Gene selection for DNA microarray data

Abstract

One problem with discriminant analysis of DNA microarray data is that each sample is represented by quite a large number of genes, and many of them are irrelevant, insignificant or redundant to the discriminant problem under investigation. Methods for selecting important genes are, therefore, of much significance in microarray data analysis. Gene selection can be cast as a feature selection problem in the context of pattern classification. Feature selection approaches can be divided into two broad groups, filter methods and wrapper methods. Generally speaking, the wrapper method provides features with better predictive accuracy than the filter method. In this thesis, wrapper-based gene selection is the focus.