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

Bobak Pezeshki, Radu Marinescu, Alexander Ihler, Rina Dechter

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, optimization, 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 algorithms. We designed an AND/OR branch-and-bound algorithm, AOBB-K*, for optimizing K* that is guided by a new K* heuristic and can incorporate specialized performance improvements with theoretical guarantees. As AOBB-K* is inspired by algorithms from the well studied task of Marginal MAP, this work provides a foundation for harnessing advancements in state-of-the-art mixed inference schemes and adapting them to protein design.