are consistently top-performing in blind molecular modeling completions.