Non-Negative Factorization for Clustering of Microarray Data

Typically, gene expression data are formed by thousands of genes associated to tens or hundreds of samples. Gene expression data comprise relevant (discriminant) information as well as irrelevant information often interpreted as noise. The irrelevant information usually affects the efficiency of discovering and grouping meaningful latent information correlated to biological significance, process closely related to data clustering. Class discovery through clustering may help in identifying latent features that reflect molecular signatures, ultimately leading to class forming. One solution for improving the class discovery efficiency is provided by data dimensionality reduction, where data is decomposed into lower dimensional factors, so that those factors approximate original data.