{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,20]],"date-time":"2025-10-20T10:21:48Z","timestamp":1760955708455},"reference-count":39,"publisher":"Oxford University Press (OUP)","issue":"14","license":[{"start":{"date-parts":[[2017,7,12]],"date-time":"2017-07-12T00:00:00Z","timestamp":1499817600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,7,15]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Biclustering has become a major tool for analyzing large datasets given as matrix of samples times features and has been successfully applied in life sciences and e-commerce for drug design and recommender systems, respectively. Factor Analysis for Bicluster Acquisition (FABIA), one of the most successful biclustering methods, is a generative model that represents each bicluster by two sparse membership vectors: one for the samples and one for the features. However, FABIA is restricted to about 20 code units because of the high computational complexity of computing the posterior. Furthermore, code units are sometimes insufficiently decorrelated and sample membership is difficult to determine. We propose to use the recently introduced unsupervised Deep Learning approach Rectified Factor Networks (RFNs) to overcome the drawbacks of existing biclustering methods. RFNs efficiently construct very sparse, non-linear, high-dimensional representations of the input via their posterior means. RFN learning is a generalized alternating minimization algorithm based on the posterior regularization method which enforces non-negative and normalized posterior means. Each code unit represents a bicluster, where samples for which the code unit is active belong to the bicluster and features that have activating weights to the code unit belong to the bicluster.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>On 400 benchmark datasets and on three gene expression datasets with known clusters, RFN outperformed 13 other biclustering methods including FABIA. On data of the 1000 Genomes Project, RFN could identify DNA segments which indicate, that interbreeding with other hominins starting already before ancestors of modern humans left Africa.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>https:\/\/github.com\/bioinf-jku\/librfn<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btx226","type":"journal-article","created":{"date-parts":[[2017,4,20]],"date-time":"2017-04-20T07:52:13Z","timestamp":1492674733000},"page":"i59-i66","source":"Crossref","is-referenced-by-count":7,"title":["Rectified factor networks for biclustering of omics data"],"prefix":"10.1093","volume":"33","author":[{"given":"Djork-Arn\u00e9","family":"Clevert","sequence":"first","affiliation":[{"name":"Bioinformatics Department, Bayer AG, Berlin, Germany"}]},{"given":"Thomas","family":"Unterthiner","sequence":"additional","affiliation":[{"name":"Institute of Bioinformatics, Johannes Kepler University Linz, Linz, Austria"}]},{"given":"Gundula","family":"Povysil","sequence":"additional","affiliation":[{"name":"Institute of Bioinformatics, Johannes Kepler University Linz, Linz, Austria"}]},{"given":"Sepp","family":"Hochreiter","sequence":"additional","affiliation":[{"name":"Institute of Bioinformatics, Johannes Kepler University Linz, Linz, Austria"}]}],"member":"286","published-online":{"date-parts":[[2017,7,12]]},"reference":[{"key":"2023051506495799900_btx226-B1","doi-asserted-by":"crossref","first-page":"373","DOI":"10.1089\/10665270360688075","article-title":"Discovering local structure in gene expression data: the order-preserving submatrix problem","volume":"10","author":"Ben-Dor","year":"2003","journal-title":"J. Comput. Biol"},{"key":"2023051506495799900_btx226-B2","doi-asserted-by":"crossref","first-page":"174","DOI":"10.1109\/TAC.1976.1101194","article-title":"On the Goldstein-Levitin-Polyak gradient projection method","volume":"21","author":"Bertsekas","year":"1976","journal-title":"IEEE Trans. Automat. Control"},{"key":"2023051506495799900_btx226-B3","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1016\/j.ajhg.2011.01.010","article-title":"A fast, powerful method for detecting identity by descent","volume":"88","author":"Browning","year":"2011","journal-title":"Am. J. Hum. Genet"},{"key":"2023051506495799900_btx226-B4","doi-asserted-by":"crossref","first-page":"1643","DOI":"10.1214\/15-AOAS854","article-title":"The gibbs-plaid biclustering model","volume":"9","author":"Chekouo","year":"2015","journal-title":"Ann. Appl. Stat"},{"key":"2023051506495799900_btx226-B5","first-page":"93","article-title":"Biclustering of expression data","volume":"8","author":"Cheng","year":"2000","journal-title":"Proceedings