Microarray sample clustering using independent component analysis

DNA microarray technology has been used to measure expression levels for thousands of genes in a single experiment, across different samples. These samples can be clustered into homogeneous groups corresponding to some particular macroscopic phenotypes. In sample clustering problems, it is common to come up against the challenges of high dimensional data due to small sample volume and high feature (gene) dimensionality. Therefore, it is necessary to conduct dimension reduction on the gene dimension and identify informative genes prior to the clustering on the samples. This paper introduces a method for informative genes selection by utilizing independent component analysis (ICA). The performance of the proposed method on various microarray datasets is reported to illustrate its effectiveness.