{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T15:54:26Z","timestamp":1772639666757,"version":"3.50.1"},"reference-count":37,"publisher":"Oxford University Press (OUP)","issue":"13","license":[{"start":{"date-parts":[[2016,10,2]],"date-time":"2016-10-02T00:00:00Z","timestamp":1475366400000},"content-version":"vor","delay-in-days":3015,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/2.0\/uk\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2008,7,1]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Motivation: Array-based comparative genomic hybridization (arrayCGH) has recently become a popular tool to identify DNA copy number variations along the genome. These profiles are starting to be used as markers to improve prognosis or diagnosis of cancer, which implies that methods for automated supervised classification of arrayCGH data are needed. Like gene expression profiles, arrayCGH profiles are characterized by a large number of variables usually measured on a limited number of samples. However, arrayCGH profiles have a particular structure of correlations between variables, due to the spatial organization of bacterial artificial chromosomes along the genome. This suggests that classical classification methods, often based on the selection of a small number of discriminative features, may not be the most accurate methods and may not produce easily interpretable prediction rules.<\/jats:p><jats:p>Results: We propose a new method for supervised classification of arrayCGH data. The method is a variant of support vector machine that incorporates the biological specificities of DNA copy number variations along the genome as prior knowledge. The resulting classifier is a sparse linear classifier based on a limited number of regions automatically selected on the chromosomes, leading to easy interpretation and identification of discriminative regions of the genome. We test this method on three classification problems for bladder and uveal cancer, involving both diagnosis and prognosis. We demonstrate that the introduction of the new prior on the classifier leads not only to more accurate predictions, but also to the identification of known and new regions of interest in the genome.<\/jats:p><jats:p>Availability: All data and algorithms are publicly available.<\/jats:p><jats:p>Contact: \u00a0franck.rapaport@curie.fr<\/jats:p>","DOI":"10.1093\/bioinformatics\/btn188","type":"journal-article","created":{"date-parts":[[2008,6,27]],"date-time":"2008-06-27T07:43:13Z","timestamp":1214552593000},"page":"i375-i382","source":"Crossref","is-referenced-by-count":55,"title":["Classification of arrayCGH data using fused SVM"],"prefix":"10.1093","volume":"24","author":[{"given":"Franck","family":"Rapaport","sequence":"first","affiliation":[{"name":"1 Institut Curie, Centre de Recherche, 2INSERM, U900, Paris, F-75248 France and 3Center for Computational Biology, Ecole des Mines de Paris, 35 rue saint Honore, 77305 Fontainebleau, France"},{"name":"1 Institut Curie, Centre de Recherche, 2INSERM, U900, Paris, F-75248 France and 3Center for Computational Biology, Ecole des Mines de Paris, 35 rue saint Honore, 77305 Fontainebleau, France"},{"name":"1 Institut Curie, Centre de Recherche, 2INSERM, U900, Paris, F-75248 France and 3Center for Computational Biology, Ecole des Mines de Paris, 35 rue saint Honore, 77305 Fontainebleau, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Emmanuel","family":"Barillot","sequence":"additional","affiliation":[{"name":"1 Institut Curie, Centre de Recherche, 2INSERM, U900, Paris, F-75248 France and 3Center for Computational Biology, Ecole des Mines de Paris, 35 rue saint Honore, 77305 Fontainebleau, France"},{"name":"1 Institut Curie, Centre de Recherche, 2INSERM, U900, Paris, F-75248 France and 3Center for Computational Biology, Ecole des Mines de Paris, 35 rue saint Honore, 77305 Fontainebleau, France"},{"name":"1 Institut Curie, Centre de