Rough-Fuzzy Clustering for Grouping Functionally Similar Genes from Microarray Data

Gene expression data clustering is one of the important tasks of functional genomics as it provides a powerful tool for studying functional relationships of genes in a biological process. Identifying co-expressed groups of genes represents the basic challenge in gene clustering problem. In this regard, a gene clustering algorithm, termed as rough-fuzzy c-means, is proposed judiciously integrating the merits of rough sets and fuzzy sets. While the concept of lower and upper approximations of rough sets deals with uncertainty, vagueness, and incompleteness in cluster definition, the integration of probabilistic and possibilistic memberships of fuzzy sets enables efficient handling of overlapping partitions in noisy environment. The concept of possibilistic lower bound and probabilistic boundary of a cluster, introduced in rough-fuzzy c-means, enables efficient selection of gene clusters. An efficient method is proposed to select initial prototypes of different gene clusters, which enables the proposed c-means algorithm to converge to an optimum or near optimum solutions and helps to discover co-expressed gene clusters. The effectiveness of the algorithm, along with a comparison with other algorithms, is demonstrated both qualitatively and quantitatively on fourteen yeast microarray data sets.