of the International Conference on Intelligent Systems for Molecular Biology"},{"key":"2023051506495799900_btx226-B6","volume-title":"Advances in Neural Information Processing Systems 28","author":"Clevert","year":"2015"},{"key":"2023051506495799900_btx226-B7","first-page":"2001","article-title":"Posterior regularization for structured latent variable models","volume":"11","author":"Ganchev","year":"2010","journal-title":"J. Mach. Learn. Res"},{"key":"2023051506495799900_btx226-B8","first-page":"2049","article-title":"Convergence theorems for generalized alternating minimization procedures","volume":"6","author":"Gunawardana","year":"2005","journal-title":"J. Mach. Learn. Res"},{"key":"2023051506495799900_btx226-B9","doi-asserted-by":"crossref","first-page":"318","DOI":"10.1101\/gr.081398.108","article-title":"Whole population, genome-wide mapping of hidden relatedness","volume":"19","author":"Gusev","year":"2009","journal-title":"Genome Res"},{"key":"2023051506495799900_btx226-B10","doi-asserted-by":"crossref","first-page":"e202.","DOI":"10.1093\/nar\/gkt1013","article-title":"HapFABIA: Identification of very short segments of identity by descent characterized by rare variants in large sequencing data","volume":"41","author":"Hochreiter","year":"2013","journal-title":"Nucleic Acids Res"},{"key":"2023051506495799900_btx226-B11","doi-asserted-by":"crossref","first-page":"1520","DOI":"10.1093\/bioinformatics\/btq227","article-title":"FABIA: factor analysis for bicluster acquisition","volume":"26","author":"Hochreiter","year":"2010","journal-title":"Bioinformatics"},{"key":"2023051506495799900_btx226-B12","doi-asserted-by":"crossref","first-page":"e1195","DOI":"10.1371\/journal.pone.0001195","article-title":"Subclass mapping: Identifying common subtypes in independent disease data sets","volume":"2","author":"Hoshida","year":"2007","journal-title":"PLoS One"},{"key":"2023051506495799900_btx226-B13","first-page":"1457","article-title":"Non-negative matrix factorization with sparseness constraints","volume":"5","author":"Hoyer","year":"2004","journal-title":"J. Mach. Learn. Res"},{"key":"2023051506495799900_btx226-B14","doi-asserted-by":"crossref","first-page":"1993","DOI":"10.1093\/bioinformatics\/bth166","article-title":"Defining transcription modules using large-scale gene expression data","volume":"20","author":"Ihmels","year":"2004","journal-title":"Bioinformatics"},{"key":"2023051506495799900_btx226-B15","doi-asserted-by":"crossref","DOI":"10.1201\/9781315373966","volume-title":"Applied Biclustering Methods for Big and High-Dimensional Data Using R","author":"Kasim","year":"2016"},{"key":"2023051506495799900_btx226-B16","doi-asserted-by":"crossref","DOI":"10.1137\/1.9781611970920","volume-title":"Iterative Methods for Optimization","author":"Kelley","year":"1999"},{"key":"2023051506495799900_btx226-B17","doi-asserted-by":"crossref","first-page":"703","DOI":"10.1101\/gr.648603","article-title":"Spectral biclustering of microarray data: coclustering genes and conditions","volume":"13","author":"Kluger","year":"2003","journal-title":"Genome Res"},{"key":"2023051506495799900_btx226-B18","first-page":"909","volume-title":"Advances in Neural Information Processing Systems 24","author":"Kolar","year":"2011"},{"key":"2023051506495799900_btx226-B19","first-page":"61","article-title":"Plaid models for gene expression data","volume":"12","author":"Lazzeroni","year":"2002","journal-title":"Stat. Sinica"},{"key":"2023051506495799900_btx226-B20","first-page":"1324","volume-title":"Advances in Neural Information Processing Systems 28","author":"Lee","year":"2015"},{"key":"2023051506495799900_btx226-B21","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1109\/TCBB.2004.2","article-title":"Biclustering algorithms for biological data analysis: a survey","volume":"1","author":"Madeira","year":"2004","journal-title":"IEEE ACM Trans. Comput. Biol. Bioinform"},{"key":"2023051506495799900_btx226-B22","doi-asserted-by":"crossref","first-page":"222","DOI":"10.1126\/science.1224344","article-title":"A high-coverage genome sequence from an archaic denisovan individual","volume":"338","author":"Meyer","year":"2012","journal-title":"Science"},{"key":"2023051506495799900_btx226-B23","first-page":"77","volume-title":"Pacific Symposium on Biocomputing","author":"Murali","year":"2003"},{"key":"2023051506495799900_btx226-B24","doi-asserted-by":"crossref","first-page":"355","DOI":"10.1007\/978-94-011-5014-9_12","volume-title":"Learning in Graphical Models","author":"Neal","year":"1998"},{"key":"2023051506495799900_btx226-B25","first-page":"3617","volume-title":"Advances