Boosting AND/OR-Based Computational Protein Design: Dynamic Heuristics and Generalizable UFO

TL;DR

This paper introduces three enhanced algorithms for protein re-design that significantly improve the scalability of existing AND/OR-based methods, leveraging dynamic heuristics, boosting techniques, and underflow optimization.

Contribution

The authors develop and evaluate three new versions of the AOBB-K* algorithm, improving its scalability for larger protein re-design problems.

Findings

AOBB-K*-b outperforms previous methods in scalability.

AOBB-K*-DH effectively incorporates dynamic heuristics.

AOBB-K*-UFO reduces computational underflow issues.

Abstract

Scientific computing has experienced a surge empowered by advancements in technologies such as neural networks. However, certain important tasks are less amenable to these technologies, benefiting from innovations to traditional inference schemes. One such task is protein re-design. Recently a new re-design algorithm, AOBB-K*, was introduced and was competitive with state-of-the-art BBK* on small protein re-design problems. However, AOBB-K* did not scale well. In this work we focus on scaling up AOBB-K* and introduce three new versions: AOBB-K*-b (boosted), AOBB-K*-DH (with dynamic heuristics), and AOBB-K*-UFO (with underflow optimization) that significantly enhance scalability.