Clustering of Multiple DNA Microarrays through Combination of Particle Swarm Intelligence and K-Means

Veselka Boeva, Elena Tsiporkova, and Anna Hristoskova


data clustering, k-means, particle swarm intelligence, integration analysis


In this article we propose a hybrid approach for clustering of gene expression data across multiple experiments, based on Particle Swarm Optimization and k-means clustering. In the proposed algorithm, each experiment identifies a particle initialized with the result of the k-means algorithm applied over the experiment. The final clustering solution is found by updating the particles using the information about the best clustering solution generated by each experiment and the entire set of experiments. The performance of the proposed cluster algorithm is evaluated on time series expression data obtained from a study examining the global cell-cycle control of gene expression in fission yeast Schizosaccharomyces pombe. The obtained experimental results demonstrate that the hybrid algorithm is able to produce good quality clustering solution, which is representative for the whole test compendium and at the same time adequately reflects the specific characteristics of the individual experiments.

Important Links:

Go Back