Recherche, 2INSERM, U900, Paris, F-75248 France and 3Center for Computational Biology, Ecole des Mines de Paris, 35 rue saint Honore, 77305 Fontainebleau, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jean-Philippe","family":"Vert","sequence":"additional","affiliation":[{"name":"1 Institut Curie, Centre de Recherche, 2INSERM, U900, Paris, F-75248 France and 3Center for Computational Biology, Ecole des Mines de Paris, 35 rue saint Honore, 77305 Fontainebleau, France"},{"name":"1 Institut Curie, Centre de Recherche, 2INSERM, U900, Paris, F-75248 France and 3Center for Computational Biology, Ecole des Mines de Paris, 35 rue saint Honore, 77305 Fontainebleau, France"},{"name":"1 Institut Curie, Centre de Recherche, 2INSERM, U900, Paris, F-75248 France and 3Center for Computational Biology, Ecole des Mines de Paris, 35 rue saint Honore, 77305 Fontainebleau, France"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2008,7,1]]},"reference":[{"key":"2023020210385738100_B1","doi-asserted-by":"crossref","first-page":"7012","DOI":"10.1158\/1078-0432.CCR-05-0177","article-title":"Bladder cancer stage and outcome by array-based comparative genomic hybridization","volume":"11","author":"Blaveri","year":"2005","journal-title":"Clin. Cancer Res"},{"key":"2023020210385738100_B2","doi-asserted-by":"crossref","first-page":"144","DOI":"10.1145\/130385.130401","article-title":"A training algorithm for optimal margin classifiers","volume-title":"COLT'92: Proceedings of the fifth annual workshop on Computational learning theory","author":"Boser","year":"1992"},{"key":"2023020210385738100_B3","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1002\/1096-911X(20010101)36:1<14::AID-MPO1005>3.0.CO;2-G","article-title":"17q gain in neuroblastoma predicts adverse clinical outcome. U.K. cancer cytogenetics group and the U.K. children's cancer study group","volume":"36","author":"Bown","year":"2001","journal-title":"Med. Pediatr. Oncol"},{"key":"2023020210385738100_B4","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511804441","volume-title":"Convex Optimization","author":"Boyd","year":"2004"},{"key":"2023020210385738100_B5","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1137\/S1064827596304010","article-title":"Atomic decomposition by basis pursuit","volume":"20","author":"Chen","year":"1998","journal-title":"SIAM J. Sci. Comput"},{"key":"2023020210385738100_B6","doi-asserted-by":"crossref","first-page":"1959","DOI":"10.1038\/sj.onc.1209985","article-title":"Using array-comparative genomic hybridization to define molecular portraits of primary breast cancers","volume":"26","author":"Chin","year":"2006","journal-title":"Oncogene"},{"key":"2023020210385738100_B7","doi-asserted-by":"crossref","first-page":"4741","DOI":"10.1038\/sj.onc.1208641","article-title":"Kif14 is a candidate oncogene in the 1q minimal region of genomic gain in multiple cancers","volume":"24","author":"Corson","year":"2005","journal-title":"Oncogene"},{"key":"2023020210385738100_B8","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1007\/BF00994018","article-title":"Support-vector networks","volume":"20","author":"Cortes","year":"1995","journal-title":"Machine Learning"},{"key":"2023020210385738100_B9","doi-asserted-by":"crossref","first-page":"407","DOI":"10.1214\/009053604000000067","article-title":"Least angle regression","volume":"32","author":"Efron","year":"2004","journal-title":"Ann. Stat"},{"key":"2023020210385738100_B10","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1198\/004017007000000245","article-title":"Large-scale Bayesian logistic regression for text categorization","volume":"49","author":"Genkin","year":"2007","journal-title":"Technometrics"},{"key":"2023020210385738100_B11","doi-asserted-by":"crossref","first-page":"1195","DOI":"10.1038\/4371195a","article-title":"DNA microarrays: more than gene