{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,25]],"date-time":"2026-07-25T07:17:08Z","timestamp":1784963828402,"version":"3.55.0"},"reference-count":27,"publisher":"Oxford University Press (OUP)","issue":"D1","license":[{"start":{"date-parts":[[2020,10,30]],"date-time":"2020-10-30T00:00:00Z","timestamp":1604016000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"European Union's Horizon 2020 MSCA-RISE action","award":["823886"],"award-info":[{"award-number":["823886"]}]},{"DOI":"10.13039\/100010269","name":"Wellcome","doi-asserted-by":"publisher","award":["108433\/Z\/15\/Z"],"award-info":[{"award-number":["108433\/Z\/15\/Z"]}],"id":[{"id":"10.13039\/100010269","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000268","name":"BBSRC","doi-asserted-by":"publisher","award":["BB\/S020381\/1"],"award-info":[{"award-number":["BB\/S020381\/1"]}],"id":[{"id":"10.13039\/501100000268","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Open Targets"},{"name":"European Molecular Biology Laboratory Core Funds"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,1,8]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>The Pfam database is a widely used resource for classifying protein sequences into families and domains. Since Pfam was last described in this journal, over 350 new families have been added in Pfam 33.1 and numerous improvements have been made to existing entries. To facilitate research on COVID-19, we have revised the Pfam entries that cover the SARS-CoV-2 proteome, and built new entries for regions that were not covered by Pfam. We have reintroduced Pfam-B which provides an automatically generated supplement to Pfam and contains 136 730 novel clusters of sequences that are not yet matched by a Pfam family. The new Pfam-B is based on a clustering by the MMseqs2 software. We have compared all of the regions in the RepeatsDB to those in Pfam and have started to use the results to build and refine Pfam repeat families. Pfam is freely available for browsing and download at http:\/\/pfam.xfam.org\/.<\/jats:p>","DOI":"10.1093\/nar\/gkaa913","type":"journal-article","created":{"date-parts":[[2020,10,6]],"date-time":"2020-10-06T11:39:25Z","timestamp":1601984365000},"page":"D412-D419","source":"Crossref","is-referenced-by-count":6356,"title":["Pfam: The protein families database in 2021"],"prefix":"10.1093","volume":"49","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2479-5322","authenticated-orcid":false,"given":"Jaina","family":"Mistry","sequence":"first","affiliation":[{"name":"European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Hinxton CB10 1SD, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0520-0736","authenticated-orcid":false,"given":"Sara","family":"Chuguransky","sequence":"additional","affiliation":[{"name":"European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Hinxton CB10 1SD, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5551-8526","authenticated-orcid":false,"given":"Lowri","family":"Williams","sequence":"additional","affiliation":[{"name":"European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Hinxton CB10 1SD, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2208-4236","authenticated-orcid":false,"given":"Matloob","family":"Qureshi","sequence":"additional","affiliation":[{"name":"European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Hinxton CB10 1SD, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gustavo\u00a0A","family":"Salazar","sequence":"additional","affiliation":[{"name":"European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Hinxton CB10 1SD, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Erik L L","family":"Sonnhammer","sequence":"additional","affiliation":[{"name":"Department of Biochemistry and Biophysics, Science for Life Laboratory, Stockholm University, Box 1031, 17121 Solna, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4525-7793","authenticated-orcid":false,"given":"Silvio C E","family":"Tosatto","sequence":"additional","affiliation":[{"name":"Department of Biomedical Sciences, University of Padua, 35131 Padova, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0011-9397","authenticated-orcid":false,"given":"Lisanna","family":"Paladin","sequence":"additional","affiliation":[{"name":"Department of Biomedical Sciences, University of Padua, 35131 Padova, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1973-6347","authenticated-orcid":false,"given":"Shriya","family":"Raj","sequence":"additional","affiliation":[{"name":"European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Hinxton CB10 1SD, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3655-5660","authenticated-orcid":false,"given":"Lorna