An efficient unsupervised sample clustering for cancer datasets based on statistical model pre-processing

DNA microarray technology can be used to measure expression levels for thousands of genes in a single experiment across different samples. Within a gene expression matrix there are usually several particular macroscopic phenotypes of samples related to some diseases or drug effects such as diseased samples, normal samples or drug treated samples. The goal of sample-based clustering is to find the phenotype structure or substructure of the samples. In this paper, we present a new framework for unsupervised sample-based clustering using informative genes for microarray data. In our work, initial clusters are formed using k-means with fixed initial centroid and then we have used statistical method to find informative genes which are used in turn to obtain an improved clustering. The goal of our clustering approach is to perform better cluster discovery on samples with informative genes. By comparing the results of proposed method with the existing methods, it was found that the results obtained are more accurate in cancer datasets.