{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T09:05:37Z","timestamp":1775639137828,"version":"3.50.1"},"reference-count":28,"publisher":"Oxford University Press (OUP)","issue":"21","license":[{"start":{"date-parts":[[2017,7,13]],"date-time":"2017-07-13T00:00:00Z","timestamp":1499904000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["U41HG007822"],"award-info":[{"award-number":["U41HG007822"]}],"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":["U41HG002273"],"award-info":[{"award-number":["U41HG002273"]}],"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":["R01GM080646"],"award-info":[{"award-number":["R01GM080646"]}],"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":["P20GM103446"],"award-info":[{"award-number":["P20GM103446"]}],"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":["U01GM120953"],"award-info":[{"award-number":["U01GM120953"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000274","name":"British Heart Foundation","doi-asserted-by":"publisher","award":["RG\/13\/5\/30112"],"award-info":[{"award-number":["RG\/13\/5\/30112"]}],"id":[{"id":"10.13039\/501100000274","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,11,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Biological knowledgebases, such as UniProtKB\/Swiss-Prot, constitute an essential component of daily scientific research by offering distilled, summarized and computable knowledge extracted from the literature by expert curators. While knowledgebases play an increasingly important role in the scientific community, their ability to keep up with the growth of biomedical literature is under scrutiny. Using UniProtKB\/Swiss-Prot as a case study, we address this concern via multiple literature triage approaches.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>With the assistance of the PubTator text-mining tool, we tagged more than 10\u2009000 articles to assess the ratio of papers relevant for curation. We first show that curators read and evaluate many more papers than they curate, and that measuring the number of curated publications is insufficient to provide a complete picture as demonstrated by the fact that 8000\u201310\u2009000 papers are curated in UniProt each year while curators evaluate 50\u2009000\u201370\u2009000 papers per year. We show that 90% of the papers in PubMed are out of the scope of UniProt, that a maximum of 2\u20133% of the papers indexed in PubMed each year are relevant for UniProt curation, and that, despite appearances, expert curation in UniProt is scalable.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>UniProt is freely available at http:\/\/www.uniprot.org\/.<\/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\/btx439","type":"journal-article","created":{"date-parts":[[2017,7,10]],"date-time":"2017-07-10T11:10:36Z","timestamp":1499685036000},"page":"3454-3460","source":"Crossref","is-referenced-by-count":116,"title":["On expert curation and scalability: UniProtKB\/Swiss-Prot as a case study"],"prefix":"10.1093","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7299-6685","authenticated-orcid":false,"given":"Sylvain","family":"Poux","sequence":"first","affiliation":[{"name":"Swiss-Prot Group, SIB Swiss Institute of Bioinformatics, Centre Medical Universitaire, Geneva 4, Switzerland"}]},{"given":"Cecilia N","family":"Arighi","sequence":"additional","affiliation":[{"name":"Protein Information Resource, University of Delaware, Newark, DE, USA"}]},{"given":"Michele","family":"Magrane","sequence":"additional","affiliation":[{"name":"European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Hinxton, Cambridge, UK"}]},{"given":"Alex","family":"Bateman","sequence":"additional","affiliation":[{"name":"European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Hinxton, Cambridge, UK"}]},{"given":"Chih-Hsuan","family":"Wei","sequence":"additional","affiliation":[{"name":"National Center for Biotechnology Information (NCBI), US National Library of Medicine, Bethesda, MD, USA"}]},{"given":"Zhiyong","family":"Lu","sequence":"additional","affiliation":[{"name":"National Center for Biotechnology Information (NCBI), US National Library of Medicine, Bethesda, MD, USA"}]},{"given":"Emmanuel","family":"Boutet","sequence":"additional","affiliation":[{"name":"Swiss-Prot Group, SIB Swiss Institute of Bioinformatics, Centre Medical Universitaire, Geneva 4, Switzerland"}]},{"given":"Hema","family":"Bye-A-Jee","sequence":"additional","affiliation":[{"name":"European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Hinxton, Cambridge, UK"}]},{"given":"Maria Livia","family":"Famiglietti","sequence":"additional","affiliation":[{"name":"Swiss-Prot