ReFold-MAP: Protein remote homology detection and fold recognition based on features extracted from profiles

Abstract

Protein remote homology detection and protein fold recognition are two important tasks in protein structure and function prediction. There are three kinds of methods in this field, including the discriminative methods, the alignment methods, and the ranking methods. In this study, a new discriminative method called ReFold-MAP is proposed. The proposed method extracts comprehensive features based on three profile-based features: Motif-PSSM, ACC-PSSM, and PDT-profile. We call these features as MAP features, which incorporate the structural motif kernel information, the evolutionary information, and the sequence information. The experiments prove that ReFold-MAP outperforms other approaches. Therefore, ReFold-MAP will be a useful tool for protein remote homology detection and fold recognition.