{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,22]],"date-time":"2025-02-22T00:44:57Z","timestamp":1740185097500,"version":"3.37.3"},"reference-count":39,"publisher":"Oxford University Press (OUP)","issue":"24","license":[{"start":{"date-parts":[[2018,6,21]],"date-time":"2018-06-21T00:00:00Z","timestamp":1529539200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"Basic Science Research Program"},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["NRF-2015R1C1A2A01055739"],"award-info":[{"award-number":["NRF-2015R1C1A2A01055739"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,12,15]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Motivation<\/jats:title><jats:p>Given multi-platform genome data with prior knowledge of functional gene sets, how can we extract interpretable latent relationships between patients and genes? More specifically, how can we devise a tensor factorization method which produces an interpretable gene factor matrix based on functional gene set information while maintaining the decomposition quality and speed?<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>We propose GIFT, a Guided and Interpretable Factorization for Tensors. GIFT provides interpretable factor matrices by encoding prior knowledge as a regularization term in its objective function. We apply GIFT to the PanCan12 dataset (TCGA multi-platform genome data) and compare the performance with P-Tucker, our baseline method without prior knowledge constraint, and Silenced-TF, our naive interpretable method. Results show that GIFT produces interpretable factorizations with high scalability and accuracy. Furthermore, we demonstrate how results of GIFT can be used to reveal significant relations between (cancer, gene sets, genes) and validate the findings based on literature evidence.<\/jats:p><\/jats:sec><jats:sec><jats:title>Availability and implementation<\/jats:title><jats:p>The code and datasets used in the paper are available at https:\/\/github.com\/leesael\/GIFT.<\/jats:p><\/jats:sec><jats:sec><jats:title>Supplementary information<\/jats:title><jats:p>Supplementary data are available at Bioinformatics online.<\/jats:p><\/jats:sec>","DOI":"10.1093\/bioinformatics\/bty490","type":"journal-article","created":{"date-parts":[[2018,6,18]],"date-time":"2018-06-18T11:48:28Z","timestamp":1529322508000},"page":"4151-4158","source":"Crossref","is-referenced-by-count":8,"title":["GIFT: Guided and Interpretable Factorization for Tensors with an application to large-scale multi-platform cancer analysis"],"prefix":"10.1093","volume":"34","author":[{"given":"Jungwoo","family":"Lee","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sejoon","family":"Oh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9066-5756","authenticated-orcid":false,"given":"Lee","family":"Sael","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2018,6,21]]},"reference":[{"key":"2023012712261690100_bty490-B1","doi-asserted-by":"crossref","first-page":"6149","DOI":"10.1128\/MCB.00220-08","article-title":"Regulation of the endosomal snare protein syntaxin 7 by colony-stimulating factor 1 in macrophages","volume":"28","author":"Achuthan","year":"2008","journal-title":"Mol. Cell Biol"},{"key":"2023012712261690100_bty490-B2","doi-asserted-by":"crossref","first-page":"795","DOI":"10.1016\/j.biopha.2017.01.120","article-title":"The role of il17b-il17rb signaling pathway in breast cancer","volume":"88","author":"Alinejad","year":"2017","journal-title":"Biomed. Pharmacother"},{"key":"2023012712261690100_bty490-B3","doi-asserted-by":"crossref","first-page":"e1499.","DOI":"10.7717\/peerj.1499","article-title":"A pan-cancer analysis of prognostic genes","volume":"3","author":"Anaya","year":"2015","journal-title":"PeerJ"},{"key":"2023012712261690100_bty490-B4","first-page":"379","volume-title":"Semin. Thromb. Hemost","author":"Bikfalvi","year":"2004"},{"key":"2023012712261690100_bty490-B5","article-title":"Fast, accurate, and scalable method for sparse coupled matrix-tensor factorization","author":"Choi","year":"2017","journal-title":"arXiv Preprint arXiv: 1708.08640"},{"volume-title":"SIGKDD 2016, Philadelphia, PA, USA, August 20\u201323, 2006","year":"2006","author":"Eliassi-Rad","key":"2023012712261690100_bty490-B6"},{"key":"2023012712261690100_bty490-B7","doi-asserted-by":"crossref","first-page":"677","DOI":"10.1007\/s11045-013-0269-9","article-title":"Tucker factorization with missing data with application to low-n-rank tensor completion","volume":"26","author":"Filipovi\u0107","year":"2015","journal-title":"Multidimensional Syst. Signal