{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T13:08:43Z","timestamp":1751288923414,"version":"3.37.3"},"reference-count":31,"publisher":"Oxford University Press (OUP)","issue":"4","license":[{"start":{"date-parts":[[2017,9,26]],"date-time":"2017-09-26T00:00:00Z","timestamp":1506384000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/about_us\/legal\/notices"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,2,15]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>The increase in publication rates makes it challenging for an individual researcher to stay abreast of all relevant research in order to find novel research hypotheses. Literature-based discovery methods make use of knowledge graphs built using text mining and can infer future associations between biomedical concepts that will likely occur in new publications. These predictions are a valuable resource for researchers to explore a research topic. Current methods for prediction are based on the local structure of the knowledge graph. A method that uses global knowledge from across the knowledge graph needs to be developed in order to make knowledge discovery a frequently used tool by researchers.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>We propose an approach based on the singular value decomposition (SVD) that is able to combine data from across the knowledge graph through a reduced representation. Using cooccurrence data extracted from published literature, we show that SVD performs better than the leading methods for scoring discoveries. We also show the diminishing predictive power of knowledge discovery as we compare our predictions with real associations that appear further into the future. Finally, we examine the strengths and weaknesses of the SVD approach against another well-performing system using several predicted associations.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>All code and results files for this analysis can be accessed at https:\/\/github.com\/jakelever\/knowledgediscovery.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Supplementary information<\/jats:title>\n                  <jats:p>Supplementary data are available at Bioinformatics online.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btx613","type":"journal-article","created":{"date-parts":[[2017,9,25]],"date-time":"2017-09-25T11:09:52Z","timestamp":1506337792000},"page":"652-659","source":"Crossref","is-referenced-by-count":22,"title":["A collaborative filtering-based approach to biomedical knowledge discovery"],"prefix":"10.1093","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8198-2939","authenticated-orcid":false,"given":"Jake","family":"Lever","sequence":"first","affiliation":[{"name":"Canada\u2019s Michael Smith Genome Sciences Centre, Vancouver, BC, Canada"},{"name":"University of British Columbia, Vancouver, BC, Canada"}]},{"given":"Sitanshu","family":"Gakkhar","sequence":"additional","affiliation":[{"name":"Canada\u2019s Michael Smith Genome Sciences Centre, Vancouver, BC, Canada"}]},{"given":"Michael","family":"Gottlieb","sequence":"additional","affiliation":[{"name":"Canada\u2019s Michael Smith Genome Sciences Centre, Vancouver, BC, Canada"}]},{"given":"Tahereh","family":"Rashnavadi","sequence":"additional","affiliation":[{"name":"Canada\u2019s Michael Smith Genome Sciences Centre, Vancouver, BC, Canada"}]},{"given":"Santina","family":"Lin","sequence":"additional","affiliation":[{"name":"Canada\u2019s Michael Smith Genome Sciences Centre, Vancouver, BC, Canada"}]},{"given":"Celia","family":"Siu","sequence":"additional","affiliation":[{"name":"Canada\u2019s Michael Smith Genome Sciences Centre, Vancouver, BC, Canada"}]},{"given":"Maia","family":"Smith","sequence":"additional","affiliation":[{"name":"Canada\u2019s Michael Smith Genome Sciences Centre, Vancouver, BC, Canada"}]},{"given":"Martin R","family":"Jones","sequence":"additional","affiliation":[{"name":"Canada\u2019s Michael Smith Genome Sciences Centre, Vancouver, BC, Canada"}]},{"given":"Martin","family":"Krzywinski","sequence":"additional","affiliation":[{"name":"Canada\u2019s Michael Smith Genome Sciences Centre, Vancouver, BC, Canada"}]},{"given":"Steven J M","family":"Jones","sequence":"additional","affiliation":[{"name":"Canada\u2019s