Finding regularity in protein secondary structures using a cluster-based genetic algorithm

  • Authors:
  • Yen-Wei Chu;Chuen-Tsai Sun;Chung-Yuan Huang

  • Affiliations:
  • Department of Information Management, Yuanpei Institute of Science and Technology, Hsinchu, Taiwan, ROC and Department of Computer Science, National Chiao Tung University, Hsinchu, Taiwan, ROC;Department of Computer Science, National Chiao Tung University, Hsinchu, Taiwan, ROC;Department of Computer Science and Information Engineering, Yuanpei Institute of Science and Technology, Hsinchu, Taiwan, ROC and Department of Computer Science, National Chiao Tung University, Hs ...

  • Venue:
  • CIMMACS'05 Proceedings of the 4th WSEAS international conference on Computational intelligence, man-machine systems and cybernetics
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

Secondary structures help in the identification of biological features such as protein classification, protein structure and function, and evolutionary relationships between proteins. However, secondary protein structures are sometimes hard to identify from experimental analysis, therefore researchers are forced to rely on predictive information. In this paper we offer an evolutionary computation approach that combines clustering and genetic algorithms to produce schemata for the visual representations of protein secondary structures. The two major roles of a clustering algorithm are to a) generate parts of initial chromosomes in genetic algorithms and b) assist schemata in predicting secondary protein structures. According to our tests, the new approach improves Q3 accuracy by 12% compared to previous efforts. We also discuss some examples of schemata with interesting biological meaning.