{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T01:24:04Z","timestamp":1773278644884,"version":"3.50.1"},"reference-count":35,"publisher":"Oxford University Press (OUP)","issue":"12","license":[{"start":{"date-parts":[[2016,10,2]],"date-time":"2016-10-02T00:00:00Z","timestamp":1475366400000},"content-version":"vor","delay-in-days":2685,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/2.0\/uk\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2009,6,15]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Motivation: Personalized medicine based on molecular aspects of diseases, such as gene expression profiling, has become increasingly popular. However, one faces multiple challenges when analyzing clinical gene expression data; most of the well-known theoretical issues such as high dimension of feature spaces versus few examples, noise and missing data apply. Special care is needed when designing classification procedures that support personalized diagnosis and choice of treatment. Here, we particularly focus on classification of interferon-\u03b2 (IFN\u03b2) treatment response in Multiple Sclerosis (MS) patients which has attracted substantial attention in the recent past. Half of the patients remain unaffected by IFN\u03b2 treatment, which is still the standard. For them the treatment should be timely ceased to mitigate the side effects.<\/jats:p>\n               <jats:p>Results: We propose constrained estimation of mixtures of hidden Markov models as a methodology to classify patient response to IFN\u03b2 treatment. The advantages of our approach are that it takes the temporal nature of the data into account and its robustness with respect to noise, missing data and mislabeled samples. Moreover, mixture estimation enables to explore the presence of response sub-groups of patients on the transcriptional level. We clearly outperformed all prior approaches in terms of prediction accuracy, raising it, for the first time, &amp;gt;90%. Additionally, we were able to identify potentially mislabeled samples and to sub-divide the good responders into two sub-groups that exhibited different transcriptional response programs. This is supported by recent findings on MS pathology and therefore may raise interesting clinical follow-up questions.<\/jats:p>\n               <jats:p>Availability: The method is implemented in the GQL framework and is available at http:\/\/www.ghmm.org\/gql. Datasets are available at http:\/\/www.cin.ufpe.br\/\u223cigcf\/MSConst<\/jats:p>\n               <jats:p>Contact: \u00a0igcf@cin.ufpe.br<\/jats:p>\n               <jats:p>Supplementary information: \u00a0Supplementary data are available at Bioinformatics online.<\/jats:p>","DOI":"10.1093\/bioinformatics\/btp222","type":"journal-article","created":{"date-parts":[[2009,5,28]],"date-time":"2009-05-28T15:48:54Z","timestamp":1243525734000},"page":"i6-i14","source":"Crossref","is-referenced-by-count":28,"title":["Constrained mixture estimation for analysis and robust classification of clinical time series"],"prefix":"10.1093","volume":"25","author":[{"given":"Ivan G.","family":"Costa","sequence":"first","affiliation":[{"name":"1 Center of Informatics, Federal University of Pernambuco, Recife, Brazil, 2School of Computing Science, Simon Fraser University, Burnaby, BC, Canada and 3Department of Computational Molecular Biology, Max Planck Institute for Molecular Genetics, Berlin, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexander","family":"Sch\u00f6nhuth","sequence":"additional","affiliation":[{"name":"1 Center of Informatics, Federal University of Pernambuco, Recife, Brazil, 2School of Computing Science, Simon Fraser University, Burnaby, BC, Canada and 3Department of Computational Molecular Biology, Max Planck Institute for Molecular Genetics, Berlin, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christoph","family":"Hafemeister","sequence":"additional","affiliation":[{"name":"1 Center of Informatics, Federal University of Pernambuco, Recife, Brazil, 2School of Computing Science, Simon Fraser University, Burnaby, BC, Canada and 3Department of Computational Molecular Biology, Max Planck Institute for Molecular Genetics, Berlin, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexander","family":"Schliep","sequence":"additional","affiliation":[{"name":"1 Center of Informatics, Federal University of Pernambuco, Recife, Brazil, 2School of Computing Science, Simon Fraser University, Burnaby, BC, Canada and 3Department of Computational Molecular Biology, Max Planck Institute for Molecular Genetics, Berlin, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2009,5,27]]},"reference":[{"key":"2023013111572140200_B1","doi-asserted-by":"crossref","first-page":"694","DOI":"10.1002\/1531-8249(200006)47:6<694::AID-ANA2>3.0.CO;2-W","article-title":"The role of b cells and autoantibodies in multiple sclerosis","volume":"47","author":"Archelos","year":"2000","journal-title":"Ann. Neurol."