Method of Fuzzy Matching Feature Extraction and Clustering Genome Data

Cluster analysis divides data into groups that are meaningful and useful. Sequence clustering is needed and contributes to the assessment of gene and species evolutionary relationships. Clustering methods are thus necessary to carry out these identification operations in an accurate and fast way. In this paper, a method for feature extraction based on fuzzy matching is proposed and these features are used for genome data clustering. Given a database of genome sequences, our proposed work includes generating candidates of length equal to query, find total number of approximate matching patterns to query with given fault tolerance and then using this total number of matches for clustering. Fuzzy C-Means algorithm is used for genome data clustering. Genome data of two species namely Yeast and E. coli are used to verify proposed method.