Analysis of temporal gene expression profiles: clustering by simulated annealing and determining the optimal number of clusters.

@article{citeulike:1319145, abstract = {MOTIVATION: Cluster analysis of genome-wide expression data from DNA microarray hybridization studies has proved to be a useful tool for identifying biologically relevant groupings of genes and samples. In the present paper, we focus on several important issues related to clustering algorithms that have not yet been fully studied. RESULTS: We describe a simple and robust algorithm for the clustering of temporal gene expression profiles that is based on the simulated annealing procedure. In general, this algorithm guarantees to eventually find the globally optimal distribution of genes over clusters. We introduce an iterative scheme that serves to evaluate quantitatively the optimal number of clusters for each specific data set. The scheme is based on standard approaches used in regular statistical tests. The basic idea is to organize the search of the optimal number of clusters simultaneously with the optimization of the distribution of genes over clusters. The efficiency of the proposed algorithm has been evaluated by means of a reverse engineering experiment, that is, a situation in which the correct distribution of genes over clusters is known a priori. The employment of this statistically rigorous test has shown that our algorithm places greater than 90\% genes into correct clusters. Finally, the algorithm has been tested on real gene expression data (expression changes during yeast cell cycle) for which the fundamental patterns of gene expression and the assignment of genes to clusters are well understood from numerous previous studies.}, address = {Biogen Inc., 14 Cambridge Center, Cambridge, MA 02142, USA. alex\_lukashin@biogen.com}, author = {Lukashin, A. V. and Fuchs, R. }, citeulike-article-id = {1319145}, issn = {1367-4803}, journal = {Bioinformatics}, keywords = {clustering, microarray, time\_series}, month = {May}, number = {5}, pages = {405--414}, posted-at = {2007-05-22 11:28:38}, priority = {2}, title = {Analysis of temporal gene expression profiles: clustering by simulated annealing and determining the optimal number of clusters.}, url = {http://view.ncbi.nlm.nih.gov/pubmed/11331234}, volume = {17}, year = {2001} }

TY - JOUR ID - citeulike:1319145 L3 - citeulike-article-id:1319145 TI - Analysis of temporal gene expression profiles: clustering by simulated annealing and determining the optimal number of clusters. JF - Bioinformatics VL - 17 IS - 5 SP - 405 EP - 414 AD - Biogen Inc., 14 Cambridge Center, Cambridge, MA 02142, USA. alex_lukashin@biogen.com SN - 1367-4803 N2 - MOTIVATION: Cluster analysis of genome-wide expression data from DNA microarray hybridization studies has proved to be a useful tool for identifying biologically relevant groupings of genes and samples. In the present paper, we focus on several important issues related to clustering algorithms that have not yet been fully studied. RESULTS: We describe a simple and robust algorithm for the clustering of temporal gene expression profiles that is based on the simulated annealing procedure. In general, this algorithm guarantees to eventually find the globally optimal distribution of genes over clusters. We introduce an iterative scheme that serves to evaluate quantitatively the optimal number of clusters for each specific data set. The scheme is based on standard approaches used in regular statistical tests. The basic idea is to organize the search of the optimal number of clusters simultaneously with the optimization of the distribution of genes over clusters. The efficiency of the proposed algorithm has been evaluated by means of a reverse engineering experiment, that is, a situation in which the correct distribution of genes over clusters is known a priori. The employment of this statistically rigorous test has shown that our algorithm places greater than 90% genes into correct clusters. Finally, the algorithm has been tested on real gene expression data (expression changes during yeast cell cycle) for which the fundamental patterns of gene expression and the assignment of genes to clusters are well understood from numerous previous studies. KW - clustering KW - microarray KW - time_series AU - Lukashin, AV AU - Fuchs, R PY - 2001/05// UR - http://view.ncbi.nlm.nih.gov/pubmed/11331234 ER -