Title: Towards a scalable emulator of molecular biophysics
Abstract:
I will discuss the key challenges towards a scalable method for discovering biomolecular mechanisms and the impact of such a method on drug discovery and other fields. In this talk, I will focus on the our recent biomolecular emulator (BioEmu). BioEmu can predict the flexibility and conformational states of proteins, emulate the distributions generated by long-term molecular dynamics (MD) simulations orders of magnitude faster and predict protein stabilities consistent with experiment. I will highlight opportunities for drug discovery and discuss limitations of faithful physics representation and training data availability and how they might be overcome.
Bio:
Frank has a Bachelor degree in Electrical Engineering, a Master degree in Computer Science and a PhD from University of Heidelberg (Germany) in Computer Science and Biophysics. For 10 years he has been professor for AI for Science at Freie Universität Berlin and since 2022 he is Partner Research Manager at Microsoft Research AI for Science, leading the lab in Berlin. Frank is still honorary professor at Freie Universität Berlin and adjunct professor at Rice University Houston. Frank‘s research focuses on the development of AI methods to advance the molecular sciences, in particular addressing fundamental challenges such as the electronic structure problem in quantum Chemsitry, the many-body sampling problem in statistical Mechanics and the modeling and simulation of biomolecular structure, dynamics and function. His research was awarded with two grants of the European Research Council (ERC), Frank is an ISI highly cited fellow, a member of Berlin-Brandenburg Academy of Sciences, a fellow of the European Laboratory for Learning and Intelligent Systems (ELLIS) and a fellow of the American Physical Society (APS).
Host: Prof. Xuhui Huang
Live Stream Link: http://128.104.155.144/ClassroomStreams/chemistry1315_stream.html