K-Boost: a scalable algorithm for high-quality clustering of microarray gene expression data. Export

@article{citeulike:4872083, abstract = {Microarray technology for profiling gene expression levels is a popular tool in modern biological research. Applications range from tissue classification to the detection of metabolic networks, from drug discovery to time-critical personalized medicine. Given the increase in size and complexity of the data sets produced, their analysis is becoming problematic in terms of time/quality trade-offs. Clustering genes with similar expression profiles is a key initial step for subsequent manipulations and the increasing volumes of data to be analyzed requires methods that are at the same time efficient (completing an analysis in minutes rather than hours) and effective (identifying significant clusters with high biological correlations). In this paper, we propose K-Boost, a clustering algorithm based on a combination of the furthest-point-first (FPF) heuristic for solving the metric k-center problem, a stability-based method for determining the number of clusters, and a k-means-like cluster refinement. K-Boost runs in O (|N| x k) time, where N is the input matrix and k is the number of proposed clusters. Experiments show that this low complexity is usually coupled with a very good quality of the computed clusterings, which we measure using both internal and external criteria. Supporting data can be found as online Supplementary Material at www.liebertonline.com.}, author = {Geraci, Filippo and Leoncini, Mauro and Montangero, Manuela and Pellegrini, Marco and Renda, M. Elena}, citeulike-article-id = {4872083}, citeulike-linkout-0 = {http://dx.doi.org/10.1089/cmb.2008.0201}, citeulike-linkout-1 = {http://view.ncbi.nlm.nih.gov/pubmed/19522668}, citeulike-linkout-2 = {http://www.hubmed.org/display.cgi?uids=19522668}, doi = {10.1089/cmb.2008.0201}, issn = {1557-8666}, journal = {Journal of computational biology : a journal of computational molecular cell biology}, keywords = {clustering}, month = {June}, number = {6}, pages = {859--873}, posted-at = {2009-06-23 22:17:29}, priority = {2}, title = {K-Boost: a scalable algorithm for high-quality clustering of microarray gene expression data.}, url = {http://dx.doi.org/10.1089/cmb.2008.0201}, volume = {16}, year = {2009} }

TY - JOUR ID - citeulike:4872083 L3 - citeulike-article-id:4872083 N2 - Microarray technology for profiling gene expression levels is a popular tool in modern biological research. Applications range from tissue classification to the detection of metabolic networks, from drug discovery to time-critical personalized medicine. Given the increase in size and complexity of the data sets produced, their analysis is becoming problematic in terms of time/quality trade-offs. Clustering genes with similar expression profiles is a key initial step for subsequent manipulations and the increasing volumes of data to be analyzed requires methods that are at the same time efficient (completing an analysis in minutes rather than hours) and effective (identifying significant clusters with high biological correlations). In this paper, we propose K-Boost, a clustering algorithm based on a combination of the furthest-point-first (FPF) heuristic for solving the metric k-center problem, a stability-based method for determining the number of clusters, and a k-means-like cluster refinement. K-Boost runs in O (|N| x k) time, where N is the input matrix and k is the number of proposed clusters. Experiments show that this low complexity is usually coupled with a very good quality of the computed clusterings, which we measure using both internal and external criteria. Supporting data can be found as online Supplementary Material at www.liebertonline.com. IS - 6 JF - Journal of computational biology : a journal of computational molecular cell biology SN - 1557-8666 EP - 873 TI - K-Boost: a scalable algorithm for high-quality clustering of microarray gene expression data. VL - 16 SP - 859 KW - clustering AU - Geraci, Filippo AU - Leoncini, Mauro AU - Montangero, Manuela AU - Pellegrini, Marco AU - Renda, Elena PY - 2009/06// UR - http://dx.doi.org/10.1089/cmb.2008.0201 ER -