expression","volume":"437","author":"Gershon","year":"2005","journal-title":"Nature"},{"key":"2023020210385738100_B12","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1016\/S0092-8674(00)81683-9","article-title":"The hallmarks of cancer","volume":"100","author":"Hanahan","year":"2000","journal-title":"Cell"},{"key":"2023020210385738100_B13","article-title":"BAC array CGH distinguishes mutually exclusive alterations that define clinicogenetic subtypes of gliomas","volume-title":"Int. J. Cancer","author":"Idbaih","year":"2007"},{"key":"2023020210385738100_B14","doi-asserted-by":"crossref","first-page":"5988","DOI":"10.1158\/1078-0432.CCR-03-0731","article-title":"Molecular cytogenetic identification of subgroups of grade III invasive ductal breast carcinomas with different clinical outcomes","volume":"10","author":"Jones","year":"2004","journal-title":"Clin. Cancer Res"},{"key":"2023020210385738100_B15","doi-asserted-by":"crossref","first-page":"1105","DOI":"10.1109\/TPAMI.2004.55","article-title":"A Bayesian approach to joint feature selection and classifier design","volume":"26","author":"Krishnapuram","year":"2004","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"2023020210385738100_B16","doi-asserted-by":"crossref","first-page":"957","DOI":"10.1109\/TPAMI.2005.127","article-title":"Sparse multinomial logistic regression: fast algorithms and generalization bounds","volume":"27","author":"Krishnapuram","year":"2005","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2023020210385738100_B17","article-title":"Variable fusion: a new adaptive signal regression method","volume-title":"Technical Report","author":"Land","year":"1996"},{"key":"2023020210385738100_B18","doi-asserted-by":"crossref","first-page":"162","DOI":"10.1002\/(SICI)1098-2264(199703)18:3<162::AID-GCC2>3.0.CO;2-#","article-title":"Comparative genomic hybridization study of primary neuroblastoma tumors. united kingdom children's cancer study group","volume":"18","author":"Lastowska","year":"1997","journal-title":"Genes Chromosomes Cancer"},{"key":"2023020210385738100_B19","first-page":"5352","article-title":"Array comparative genome hybridization for tumor classification and gene discovery in mouse models of malignant melanoma","volume":"63","author":"O'Hagan","year":"2003","journal-title":"Cancer Res"},{"key":"2023020210385738100_B20","first-page":"8507","article-title":"Fine mapping of chromosome 3 in uveal melanoma: identification of a minimal region of deletion on chromosomal arm 3p25.1-p25.2","volume":"63","author":"Parrella","year":"2003","journal-title":"Cancer Res"},{"key":"2023020210385738100_B21","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1038\/2524","article-title":"High resolution analysis of DNA copy number variation using comparative genomic hybridization to microarrays","volume":"20","author":"Pinkel","year":"1998","journal-title":"Nat. Genet"},{"key":"2023020210385738100_B22","first-page":"4568","article-title":"FUS\/ERG gene fusions in Ewing's tumors","volume":"63","author":"Shing","year":"2003","journal-title":"Cancer Res"},{"key":"2023020210385738100_B23","first-page":"3817","article-title":"Chromosomal gains and losses in uveal melanomas detected by comparative genomic hybridization","volume":"54","author":"Speicher","year":"1994","journal-title":"Cancer Res"},{"key":"2023020210385738100_B24","doi-asserted-by":"crossref","first-page":"1386","DOI":"10.1038\/ng1923","article-title":"Regional copy number-independent deregulation of transcription in cancer","volume":"38","author":"Stransky","year":"2006","journal-title":"Nat. Genet"},{"key":"2023020210385738100_B25","doi-asserted-by":"crossref","first-page":"625","DOI":"10.1080\/10556789908805766","article-title":"Using SeDuMi 1.02, a MATLAB toolbox for optimization over symmetric cones","volume":"11\u201312","author":"Sturm","year":"1999","journal-title":"Optimization Methods and Software"},{"key":"2023020210385738100_B26","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1111\/j.2517-6161.1996.tb02080.x","article-title":"Regression