AND/OR Branch-and-Bound for Computational Protein Design Optimizing K*Download PDF

13 Jun 2022, 06:01 (modified: 02 Sept 2022, 01:35)TPM 2022Readers: Everyone
Keywords: graphical models, protein design, constraint satisfaction, computational protein design, AND/OR search, bucket elimination, mini-bucket elimination, weighted mini-bucket elimination, heuristic search, marginal MAP, branch-and-bound, cpd, computational biology
TL;DR: This work presents a new graphical model framework for computational protein design optimizing the K* objective along with a new depth-first branch-and-bound algorithm over AND/OR search spaces guided by a new related weighted mini-bucket heuristic.
Abstract: The importance of designing proteins, such as high affinity antibodies, has become ever more apparent. Computational Protein Design can cast such design problems as optimization tasks with the objective of maximizing K*, an approximation of binding affinity. Here we lay out a graphical model framework for K* optimization that enables use of compact AND/OR search spaces. We introduce two distinct graphical model formulations, a new K* heuristic, AOBB-K* - an efficient depth-first branch-and-bound algorithm, and modifications that improve performance with theoretical guarantees. As AOBB-K* is inspired by algorithms from the well studied task of Marginal MAP, this work provides a foundation for adaptation of state-of-the-art mixed inference schemes to protein design.
1 Reply

Loading