Past talk · AI/ML Seminar Series
AND/OR Branch-and-Bound for Computational Protein Design Optimizing K*
PhD Student, Department of Computer Science, University of California, Irvine
- Date & time
- Monday, June 6, 2022 · 1:00 PM
- Location
- Donald Bren Hall 4011
Abstract
Computational protein design (CPD) is the task of creating new proteins to fulfill a desired function. In this talk, I share work accepted at UAI 2022 based on a new formulation of CPD as a graphical model designed for optimizing subunit binding affinity (approximated by a quantity called K*). I relate this to the task of MMAP, present the formulation of the problem as a graphical model, and introduce a weighted mini-bucket heuristic for bounding K* and guiding search. Finally, I share our algorithm AOBB-K* and modifications that enhance it, describing its empirical benefits and limitations.
About the speaker
Bobak Pezeshki is a fifth-year PhD student of Computer Science at UC Irvine, advised by Professor Rina Dechter. His research focuses on automated reasoning over graphical models, with an emphasis on Abstraction Sampling and applications to computational protein design. He completed his undergraduate studies at UC Berkeley.