Remote Homology Detection in Proteins Using Graphical Models

TL;DR

This paper introduces two novel, computationally efficient graphical model approaches for remote homology detection in proteins based solely on amino acid sequences, significantly improving detection accuracy for beta-structural proteins.

Contribution

It presents the first tractable methods to approximate Markov random fields for all protein folds, enhancing remote homology detection accuracy.

Findings

Both methods outperform previous state-of-the-art techniques.

The approaches are computationally feasible for all protein folds.

Significant improvements in detecting remote homology in beta-structural proteins.

Abstract

Given the amino acid sequence of a protein, researchers often infer its structure and function by finding homologous, or evolutionarily-related, proteins of known structure and function. Since structure is typically more conserved than sequence over long evolutionary distances, recognizing remote protein homologs from their sequence poses a challenge. We first consider all proteins of known three-dimensional structure, and explore how they cluster according to different levels of homology. An automatic computational method reasonably approximates a human-curated hierarchical organization of proteins according to their degree of homology. Next, we return to homology prediction, based only on the one-dimensional amino acid sequence of a protein. Menke, Berger, and Cowen proposed a Markov random field model to predict remote homology for beta-structural proteins, but their formulation was computationally intractable on many beta-strand topologies. We show two different approaches to approximate this random field, both of which make it computationally tractable, for the first time, on all protein folds. One method simplifies the random field itself, while the other retains the full random field, but approximates the solution through stochastic search. Both methods achieve improvements over the state of the art in remote homology detection for beta-structural protein folds.