Group, SIB Swiss Institute of Bioinformatics, Centre Medical Universitaire, Geneva 4, Switzerland"}]},{"given":"Bernd","family":"Roechert","sequence":"additional","affiliation":[{"name":"Swiss-Prot Group, SIB Swiss Institute of Bioinformatics, Centre Medical Universitaire, Geneva 4, Switzerland"}]},{"given":"The","family":"UniProt Consortium","sequence":"additional","affiliation":[{"name":"Swiss-Prot Group, SIB Swiss Institute of Bioinformatics, Centre Medical Universitaire, Geneva 4, Switzerland"},{"name":"Protein Information Resource, University of Delaware, Newark, DE, USA"},{"name":"European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Hinxton, Cambridge, UK"},{"name":"Protein Information Resource, Georgetown University Medical Center, Washington, DC, USA"}]}],"member":"286","published-online":{"date-parts":[[2017,7,13]]},"reference":[{"key":"2023051506351507800_btx439-B2","doi-asserted-by":"crossref","first-page":"452","DOI":"10.1038\/533452a","article-title":"1,500 scientists lift the lid on reproducibility","volume":"533","author":"Baker","year":"2016","journal-title":"Nature"},{"key":"2023051506351507800_btx439-B3","doi-asserted-by":"crossref","first-page":"134.","DOI":"10.12688\/f1000research.6555.1","article-title":"The Resource Identification Initiative: a cultural shift in publishing","volume":"4","author":"Bandrowski","year":"2015","journal-title":"F1000Research"},{"key":"2023051506351507800_btx439-B4","doi-asserted-by":"crossref","first-page":"2454","DOI":"10.1002\/pmic.201600034","article-title":"Strategies to improve usability and preserve accuracy in biological sequence databases","volume":"16","author":"Bengtsson-Palme","year":"2016","journal-title":"Proteomics"},{"key":"2023051506351507800_btx439-B5","doi-asserted-by":"crossref","first-page":"S16","DOI":"10.1038\/527S16a","article-title":"Perspective: Sustaining the big-data ecosystem","volume":"527","author":"Bourne","year":"2015","journal-title":"Nature"},{"key":"2023051506351507800_btx439-B6","doi-asserted-by":"crossref","first-page":"bav120.","DOI":"10.1093\/database\/bav120","article-title":"The UniProtKB guide to the human proteome","volume":"2016","author":"Breuza","year":"2016","journal-title":"Database (Oxford)"},{"key":"2023051506351507800_btx439-B7","doi-asserted-by":"crossref","first-page":"362","DOI":"10.1021\/jm501326k","article-title":"SAR156497, an exquisitely selective inhibitor of aurora kinases","volume":"58","author":"Carry","year":"2015","journal-title":"J. Med. Chem"},{"key":"2023051506351507800_btx439-B8","doi-asserted-by":"crossref","first-page":"308","DOI":"10.1038\/nature18610","article-title":"Ki-67 acts as a biological surfactant to disperse mitotic chromosomes","volume":"535","author":"Cuylen","year":"2016","journal-title":"Nature"},{"key":"2023051506351507800_btx439-B9","doi-asserted-by":"crossref","first-page":"1656","DOI":"10.1093\/jnci\/djr393","article-title":"Assessment of Ki67 in breast cancer: recommendations from the International Ki67 in Breast Cancer working group","volume":"103","author":"Dowsett","year":"2011","journal-title":"J. Natl. Cancer Inst"},{"key":"2023051506351507800_btx439-B10","doi-asserted-by":"crossref","first-page":"1122","DOI":"10.1126\/science.351.6278.1122","article-title":"PLANETARY SCIENCE. Mars orbiter to sniff for methane","volume":"351","author":"Hand","year":"2016","journal-title":"Science (New York, N.Y.)"},{"key":"2023051506351507800_btx439-B11","doi-asserted-by":"crossref","DOI":"10.1093\/database\/baw110","article-title":"How much does curation cost?","volume":"2016","author":"Karp","year":"2016","journal-title":"Database (Oxford)"},{"key":"2023051506351507800_btx439-B12","doi-asserted-by":"crossref","DOI":"10.1093\/database\/bau058","article-title":"Curation accuracy of model organism databases","volume":"2014","author":"Keseler","year":"2014","journal-title":"Database (Oxford)"},{"key":"2023051506351507800_btx439-B13","doi-asserted-by":"crossref","DOI":"10.7554\/eLife.16550","article-title":"Physical association between a novel plasma-membrane structure and centrosome orients cell division","volume":"5","author":"Negishi","year":"2016","journal-title":"eLife"},{"key":"2023051506351507800_btx439-B14","doi-asserted-by":"crossref","first-page":"49.","DOI":"10.1186\/s12915-016-0276-z","article-title":"Model organism databases: essential resources that need the support of both funders and users","volume":"14","author":"Oliver","year":"2016","journal-title":"BMC Biol"},{"key":"2023051506351507800_btx439-B15","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1038\/nature17656","article-title":"Architecture