Events

CS Colloquium: Euclidean Deep Learning Models for 3D Structures and Interactions of Molecules

Speaker: Octavian Ganea

Location: 60 Fifth Avenue, Room 150
Videoconference link: https://nyu.zoom.us/j/92168854992

Date: Monday, March 21, 2022

Understanding the 3D structures and interactions of proteins and
drug-like molecules is a key part of therapeutics discovery. A core
problem is molecular docking, i.e., determining how two molecules attach
and create a molecular complex. Having access to very fast accurate
computational docking tools would enable applications such as virtual
screening of cancer protein inhibitors, de novo drug design, or rapid in
silico drug side-effect prediction. However, existing computer models
are insufficient, being very time-consuming and having difficulties
exploring the vast space of molecular complex candidates. In this talk,
I will show that geometry and deep learning (DL) can significantly
reduce this enormous search space inherent in docking and molecular
conformation prediction. I will present EquiDock and EquiBind, my recent
DL architectures for direct shot prediction of the molecular complex,
and GeoMol, a model for 3D molecular flexibility. I will argue that the
governing laws of geometry, physics, or chemistry that naturally
constrain these 3D structures should be incorporated in DL solutions in
a mathematically meaningful way. This will be exemplified by leveraging
key modeling concepts such as SE(3)-equivariant graph matching networks,
optimal transport for binding pocket prediction, and torsion angle
neural networks. My approaches reduce the inference runtimes of
open-source and commercial software by factors of tens or hundreds,
while being competitive or better in terms of quality. Finally, I will
highlight a number of exciting on-going and future efforts in the space
of artificial intelligence for structural biology and chemistry.