STA 290 Seminar: Brian Trippe

Statistics Seminar Thumbnail blue

Event Date

Location
Mathematical Sciences Building 1147

Speaker: Brian Trippe (Assistant Professor, Statistics, Stanford University)

Title: Probabilistic methods for designing functional protein structures

Abstract: The biochemical functions of proteins, such as catalyzing a chemical reaction or binding to a virus, are
typically conferred by the geometry of only a handful of atoms. This arrangement of atoms, known as a
motif, is structurally supported by the rest of the protein, referred to as a scaffold. A central task in protein
design is to identify a diverse set of stabilizing scaffolds to support a motif known or theorized to confer
function. This long-standing challenge is known as the motif-scaffolding problem.

In this talk, I describe a statistical approach I have developed to address the motif-scaffolding problem. My
approach involves (1) estimating a distribution supported on realizable protein structures and (2) sampling
scaffolds from this distribution conditioned on a motif. For step (1) I adapt diffusion generative models to
fit example protein structures from nature. For step (2) I develop sequential Monte Carlo algorithms to
sample from the conditional distributions of these models. I finally describe how, with experimental and
computational collaborators, I have generalized and scaled this approach to generate and experimentally
validate hundreds of proteins with various functional specifications.

Bio: Dr. Brian Trippe is an assistant professor at Stanford in the Department of Statistics, with an affiliation in Stanford Data Science. In his research, Dr. Trippe develops probabilistic machine learning methods to address challenges in biotechnology and medicine. Recently, his focus has been on generative modeling and inference algorithms for protein engineering. Before joining Stanford, Dr. Trippe was a postdoctoral fellow at Columbia University in the Department of Statistics, and a visiting researcher at the Institute for Protein Design at the University of Washington.

Faculty web-page (links to Stanford): https://statistics.stanford.edu/people/brian-trippe 
 

Tags