Soft Computing

, Volume 12, Issue 11, pp 1039–1048

Gene selection using hybrid particle swarm optimization and genetic algorithm

Original Paper

DOI: 10.1007/s00500-007-0272-x

Cite this article as:
Li, S., Wu, X. & Tan, M. Soft Comput (2008) 12: 1039. doi:10.1007/s00500-007-0272-x


Selecting high discriminative genes from gene expression data has become an important research. Not only can this improve the performance of cancer classification, but it can also cut down the cost of medical diagnoses when a large number of noisy, redundant genes are filtered. In this paper, a hybrid Particle Swarm Optimization (PSO) and Genetic Algorithm (GA) method is used for gene selection, and Support Vector Machine (SVM) is adopted as the classifier. The proposed approach is tested on three benchmark gene expression datasets: Leukemia, Colon and breast cancer data. Experimental results show that the proposed method can reduce the dimensionality of the dataset, and confirm the most informative gene subset and improve classification accuracy.


Gene selectionParticle swarm optimizationGenetic algorithmSupport vector machine

Copyright information

© Springer-Verlag 2007

Authors and Affiliations

  1. 1.College of Electrical and Information EngineeringHunan UniversityChangshaChina