{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,22]],"date-time":"2025-02-22T00:45:42Z","timestamp":1740185142609,"version":"3.37.3"},"reference-count":26,"publisher":"Oxford University Press (OUP)","issue":"10","license":[{"start":{"date-parts":[[2020,2,17]],"date-time":"2020-02-17T00:00:00Z","timestamp":1581897600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["1657306","1931134","1419282"],"award-info":[{"award-number":["1657306","1931134","1419282"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"NIH","doi-asserted-by":"publisher","award":["R21CA231904","UL1TR001998-01"],"award-info":[{"award-number":["R21CA231904","UL1TR001998-01"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,5,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>The Gene Ontology (GO) is the unifying biological vocabulary for codifying, managing and sharing biological knowledge. Quality issues in GO, if not addressed, can cause misleading results or missed biological discoveries. Manual identification of potential quality issues in GO is a challenging and arduous task, given its growing size. We introduce an automated auditing approach for suggesting potentially missing is-a relations, which may further reveal erroneous is-a relations.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>We developed a Subsumption-based Sub-term Inference Framework (SSIF) by leveraging a novel term-algebra on top of a sequence-based representation of GO concepts along with three conditional rules (monotonicity, intersection and sub-concept rules). Applying SSIF to the October 3, 2018 release of GO suggested 1938 unique potentially missing is-a relations. Domain experts evaluated a random sample of 210 potentially missing is-a relations. The results showed SSIF achieved a precision of 60.61, 60.49 and 46.03% for the monotonicity, intersection and sub-concept rules, respectively.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>SSIF is implemented in Java. The source code is available at https:\/\/github.com\/rashmie\/SSIF.<\/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\/btaa106","type":"journal-article","created":{"date-parts":[[2020,2,12]],"date-time":"2020-02-12T12:25:46Z","timestamp":1581510346000},"page":"3207-3214","source":"Crossref","is-referenced-by-count":5,"title":["SSIF: Subsumption-based Sub-term Inference Framework to audit Gene Ontology"],"prefix":"10.1093","volume":"36","author":[{"given":"Rashmie","family":"Abeysinghe","sequence":"first","affiliation":[{"name":"School of Biomedical Informatics , University of Texas Health Science Center at Houston, Houston, TX 77030, USA"},{"name":"Department of Computer Science"}]},{"suffix":"III","given":"Eugene W","family":"Hinderer","sequence":"additional","affiliation":[{"name":"Department of Molecular and Cellular Biochemistry"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3995-5368","authenticated-orcid":false,"given":"Hunter N B","family":"Moseley","sequence":"additional","affiliation":[{"name":"Department of Molecular and Cellular Biochemistry"},{"name":"Institute for Biomedical Informatics"},{"name":"Markey Cancer Center"},{"name":"Center for Environmental and Systems Biochemistry , University of Kentucky, Lexington, KY 40506, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5549-8780","authenticated-orcid":false,"given":"Licong","family":"Cui","sequence":"additional","affiliation":[{"name":"School of Biomedical Informatics , University of Texas Health Science Center at Houston, Houston, TX 77030, USA"}]}],"member":"286","published-online":{"date-parts":[[2020,2,17]]},"reference":[{"year":"2017","author":"Abeysinghe","key":"2023013111511747100_btaa106-B1"},{"key":"2023013111511747100_btaa106-B2","first-page":"D322","article-title":"Go PaD: the gene ontology partition database","volume":"35 (Suppl. 1","author":"Alterovitz","year":"2006","journal-title":"Nucleic Acids Res"},{"key":"2023013111511747100_btaa106-B3","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1038\/75556","article-title":"Gene ontology: tool for the unification of biology","volume":"25","author":"Ashburner","year":"2000","journal-title":"Nat. Genet"},{"year":"2018","author":"Balhoff","key":"2023013111511747100_btaa106-B4"},{"key":"2023013111511747100_btaa106-B5","doi-asserted-by":"crossref","first-page":"288","DOI":"10.1093\/bioinformatics\/btn615","article-title":"AmiGO: online access to ontology and annotation data","volume":"25","author":"Carbon","year":"2009","journal-title":"Bioinformatics"},{"key":"2023013111511747100_btaa106-B6","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1016\/j.jbi.2017.12.010","article-title":"Auditing SNOMED CT hierarchical relations based on lexical features of concepts in non-lattice subgraphs","volume":"78","author":"Cui","year":"2017","journal-title":"J. Biomed. Inform"},{"key":"2023013111511747100_btaa106-B7","doi-asserted-by":"crossref","first-page":"788","DOI":"10.1093\/jamia\/ocw175","article-title":"Mining non-lattice subgraphs for detecting missing hierarchical relations and concepts in SNOMED CT","volume":"24","author":"Cui","year":"2017","journal-title":"J. Am. Med. Inform. Assoc"},{"key":"2023013111511747100_btaa106-B8","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4939-3743-1","volume-title":"The Gene Ontology Handbook","author":"Dessimoz","year":"2017"},{"key":"2023013111511747100_btaa106-B9","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1038\/nbt.2463","article-title":"A gene ontology inferred from molecular networks","volume":"31","author":"Dutkowski","year":"2013","journal-title":"Nat. Biotechnol"},{"key":"2023013111511747100_btaa106-B10","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1155\/2013\/594528","article-title":"GOLink: finding cooccurring terms across gene ontology namespaces","volume":"2013","author":"Francis","year":"2013","journal-title":"Int. J. Genomics"},{"key":"2023013111511747100_btaa106-B11","doi-asserted-by":"crossref","first-page":"106","DOI":"10.1016\/j.jbi.2018.09.006","article-title":"Quality assurance of biomedical terminologies and ontologies","volume":"86","author":"Geller","year":"2018","journal-title":"J. Biomed. Inform"},{"key":"2023013111511747100_btaa106-B12","first-page":"D322","article-title":"The gene ontology (GO) project in 2006","volume":"34 (Suppl. 