shrinkage and selection via the lasso","volume":"58","author":"Tibshirani","year":"1996","journal-title":"J. Roy. Statist. Soc. B"},{"key":"2023020210385738100_B27","doi-asserted-by":"crossref","first-page":"385","DOI":"10.1002\/(SICI)1097-0258(19970228)16:4<385::AID-SIM380>3.0.CO;2-3","article-title":"The lasso method for variable selection in the Cox model","volume":"16","author":"Tibshirani","year":"1997","journal-title":"Stat. Med"},{"key":"2023020210385738100_B28","article-title":"Spatial smoothing and hot spot detection for CGH data using the fused lasso","volume-title":"Biostatistics","author":"Tibshirani","year":"2007"},{"key":"2023020210385738100_B29","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1111\/j.1467-9868.2005.00490.x","article-title":"Sparsity and smoothness via the fused lasso","volume":"67","author":"Tibshirani","year":"2005","journal-title":"J. Roy. Statist. Soc. B"},{"key":"2023020210385738100_B30","article-title":"Genomic profiling and identification of high risk tumors in uveal melanoma by array-CGH analysis of primary tumors and liver metastases","volume-title":"submitted to Cancer Res","author":"Trolet","year":"2008"},{"key":"2023020210385738100_B31","first-page":"3439","article-title":"Partial deletions of the long and short arm of chromosome 3 point to two tumor suppressor genes in uveal melanoma","volume":"61","author":"Tschentscher","year":"2001","journal-title":"Cancer Res"},{"key":"2023020210385738100_B32","doi-asserted-by":"crossref","first-page":"210","DOI":"10.1186\/bcr1510","article-title":"Array-CGH and breast cancer","volume":"8","author":"van Beers","year":"2006","journal-title":"Breast Cancer Res"},{"key":"2023020210385738100_B33","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1002\/gcc.10034","article-title":"Localization of the 17q breakpoint of a constitutional 1;17 translocation in a patient with neuroblastoma within a 25-kb segment located between the accn1 and tlk2 genes and near the distal breakpoints of two microdeletions in neurofibromatosis type 1 patients","volume":"35","author":"Van Roy","year":"2002","journal-title":"Genes, Chromosomes Cancer"},{"key":"2023020210385738100_B34","volume-title":"Statistical Learning Theory","author":"Vapnik","year":"1998"},{"key":"2023020210385738100_B35","first-page":"3807","article-title":"Centromeric copy number of chromosome 7 is strongly correlated with tumor grade and labeling index in human bladder cancer","volume":"51","author":"Waldman","year":"1991","journal-title":"Cancer Res"},{"key":"2023020210385738100_B36","doi-asserted-by":"crossref","first-page":"4065","DOI":"10.1158\/0008-5472.CAN-05-4083","article-title":"Combined cDNA Array Comparative Genomic Hybridization and Serial Analysis of Gene Expression Analysis of Breast Tumor Progression","volume":"66","author":"Yao","year":"2006","journal-title":"Cancer Res"},{"key":"2023020210385738100_B37","article-title":"1-norm support vector machines","volume-title":"Adv. Neural. Inform. Process Syst","author":"Zhu","year":"2004"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/24\/13\/i375\/49050301\/bioinformatics_24_13_i375.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/24\/13\/i375\/49050301\/bioinformatics_24_13_i375.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,30]],"date-time":"2025-01-30T21:40:28Z","timestamp":1738273228000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/24\/13\/i375\/236872"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2008,7,1]]},"references-count":37,"journal-issue":{"issue":"13","published-print":{"date-parts":[[2008,7,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btn188","relation":{},"ISSN":["1367-4811","1367-4803"],"issn-type":[{"value":"1367-4811","type":"electronic"},{"value":"1367-4803","type":"print"}],"subject":[],"published-other":{"date-parts":[[2008,7,1]]},"published":{"date-parts":[[2008,7,1]]}}}