{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T01:34:48Z","timestamp":1768872888771,"version":"3.49.0"},"reference-count":19,"publisher":"Oxford University Press (OUP)","issue":"16","license":[{"start":{"date-parts":[[2020,5,29]],"date-time":"2020-05-29T00:00:00Z","timestamp":1590710400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["GM083107"],"award-info":[{"award-number":["GM083107"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["GM136422"],"award-info":[{"award-number":["GM136422"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["AI134678"],"award-info":[{"award-number":["AI134678"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["DBI1564756"],"award-info":[{"award-number":["DBI1564756"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS1901191"],"award-info":[{"award-number":["IIS1901191"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","award":["201506240207"],"award-info":[{"award-number":["201506240207"]}],"id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,8,15]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Many protein function databases are built on automated or semi-automated curations and can contain various annotation errors. The correction of such misannotations is critical to improving the accuracy and reliability of the databases.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>We proposed a new approach to detect potentially incorrect Gene Ontology (GO) annotations by comparing the ratio of annotation rates (RAR) for the same GO term across different taxonomic groups, where those with a relatively low RAR usually correspond to incorrect annotations. As an illustration, we applied the approach to 20 commonly studied species in two recent UniProt-GOA releases and identified 250 potential misannotations in the 2018-11-6 release, where only 25% of them were corrected in the 2019-6-3 release. Importantly, 56% of the misannotations are \u2018Inferred from Biological aspect of Ancestor (IBA)\u2019 which is in contradiction with previous observations that attributed misannotations mainly to \u2018Inferred from Sequence or structural Similarity (ISS)\u2019, probably reflecting an error source shift due to the new developments of function annotation databases. The results demonstrated a simple but efficient misannotation detection approach that is useful for large-scale comparative protein function studies.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>https:\/\/zhanglab.ccmb.med.umich.edu\/RAR.<\/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\/btaa548","type":"journal-article","created":{"date-parts":[[2020,5,26]],"date-time":"2020-05-26T11:09:28Z","timestamp":1590491368000},"page":"4383-4388","source":"Crossref","is-referenced-by-count":15,"title":["Detecting Gene Ontology misannotations using taxon-specific rate ratio comparisons"],"prefix":"10.1093","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7576-4820","authenticated-orcid":false,"given":"Xiaoqiong","family":"Wei","sequence":"first","affiliation":[{"name":"State Key Laboratory of Biotherapy and Cancer Center\/Collaborative Innovation Center of Biotherapy, West China Hospital, Sichuan University , Chengdu, Sichuan 610041,","place":["China"]},{"name":"Department of Computational Medicine and Bioinformatics"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7290-1324","authenticated-orcid":false,"given":"Chengxin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Computational Medicine and Bioinformatics"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lydia","family":"Freddolino","sequence":"additional","affiliation":[{"name":"Department of Computational Medicine and Bioinformatics"},{"name":"Department of Biological Chemistry, University of Michigan , Ann Arbor, MI 48109,","place":["USA"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Computational Medicine and Bioinformatics"},{"name":"Department of Biological Chemistry, University of Michigan , Ann Arbor, MI 48109,","place":["USA"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2020,5,29]]},"reference":[{"key":"2025050920014313200_btaa548-B1","doi-asserted-by":"crossref","first-page":"284","DOI":"10.1186\/1471-2105-8-284","article-title":"Exploring inconsistencies in genome-wide protein function annotations: a machine learning approach","volume":"8","author":"Andorf","year":"2007","journal-title":"BMC Bioinformatics"},{"key":"2025050920014313200_btaa548-B2","doi-asserted-by":"crossref","first-page":"D506","DOI":"10.1093\/nar\/gky1049","article-title":"UniProt: a worldwide hub of protein knowledge","volume":"47","author":"Bateman","year":"2019","journal-title":"Nucleic Acids Res"},{"key":"2025050920014313200_btaa548-B3","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1128\/AAC.00558-10","article-title":"Structure of the Mycobacterium tuberculosis d-alanine: d-alanine ligase, a target of the antituberculosis drug d-cycloserine","volume":"55","author":"Bruning","year":"2011","journal-title":"Antimicrob. Agents Chemother"},{"key":"2025050920014313200_btaa548-B4","doi-asserted-by":"crossref","first-page":"530","DOI":"10.1186\/1471-2105-11-530","article-title":"Formalization of taxon-based constraints to detect inconsistencies in annotation and ontology development","volume":"11","author":"Deegan","year":"2010","journal-title":"BMC