{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T06:42:07Z","timestamp":1776062527250,"version":"3.50.1"},"reference-count":36,"publisher":"Oxford University Press (OUP)","issue":"13","license":[{"start":{"date-parts":[[2018,2,14]],"date-time":"2018-02-14T00:00:00Z","timestamp":1518566400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100007660","name":"University of Antwerp","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100007660","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Fund for Scientific Research, Flanders"},{"DOI":"10.13039\/501100003130","name":"FWO","doi-asserted-by":"publisher","award":["G.0221.12"],"award-info":[{"award-number":["G.0221.12"]}],"id":[{"id":"10.13039\/501100003130","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003130","name":"FWO","doi-asserted-by":"publisher","award":["1513715N"],"award-info":[{"award-number":["1513715N"]}],"id":[{"id":"10.13039\/501100003130","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003130","name":"FWO","doi-asserted-by":"publisher","award":["12D1717N"],"award-info":[{"award-number":["12D1717N"]}],"id":[{"id":"10.13039\/501100003130","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002996","name":"Dutch Heart Foundation","doi-asserted-by":"publisher","award":["2013T093"],"award-info":[{"award-number":["2013T093"]}],"id":[{"id":"10.13039\/501100002996","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001674","name":"Fondation Leducq","doi-asserted-by":"publisher","award":["MIBAVA-Leducq 12CVD03"],"award-info":[{"award-number":["MIBAVA-Leducq 12CVD03"]}],"id":[{"id":"10.13039\/501100001674","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004040","name":"KU Leuven","doi-asserted-by":"publisher","award":["CELSA\/17\/032"],"award-info":[{"award-number":["CELSA\/17\/032"]}],"id":[{"id":"10.13039\/501100004040","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011878","name":"Flemish Government","doi-asserted-by":"crossref","award":["IWT 150865"],"award-info":[{"award-number":["IWT 150865"]}],"id":[{"id":"10.13039\/501100011878","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100011878","name":"Flemish Government","doi-asserted-by":"crossref","award":["FWO 06260"],"award-info":[{"award-number":["FWO 06260"]}],"id":[{"id":"10.13039\/501100011878","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Fund for Scientific Research"},{"DOI":"10.13039\/100010663","name":"European Research Council","doi-asserted-by":"publisher","award":["ERC-StG-2012-30972-BRAVE"],"award-info":[{"award-number":["ERC-StG-2012-30972-BRAVE"]}],"id":[{"id":"10.13039\/100010663","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,7,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Computational gene prioritization can aid in disease gene identification. Here, we propose pBRIT (prioritization using Bayesian Ridge regression and Information Theoretic model), a novel adaptive and scalable prioritization tool, integrating Pubmed abstracts, Gene Ontology, Sequence similarities, Mammalian and Human Phenotype Ontology, Pathway, Interactions, Disease Ontology, Gene Association database and Human Genome Epidemiology database, into the prediction model. We explore and address effects of sparsity and inter-feature dependencies within annotation sources, and the impact of bias towards specific annotations.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>pBRIT models feature dependencies and sparsity by an Information-Theoretic (data driven) approach and applies intermediate integration based data fusion. Following the hypothesis that genes underlying similar diseases will share functional and phenotype characteristics, it incorporates Bayesian Ridge regression to learn a linear mapping between functional and phenotype annotations. Genes are prioritized on phenotypic concordance to the training genes. We evaluated pBRIT against nine existing methods, and on over 2000 HPO-gene associations retrieved after construction of pBRIT data sources. We achieve maximum AUC scores ranging from 0.92 to 0.96 against benchmark datasets and of 0.80 against the time-stamped HPO entries, indicating good performance with high sensitivity and specificity. Our model shows stable performance with regard to changes in the underlying annotation data, is fast and scalable for implementation in routine pipelines.