},{"key":"2023013111572140200_B2","article-title":"A new approach to analyzing gene expression time series data","author":"Bar-Joseph","year":"2002","journal-title":"Proceedings of the 6th Annual International Conference on Research in Computational Molecular Biology"},{"key":"2023013111572140200_B3","doi-asserted-by":"crossref","first-page":"e2","DOI":"10.1371\/journal.pbio.0030002","article-title":"Transcription-based prediction of response to ifnbeta using supervised computational methods","volume":"3","author":"Baranzini","year":"2005","journal-title":"PLoS Biol"},{"key":"2023013111572140200_B4","first-page":"333","article-title":"Active semi-supervision for pairwise constrained clustering","volume-title":"Proceedings of the 2004 SIAM International Conference on Data Mining (SDM-04).","author":"Basu","year":"2004"},{"key":"2023013111572140200_B5","article-title":"A gentle tutorial of the em algorithm and its application to parameter estimation for gaussian mixture and hidden markov models","volume-title":"Technical Report TR-97-021.","author":"Bilmes","year":"1998"},{"key":"2023013111572140200_B6","first-page":"547","article-title":"Class prediction from time series gene expression profiles using dynamical systems kernel","volume":"11","author":"Borgwardt","year":"2006","journal-title":"Pac. Symp. Biocomput."},{"key":"2023013111572140200_B7","doi-asserted-by":"crossref","first-page":"4164","DOI":"10.1073\/pnas.0308531101","article-title":"Metagenes and molecular pattern discovery using matrix factorization","volume":"101","author":"Brunet","year":"2004","journal-title":"Proc. Natl Acad. Sci. USA"},{"key":"2023013111572140200_B8","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1016\/0167-8655(94)00074-D","article-title":"On the exponential value of labeled samples","volume":"16","author":"Castelli","year":"1994","journal-title":"Patt. Recog. Lett."},{"key":"2023013111572140200_B9","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/9780262033589.001.0001","volume-title":"Semi-supervised Learning.","author":"Chapelle","year":"2006"},{"key":"2023013111572140200_B10","doi-asserted-by":"crossref","first-page":"S3","DOI":"10.1186\/1471-2105-8-S10-S3","article-title":"Semi-supervised learning for the identification of syn-expressed genes from fused microarray and in situ image data","volume":"8","author":"Costa","year":"2007","journal-title":"BMC Bioinformatics"},{"key":"2023013111572140200_B11","doi-asserted-by":"crossref","first-page":"14863","DOI":"10.1073\/pnas.95.25.14863","article-title":"Cluster analysis and display of genome-wide expression patterns","volume":"95","author":"Eisen","year":"1998","journal-title":"Proc. Natl Acad. Sci. USA"},{"key":"2023013111572140200_B12","doi-asserted-by":"crossref","first-page":"i159","DOI":"10.1093\/bioinformatics\/bti1022","article-title":"Clustering short time series gene expression data","volume":"21","author":"Ernst","year":"2005","journal-title":"Bioinformatics"},{"key":"2023013111572140200_B13","doi-asserted-by":"crossref","first-page":"578","DOI":"10.1093\/comjnl\/41.8.578","article-title":"How many clusters? which clustering method? answers via model-based cluster analysis","volume":"41","author":"Fraley","year":"1998","journal-title":"Comput. J."},{"key":"2023013111572140200_B14","doi-asserted-by":"crossref","DOI":"10.1007\/978-0-387-21606-5","volume-title":"The Elements of Statistical Learning: Data Mining, Inference and Prediction.","author":"Hastie","year":"2001"},{"key":"2023013111572140200_B15","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1038\/nmeth756","article-title":"Multiple-laboratory comparison of microarray platforms","volume":"2","author":"Irizarry","year":"2005","journal-title":"Nat. Methods"},{"key":"2023013111572140200_B16","doi-asserted-by":"crossref","first-page":"324","DOI":"10.1089\/cmb.2007.0001","article-title":"A patient-gene model for temporal expression profiles in clinical studies","volume":"14","author":"Kaminski","year":"2007","journal-title":"J. Computat. Biol."},{"key":"2023013111572140200_B17","first-page":"731","article-title":"Learning with constrained and unlabelled data","volume-title":"Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition.","author":"Lange","year":"2005"},{"key":"2023013111572140200_B18","doi-asserted-by":"crossref","first-page":"i147","DOI":"10.1093\/bioinformatics\/btn152","article-title":"Alignment and classification of time series gene expression in clinical studies","volume":"24","author":"Lin","year":"2008","journal-title":"Bioinformatics"},{"key":"2023013111572140200_B19","doi-asserted-by":"crossref","first-page":"281","DOI":"10.1007\/978-1-60327-429-6_15","article-title":"Computational diagnostics with gene expression profiles","volume":"453","author":"Lottaz","year":"2008","journal-title":"Meth. Mol. Biol."