A review on biclustering of gene expression microarray data: algorithms, effective measures and validations

Analysis of gene expression microarray data interprets the actual expression data for revealing relevant information regarding genes, proteins, diseases etc. DNA microarrays promote the contemporary assessment of gene expression levels and are often meaningful in the study of gene co-regulation, gene function identification, pathway identification, gene regulatory networks etc. Popular microarray data mining techniques such as classification, clustering, biclustering, and association analysis rely on various statistical methods and machine learning algorithms. Many of these techniques are unable to contribute a significant amount of biological knowledge as they are completely data-driven in nature. Therefore, several types of validations are further needed to validate the output. Furthermore, like other data mining techniques, selecting a proper evaluation measure is another challenge. This review article presents a brief idea about these three aspects, i.e. biclustering algorithms, their relevant evaluation measures and different types of validations applied upon biclustering of gene expression microarray data.