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>http:\/\/biomina.be\/apps\/pbrit\/; https:\/\/bitbucket.org\/medgenua\/pbrit.<\/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\/bty079","type":"journal-article","created":{"date-parts":[[2018,2,12]],"date-time":"2018-02-12T12:19:12Z","timestamp":1518437952000},"page":"2254-2262","source":"Crossref","is-referenced-by-count":26,"title":["pBRIT: gene prioritization by correlating functional and phenotypic annotations through integrative data fusion"],"prefix":"10.1093","volume":"34","author":[{"given":"Ajay Anand","family":"Kumar","sequence":"first","affiliation":[{"name":"Center of Medical Genetics, University of Antwerp and Antwerp University Hospital, Antwerp, Belgium"},{"name":"Biomedical Informatics Research Network Antwerp (biomina), University of Antwerp, Antwerp, Belgium"}]},{"given":"Lut","family":"Van Laer","sequence":"additional","affiliation":[{"name":"Center of Medical Genetics, University of Antwerp and Antwerp University Hospital, Antwerp, Belgium"}]},{"given":"Maaike","family":"Alaerts","sequence":"additional","affiliation":[{"name":"Center of Medical Genetics, University of Antwerp and Antwerp University Hospital, Antwerp, Belgium"}]},{"given":"Amin","family":"Ardeshirdavani","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering (ESAT), STADIUS Center for Dynamical Systems, Signal Processing and Data Analytics, Belgium"},{"name":"imec, Leuven, Belgium"}]},{"given":"Yves","family":"Moreau","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering (ESAT), STADIUS Center for Dynamical Systems, Signal Processing and Data Analytics, Belgium"},{"name":"imec, Leuven, Belgium"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8217-2564","authenticated-orcid":false,"given":"Kris","family":"Laukens","sequence":"additional","affiliation":[{"name":"Biomedical Informatics Research Network Antwerp (biomina), University of Antwerp, Antwerp, Belgium"},{"name":"ADReM Data Laboratory, University of Antwerp, Antwerp, Belgium"}]},{"given":"Bart","family":"Loeys","sequence":"additional","affiliation":[{"name":"Center of Medical Genetics, University of Antwerp and Antwerp University Hospital, Antwerp, Belgium"}]},{"given":"Geert","family":"Vandeweyer","sequence":"additional","affiliation":[{"name":"Center of Medical Genetics, University of Antwerp and Antwerp University Hospital, Antwerp, Belgium"},{"name":"Biomedical Informatics Research Network Antwerp (biomina), University of Antwerp, Antwerp, Belgium"}]}],"member":"286","published-online":{"date-parts":[[2018,2,14]]},"reference":[{"key":"2023051604103841100_bty079-B1","doi-asserted-by":"crossref","first-page":"537","DOI":"10.1038\/nbt1203","article-title":"Gene prioritization through genomic data fusion","volume":"24","author":"Aerts","year":"2006","journal-title":"Nat. Biotechnol"},{"key":"2023051604103841100_bty079-B2","author":"Baglama","year":"2012"},{"key":"2023051604103841100_bty079-B3","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1007\/s10044-007-0096-4","article-title":"The aspect Bernoulli model: multiple causes of presences and absences","volume":"12","author":"Bingham","year":"2009","journal-title":"Pattern Anal. Appl"},{"key":"2023051604103841100_bty079-B4","first-page":"993","article-title":"Latent dirichlet allocation","volume":"3","author":"Blei","year":"2003","journal-title":"J. Mach. Learn. Res"},{"key":"2023051604103841100_bty079-B5","doi-asserted-by":"crossref","first-page":"S2.","DOI":"10.1186\/1755-8794-7-S2-S2","article-title":"Identifying disease genes by integrating multiple data sources","volume":"7","author":"Chen","year":"2014","journal-title":"BMC Med. Genomics"},{"key":"2023051604103841100_bty079-B6","doi-asserted-by":"crossref","first-page":"S2.","DOI":"10.1186\/1755-8794-8-S3-S2","article-title":"A fast and high performance multiple data integration algorithm for identifying human disease genes","volume":"8","author":"Chen","year":"2015","journal-title":"BMC Medical Genomics"},{"key":"2023051604103841100_bty079-B7","doi-asserted-by":"crossref","first-page":"W305","DOI":"10.1093\/nar\/gkp427","article-title":"ToppGene Suite for gene list enrichment analysis and candidate gene prioritization","volume":"37","author":"Chen","year":"2009","journal-title":"Nucleic Acids