J","family":"Richardson","sequence":"additional","affiliation":[{"name":"European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Hinxton CB10 1SD, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6982-4660","authenticated-orcid":false,"given":"Robert D","family":"Finn","sequence":"additional","affiliation":[{"name":"European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Hinxton CB10 1SD, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8626-2148","authenticated-orcid":false,"given":"Alex","family":"Bateman","sequence":"additional","affiliation":[{"name":"European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Hinxton CB10 1SD, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2020,10,30]]},"reference":[{"key":"2021010313124666100_B1","doi-asserted-by":"crossref","first-page":"405","DOI":"10.1002\/(SICI)1097-0134(199707)28:3<405::AID-PROT10>3.0.CO;2-L","article-title":"Pfam: a comprehensive database of protein domain families based on seed alignments","volume":"28","author":"Sonnhammer","year":"1997","journal-title":"Proteins"},{"key":"2021010313124666100_B2","doi-asserted-by":"crossref","first-page":"D427","DOI":"10.1093\/nar\/gky995","article-title":"The Pfam protein families database in 2019","volume":"47","author":"El-Gebali","year":"2019","journal-title":"Nucleic Acids Res."},{"key":"2021010313124666100_B3","doi-asserted-by":"crossref","first-page":"D279","DOI":"10.1093\/nar\/gkv1344","article-title":"The Pfam protein families database: towards a more sustainable future","volume":"44","author":"Finn","year":"2016","journal-title":"Nucleic Acids Res."},{"key":"2021010313124666100_B4","doi-asserted-by":"crossref","first-page":"D506","DOI":"10.1093\/nar\/gky1049","article-title":"UniProt: a worldwide hub of protein knowledge","volume":"47","author":"Consortium","year":"2019","journal-title":"Nucleic Acids Res."},{"key":"2021010313124666100_B5","doi-asserted-by":"crossref","first-page":"e18910","DOI":"10.1371\/journal.pone.0018910","article-title":"Representative proteomes: a stable, scalable and unbiased proteome set for sequence analysis and functional annotation","volume":"6","author":"Chen","year":"2011","journal-title":"PLoS One"},{"key":"2021010313124666100_B6","doi-asserted-by":"crossref","first-page":"D247","DOI":"10.1093\/nar\/gkj149","article-title":"Pfam: clans, web tools and services","volume":"34","author":"Finn","year":"2006","journal-title":"Nucleic Acids Res."},{"key":"2021010313124666100_B7","doi-asserted-by":"crossref","first-page":"951","DOI":"10.1093\/bioinformatics\/bti125","article-title":"Protein homology detection by HMM-HMM comparison","volume":"21","author":"S\u00f6ding","year":"2005","journal-title":"Bioinformatics"},{"key":"2021010313124666100_B8","doi-asserted-by":"crossref","first-page":"baw139","DOI":"10.1093\/database\/baw139","article-title":"Minimizing proteome redundancy in the UniProt Knowledgebase","volume":"2016","author":"Bursteinas","year":"2016","journal-title":"Database"},{"key":"2021010313124666100_B9","doi-asserted-by":"crossref","first-page":"980","DOI":"10.1038\/nsb1203-980","article-title":"Announcing the worldwide Protein Data Bank","volume":"10","author":"Berman","year":"2003","journal-title":"Nat. Struct. Biol."},{"key":"2021010313124666100_B10","doi-asserted-by":"crossref","first-page":"D301","DOI":"10.1093\/nar\/gkl971","article-title":"The worldwide Protein Data Bank (wwPDB): ensuring a single, uniform archive of PDB data","volume":"35","author":"Berman","year":"2007","journal-title":"Nucleic Acids Res."},{"key":"2021010313124666100_B11","first-page":"D570","article-title":"MGnify: the microbiome analysis resource in 2020","volume":"48","author":"Mitchell","year":"2020","journal-title":"Nucleic Acids Res."},{"key":"2021010313124666100_B12","doi-asserted-by":"crossref","first-page":"D351","DOI":"10.1093\/nar\/gky1100","article-title":"InterPro in 2019: improving coverage, classification and access to protein sequence annotations","volume":"47","author":"Mitchell","year":"2019","journal-title":"Nucleic Acids Res."},{"key":"2021010313124666100_B13","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1016\/j.antiviral.2017.11.001","article-title":"Nsp3 of coronaviruses: Structures and functions of a large multi-domain protein","volume":"149","author":"Lei","year":"2018","journal-title":"Antiviral Res."},{"key":"2021010313124666100_B14","doi-asserted-by":"crossref","first-page":"e01925-19","DOI":"10.1128\/JVI.01925-19","article-title":"Nucleocapsid protein recruitment to replication\u2013transcription complexes plays a crucial role in coronaviral life cycle","volume":"94","author":"Cong","year":"2020","journal-title":"J. Virol."