Due to a large number of genes and a small sample size, gene expression microarray data poses a severe challenge to the accurate classification of diseases or phenotypes. Gene selection is a frequently used technique in preprocessing microarray data for successful classification of diseases or phenotypes. Widely used gene selection methods are mainly focused on filter approaches. They have been proved to be efficient and effective. However, the researcher finds that some genes discarded by many existing methods are helpful for classification at certain conditions and cannot be removed blindly. With more and more biological information generated, the most pressing task of bioinformatics has been to analyze and interpret various types of data, including nucleotide and amino acid sequences, protein structures, gene expression profiling and so on. The researchers have applied the data mining techniques of feature generation, feature selection, and feature integration with learning algorithms to tackle the problems of disease phenotype classification and patient survival prediction from gene expression profiles, and the problems of functional site prediction from DNA sequences.