Evolutionary Fuzzy Clustering for Gene Expression Profile Analysis

Abstract

Fuzzy clustering, which is one category of clustering method, assigns one sample to multiple clusters according to the degrees of membership. It is more appropriate for analyzing gene expression profiles because single gene might involve multiple genetic functions. General clustering methods, however, have problems that they are sensitive to initialization and can be trapped into local optima. To solve these problems, we propose an evolutionary fuzzy clustering method. The proposed method uses a genetic algorithm for clustering and Bayesian validation for evaluation. We have performed experiments to show the usefulness of the proposed method with yeast cell-cycle dataset.