Scalable Sequential Rough Parallel Bounded Symmetrical Clustering for Gene Expression Profile Analysis

The study on gene expression profiling of tissues and cells has become a major tool for discovery in medicine. Identification of co-expressed genes and coherent patterns is the central goal in gene expression profiling and the important task in the field of bioinformatics research. Clustering is an important unsupervised learning technique for Gene Expression Profile Analysis. Many conventional clustering algorithms have been adapted or directly applied to gene expression data. Among them, Rough Point Symmetry (RoughPsym) and Rough Symmetry (Roughsym) based clustering is applied for recognizing symmetrical patterns of gene expression profiles. Rough-set theory helps in faster convergence and initial automatic optimal classification, thereby solving the problem of unknown knowledge of number of clusters in microarray data. In case of RoughPsym and Roughsym methods, efficiency or higher accuracy is not achieved because of the larger dataset samples. To solve this problem and to further enhance the clustering and thereby enabling the clustering results of large microarray data, in this article, a distributed time-efficient scalable Sequential Rough Parallel Bounded Symmetrical clustering (SeqRoughPBSym) is applied to rough set based approach.