{"id":"https://openalex.org/W2557595285","doi":"https://doi.org/10.1093/nar/gkw1081","title":"Uniclust databases of clustered and deeply annotated protein sequences and alignments","display_name":"Uniclust databases of clustered and deeply annotated protein sequences and alignments","publication_year":2016,"publication_date":"2016-11-01","ids":{"openalex":"https://openalex.org/W2557595285","doi":"https://doi.org/10.1093/nar/gkw1081","mag":"2557595285","pmid":"https://pubmed.ncbi.nlm.nih.gov/27899574"},"language":"en","primary_location":{"id":"doi:10.1093/nar/gkw1081","is_oa":true,"landing_page_url":"https://doi.org/10.1093/nar/gkw1081","pdf_url":"https://academic.oup.com/nar/article-pdf/45/D1/D170/8846789/gkw1081.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":true,"is_in_doaj":true,"is_core":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nucleic Acids Research","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://academic.oup.com/nar/article-pdf/45/D1/D170/8846789/gkw1081.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016012053","display_name":"Milot Mirdita","orcid":"https://orcid.org/0000-0001-8637-6719"},"institutions":[{"id":"https://openalex.org/I4210131661","display_name":"Max Planck Institute for Biophysical Chemistry","ror":"https://ror.org/03e76ya46","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210131661"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Milot Mirdita","raw_affiliation_strings":["Quantitative and Computational Biology Group, Max Planck Institute for Biophysical Chemistry, G\u00f6ttingen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Quantitative and Computational Biology Group, Max Planck Institute for Biophysical Chemistry, G\u00f6ttingen, Germany","institution_ids":["https://openalex.org/I4210131661"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059182357","display_name":"Lars von den Driesch","orcid":null},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]},{"id":"https://openalex.org/I4210131661","display_name":"Max Planck Institute for Biophysical Chemistry","ror":"https://ror.org/03e76ya46","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210131661"]},{"id":"https://openalex.org/I87048295","display_name":"Wellcome Trust","ror":"https://ror.org/029chgv08","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I87048295"]}],"countries":["DE","GB"],"is_corresponding":false,"raw_author_name":"Lars von\u00a0den\u00a0Driesch","raw_affiliation_strings":["European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Trust Genome Campus, Cambridge, UK","Quantitative and Computational Biology Group, Max Planck Institute for Biophysical Chemistry, G\u00f6ttingen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Trust Genome Campus, Cambridge, UK","institution_ids":["https://openalex.org/I1303153112","https://openalex.org/I87048295"]},{"raw_affiliation_string":"Quantitative and Computational Biology Group, Max Planck Institute for Biophysical Chemistry, G\u00f6ttingen, Germany","institution_ids":["https://openalex.org/I4210131661"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065367548","display_name":"Clovis Galiez","orcid":"https://orcid.org/0000-0002-0560-6023"},"institutions":[{"id":"https://openalex.org/I4210131661","display_name":"Max Planck Institute for Biophysical Chemistry","ror":"https://ror.org/03e76ya46","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210131661"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Clovis Galiez","raw_affiliation_strings":["Quantitative and Computational Biology Group, Max Planck Institute for Biophysical Chemistry, G\u00f6ttingen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Quantitative and Computational Biology Group, Max Planck Institute for Biophysical Chemistry, G\u00f6ttingen, Germany","institution_ids":["https://openalex.org/I4210131661"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071535801","display_name":"Mar\u00eda Martin","orcid":"https://orcid.org/0000-0001-5454-2815"},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]},{"id":"https://openalex.org/I87048295","display_name":"Wellcome Trust","ror":"https://ror.org/029chgv08","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I87048295"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Maria J. Martin","raw_affiliation_strings":["European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Trust Genome Campus, Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Trust Genome Campus, Cambridge, UK","institution_ids":["https://openalex.org/I1303153112","https://openalex.org/I87048295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010030898","display_name":"Johannes S\u00f6ding","orcid":"https://orcid.org/0000-0001-9642-8244"},"institutions":[{"id":"https://openalex.org/I4210131661","display_name":"Max Planck Institute for Biophysical Chemistry","ror":"https://ror.org/03e76ya46","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210131661"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Johannes S\u00f6ding","raw_affiliation_strings":["Quantitative and Computational Biology Group, Max Planck Institute for Biophysical Chemistry, G\u00f6ttingen, Germany soeding@mpibpc.mpg.de","Quantitative and Computational Biology Group, Max Planck Institute for Biophysical Chemistry, G\u00f6ttingen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Quantitative