Data-driven modeling and deep learning present powerful tools that are opening up new paradigms and opportunities in the understanding, discovery, and design of soft and biological materials.
In the first part of this talk, I will describe an approach based on gentlest ascent dynamics to perform accelerated sampling of molecular free energy landscapes without any knowledge of critical points or collective variables.
Andrew Ferguson,
University of Chicago
In the second part of the talk, I will discuss our recent work on autoregressive discrete diffusion models employing physicochemical and natural language text-prompting for data-driven functional protein design within experimental machine learning-guided directed evolution campaigns.
Andrew Ferguson is a Professor and Vice Dean for Education and Outreach at the Pritzker School of Molecular Engineering and a Professor of Chemistry at the University of Chicago. His research uses theory, simulation, and machine learning to understand and design self-assembling materials, macromolecularfolding, and antiviral therapies. He is the recipient of the 2022-23 Professorial Amsterdam Center ofMultiscale Modelling (ACMM) Chair of Computational Science at the University of Amsterdam, 2020Dreyfus Foundation Award for Machine Learning in the Chemical Sciences and Engineering, 2018/19Junior Moulton Medal of the Institution of Chemical Engineers, 2016 AIChE CoMSEF Young InvestigatorAward for Modeling & Simulation, 2015 ACS OpenEye Outstanding Junior Faculty Award, and 2014 NSFCAREER Award. He is a founder of the protein engineering company Evozyne, Inc. (www.evozyne.com).