Bioinformatics"},{"key":"2025050920014313200_btaa548-B5","doi-asserted-by":"crossref","first-page":"53","DOI":"10.32614\/RJ-2010-008","article-title":"Two-sided exact tests and matching confidence intervals for discrete data","volume":"2","author":"Fay","year":"2010","journal-title":"R. J"},{"key":"2025050920014313200_btaa548-B6","doi-asserted-by":"crossref","first-page":"449","DOI":"10.1093\/bib\/bbr042","article-title":"Phylogenetic-based propagation of functional annotations within the gene ontology consortium","volume":"12","author":"Gaudet","year":"2011","journal-title":"Brief. Bioinf"},{"key":"2025050920014313200_btaa548-B7","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1186\/2047-217X-3-4","article-title":"Understanding how and why the gene ontology and its annotations evolve: the GO within UniProt","volume":"3","author":"Huntley","year":"2014","journal-title":"Gigascience"},{"key":"2025050920014313200_btaa548-B8","doi-asserted-by":"crossref","first-page":"D1057","DOI":"10.1093\/nar\/gku1113","article-title":"The GOA database: gene ontology annotation updates for 2015","volume":"43","author":"Huntley","year":"2015","journal-title":"Nucleic Acids Res"},{"key":"2025050920014313200_btaa548-B9","article-title":"Estimating the annotation error rate of curated GO database sequence annotations","volume":"8, 170","author":"Jones","year":"2007","journal-title":"BMC Bioinformatics"},{"key":"2025050920014313200_btaa548-B10","doi-asserted-by":"crossref","first-page":"1236","DOI":"10.1093\/bioinformatics\/btu031","article-title":"InterProScan 5: genome-scale protein function classification","volume":"30","author":"Jones","year":"2014","journal-title":"Bioinformatics"},{"key":"2025050920014313200_btaa548-B11","doi-asserted-by":"crossref","first-page":"bau058","DOI":"10.1093\/database\/bau058","article-title":"Curation accuracy of model organism databases","volume":"2014","author":"Keseler","year":"2014","journal-title":"Database"},{"key":"2025050920014313200_btaa548-B12","doi-asserted-by":"crossref","first-page":"D419","DOI":"10.1093\/nar\/gky1038","article-title":"PANTHER version 14: more genomes, a new PANTHER GO-slim and improvements in enrichment analysis tools","volume":"47","author":"Mi","year":"2019","journal-title":"Nucleic Acids Res"},{"key":"2025050920014313200_btaa548-B13","doi-asserted-by":"crossref","first-page":"4864","DOI":"10.1073\/pnas.0811058106","article-title":"A family of Salmonella virulence factors functions as a distinct class of autoregulated E3 ubiquitin ligases","volume":"106","author":"Quezada","year":"2009","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"2025050920014313200_btaa548-B14","doi-asserted-by":"crossref","first-page":"20201","DOI":"10.1074\/jbc.270.34.20201","article-title":"Identification of Plakoglobin domains required for association with N-cadherin and alpha-catenin","volume":"270","author":"Sacco","year":"1995","journal-title":"J. Biol. Chem"},{"key":"2025050920014313200_btaa548-B15","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":"2025050920014313200_btaa548-B16","doi-asserted-by":"crossref","first-page":"e1003063","DOI":"10.1371\/journal.pcbi.1003063","article-title":"Biases in the experimental annotations of protein function and their effect on our understanding of protein function space","volume":"9","author":"Schnoes","year":"2013","journal-title":"PLoS Comput. Biol"},{"key":"2025050920014313200_btaa548-B17","doi-asserted-by":"crossref","first-page":"e1002533","DOI":"10.1371\/journal.pcbi.1002533","article-title":"Quality of computationally inferred gene ontology annotations","volume":"8","author":"Skunca","year":"2012","journal-title":"PLoS Comput. Biol"},{"key":"2025050920014313200_btaa548-B18","doi-asserted-by":"crossref","first-page":"1673","DOI":"10.1021\/bi00220a033","article-title":"Existence of two d-alanine-d-alanine ligases in Escherichia coli: cloning and sequencing of the DdlA gene and purification and characterization of the DdlA and DdlB enzymes","volume":"30","author":"Zawadzke","year":"1991","journal-title":"Biochemistry"},{"key":"2025050920014313200_btaa548-B19","doi-asserted-by":"crossref","first-page":"4186","DOI":"10.1021\/acs.jproteome.8b00453","article-title":"Structure and protein interaction-based gene ontology annotations reveal likely functions of uncharacterized proteins on human chromosome 17","volume":"17","author":"Zhang","year":"2018","journal-title":"J. Proteome Res"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btaa548\/33709188\/btaa548.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/36\/16\/4383\/50677562\/btaa548.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/36\/16\/4383\/50677562\/btaa548.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,10]],"date-time":"2025-05-10T00:01:53Z","timestamp":1746835313000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/36\/16\/4383\/5848643"}},"subtitle":[],"editor":[{"given":"Zhiyong","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2020,5,29]]},"references-count":19,"journal-issue":{"issue":"16","published-print":{"date-parts":[[2020,8,15]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btaa548","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2020,8,15]]},"published":{"date-parts":[[2020,5,29]]}}}