Res"},{"key":"2023051604103841100_bty079-B8","doi-asserted-by":"crossref","first-page":"e21137.","DOI":"10.1371\/journal.pone.0021137","article-title":"In silico gene prioritization by integrating multiple data sources","volume":"6","author":"Chen","year":"2011","journal-title":"PLoS One"},{"key":"2023051604103841100_bty079-B9","author":"de los Campos","year":"2013"},{"key":"2023051604103841100_bty079-B10","doi-asserted-by":"crossref","first-page":"476","DOI":"10.1093\/bioinformatics\/bts727","article-title":"Assessing identity, redundancy and confounds in Gene Ontology annotations over time","volume":"29","author":"Gillis","year":"2013","journal-title":"Bioinformatics"},{"key":"2023051604103841100_bty079-B11","doi-asserted-by":"crossref","first-page":"8685","DOI":"10.1073\/pnas.0701361104","article-title":"The human disease network","volume":"104","author":"Goh","year":"2007","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"2023051604103841100_bty079-B12","doi-asserted-by":"crossref","first-page":"2671","DOI":"10.1093\/bioinformatics\/bts498","article-title":"Impact of ontology evolution on functional analyses","volume":"28","author":"Gro\u00df","year":"2012","journal-title":"Bioinformatics"},{"key":"2023051604103841100_bty079-B13","doi-asserted-by":"crossref","first-page":"597","DOI":"10.1214\/14-BA868","article-title":"Informative g-priors for logistic regression","volume":"9","author":"Hanson","year":"2014","journal-title":"Bayesian Anal"},{"key":"2023051604103841100_bty079-B14","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1145\/963770.963774","article-title":"Latent semantic models for collaborative filtering","volume":"22","author":"Hofmann","year":"2004","journal-title":"ACM Trans. Inform. Syst"},{"key":"2023051604103841100_bty079-B15","doi-asserted-by":"crossref","first-page":"184","DOI":"10.1186\/s13059-016-1037-6","article-title":"An expanded evaluation of protein function prediction methods shows an improvement in accuracy","volume":"17","author":"Jiang","year":"2016","journal-title":"Genome Biol"},{"key":"2023051604103841100_bty079-B16","doi-asserted-by":"crossref","first-page":"1034","DOI":"10.1093\/bioinformatics\/btu766","article-title":"HyDRA: gene prioritization via hybrid distance-score rank aggregation","volume":"31","author":"Kim","year":"2015","journal-title":"Bioinformatics"},{"key":"2023051604103841100_bty079-B17","doi-asserted-by":"crossref","first-page":"949","DOI":"10.1016\/j.ajhg.2008.02.013","article-title":"Walking the interactome for prioritization of candidate disease genes","volume":"82","author":"Kohler","year":"2008","journal-title":"Am. J. Hum. Genet"},{"key":"2023051604103841100_bty079-B18","doi-asserted-by":"crossref","first-page":"242.","DOI":"10.1186\/1471-2105-14-242","article-title":"GOParGenPy: a high throughput method to generate Gene Ontology data matrices","volume":"14","author":"Kumar","year":"2013","journal-title":"BMC Bioinformatics"},{"key":"2023051604103841100_bty079-B19","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1038\/nbt1295","article-title":"A human phenome-interactome network of protein complexes implicated in genetic disorders","volume":"25","author":"Lage","year":"2007","journal-title":"Nat. Biotechnol"},{"key":"2023051604103841100_bty079-B20","doi-asserted-by":"crossref","first-page":"285","DOI":"10.1038\/nature19057","article-title":"Analysis of protein-coding genetic variation in 60\u00a0706 humans","volume":"536","author":"Lek","year":"2016","journal-title":"Nature"},{"key":"2023051604103841100_bty079-B21","doi-asserted-by":"crossref","first-page":"1219","DOI":"10.1093\/bioinformatics\/btq108","article-title":"Genome-wide inferring gene-phenotype relationship by walking on the heterogeneous network","volume":"26","author":"Li","year":"2010","journal-title":"Bioinformatics"},{"key":"2023051604103841100_bty079-B22","doi-asserted-by":"crossref","first-page":"R57.","DOI":"10.1186\/gb-2011-12-6-r57","article-title":"BioGraph: unsupervised biomedical knowledge discovery via automated hypothesis generation","volume":"12","author":"Liekens","year":"2011","journal-title":"Genome Biol"},{"key":"2023051604103841100_bty079-B23","doi-asserted-by":"crossref","first-page":"523","DOI":"10.1038\/nrg3253","article-title":"Computational tools for prioritizing candidate genes: boosting disease gene