Improving protein threading accuracy via combining local and global potential using TreeCRF model

TL;DR

This paper introduces a TreeCRF model that combines local and global potentials to improve the accuracy of protein threading, a key method in template-based protein structure prediction.

Contribution

The paper proposes a novel TreeCRF-based approach that enhances protein threading accuracy by integrating local and global structural potentials.

Findings

Improved threading accuracy demonstrated on benchmark datasets.

Enhanced detection of remote homology.

Effective integration of local and global potentials in TreeCRF.

Abstract

Protein structure prediction remains to be an open problem in bioinformatics. There are two main categories of methods for protein structure prediction: Free Modeling (FM) and Template Based Modeling (TBM). Protein threading, belonging to the category of template based modeling, identifies the most likely fold with the target by making a sequence-structure alignment between target protein and template protein. Though protein threading has been shown to more be successful for protein structure prediction, it performs poorly for remote homology detection.