{"id":"https://openalex.org/W2124871329","doi":"https://doi.org/10.1093/nar/26.1.320","title":"Pfam: multiple sequence alignments and HMM-profiles of protein domains","display_name":"Pfam: multiple sequence alignments and HMM-profiles of protein domains","publication_year":1998,"publication_date":"1998-01-01","ids":{"openalex":"https://openalex.org/W2124871329","doi":"https://doi.org/10.1093/nar/26.1.320","mag":"2124871329","pmid":"https://pubmed.ncbi.nlm.nih.gov/9399864","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/147209"},"language":"en","primary_location":{"id":"doi:10.1093/nar/26.1.320","doi":"https://doi.org/10.1093/nar/26.1.320","is_oa":true,"landing_page_url":"https://doi.org/10.1093/nar/26.1.320","pdf_url":"https://academic.oup.com/nar/article-pdf/26/1/320/7048768/26-1-320.pdf","source":{"id":"https://openalex.org/S134668137","display_name":"Nucleic Acids Research","issn_l":"0305-1048","issn":["0305-1048","1362-4954","1362-4962"],"is_oa":false,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","dongbi-a","doyens","jufo-3","ki-jl-3","medline","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nucleic Acids Research","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/nar/article-pdf/26/1/320/7048768/26-1-320.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032432650","display_name":"Erik L. L. Sonnhammer","orcid":"https://orcid.org/0000-0002-9015-5588","observed_orcids":["https://orcid.org/0000-0002-9015-5588"]},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]},{"id":"https://openalex.org/I4210109390","display_name":"National Center for Biotechnology Information","ror":"https://ror.org/02meqm098","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410","https://openalex.org/I4210109390"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"E. Sonnhammer","raw_affiliation_strings":["Computational Biology Branch, National Center for Biotechnology Information, National Library of Medicine, Building 38A, Room 8N805, National Institutes of Health, Bethesda, MD 20894, USA. sonnhammer@ncbi.nlm.nih.gov","Computational Biology Branch, National Center for Biotechnology Information, National Library of Medicine , Building 38A, Room 8N805 , National Institutes of Health , Bethesda, MD 20894, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Biology Branch, National Center for Biotechnology Information, National Library of Medicine, Building 38A, Room 8N805, National Institutes of Health, Bethesda, MD 20894, USA. sonnhammer@ncbi.nlm.nih.gov","institution_ids":["https://openalex.org/I1299303238","https://openalex.org/I4210109390"]},{"raw_affiliation_string":"Computational Biology Branch, National Center for Biotechnology Information, National Library of Medicine , Building 38A, Room 8N805 , National Institutes of Health , Bethesda, MD 20894, USA","institution_ids":["https://openalex.org/I1299303238","https://openalex.org/I4210109390"]}]},{"author_position":"middle","author":{"id":null,"display_name":"S R Eddy","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"S R Eddy","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"E Birney","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"E Birney","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"A Bateman","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"A Bateman","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"R Durbin","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"R Durbin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5032432650"],"corresponding_institution_ids":["https://openalex.org/I1299303238","https://openalex.org/I4210109390"],"apc_list":{"value":3992,"currency":"USD","value_usd":3992},"apc_paid":null,"fwci":12.04,"has_fulltext":true,"cited_by_count":774,"citation_normalized_percentile":{"value":0.99366657,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"26","issue":"1","first_page":"320","last_page":"322"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9839000105857849,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9839000105857849,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.007899999618530273,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.0032999999821186066,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/pfam","display_name":"Pfam","score":0.9269999861717224},{"id":"https://openalex.org/keywords/protein-domains","display_name":"protein domains","score":0.9750000238418579},{"id":"https://openalex.org/keywords/multiple-sequence-alignment","display_name":"multiple