Process"},{"key":"2023012712261690100_bty490-B8","doi-asserted-by":"crossref","first-page":"1050","DOI":"10.1182\/blood-2006-01-0322","article-title":"Genes contributing to minimal residual disease in childhood acute lymphoblastic leukemia: prognostic significance of casp8ap2","volume":"108","author":"Flotho","year":"2006","journal-title":"Blood"},{"key":"2023012712261690100_bty490-B9","doi-asserted-by":"crossref","first-page":"929","DOI":"10.1016\/j.cell.2014.06.049","article-title":"Multiplatform analysis of 12 cancer types reveals molecular classification within and across tissues of origin","volume":"158","author":"Hoadley","year":"2014","journal-title":"Cell"},{"key":"2023012712261690100_bty490-B10","doi-asserted-by":"crossref","first-page":"1108","DOI":"10.1038\/nmeth.2651","article-title":"Network-based stratification of tumor mutations","volume":"10","author":"Hofree","year":"2013","journal-title":"Nat. Methods"},{"key":"2023012712261690100_bty490-B11","doi-asserted-by":"crossref","first-page":"777","DOI":"10.1038\/19709","article-title":"The CED-4-homologous protein FLASH is involved in Fas-mediated activation of caspase-8 during apoptosis","volume":"398","author":"Imai","year":"1999","journal-title":"Nature"},{"key":"2023012712261690100_bty490-B12","first-page":"811","volume-title":"ICDE 2016","author":"Jeon","year":"2016"},{"key":"2023012712261690100_bty490-B13","doi-asserted-by":"crossref","first-page":"519","DOI":"10.1007\/s00778-016-0427-4","article-title":"Mining billion-scale tensors: algorithms and discoveries","volume":"25","author":"Jeon","year":"2016","journal-title":"VLDB J"},{"key":"2023012712261690100_bty490-B14","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1038\/nature12113","article-title":"Integrated genomic characterization of endometrial carcinoma","volume":"497","author":"Kandoth","year":"2013","journal-title":"Nature"},{"key":"2023012712261690100_bty490-B15","doi-asserted-by":"crossref","first-page":"3653","DOI":"10.1093\/bioinformatics\/btv409","article-title":"A mutation profile for top-k patient search exploiting gene-ontology and orthogonal non-negative matrix factorization","volume":"31","author":"Kim","year":"2015","journal-title":"Bioinformatics"},{"key":"2023012712261690100_bty490-B16","first-page":"1","article-title":"Discriminative and distinct phenotyping by constrained tensor factorization","volume":"7","author":"Kim","year":"2017","journal-title":"Sci. Rep"},{"key":"2023012712261690100_bty490-B17","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1038\/nature11412","article-title":"Comprehensive molecular portraits of human breast tumours","volume":"490","author":"Koboldt","year":"2012","journal-title":"Nature"},{"key":"2023012712261690100_bty490-B18","doi-asserted-by":"crossref","first-page":"107.","DOI":"10.1186\/bcr42","article-title":"Transforming growth factor-\u03b2 and breast cancer: transforming growth factor-\u03b2\/smad signaling defects and cancer","volume":"2","author":"Kretzschmar","year":"2000","journal-title":"Breast Cancer Res"},{"key":"2023012712261690100_bty490-B19","article-title":"CTD: fast, accurate, and interpretable method for static and dynamic tensor decompositions","author":"Lee","year":"2017","journal-title":"arXiv, Preprint arXiv: 1710.03608"},{"key":"2023012712261690100_bty490-B20","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1016\/j.cels.2015.12.004","article-title":"The molecular signatures database hallmark gene set collection","volume":"1","author":"Liberzon","year":"2015","journal-title":"Cell Syst"},{"key":"2023012712261690100_bty490-B21","doi-asserted-by":"crossref","first-page":"djv032","DOI":"10.1093\/jnci\/djv032","article-title":"Serum lipids, lipoproteins, and risk of breast cancer: a nested case\u2013control study using multiple time points","volume":"107","author":"Martin","year":"2015","journal-title":"J. Natl. Cancer Inst"},{"key":"2023012712261690100_bty490-B22","doi-asserted-by":"crossref","first-page":"465","DOI":"10.1530\/ERC-15-0129","article-title":"Tff3 is a valuable predictive biomarker of endocrine response in metastatic breast cancer","volume":"22","author":"May","year":"2015","journal-title":"Endocr. Relat. Cancer"},{"key":"2023012712261690100_bty490-B23","doi-asserted-by":"crossref","first-page":"856","DOI":"10.1038\/bjc.1980.333","article-title":"Faecal bile acids and clostridia in patients with breast cancer","volume":"42","author":"Murray","year":"1980","journal-title":"Br. J. Cancer"},{"year":"2017","author":"Oh","key":"2023012712261690100_bty490-B24"},{"volume-title":"ICDE 2018","year":"2018","author":"Oh","key":"2023012712261690100_bty490-B25"},{"key":"2023012712261690100_bty490-B26","doi-asserted-by":"crossref","first-page":"1121","DOI":"10.1038\/ng.2761","article-title":"Enabling