discovery","volume":"13","author":"Moreau","year":"2012","journal-title":"Nat. Rev. Genet"},{"key":"2023051604103841100_bty079-B24","doi-asserted-by":"crossref","first-page":"401","DOI":"10.1089\/10665270252935539","article-title":"Learning gene functional classifications from multiple data types","volume":"9","author":"Pavlidis","year":"2002","journal-title":"J. Comput. Biol"},{"key":"2023051604103841100_bty079-B25","doi-asserted-by":"crossref","first-page":"bav028","DOI":"10.1093\/database\/bav028","article-title":"DisGeNET: a discovery platform for the dynamical exploration of human diseases and their genes","volume":"2015","author":"Pinero","year":"2015","journal-title":"Database"},{"key":"2023051604103841100_bty079-B27","doi-asserted-by":"crossref","first-page":"e1000605.","DOI":"10.1371\/journal.pcbi.1000605","article-title":"Annotation error in public databases: misannotation of molecular function in enzyme superfamilies","volume":"5","author":"Schnoes","year":"2009","journal-title":"PLoS Comput. Biol"},{"key":"2023051604103841100_bty079-B28","doi-asserted-by":"crossref","first-page":"393","DOI":"10.1038\/ng.3239","article-title":"De novo loss-or gain-of-function mutations in KCNA2 cause epileptic encephalopathy","volume":"47","author":"Syrbe","year":"2015","journal-title":"Nat. Genet"},{"key":"2023051604103841100_bty079-B151","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1007\/s10766-008-0077-2","article-title":"Snow: A parallel computing framework for the R system","volume":"37","author":"Tierney","year":"2009","journal-title":"International Journal of Parallel Programming"},{"key":"2023051604103841100_bty079-B29","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1093\/bib\/bbq007","article-title":"A guide to web tools to prioritize candidate genes","volume":"12","author":"Tranchevent","year":"2011","journal-title":"Brief. Bioinformatics"},{"key":"2023051604103841100_bty079-B30","doi-asserted-by":"crossref","first-page":"W117","DOI":"10.1093\/nar\/gkw365","article-title":"Candidate gene prioritization with Endeavour","volume":"44","author":"Tranchevent","year":"2016","journal-title":"Nucleic Acids Res"},{"key":"2023051604103841100_bty079-B31","author":"Valdeolivas","year":"2017"},{"key":"2023051604103841100_bty079-B32","doi-asserted-by":"crossref","first-page":"705","DOI":"10.1038\/nmeth.3963","article-title":"Impact of outdated gene annotations on pathway enrichment analysis","volume":"13","author":"Wadi","year":"2016","journal-title":"Nat. Methods"},{"key":"2023051604103841100_bty079-B33","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1038\/msb.2008.27","article-title":"Network-based global inference of human disease genes","volume":"4","author":"Wu","year":"2008","journal-title":"Mol. Syst. Biol"},{"key":"2023051604103841100_bty079-B34","doi-asserted-by":"crossref","first-page":"55.","DOI":"10.1186\/1752-0509-5-55","article-title":"DomainRBF: a Bayesian regression approach to the prioritization of candidate domains for complex diseases","volume":"5","author":"Zhang","year":"2011","journal-title":"BMC Syst. Biol"},{"key":"2023051604103841100_bty079-B35","first-page":"5","article-title":"Do we need more training data or better models for object detection?","volume":"3","author":"Zhu","year":"2012","journal-title":"BMVC"},{"key":"2023051604103841100_bty079-B36","doi-asserted-by":"crossref","first-page":"e1004552.","DOI":"10.1371\/journal.pcbi.1004552","article-title":"Gene prioritization by compressive data fusion and chaining","volume":"11","author":"Zitnik","year":"2015","journal-title":"PLoS Comput. Biol"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/34\/13\/2254\/50316033\/bioinformatics_34_13_2254.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/34\/13\/2254\/50316033\/bioinformatics_34_13_2254.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,16]],"date-time":"2023-05-16T04:13:51Z","timestamp":1684210431000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/34\/13\/2254\/4857360"}},"subtitle":[],"editor":[{"given":"Inanc","family":"Birol","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2018,2,14]]},"references-count":36,"journal-issue":{"issue":"13","published-print":{"date-parts":[[2018,7,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/bty079","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2018,7,1]]},"published":{"date-parts":[[2018,2,14]]}}}