Guiding belief propagation using domain knowledge for protein-structure determination

Abstract

A major bottleneck in high-throughput protein crystallography is producing protein-structure models from an electron-density map. In previous work, we developed Acmi, a probabilistic framework for sampling all-atom protein-structure models. Acmi uses a fully connected, pairwise Markov random field to model the 3D location of each non-hydrogen atom in a protein. Since exact inference in this model is intractable, Acmi uses loopy belief propagation (BP) to calculate marginal probability distributions. In cases of approximation, BP's message-passing protocol becomes a crucial design decision. Previously, Acmi took a naive, round-robin protocol to sequentially process messages. Others have proposed informed methods for message scheduling by ranking messages based on the amount of new information they contain. These information-theoretic measures, however, fail in the highly connected, large output space domain of protein-structure inference. In this work, we develop a framework for using domain knowledge as a criterion for prioritizing messages in BP. Specifically, we show that using predictions of protein-disorder regions effectively guides BP in our task. Our results show that guiding BP using protein-disorder prediction improves the accuracy of marginal probability distributions and also produces more accurate, complete protein-structure models.