Due to the high dimensionality of microarray data, feature selection is an indispensable task in classification to identify a smaller subset of relevant genes. However, feature selection techniques that consider solely on gene expression values might not be able to identify biologically meaningful genes. Thus, this paper presents an integrative feature selection method that is able to incorporate gene expression data with additional biological data for finding informative genes. The proposed approach is a two-stage method that combined the strength of both filter method and association analysis. The experimental results show that the selected gene subsets are able to improve classification accuracy.