Gene selection from microarray data is an important issue for gene expression based classification and to carry out a diagnostic test. In this regard, a rough set based gene selection algorithm is presented. It selects the set of genes by maximizing the relevance and significance of the genes, which are calculated based on the theory of rough sets. Using the predictive accuracy of K-nearest neighbor rule and support vector machine, the performance of the proposed algorithm, along with a comparison with other related methods is studied on five cancer and two arthritis microarray data sets. Promising performance was achieved by the proposed gene selection algorithm with relevant and significant genes from microarray data set in a reasonable time. © 2010 IEEE.