Abstract: In microarray data analyses, three important issues are how to determine incomplete data, how to choose genes, which provide reliable and good prediction for disease status, and how to determine the final gene set that is best for classification. To deal with redundant information and improve classification, propose a Mean Weight Artificial Bee Colony (MWABC) gene selection which combines ABC and mean weight function. First select a small subset of genes based on fuzzy and mean value of the attribute by considering the preference-ordered domains of the gene expression data. Propose an MWABC analysis to select discriminative genes and to use these genes to classify tissue samples of microarray data. Experiments show that the proposed MWABC is able to reach high classification accuracies with a small number of selected genes and its performance is robust to noise.

Keywords: : Gene selection, microarray, classification, supervised-learning, Mean Weight Artificial Bee Colony (MWABC)