A Dirichlet process mixture of hidden Markov models for protein structure prediction

TL;DR

This paper introduces a novel semiparametric Dirichlet process mixture model for joint torsion angle distributions in proteins, enabling improved structure prediction especially in variable loop and turn regions.

Contribution

It develops a new model that handles sparse, multi-position angle data, enhancing protein structure prediction accuracy in challenging regions.

Findings

Successfully predicts torsion angles in globin loops.

Extends template-based methods to difficult loop regions.

Demonstrates improved modeling of sparse, multi-position data.

Abstract

By providing new insights into the distribution of a protein's torsion angles, recent statistical models for this data have pointed the way to more efficient methods for protein structure prediction. Most current approaches have concentrated on bivariate models at a single sequence position. There is, however, considerable value in simultaneously modeling angle pairs at multiple sequence positions in a protein. One area of application for such models is in structure prediction for the highly variable loop and turn regions. Such modeling is difficult due to the fact that the number of known protein structures available to estimate these torsion angle distributions is typically small. Furthermore, the data is "sparse" in that not all proteins have angle pairs at each sequence position. We propose a new semiparametric model for the joint distributions of angle pairs at multiple sequence positions. Our model accommodates sparse data by leveraging known information about the behavior of protein secondary structure. We demonstrate our technique by predicting the torsion angles in a loop from the globin fold family. Our results show that a template-based approach can now be successfully extended to modeling the notoriously difficult loop and turn regions.