Evolutionary biclustering of gene expression data: Shifting and scaling pattern-based evaluation

摘要

Biclustering has become a very popular data mining technique due to its ability to explore bidimensional data matrices. In the context of Bioinformatics, microarray technology offers the possibility of quantifying the expression levels of thousands of genes simultaneously, under different circumstances. This way, biclustering of expression data aim at discovering functionally related gene sets under different subsets of experimental conditions. Different heuristics have been proposed in order to discover interesting biclusters in data. Many of them are guided by a measure that determines the quality of biclusters. Thus, defining a quality measure represents a key factor in the search for biclusters. In this work we propose two different quality bicluster measures, together with a fully customizable evolutionary biclustering technique. The obtained results from real microarray experiments confirm the validity of our approaches.