Selection for feature gene subset in microarray expression profiles based on an improved genetic algorithm

  • Authors:

  • Chen Zhang;Yanchun Liang;Wei Xiong;Hongwei Ge

  • Affiliations:

  • College of Computer Science and Technology, Jilin University, Key Laboratory of Symbol Computation and Knowledge Engineering of, Ministry of Education, Changchun, China;College of Computer Science and Technology, Jilin University, Key Laboratory of Symbol Computation and Knowledge Engineering of, Ministry of Education, Changchun, China;College of Computer Science and Technology, Jilin University, Key Laboratory of Symbol Computation and Knowledge Engineering of, Ministry of Education, Changchun, China;College of Computer Science and Technology, Jilin University, Key Laboratory of Symbol Computation and Knowledge Engineering of, Ministry of Education, Changchun, China

  • Venue:
  • AI'06 Proceedings of the 19th Australian joint conference on Artificial Intelligence: advances in Artificial Intelligence
  • Year:
  • 2006

Quantified Score

Hi-index 0.00

Visualization

Abstract

It is an important subject to extract feature genes from microarray expression profiles in the study of computational biology. Based on an improved genetic algorithm (IGA), a feature selection method is proposed in this paper to find a feature gene subset so that the genes related to diseases could be kept and the redundant genes could be eliminated more effectively. In the proposed method, the information entropy is used as a separate criterion, and the crossover and mutation operators in the genetic algorithm are improved to control the number of the feature genes in the subset. After analyzing the microarray expression data, the artificial neural network (ANN) is used to evaluate the feature gene subsets obtained in different parameter conditions. Simulation results show that the proposed method can be used to find the optimal or quasi-optimal feature gene subset with more useful and less redundant information.