Prediction of protein B-factors using multi-class bounded SVM

Protein Pept Lett. 2007;14(2):185-90. doi: 10.2174/092986607779816078.

Abstract

In this paper, we propose the adoption of the bounded support vector machine (BSVM) to predict the B-factors of residues based on a number of distinctive properties of residues. Due to the ability of multi-class classification of the BSVM, we can elaborately distinguish our targets and obtain relatively higher accuracy.

Publication types

  • Comparative Study
  • Research Support, Non-U.S. Gov't

MeSH terms

  • Algorithms*
  • Artificial Intelligence*
  • Computational Biology
  • Databases, Protein
  • Hydrophobic and Hydrophilic Interactions
  • Models, Molecular
  • Protein Structure, Secondary
  • Proteins / chemistry*

Substances

  • Proteins