1","year":"2006","journal-title":"Nucleic Acids Res"},{"key":"2023013111511747100_btaa106-B13","first-page":"D330","article-title":"The gene ontology resource: 20 years and still going strong","volume":"47","year":"2018","journal-title":"Nucleic Acids Res"},{"key":"2023013111511747100_btaa106-B14","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s10817-013-9296-3","article-title":"The incredible ELK","volume":"53","author":"Kazakov","year":"2014","journal-title":"J. Autom. Reason"},{"key":"2023013111511747100_btaa106-B15","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1186\/s13326-015-0002-8","article-title":"Completing the is-a structure in light-weight ontologies","volume":"6","author":"Lambrix","year":"2015","journal-title":"J. Biomed. Semantics"},{"key":"2023013111511747100_btaa106-B16","doi-asserted-by":"crossref","first-page":"3448","DOI":"10.1093\/bioinformatics\/bti551","article-title":"BiNGO: a Cytoscape plugin to assess overrepresentation of gene ontology categories in biological networks","volume":"21","author":"Maere","year":"2005","journal-title":"Bioinformatics"},{"key":"2023013111511747100_btaa106-B17","first-page":"195","article-title":"Identifying redundant and missing relations in the gene ontology","volume":"210","author":"Mougin","year":"2015","journal-title":"Stud. Health Technol. Inform"},{"key":"2023013111511747100_btaa106-B18","doi-asserted-by":"crossref","first-page":"1642001","DOI":"10.1142\/S0219720016420014","article-title":"Quality assurance of the gene ontology using abstraction networks","volume":"14","author":"Ochs","year":"2016","journal-title":"J. Bioinform. Comput. Biol"},{"key":"2023013111511747100_btaa106-B19","first-page":"214","article-title":"The compositional structure of Gene Ontology terms","volume":"2004","author":"Ogren","year":"2003","journal-title":"Pac. Symp. Biocomput"},{"key":"2023013111511747100_btaa106-B20","doi-asserted-by":"crossref","first-page":"1185","DOI":"10.1093\/bioinformatics\/btv712","article-title":"Extending gene ontology with gene association networks","volume":"32","author":"Peng","year":"2016","journal-title":"Bioinformatics"},{"key":"2023013111511747100_btaa106-B21","doi-asserted-by":"crossref","first-page":"W193","DOI":"10.1093\/nar\/gkm226","article-title":"g:Profiler - a web-based toolset for functional profiling of gene lists from large-scale experiments","volume":"35 (Suppl. 2","author":"Reimand","year":"2007","journal-title":"Nucleic Acids Res"},{"year":"2003","author":"Toutanova","key":"2023013111511747100_btaa106-B22"},{"key":"2023013111511747100_btaa106-B23","doi-asserted-by":"crossref","first-page":"i77","DOI":"10.1093\/bioinformatics\/btp195","article-title":"Ontology quality assurance through analysis of term transformations","volume":"25","author":"Verspoor","year":"2009","journal-title":"Bioinformatics"},{"key":"2023013111511747100_btaa106-B24","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1186\/s13040-016-0110-8","article-title":"FEDRR: fast, exhaustive detection of redundant hierarchical relations for quality improvement of large biomedical ontologies","volume":"9","author":"Xing","year":"2016","journal-title":"BioData Min"},{"key":"2023013111511747100_btaa106-B25","first-page":"1903","article-title":"Can SNOMED CT changes be used as a surrogate standard for evaluating the performance of its auditing methods?","volume":"2017","author":"Zhang","year":"2017","journal-title":"AMIA Annu. Symp. Proc"},{"key":"2023013111511747100_btaa106-B26","doi-asserted-by":"crossref","first-page":"413","DOI":"10.1016\/j.jbi.2009.03.003","article-title":"A review of auditing methods applied to the content of controlled biomedical terminologies","author":"Zhu","year":"2009","journal-title":"J. Biomed. Inform"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btaa106\/32914402\/btaa106.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/36\/10\/3207\/48990872\/bioinformatics_36_10_3207.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/36\/10\/3207\/48990872\/bioinformatics_36_10_3207.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,31]],"date-time":"2023-01-31T20:58:13Z","timestamp":1675198693000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/36\/10\/3207\/5739437"}},"subtitle":[],"editor":[{"given":"Pier","family":"Luigi Martelli","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2020,2,17]]},"references-count":26,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2020,5,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btaa106","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"type":"print","value":"1367-4803"},{"type":"electronic","value":"1367-4811"}],"subject":[],"published-other":{"date-parts":[[2020,5,15]]},"published":{"date-parts":[[2020,2,17]]}}}