},{"key":"2021010313124666100_B15","doi-asserted-by":"crossref","first-page":"D624","DOI":"10.1093\/nar\/gkx1134","article-title":"The MEROPS database of proteolytic enzymes, their substrates and inhibitors in 2017 and a comparison with peptidases in the PANTHER database","volume":"46","author":"Rawlings","year":"2018","journal-title":"Nucleic Acids Res."},{"key":"2021010313124666100_B16","doi-asserted-by":"crossref","first-page":"2342","DOI":"10.1038\/s41467-019-10280-3","article-title":"Structure of the SARS-CoV nsp12 polymerase bound to nsp7 and nsp8 co-factors","volume":"10","author":"Kirchdoerfer","year":"2019","journal-title":"Nat. Commun."},{"key":"2021010313124666100_B17","doi-asserted-by":"crossref","first-page":"9436","DOI":"10.1073\/pnas.1508686112","article-title":"Structural basis and functional analysis of the SARS coronavirus nsp14-nsp10 complex","volume":"112","author":"Ma","year":"2015","journal-title":"Proc. Natl. Acad. Sci. U.S.A."},{"key":"2021010313124666100_B18","doi-asserted-by":"crossref","first-page":"1596","DOI":"10.1002\/pro.3873","article-title":"Crystal structure of Nsp15 endoribonuclease NendoU from SARS-CoV-2","volume":"29","author":"Kim","year":"2020","journal-title":"Protein Sci."},{"key":"2021010313124666100_B19","doi-asserted-by":"crossref","first-page":"D188","DOI":"10.1093\/nar\/gki096","article-title":"ADDA: a domain database with global coverage of the protein universe","volume":"33","author":"Heger","year":"2005","journal-title":"Nucleic Acids Res."},{"key":"2021010313124666100_B20","doi-asserted-by":"crossref","first-page":"3389","DOI":"10.1093\/nar\/25.17.3389","article-title":"Gapped BLAST and PSI-BLAST: a new generation of protein database search programs","volume":"25","author":"Altschul","year":"1997","journal-title":"Nucleic Acids Res."},{"key":"2021010313124666100_B21","doi-asserted-by":"crossref","first-page":"1323","DOI":"10.1093\/bioinformatics\/btw006","article-title":"MMseqs software suite for fast and deep clustering and searching of large protein sequence sets","volume":"32","author":"Hauser","year":"2016","journal-title":"Bioinformatics"},{"key":"2021010313124666100_B22","doi-asserted-by":"crossref","first-page":"33964","DOI":"10.1038\/srep33964","article-title":"FAMSA: fast and accurate multiple sequence alignment of huge protein families","volume":"6","author":"Deorowicz","year":"2016","journal-title":"Sci. Rep."},{"key":"2021010313124666100_B23","doi-asserted-by":"crossref","first-page":"1162","DOI":"10.1126\/science.252.5009.1162","article-title":"Predicting coiled coils from protein sequences","volume":"252","author":"Lupas","year":"1991","journal-title":"Science"},{"key":"2021010313124666100_B24","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1016\/0097-8485(93)85006-X","article-title":"Statistics of local complexity in amino acid sequences and sequence databases","volume":"17","author":"Wootton","year":"1993","journal-title":"Comput. Chem."},{"key":"2021010313124666100_B25","doi-asserted-by":"crossref","first-page":"D471","DOI":"10.1093\/nar\/gkx1071","article-title":"MobiDB 3.0: more annotations for intrinsic disorder, conformational diversity and interactions in proteins","volume":"46","author":"Piovesan","year":"2018","journal-title":"Nucleic Acids Res."},{"key":"2021010313124666100_B26","doi-asserted-by":"crossref","first-page":"D308","DOI":"10.1093\/nar\/gkw1136","article-title":"RepeatsDB 2.0: improved annotation, classification, search and visualization of repeat protein structures","volume":"45","author":"Paladin","year":"2017","journal-title":"Nucleic Acids Res."},{"key":"2021010313124666100_B27","doi-asserted-by":"crossref","first-page":"e77074","DOI":"10.1371\/journal.pone.0077074","article-title":"\u03b2-Propeller blades as ancestral peptides in protein evolution","volume":"8","author":"Kopec","year":"2013","journal-title":"PLoS One"}],"container-title":["Nucleic Acids Research"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/nar\/article-pdf\/49\/D1\/D412\/35363969\/gkaa913.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/academic.oup.com\/nar\/article-pdf\/49\/D1\/D412\/35363969\/gkaa913.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,1,3]],"date-time":"2021-01-03T18:16:49Z","timestamp":1609697809000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/nar\/article\/49\/D1\/D412\/5943818"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,30]]},"references-count":27,"journal-issue":{"issue":"D1","published-online":{"date-parts":[[2020,10,30]]},"published-print":{"date-parts":[[2021,1,8]]}},"URL":"https:\/\/doi.org\/10.1093\/nar\/gkaa913","relation":{},"ISSN":["0305-1048","1362-4962"],"issn-type":[{"value":"0305-1048","type":"print"},{"value":"1362-4962","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2021,1,8]]},"published":{"date-parts":[[2020,10,30]]}}}