Abstract

Microarray technology is capable of providing biomedical and biological researchers with a massive amount of gene expression information to enable rapid significant discoveries in life sciences. Microarray data analysis has been developing at a fast pace during the last decade and has become a popular and standard research method for gene expression studies undertaken by genomics research groups worldwide. Many computational tools have been applied to mine this data in order to discover biologically meaningful knowledge. One of the most useful analysis tools is the fuzzy clustering approach which can be modeled in many types of the continuous partitions of data and are well known for its ability to identify co-expressed genes and annotate functions for novel genes. As the computational analysis of microarray data has been developing rapidly, articles surveying its progress of research and developments are periodically needed. In this paper, we review the recent research into microarray data analysis based on fuzzy clustering algorithms and present a newly developed fuzzy clustering technique which, potentially, can be applied to perform microarray data analysis.

Keywords: Microarray data analysis, fuzzy clustering, fuzzy C-means, fuzzy hyper-prototype clustering, Gene-based clustering, Sample-based clustering, Biclustering, Gene Regulatory Network