Determining genes by clustering algorithms in information technology

Abstract

A common problem in biology is to divide a set of experimental data into clusters (groups) in such a way that the data points in each cluster are highly similar, while the data points in different clusters are different. There are several algorithms that performs different types of clustering; each situation has its own best way of clustering and there is no common best choice in a general situation. Clustering algorithms group genes with similar expression patterns into clusters with the hope that the genes in each cluster has a common function. It, therefore, helps us to determine the new genes based on the information of already known genes. Biologists will determine the most  reasonable choice of clustering.