in Neural Information Processing Systems 27","author":"O\u2019Connor","year":"2014"},{"key":"2023051506495799900_btx226-B26","author":"Povysil","year":"2014"},{"key":"2023051506495799900_btx226-B27","doi-asserted-by":"crossref","first-page":"3406","DOI":"10.1093\/gbe\/evw234","article-title":"IBD Sharing between Africans, Neandertals, and Denisovans","volume":"8","author":"Povysil","year":"2016","journal-title":"Genome Biol. Evol"},{"key":"2023051506495799900_btx226-B28","doi-asserted-by":"crossref","first-page":"1122","DOI":"10.1093\/bioinformatics\/btl060","article-title":"A systematic comparison and evaluation of biclustering methods for gene expression data","volume":"22","author":"Prelic","year":"2006","journal-title":"Bioinformatics"},{"key":"2023051506495799900_btx226-B29","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1038\/nature12886","article-title":"The complete genome sequence of a Neanderthal from the Altai Mountains","volume":"505","author":"Pr\u00fcfer","year":"2014","journal-title":"Nature"},{"key":"2023051506495799900_btx226-B30","doi-asserted-by":"crossref","first-page":"1937","DOI":"10.1056\/NEJMoa012914","article-title":"The use of molecular profiling to predict survival after chemotherapy for diffuse large-B-cell lymphoma","volume":"346","author":"Rosenwald","year":"2002","journal-title":"N. Engl. J. Med"},{"key":"2023051506495799900_btx226-B31","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res"},{"key":"2023051506495799900_btx226-B32","doi-asserted-by":"crossref","first-page":"4465","DOI":"10.1073\/pnas.012025199","article-title":"Large-scale analysis of the human and mouse transcriptomes","volume":"99","author":"Su","year":"2002","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"2023051506495799900_btx226-B33","doi-asserted-by":"crossref","first-page":"S136","DOI":"10.1093\/bioinformatics\/18.suppl_1.S136","article-title":"Discovering statistically significant biclusters in gene expression data","volume":"18(Suppl. 1)","author":"Tanay","year":"2002","journal-title":"Bioinformatics"},{"key":"2023051506495799900_btx226-B34","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1038\/nature15393","article-title":"A global reference for human genetic variation","volume":"526","author":"The 1000 Genomes Project Consortium","year":"2015","journal-title":"Nature"},{"key":"2023051506495799900_btx226-B35","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1016\/j.csda.2004.02.003","article-title":"Improved biclustering of microarray data demonstrated through systematic performance tests","volume":"48","author":"Turner","year":"2003","journal-title":"Comput. Stat. Data Anal"},{"key":"2023051506495799900_btx226-B36","doi-asserted-by":"crossref","first-page":"530","DOI":"10.1038\/415530a","article-title":"Gene expression profiling predicts clinical outcome of breast cancer","volume":"415","author":"van\u2019t Veer","year":"2002","journal-title":"Nature"},{"key":"2023051506495799900_btx226-B37","doi-asserted-by":"crossref","first-page":"505","DOI":"10.1016\/j.drudis.2014.12.014","article-title":"Using transcriptomics to guide lead optimization in drug discovery projects: lessons learned from the QSTAR project","volume":"20","author":"Verbist","year":"2015","journal-title":"Drug Discov. Today"},{"key":"2023051506495799900_btx226-B38","doi-asserted-by":"crossref","first-page":"305","DOI":"10.1093\/bioinformatics\/btt683","article-title":"Identification of transcription factors for drug-associated gene modules and biomedical implications","volume":"30","author":"Xiong","year":"2014","journal-title":"Bioinformatics"},{"key":"2023051506495799900_btx226-B39","doi-asserted-by":"crossref","first-page":"771","DOI":"10.1142\/S0218213005002387","article-title":"An improved biclustering method for analyzing gene expression profiles","volume":"14","author":"Yang","year":"2005","journal-title":"Int. J. Artif. Intell. Tools"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/33\/14\/i59\/50315052\/bioinformatics_33_14_i59.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/33\/14\/i59\/50315052\/bioinformatics_33_14_i59.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,15]],"date-time":"2023-05-15T06:50:38Z","timestamp":1684133438000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/33\/14\/i59\/3953934"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,7,12]]},"references-count":39,"journal-issue":{"issue":"14","published-print":{"date-parts":[[2017,7,15]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btx226","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2017,7,15]]},"published":{"date-parts":[[2017,7,12]]}}}