sequence alignment","score":0.828000009059906},{"id":"https://openalex.org/keywords/profile-hidden-markov-models","display_name":"profile hidden Markov models","score":0.9179999828338623},{"id":"https://openalex.org/keywords/protein-family-classification","display_name":"protein family classification","score":0.6859999895095825},{"id":"https://openalex.org/keywords/domain-boundaries","display_name":"domain boundaries","score":0.8230000138282776},{"id":"https://openalex.org/keywords/sequence-similarity","display_name":"sequence similarity","score":0.7739999890327454},{"id":"https://openalex.org/keywords/swiss-prot","display_name":"Swiss-Prot","score":0.6209999918937683},{"id":"https://openalex.org/keywords/caenorhabditis-elegans-genome","display_name":"Caenorhabditis elegans genome","score":0.8880000114440918},{"id":"https://openalex.org/keywords/protein-databases","display_name":"protein databases","score":0.3109999895095825}],"concepts":[{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.742012083530426},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6437499523162842},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.6015492081642151},{"id":"https://openalex.org/C141674004","wikidata":"https://www.wikidata.org/wiki/Q1344256","display_name":"Ensembl","level":5,"score":0.5536864995956421},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.5373839735984802},{"id":"https://openalex.org/C171897839","wikidata":"https://www.wikidata.org/wiki/Q417841","display_name":"Protein family","level":3,"score":0.5362282395362854},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.5317831039428711},{"id":"https://openalex.org/C88031987","wikidata":"https://www.wikidata.org/wiki/Q1377767","display_name":"Multiple sequence alignment","level":5,"score":0.49810171127319336},{"id":"https://openalex.org/C144292202","wikidata":"https://www.wikidata.org/wiki/Q898273","display_name":"Protein domain","level":3,"score":0.49032166600227356},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.47986072301864624},{"id":"https://openalex.org/C76818968","wikidata":"https://www.wikidata.org/wiki/Q181940","display_name":"Sanger sequencing","level":4,"score":0.4656800627708435},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.42724689841270447},{"id":"https://openalex.org/C61053724","wikidata":"https://www.wikidata.org/wiki/Q1154615","display_name":"Sequence analysis","level":3,"score":0.42288511991500854},{"id":"https://openalex.org/C129075420","wikidata":"https://www.wikidata.org/wiki/Q10855009","display_name":"Hypothetical protein","level":3,"score":0.4206184148788452},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.41026702523231506},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.35736340284347534},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.27977854013442993},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.26608455181121826},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.23043760657310486},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.2064628005027771},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.11964225769042969},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.08277076482772827},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003195","descriptor_name":"Computer Communication Networks","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017173","descriptor_name":"Caenorhabditis elegans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":6,"locations":[{"id":"doi:10.1093/nar/26.1.320","doi":"https://doi.org/10.1093/nar/26.1.320","is_oa":true,"landing_page_url":"https://doi.org/10.1093/nar/26.1.320","pdf_url":"https://academic.oup.com/nar/article-pdf/26/1/320/7048768/26-1-320.pdf","source":{"id":"https://openalex.org/S134668137","display_name":"Nucleic Acids Research","issn_l":"0305-1048","issn":["0305-1048","1362-4954","1362-4962"],"is_oa":false,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","dongbi-a","doyens","jufo-3","ki-jl-3","medline","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nucleic Acids Research","raw_type":"journal-article"},{"id":"pmh:oai:europepmc.org:1529007","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/147209","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"Text"},{"id":"pmid:9399864","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/9399864","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nucleic acids research","raw_type":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:147209","doi":null,"is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC147209/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nucleic Acids Res","raw_type":"Text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.49.3348","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.49.3348","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.oup.co.uk/nar/Volume_26/Issue_01/ps/gkb019_gml.ps.gz","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.590.4701","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.590.4701","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://nar.oxfordjournals.org/content/26/1/320.full.