A Novel Method of Searching the Microarray Data for the Best Gene Subsets by Using a Genetic Algorithm
Searching for a small subset of genes out of the thousands of genes in Microarray is a crucial problem for accurate cancer classification. In this paper, a novel gene selection method based on genetic algorithms (GAs) is proposed. In order to reduce the search space of GAs, a novel pre-selection procedure is also introduced. To evaluate the performance of the presented method, experiments on five open datasets are conducted, and the results show that it performs rather well.
KeywordsLinear Kernel Gene Subset Gene Selection Method Quadratic Kernel Open Dataset
Unable to display preview. Download preview PDF.
- 5.Keller, A.D., Schummer, M., Hood, L., et al.: Bayesian Classification of DNA Array Expression Data, Technical Report UW-CSE-2000-08-01, Department of Computer Science & Engineering, University of Washington, Seattle (2000)Google Scholar
- 6.Ding, C., Peng, H.: Minimum Redundancy Feature Selection from Microarray Gene Expression Data. In: CSB 2003, pp. 523–529 (2003)Google Scholar
- 7.Chen, X.-w.: Gene Selection for Cancer Classification Using Bootstrapped Genetic Algorithms and Support Vector Machines. In: CSB 2003, pp. 504–505 (2003)Google Scholar
- 9.Yang, Y.H., Dudoit, S., Lin, D.M., et al.: Normalization for cDNA Microarray Data: a Robust Composite Method Addressing Single and Multiple Slide Systematic Variation. Nucleic Acids Res 10, e15.1-e15.10 (2002)Google Scholar
- 10.Krishnapuram, B., Carin, L., Hartemink, A.: Joint Classifier and Feature Optimizationi for Cancer Diagnosis Using Gene Expression Data. Journal of Computational Biology (to appear)Google Scholar