Study On Clustering Techniques And Application To Microarray Gene Expression Bioinformatics Data

With the explosive growth of the amount of publicly available genomic data, a new field of computer science i.e., bioinformatics has been emerged, focusing on the use of computing systems for efficiently deriving, storing, and analyzing the character strings of genome to help to solve problems in molecular biology. The flood of data from biology, mainly in the form of DNA, RNA and Protein sequences, puts heavy demand on computers and computational scientists. At the same time, it demands a transformation of basic ethos of biological sciences. Hence, Data mining techniques can be used efficiently to explore hidden pattern underlying in biological data. Un-supervised classification, also known as Clustering; which is one of the branch of Data Mining can be applied to biological data and this can result in a better era of rapid medical development and drug discovery. In the past decade, the advent of efficient genome sequencing tools have led to enormous progress in life sciences. Among the most important innovations, microarray technology allows to quantify the expression for thousand of genes simultaneously. The characteristic of these data which makes it different from machine-learning/pattern recognition data includes, a fair amount of random noise, missing values, a dimension in the range of thousands, and a sample size in few dozens. A particular application of the microarray technology is in the area of cancer research, where the goal is for precise and early detection of tumorous cells with high accuracy. The challenge for a biologist and computer scientist is to provide solution based on terms of automation, quality and efficiency.