The microarray technique has been widely used in recent years since it can capture the expressions of thousands of genes in a single experiment. To meet the challenge of high volume and complexity of microarray data, various data mining methods and applications have been proposed for analysing gene expressions. Although numerous clustering methods have been studied, they can not provide automation, high quality and high efficiency simultaneously for the biologists during the analysis process. In this research, we propose an integrated approach that can analyse large volume of gene expression data automatically and efficiently. Our approach integrates efficient clustering algorithms with a novel validation technique such that the quality of the discovered gene expression patterns can be evaluated on the fly. Through practical implementation and applications on real gene expression data, our approach was shown to outperform other methods in terms of efficiency, clustering quality and automation.
|Number of pages||7|
|State||Published - 1 Apr 2003|
- Data mining
- Gene expression
- Validation techniques