A faster circular binary segmentation algorithm for the analysis of array CGH data. Export

@article{citeulike:1058378, abstract = {MOTIVATION: Array CGH technologies enable the simultaneous measurement of DNA copy number for thousands of sites on a genome. We developed the circular binary segmentation (CBS) algorithm to divide the genome into regions of equal copy number. The algorithm tests for change-points using a maximal t-statistic with a permutation reference distribution to obtain the corresponding P-value. The number of computations required for the maximal test statistic is O(N2), where N is the number of markers. This makes the full permutation approach computationally prohibitive for the newer arrays that contain tens of thousands markers and highlights the need for a faster algorithm. RESULTS: We present a hybrid approach to obtain the P-value of the test statistic in linear time. We also introduce a rule for stopping early when there is strong evidence for the presence of a change. We show through simulations that the hybrid approach provides a substantial gain in speed with only a negligible loss in accuracy and that the stopping rule further increases speed. We also present the analyses of array CGH data from breast cancer cell lines to show the impact of the new approaches on the analysis of real data. AVAILABILITY: An R version of the CBS algorithm has been implemented in the "DNAcopy" package of the Bioconductor project. The proposed hybrid method for the P-value is available in version 1.2.1 or higher and the stopping rule for declaring a change early is available in version 1.5.1 or higher.}, address = {Department of Epidemiology and Biostatistics, Memorial Sloan-Kettering Cancer Center, 1275 York Avenue, New York, NY 10021, USA.}, author = {Venkatraman, E. S. and Olshen, Adam B.}, citeulike-article-id = {1058378}, citeulike-linkout-0 = {http://dx.doi.org/10.1093/bioinformatics/btl646}, citeulike-linkout-1 = {http://bioinformatics.oxfordjournals.org/cgi/content/abstract/23/6/657}, citeulike-linkout-2 = {http://view.ncbi.nlm.nih.gov/pubmed/17234643}, citeulike-linkout-3 = {http://www.hubmed.org/display.cgi?uids=17234643}, day = {15}, doi = {10.1093/bioinformatics/btl646}, issn = {1367-4811}, journal = {Bioinformatics (Oxford, England)}, keywords = {acgh, segmentation}, month = {March}, number = {6}, pages = {657--663}, posted-at = {2008-08-11 22:28:41}, priority = {2}, title = {A faster circular binary segmentation algorithm for the analysis of array CGH data.}, url = {http://dx.doi.org/10.1093/bioinformatics/btl646}, volume = {23}, year = {2007} }

TY - JOUR ID - citeulike:1058378 L3 - citeulike-article-id:1058378 N2 - MOTIVATION: Array CGH technologies enable the simultaneous measurement of DNA copy number for thousands of sites on a genome. We developed the circular binary segmentation (CBS) algorithm to divide the genome into regions of equal copy number. The algorithm tests for change-points using a maximal t-statistic with a permutation reference distribution to obtain the corresponding P-value. The number of computations required for the maximal test statistic is O(N2), where N is the number of markers. This makes the full permutation approach computationally prohibitive for the newer arrays that contain tens of thousands markers and highlights the need for a faster algorithm. RESULTS: We present a hybrid approach to obtain the P-value of the test statistic in linear time. We also introduce a rule for stopping early when there is strong evidence for the presence of a change. We show through simulations that the hybrid approach provides a substantial gain in speed with only a negligible loss in accuracy and that the stopping rule further increases speed. We also present the analyses of array CGH data from breast cancer cell lines to show the impact of the new approaches on the analysis of real data. AVAILABILITY: An R version of the CBS algorithm has been implemented in the "DNAcopy" package of the Bioconductor project. The proposed hybrid method for the P-value is available in version 1.2.1 or higher and the stopping rule for declaring a change early is available in version 1.5.1 or higher. IS - 6 JF - Bioinformatics (Oxford, England) SN - 1367-4811 AD - Department of Epidemiology and Biostatistics, Memorial Sloan-Kettering Cancer Center, 1275 York Avenue, New York, NY 10021, USA. EP - 663 TI - A faster circular binary segmentation algorithm for the analysis of array CGH data. VL - 23 SP - 657 KW - acgh KW - segmentation AU - Venkatraman, ES AU - Olshen, Adam PY - 2007/03/15/ UR - http://dx.doi.org/10.1093/bioinformatics/btl646 ER -