Many data mining techniques have been proposed for mining useful patterns in text documents. However, how to effectively use and update discovered patterns is still an open research issue, especially in the domain of text mining. Since most existing text mining methods adopted term-based approaches, they all suffer from the problems of polysemy and synonymy. The aim of this project is to automatically identify the relevant cluster for micro array gene expression data sets to keep high qualitative system update of newly recorded data. However, the selection of the most representative feature of the strongly related target clusters is needed for the appropriate selection of subset of features. Features are divided into clusters by using graph-theoretic clustering methods such as the minimum cost spanning tree clustering method. The proposed method introduces a clustering algorithm for the identification of the most relevant features from the input documents. A method is needed to select clusters genes and conditions simultaneously, finding distinctive clusters with less number of rules generated. An evaluation is done on the microarray gene expression data for the purpose of identification of the subset selection. Feature Selection is the process of selecting a subset of relevant features (variables, predictors) for use in model construction. Here fast Algorithm is used for selection of features. In Cluster algorithm clustering based strategy is used where the data are clustered according to the irrelevant features. 35 publicly available real-world high-dimensional image, microarray, and text data are used for clustering. Each reading in the data set is compared with the label and the frequency for each query is identified and based on that the documents were divided into four classes. The support values for each classes were measured. The specificity value is calculated for each classes. Then k-Mean algorithm is used to Bicluster the data employed in order to divide the input data into four classes. From the calculation of the maximum and minimum specificity of each classes were identified and based on that the classes were divided into four categories.