},{"key":"2023013111572140200_B20","first-page":"849","article-title":"Semi-supervised learning with penalized probabilistic clustering","volume-title":"Advances in Neural Information Processing Systems 17.","author":"Lu","year":"2005"},{"key":"2023013111572140200_B21","article-title":"Finite Mixture Models","volume-title":"Wiley Series in Probability and Statistics.","author":"MacLachlan","year":"2000"},{"key":"2023013111572140200_B22","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1023\/A:1023949509487","article-title":"Consensus clustering: a resampling-based method for class discovery and visualization of gene expression microarray data","volume":"52","author":"Monti","year":"2003","journal-title":"Mach. Learn."},{"key":"2023013111572140200_B23","doi-asserted-by":"crossref","first-page":"701","DOI":"10.1146\/annurev.immunol.17.1.701","article-title":"The il-4 receptor: signaling mechanisms and biologic functions","volume":"17","author":"Nelms","year":"1999","journal-title":"Annu. Rev. Immunol."},{"key":"2023013111572140200_B24","first-page":"795","article-title":"Text classification from labeled and unlabeled documents using EM","volume":"39","author":"Nigam","year":"1999","journal-title":"Mach. Learn."},{"key":"2023013111572140200_B25","doi-asserted-by":"crossref","first-page":"W193","DOI":"10.1093\/nar\/gkm226","article-title":"g:profiler\u2013a web-based toolset for functional profiling of gene lists from large-scale experiments","volume":"35","author":"Reimand","year":"2007","journal-title":"Nucleic Acids Res."},{"key":"2023013111572140200_B26","doi-asserted-by":"crossref","first-page":"400","DOI":"10.1002\/ana.10290","article-title":"Assessment of different treatment failure criteria in a cohort of relapsing-remitting multiple sclerosis patients treated with interferon beta: implications for clinical trials","volume":"52","author":"Ro","year":"2002","journal-title":"Ann. Neurol."},{"key":"2023013111572140200_B27","doi-asserted-by":"crossref","first-page":"108","DOI":"10.1016\/j.jneuroim.2006.02.004","article-title":"T cell gene expression profiling identifies distinct subgroups of japanese multiple sclerosis patients","volume":"174","author":"Satoh","year":"2006","journal-title":"J. Neuroimmunol."},{"issue":"Suppl. 1","key":"2023013111572140200_B28","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1093\/bioinformatics\/btg1036","article-title":"Using hidden Markov models to analyze gene expression time course data","volume":"19","author":"Schliep","year":"2003","journal-title":"Bioinformatics"},{"issue":"Suppl. 1","key":"2023013111572140200_B29","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1093\/bioinformatics\/bth937","article-title":"Robust inference of groups in gene expression time-courses using mixtures of HMMs","volume":"20","author":"Schliep","year":"2004","journal-title":"Bioinformatics"},{"key":"2023013111572140200_B30","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1109\/TCBB.2005.31","article-title":"Analyzing gene expression time-courses","volume":"2","author":"Schliep","year":"2005","journal-title":"IEEE\/ACM Trans. Comput. Biol. Bioinform."},{"key":"2023013111572140200_B31","article-title":"Semi-supervised clustering of yeast gene expression data","volume-title":"Japanese-German Workshop on Data Analysis and Classification.","author":"Sch\u00f6nhuth","year":"2006"},{"key":"2023013111572140200_B32","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1016\/S1478-5382(03)02329-1","article-title":"Diagnostic signatures from microarrays: a bioinformatics concept for personalized medicine","volume":"1","author":"Spang","year":"2003","journal-title":"BIOSILICO"},{"key":"2023013111572140200_B33","doi-asserted-by":"crossref","first-page":"522","DOI":"10.1038\/sj.gene.6364324","article-title":"A subtype of multiple sclerosis defined by an activated immune defense program","volume":"7","author":"van Baarsen","year":"2006","journal-title":"Genes Immun."},{"key":"2023013111572140200_B34","doi-asserted-by":"crossref","first-page":"564","DOI":"10.1038\/nature06915","article-title":"Enabling personalized cancer medicine through analysis of gene-expression patterns","volume":"452","author":"van't Veer","year":"2008","journal-title":"Nature"},{"key":"2023013111572140200_B35","doi-asserted-by":"crossref","first-page":"25849","DOI":"10.1074\/jbc.M413721200","article-title":"Interferon alpha activates nf-kappab in jak1-deficient cells through a tyk2-dependent pathway","volume":"280","author":"Yang","year":"2005","journal-title":"J. Biol. Chem."}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/25\/12\/i6\/48990680\/bioinformatics_25_12_i6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/25\/12\/i6\/48990680\/bioinformatics_25_12_i6.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,31]],"date-time":"2023-01-31T21:04:50Z","timestamp":1675199090000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/25\/12\/i6\/191509"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,5,27]]},"references-count":35,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2009,6,15]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btp222","relation":{},"ISSN":["1367-4811","1367-4803"],"issn-type":[{"value":"1367-4811","type":"electronic"},{"value":"1367-4803","type":"print"}],"subject":[],"published-other":{"date-parts":[[2009,6,15]]},"published":{"date-parts":[[2009,5,27]]}}}