transparent and collaborative computational analysis of 12 tumor types within The Cancer Genome Atlas","volume":"45","author":"Omberg","year":"2013","journal-title":"Nat. Genet"},{"key":"2023012712261690100_bty490-B27","doi-asserted-by":"crossref","first-page":"857.","DOI":"10.1038\/s41467-017-00921-w","article-title":"Pan-cancer analysis of bi-allelic alterations in homologous recombination DNA repair genes","volume":"8","author":"Riaz","year":"2017","journal-title":"Nat. Commun"},{"key":"2023012712261690100_bty490-B28","doi-asserted-by":"crossref","first-page":"999","DOI":"10.3892\/ol.2017.6230","article-title":"Overexpression of the transmembrane protein bst-2 induces akt and erk phosphorylation in bladder cancer","volume":"14","author":"Shigematsu","year":"2017","journal-title":"Oncol. Lett"},{"key":"2023012712261690100_bty490-B29","first-page":"100","article-title":"Fully scalable methods for distributed tensor factorization","volume":"29","author":"Shin","year":"2017","journal-title":"IEEE TKDE"},{"year":"2017","author":"Smith","key":"2023012712261690100_bty490-B30"},{"key":"2023012712261690100_bty490-B31","doi-asserted-by":"crossref","first-page":"26764","DOI":"10.1074\/jbc.M112.386599","article-title":"Transforming growth factor-\u03b2\/smad target gene skil is negatively regulated by the transcriptional cofactor complex snon-smad4","volume":"287","author":"Tecalco-Cruz","year":"2012","journal-title":"J. Biol. Chem"},{"year":"2015","author":"Thomas","first-page":"266","key":"2023012712261690100_bty490-B32"},{"key":"2023012712261690100_bty490-B33","doi-asserted-by":"crossref","first-page":"150","DOI":"10.1504\/IJDMB.2017.089281","article-title":"Multi-Kernel LS-SVM based integration bio-clinical data analysis and application to ovarian cancer","volume":"19","author":"Thomas","year":"2017","journal-title":"IJDMB"},{"key":"2023012712261690100_bty490-B34","doi-asserted-by":"crossref","first-page":"i237","DOI":"10.1093\/bioinformatics\/btq182","article-title":"Inference of patient-specific pathway activities from multi-dimensional cancer genomics data using PARADIGM","volume":"26","author":"Vaske","year":"2010","journal-title":"Bioinformatics"},{"key":"2023012712261690100_bty490-B35","first-page":"2487","article-title":"Ifn-\u03b3 induces apoptosis in ovarian cancer cells in vivo and in vitro","volume":"9","author":"Wall","year":"2003","journal-title":"Clin. Cancer Res"},{"key":"2023012712261690100_bty490-B36","article-title":"Tensorbeat: tensor decomposition for monitoring multi-person breathing beats with commodity wifi","volume":"9","author":"Wang","year":"2017"},{"key":"2023012712261690100_bty490-B37","doi-asserted-by":"crossref","first-page":"1113","DOI":"10.1038\/ng.2764","article-title":"The cancer genome atlas pan-cancer analysis project","volume":"45","author":"Weinstein","year":"2013","journal-title":"Nat. Genet"},{"key":"2023012712261690100_bty490-B38","doi-asserted-by":"crossref","first-page":"617","DOI":"10.1016\/S0955-0674(02)00375-7","article-title":"Versican: a versatile extracellular matrix proteoglycan in cell biology","volume":"14","author":"Wight","year":"2002","journal-title":"Curr. Opin. Cell Biol"},{"key":"2023012712261690100_bty490-B39","doi-asserted-by":"crossref","first-page":"2131.","DOI":"10.3390\/molecules22122131","article-title":"A robust manifold graph regularized nonnegative matrix factorization algorithm for cancer gene clustering","volume":"22","author":"Zhu","year":"2017","journal-title":"Molecules"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/34\/24\/4151\/48921207\/bioinformatics_34_24_4151.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/34\/24\/4151\/48921207\/bioinformatics_34_24_4151.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,3]],"date-time":"2023-09-03T06:49:19Z","timestamp":1693723759000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/34\/24\/4151\/5042168"}},"subtitle":[],"editor":[{"given":"John","family":"Hancock","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Seoul National University, Seoul, Republic of Korea"}],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2018,6,21]]},"references-count":39,"journal-issue":{"issue":"24","published-print":{"date-parts":[[2018,12,15]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/bty490","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"type":"print","value":"1367-4803"},{"type":"electronic","value":"1367-4811"}],"subject":[],"published-other":{"date-parts":[[2018,12,15]]},"published":{"date-parts":[[2018,6,21]]}}}