Evaluation and optimization of clustering in gene expression data analysis. Export

@article{citeulike:1036383, abstract = {MOTIVATION: A measurement of cluster quality is needed to choose potential clusters of genes that contain biologically relevant patterns of gene expression. This is strongly desirable when a large number of gene expression profiles have to be analyzed and proper clusters of genes need to be identified for further analysis, such as the search for meaningful patterns, identification of gene functions or gene response analysis. RESULTS: We propose a new cluster quality method, called stability, by which unsupervised learning of gene expression data can be performed efficiently. The method takes into account a cluster's stability on partition. We evaluate this method and demonstrate its performance using four independent, real gene expression and three simulated datasets. We demonstrate that our method outperforms other techniques listed in the literature. The method has applications in evaluating clustering validity as well as identifying stable clusters. AVAILABILITY: Please contact the first author.}, address = {Institute for Information Technology, National Research Council of Canada, Ottawa, ON, Canada. fazel.famili@nrc-cnrc.gc.ca}, author = {Famili, A. Fazel and Liu, Ganming and Liu, Ziying}, citeulike-article-id = {1036383}, citeulike-linkout-0 = {http://dx.doi.org/10.1093/bioinformatics/bth124}, citeulike-linkout-1 = {http://bioinformatics.oxfordjournals.org/content/20/10/1535.abstract}, citeulike-linkout-2 = {http://bioinformatics.oxfordjournals.org/content/20/10/1535.full.pdf}, citeulike-linkout-3 = {http://bioinformatics.oxfordjournals.org/cgi/content/abstract/20/10/1535}, citeulike-linkout-4 = {http://view.ncbi.nlm.nih.gov/pubmed/14962920}, citeulike-linkout-5 = {http://www.hubmed.org/display.cgi?uids=14962920}, day = {10}, doi = {10.1093/bioinformatics/bth124}, issn = {1367-4803}, journal = {Bioinformatics (Oxford, England)}, keywords = {cluster-stability, clustering, clustering-evaluation, gene-expression, kmeans, silhouette}, month = {July}, number = {10}, pages = {1535--1545}, posted-at = {2009-10-14 10:10:28}, priority = {0}, title = {Evaluation and optimization of clustering in gene expression data analysis.}, url = {http://dx.doi.org/10.1093/bioinformatics/bth124}, volume = {20}, year = {2004} }

TY - JOUR ID - citeulike:1036383 L3 - citeulike-article-id:1036383 N2 - MOTIVATION: A measurement of cluster quality is needed to choose potential clusters of genes that contain biologically relevant patterns of gene expression. This is strongly desirable when a large number of gene expression profiles have to be analyzed and proper clusters of genes need to be identified for further analysis, such as the search for meaningful patterns, identification of gene functions or gene response analysis. RESULTS: We propose a new cluster quality method, called stability, by which unsupervised learning of gene expression data can be performed efficiently. The method takes into account a cluster's stability on partition. We evaluate this method and demonstrate its performance using four independent, real gene expression and three simulated datasets. We demonstrate that our method outperforms other techniques listed in the literature. The method has applications in evaluating clustering validity as well as identifying stable clusters. AVAILABILITY: Please contact the first author. IS - 10 JF - Bioinformatics (Oxford, England) SN - 1367-4803 AD - Institute for Information Technology, National Research Council of Canada, Ottawa, ON, Canada. fazel.famili@nrc-cnrc.gc.ca EP - 1545 TI - Evaluation and optimization of clustering in gene expression data analysis. VL - 20 SP - 1535 KW - cluster-stability KW - clustering KW - clustering-evaluation KW - gene-expression KW - kmeans KW - silhouette AU - Famili, Fazel AU - Liu, Ganming AU - Liu, Ziying PY - 2004/07/10/ UR - http://dx.doi.org/10.1093/bioinformatics/bth124 ER -