Clustering Gene Expression Data with Stepwise Data Envelopment Analysis

DNA microarray technology has now made it possible to monitor the expression levels of thousands of genes simultaneously during important biological processes and across collections of related samples. Usually, gene expression matrix has several particular macroscopic phenotypes of samples. However, this matrix has few samples, and vast amounts of genes. This feature makes it difficult to classify samples correctly. A first step toward addressing this difficulty is the use of clustering techniques. In this paper considering Data Envelopment Analysis (DEA)[1], we present a new clustering algorithm for gene expression data using Stepwise DEA.