Michael Smith Genome Sciences Centre, Vancouver, BC, Canada"},{"name":"University of British Columbia, Vancouver, BC, Canada"},{"name":"Simon Fraser University, Burnaby, BC, Canada"}]}],"member":"286","published-online":{"date-parts":[[2017,9,26]]},"reference":[{"key":"2023012712332288500_btx613-B1","doi-asserted-by":"crossref","first-page":"571","DOI":"10.1016\/j.tibtech.2006.10.002","article-title":"Text mining and its potential applications in systems biology","volume":"24","author":"Ananiadou","year":"2006","journal-title":"Trends Biotechnol"},{"year":"2007","author":"Bennett","key":"2023012712332288500_btx613-B2"},{"year":"2006","author":"Bird","key":"2023012712332288500_btx613-B3"},{"year":"2016","author":"Bruskiewich","key":"2023012712332288500_btx613-B4"},{"key":"2023012712332288500_btx613-B5","doi-asserted-by":"crossref","first-page":"e333.","DOI":"10.1038\/tp.2013.106","article-title":"Flap pharmacological blockade modulates metabolism of endogenous tau in vivo","volume":"3","author":"Chu","year":"2013","journal-title":"Trans. Psychiatry"},{"key":"2023012712332288500_btx613-B6","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1075\/ijcl.14.2.02dav","article-title":"The 385+ million word Corpus of Contemporary American English (1990\u20142008+):","volume":"14","author":"Davies","year":"2009","journal-title":"Int. J. Corpus Linguist"},{"key":"2023012712332288500_btx613-B7","doi-asserted-by":"crossref","first-page":"158","DOI":"10.1016\/0002-9343(89)90261-1","article-title":"Fish-oil dietary supplementation in patients with raynaud\u2019s phenomenon: a double-blind, controlled, prospective study","volume":"86","author":"DiGiacomo","year":"1989","journal-title":"Am. J. Med"},{"key":"2023012712332288500_btx613-B8","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/BF02288367","article-title":"The approximation of one matrix by another of lower rank","volume":"1","author":"Eckart","year":"1936","journal-title":"Psychometrika"},{"key":"2023012712332288500_btx613-B9","doi-asserted-by":"crossref","first-page":"W406","DOI":"10.1093\/nar\/gkn215","article-title":"Copub: a literature-based keyword enrichment tool for microarray data analysis","volume":"36","author":"Frijters","year":"2008","journal-title":"Nucleic Acids Res"},{"key":"2023012712332288500_btx613-B10","doi-asserted-by":"crossref","first-page":"59.","DOI":"10.1186\/1471-2105-15-59","article-title":"Large-scale biomedical concept recognition: an evaluation of current automatic annotators and their parameters","volume":"15","author":"Funk","year":"2014","journal-title":"BMC Bioinformatics"},{"key":"2023012712332288500_btx613-B11","doi-asserted-by":"crossref","first-page":"674","DOI":"10.1002\/(SICI)1097-4571(199806)49:8<674::AID-ASI2>3.0.CO;2-T","article-title":"Using latent semantic indexing for literature based discovery","volume":"49","author":"Gordon","year":"1998","journal-title":"J. Am. Soc. Inform. Sci"},{"key":"2023012712332288500_btx613-B12","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1007\/978-3-540-68690-3_10","volume-title":"Literature-Based Discovery","author":"Hersh","year":"2008"},{"key":"2023012712332288500_btx613-B13","doi-asserted-by":"crossref","first-page":"e0149621.","DOI":"10.1371\/journal.pone.0149621","article-title":"The Implicitome: a resource for rationalizing gene-disease associations","volume":"11","author":"Hettne","year":"2016","journal-title":"PloS One"},{"key":"2023012712332288500_btx613-B14","doi-asserted-by":"crossref","first-page":"14","DOI":"10.2174\/1871525711311010005","article-title":"Using literature-based discovery to identify novel therapeutic approaches","volume":"11","author":"Hristovski","year":"2013","journal-title":"Cardiovasc. Hematol. Agents Med. Chem"},{"key":"2023012712332288500_btx613-B15","doi-asserted-by":"crossref","first-page":"R96","DOI":"10.1186\/gb-2008-9-6-r96","article-title":"Anni 2.0: a multipurpose text-mining tool for the life sciences","volume":"9","author":"Jelier","year":"2008","journal-title":"Genome Biol"},{"key":"2023012712332288500_btx613-B16","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1016\/j.ijmedinf.2007.07.004","article-title":"Literature-based concept profiles for gene annotation: the issue of weighting","volume":"77","author":"Jelier","year":"2008","journal-title":"Int. J. Med. Inform"},{"key":"2023012712332288500_btx613-B17","doi-asserted-by":"crossref","first-page":"1011","DOI":"10.1007\/s00264-014-2319-9","article-title":"Interference in the endplate nutritional pathway causes intervertebral disc degeneration in an immature porcine model","volume":"38","author":"Kang","year":"2014","journal-title":"Int. Orthop"},{"year":"2008","author":"Kilicoglu","key":"2023012712332288500_btx613-B18"},{"key":"2023012712332288500_btx613-B19","doi-asserted-by":"crossref","first-page":"1019","DOI":"10.1002\/asi.20591","article-title":"The link-prediction problem for social networks","volume":"58","author":"Liben-Nowell","year":"2007","journal-title":"J. Am. Soc. Inform. Sci. Technol"},{"year":"2012","author":"Lichtnwalter","key":"2023012712332288500_btx613-B20"},{"key":"2023012712332288500_btx613-B21","first-page":"2181","volume-title":"AAAI","author":"Lin","year":"2015"},{"key":"2023012712332288500_btx613-B22","article-title":"Graphlab: A new framework for parallel machine learning","author":"Low","year":"2014","journal-title":"arXiv Preprint arXiv"},{"year":"2008","author":"Pan","key":"2023012712332288500_btx613-B23"},{"key":"2023012712332288500_btx613-B24","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1111\/j.1365-2141.2010.08477.x","article-title":"Renal dysfunction in patients with thalassaemia","volume":"153","author":"Quinn","year":"2011","journal-title":"Br. J. Haematol"},{"key":"2023012712332288500_btx613-B25","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1353\/pbm.1986.0087","article-title":"Fish oil, raynauday syndrome, and undiscovered public knowledge","volume":"30","author":"Swanson","year":"1986","journal-title":"Perspect. Biol. Med"},{"key":"2023012712332288500_btx613-B26","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1016\/S0004-3702(97)00008-8","article-title":"An interactive system for finding complementary literatures: a stimulus to scientific discovery","volume":"91","author":"Swanson","year":"1997","journal-title":"Artif. Intell"},{"key":"2023012712332288500_btx613-B27","doi-asserted-by":"crossref","first-page":"382","DOI":"10.1007\/11573036_36","volume-title":"Advances in Informatics","author":"Tsuruoka","year":"2005"},{"key":"2023012712332288500_btx613-B28","doi-asserted-by":"crossref","first-page":"i111","DOI":"10.1093\/bioinformatics\/btr214","article-title":"Discovering and visualizing indirect associations between biomedical concepts","volume":"27","author":"Tsuruoka","year":"2011","journal-title":"Bioinformatics"},{"key":"2023012712332288500_btx613-B29","doi-asserted-by":"crossref","first-page":"e55814.","DOI":"10.1371\/journal.pone.0055814","article-title":"Large-scale event extraction from literature with multi-level gene normalization","volume":"8","author":"Van Landeghem","year":"2013","journal-title":"PloS One"},{"volume-title":"Numerical Recipes: The Art of Scientific Computing","year":"2007","author":"William","key":"2023012712332288500_btx613-B30"},{"key":"2023012712332288500_btx613-B31","doi-asserted-by":"crossref","first-page":"633","DOI":"10.1016\/j.jbi.2008.12.001","article-title":"A new evaluation methodology for literature-based discovery systems","volume":"42","author":"Yetisgen-Yildiz","year":"2009","journal-title":"J. Biomed. Inform"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/34\/4\/652\/48913833\/bioinformatics_34_4_652.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/34\/4\/652\/48913833\/bioinformatics_34_4_652.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T13:21:15Z","timestamp":1674825675000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/34\/4\/652\/4237509"}},"subtitle":[],"editor":[{"given":"Jonathan","family":"Wren","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2017,9,26]]},"references-count":31,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2018,2,15]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btx613","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"type":"print","value":"1367-4803"},{"type":"electronic","value":"1367-4811"}],"subject":[],"published-other":{"date-parts":[[2018,2,15]]},"published":{"date-parts":[[2017,9,26]]}}}