Research Article Open Access

Low-Homology Protein Structural Class Prediction from Secondary Structure Based on Visibility and Horizontal Visibility Network

Zhi-Qin Zhao1, Liang Luo2 and Xiao-Yan Liu1
  • 1 Xi’an Shiyou University, China
  • 2 Xi’an University of Posts and Telecommunications, China

Abstract

In this study, based on the predicted secondary structures of proteins, we propose a new approach to predict protein structural classes (α,β,α/β,α+β) for three widely used low-homology data sets. Fist, we obtain two time siries from the chaos game representation of each predicted secondary structure; second, based on two time series, we construct visibility and horizontal visibility network, respectively and generate a set of features using 17 network features; finaly, we predict each protein structure class using support vector machine and Fisher’s linear discriminant algorithm, respectively. In order to evaluate our method, the leave one out cross-validating test is employed on three data sets. Results show that our approach has been provided as a effective tool for the prediction of low-homology protein structural classes.

American Journal of Biochemistry and Biotechnology
Volume 14 No. 1, 2018, 67-75

DOI: https://doi.org/10.3844/ajbbsp.2018.67.75

Submitted On: 19 January 2018 Published On: 12 March 2018

How to Cite: Zhao, Z., Luo, L. & Liu, X. (2018). Low-Homology Protein Structural Class Prediction from Secondary Structure Based on Visibility and Horizontal Visibility Network. American Journal of Biochemistry and Biotechnology, 14(1), 67-75. https://doi.org/10.3844/ajbbsp.2018.67.75

  • 5,239 Views
  • 1,593 Downloads
  • 5 Citations

Download

Keywords

  • Protein Structure Class
  • Secondary Structure
  • Chaos Game Representation
  • Visibility and Horizontal Visibility Network
  • Support Vector Machine
  • Fisher’s Linear Discriminate