of the mitochondrial calcium uniporter","volume":"533","author":"Oxenoid","year":"2016","journal-title":"Nature"},{"key":"2023051506351507800_btx439-B16","doi-asserted-by":"crossref","first-page":"D1064","DOI":"10.1093\/nar\/gku1002","article-title":"HAMAP in 2015: updates to the protein family classification and annotation system","volume":"43","author":"Pedruzzi","year":"2015","journal-title":"Nucleic Acids Res"},{"key":"2023051506351507800_btx439-B17","doi-asserted-by":"crossref","DOI":"10.1093\/database\/bau016","article-title":"Expert curation in UniProtKB: a case study on dealing with conflicting and erroneous data","volume":"2014","author":"Poux","year":"2014","journal-title":"Database (Oxford)"},{"key":"2023051506351507800_btx439-B18","doi-asserted-by":"crossref","first-page":"509","DOI":"10.1038\/nature.2015.18031","article-title":"Antibody drugs for Alzheimer's show glimmers of promise","volume":"523","author":"Reardon","year":"2015","journal-title":"Nature"},{"key":"2023051506351507800_btx439-B19","doi-asserted-by":"crossref","first-page":"612","DOI":"10.1136\/jclinpath-2015-203340","article-title":"The assessment of Ki-67 as a prognostic marker in neuroendocrine tumours: a systematic review and meta-analysis","volume":"69","author":"Richards-Taylor","year":"2016","journal-title":"J. Clin. Pathol"},{"key":"2023051506351507800_btx439-B20","doi-asserted-by":"crossref","first-page":"355.","DOI":"10.1038\/535355b","article-title":"Research papers: Journals should drive data reproducibility","volume":"535","author":"Santori","year":"2016","journal-title":"Nature"},{"key":"2023051506351507800_btx439-B21","doi-asserted-by":"crossref","first-page":"147.","DOI":"10.1038\/533147a","article-title":"The pressure to publish pushes down quality","volume":"533","author":"Sarewitz","year":"2016","journal-title":"Nature"},{"key":"2023051506351507800_btx439-B22","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":"2023051506351507800_btx439-B23","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1056\/NEJMoa0901867","article-title":"Variants of DENND1B associated with asthma in children","volume":"362","author":"Sleiman","year":"2010","journal-title":"N. Engl. J. Med"},{"key":"2023051506351507800_btx439-B24","doi-asserted-by":"crossref","first-page":"e13722.","DOI":"10.7554\/eLife.13722","article-title":"The cell proliferation antigen Ki-67 organises heterochromatin","volume":"5","author":"Sobecki","year":"2016","journal-title":"eLife"},{"key":"2023051506351507800_btx439-B25","doi-asserted-by":"crossref","first-page":"D158","DOI":"10.1093\/nar\/gkw1099","article-title":"UniProt: the universal protein knowledgebase","volume":"45","author":"UniProt","year":"2017","journal-title":"Nucleic Acids Res"},{"key":"2023051506351507800_btx439-B26","doi-asserted-by":"crossref","DOI":"10.1093\/database\/baw119","article-title":"Overview of the interactive task in BioCreative V","volume":"2016","author":"Wang","year":"2016","journal-title":"Database (Oxford)"},{"key":"2023051506351507800_btx439-B27","doi-asserted-by":"crossref","first-page":"W518","DOI":"10.1093\/nar\/gkt441","article-title":"PubTator: a web-based text mining tool for assisting biocuration","volume":"41","author":"Wei","year":"2013","journal-title":"Nucleic Acids Res"},{"key":"2023051506351507800_btx439-B28","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1016\/j.cell.2015.11.052","article-title":"Regulation of T Cell Receptor Signaling by DENND1B in TH2 Cells and Allergic Disease","volume":"164","author":"Yang","year":"2016","journal-title":"Cell"},{"key":"2023051506351507800_btx439-B29","doi-asserted-by":"crossref","first-page":"680","DOI":"10.1038\/nature18950","article-title":"Thirst neurons anticipate the homeostatic consequences of eating and drinking","volume":"537","author":"Zimmerman","year":"2016","journal-title":"Nature"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/33\/21\/3454\/50315298\/bioinformatics_33_21_3454.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/33\/21\/3454\/50315298\/bioinformatics_33_21_3454.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,15]],"date-time":"2023-05-15T06:35:33Z","timestamp":1684132533000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/33\/21\/3454\/3964379"}},"subtitle":[],"editor":[{"given":"Janet","family":"Kelso","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2017,7,13]]},"references-count":28,"journal-issue":{"issue":"21","published-print":{"date-parts":[[2017,11,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btx439","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2017,11,1]]},"published":{"date-parts":[[2017,7,13]]}}}