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

Journal: Analytical biochemistry
Published Date: Nov 6, 2020

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.

Authors

  • Yichen Guo
    School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China. Electronic address: ycguo@bliulab.net.
  • Ke Yan
    Department of Biostatistics, Medical College of Wisconsin, Milwaukee, Wis.
  • Hao Wu
    Zhejiang Institute of Tianjin University (Shaoxing), Shaoxing, China.
  • Bin Liu
    Department of Endocrinology, the First Affiliated Hospital of Chongqing Medical University, Chongqing, China; Department of Endocrinology, Neijiang First People's Hospital, Chongqing, China.

Keywords

External Resources

Popular Topics
Recent Journals