A Survey on Feature Selection Methods in Microarray Gene Expression Data for Cancer Classification

Microarray technology is commonly used in the study of disease diagnosis using gene expression levels. It not only received the attention of the research community but also has a wide range of applications. The success of microarray technology depends on the precision of measurement, the usage of tools in data mining, analytical methods and statistical modeling. The feature selection methods are used to find an informative representation, by removing noisy and irrelevant features which would improve the classification performance. There exist several works in the literature to select the significant features from the microarray. This paper reviews the feature selection methods used to select significant genes from the microarray gene expression data for cancer classification.