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.1093/nar/26.1.320","doi":"https://doi.org/10.1093/nar/26.1.320","is_oa":true,"landing_page_url":"https://doi.org/10.1093/nar/26.1.320","pdf_url":"https://academic.oup.com/nar/article-pdf/26/1/320/7048768/26-1-320.pdf","source":{"id":"https://openalex.org/S134668137","display_name":"Nucleic Acids Research","issn_l":"0305-1048","issn":["0305-1048","1362-4954","1362-4962"],"is_oa":false,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","dongbi-a","doyens","jufo-3","ki-jl-3","medline","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nucleic Acids Research","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G3072434736","display_name":"Probabilistic models of protein and RNA structure","funder_award_id":"R01HG001363","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"}],"funders":[{"id":"https://openalex.org/F4320311904","display_name":"Wellcome Trust","ror":"https://ror.org/029chgv08"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337348","display_name":"National Human Genome Research Institute","ror":"https://ror.org/00baak391"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2124871329.pdf","grobid_xml":"https://content.openalex.org/works/W2124871329.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W363606446","https://openalex.org/W1967203238","https://openalex.org/W2038407153","https://openalex.org/W2102122585","https://openalex.org/W2102149072","https://openalex.org/W2120561148","https://openalex.org/W2129448726","https://openalex.org/W2130792460","https://openalex.org/W2915190566","https://openalex.org/W3147254695","https://openalex.org/W4239620712"],"related_works":["https://openalex.org/W2129448726","https://openalex.org/W2100018338","https://openalex.org/W7100781797","https://openalex.org/W3188141920","https://openalex.org/W2141885858","https://openalex.org/W4206168438","https://openalex.org/W7101233194","https://openalex.org/W7096012909","https://openalex.org/W129655324","https://openalex.org/W2157484293"],"abstract_inverted_index":{"Pfam":[0,52,83],"contains":[1,53],"multiple":[2],"alignments":[3],"and":[4,22,37,45,63,76,95],"hidden":[5],"Markov":[6],"model":[7],"based":[8,27],"profiles":[9],"(HMM-profiles)":[10],"of":[11,17,40,51,92,97,101],"complete":[12],"protein":[13,34],"domains.":[14],"The":[15],"definition":[16],"domain":[18],"boundaries,":[19],"family":[20,35],"members":[21],"alignment":[23],"is":[24],"done":[25],"semi-automatically":[26],"on":[28],"expert":[29],"knowledge,":[30],"sequence":[31],"similarity,":[32],"other":[33],"databases":[36],"the":[38,47,67,72,78,105],"ability":[39],"HMM-profiles":[41],"to":[42],"correctly":[43],"identify":[44],"align":[46],"members.":[48],"Release":[49],"2.0":[50,84],"527":[54],"manually":[55],"verified":[56],"families":[57],"which":[58],"are":[59],"available":[60],"for":[61],"browsing":[62],"on-line":[64],"searching":[65],"via":[66],"World":[68],"Wide":[69],"Web":[70],"in":[71,77,90],"UK":[73],"at":[74,80],"http://www.sanger.ac.uk/Pfam/":[75],"US":[79],"http://genome.wustl.":[81],"edu/Pfam/":[82],"matches":[85],"one":[86],"or":[87],"more":[88],"domains":[89],"50%":[91],"Swissprot-34":[93],"sequences,":[94],"25%":[96],"a":[98],"large":[99],"sample":[100],"predicted":[102],"proteins":[103],"from":[104],"Caenorhabditis":[106],"elegans":[107],"genome.":[108]},"counts_by_year":[{"year":2026,"cited_by_count":18},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":23},{"year":2021,"cited_by_count":35},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":26},{"year":2018,"cited_by_count":28},{"year":2017,"cited_by_count":16},{"year":2016,"cited_by_count":19},{"year":2015,"cited_by_count":12},{"year":2014,"cited_by_count":21},{"year":2013,"cited_by_count":19},{"year":2012,"cited_by_count":31}],"updated_date":"2026-11-13T13:42:25.865203","created_date":"2016-06-24T00:00:00"}