and Computational Biology Group, Max Planck Institute for Biophysical Chemistry, G\u00f6ttingen, Germany soeding@mpibpc.mpg.de","institution_ids":["https://openalex.org/I4210131661"]},{"raw_affiliation_string":"Quantitative and Computational Biology Group, Max Planck Institute for Biophysical Chemistry, G\u00f6ttingen, Germany","institution_ids":["https://openalex.org/I4210131661"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019985343","display_name":"Martin Steinegger","orcid":"https://orcid.org/0000-0001-8781-9753"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]},{"id":"https://openalex.org/I4210131661","display_name":"Max Planck Institute for Biophysical Chemistry","ror":"https://ror.org/03e76ya46","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210131661"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE","KR"],"is_corresponding":true,"raw_author_name":"Martin Steinegger","raw_affiliation_strings":["Department for Bioinformatics and Computational Biology, Technische Universit\u00e4t M\u00fcnchen, Munich, Germany","Department of Chemistry, Seoul National University, Seoul, Korea","Quantitative and Computational Biology Group, Max Planck Institute for Biophysical Chemistry, G\u00f6ttingen, Germany martin.steinegger@mpibpc.mpg.de","Quantitative and Computational Biology Group, Max Planck Institute for Biophysical Chemistry, G\u00f6ttingen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department for Bioinformatics and Computational Biology, Technische Universit\u00e4t M\u00fcnchen, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Department of Chemistry, Seoul National University, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Quantitative and Computational Biology Group, Max Planck Institute for Biophysical Chemistry, G\u00f6ttingen, Germany martin.steinegger@mpibpc.mpg.de","institution_ids":["https://openalex.org/I4210131661"]},{"raw_affiliation_string":"Quantitative and Computational Biology Group, Max Planck Institute for Biophysical Chemistry, G\u00f6ttingen, Germany","institution_ids":["https://openalex.org/I4210131661"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5019985343"],"corresponding_institution_ids":["https://openalex.org/I139264467","https://openalex.org/I4210131661","https://openalex.org/I62916508"],"apc_list":{"value":3630,"currency":"USD","value_usd":3630},"apc_paid":{"value":3630,"currency":"USD","value_usd":3630},"fwci":8.1677,"has_fulltext":true,"cited_by_count":918,"citation_normalized_percentile":{"value":0.98086025,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"45","issue":"D1","first_page":"D170","last_page":"D176"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9973999857902527,"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/T10519","display_name":"Advanced Proteomics Techniques and Applications","score":0.9950000047683716,"subfield":{"id":"https://openalex.org/subfields/1607","display_name":"Spectroscopy"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/uniprot","display_name":"UniProt","score":0.9720085263252258},{"id":"https://openalex.org/keywords/sequence-database","display_name":"Sequence database","score":0.7882665991783142},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.6595702767372131},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5930303335189819},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"Sequence alignment","score":0.5527328252792358},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5298866033554077},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4741770029067993},{"id":"https://openalex.org/keywords/multiple-sequence-alignment","display_name":"Multiple sequence alignment","score":0.4636681377887726},{"id":"https://openalex.org/keywords/refseq","display_name":"RefSeq","score":0.45485639572143555},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4449133276939392},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.44176965951919556},{"id":"https://openalex.org/keywords/protein-function-prediction","display_name":"Protein function prediction","score":0.44163304567337036},{"id":"https://openalex.org/keywords/protein-sequencing","display_name":"Protein sequencing","score":0.4251306354999542},{"id":"https://openalex.org/keywords/smith\u2013waterman-algorithm","display_name":"Smith\u2013Waterman algorithm","score":0.41999128460884094},{"id":"https://openalex.org/keywords/protein-data-bank","display_name":"Protein Data Bank (RCSB PDB)","score":0.4198365807533264},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.4180552661418915},{"id":"https://openalex.org/keywords/sequence-homology","display_name":"Sequence homology","score":0.4176395535469055},{"id":"https://openalex.org/keywords/sequence-analysis","display_name":"Sequence analysis","score":0.4154930114746094},{"id":"https://openalex.org/keywords/structural-classification-of-proteins-database","display_name":"Structural Classification of Proteins database","score":0.414957195520401},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.3111761808395386},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.2876128554344177},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.2689581513404846},{"id":"https://openalex.org/keywords/protein-function","display_name":"Protein function","score":0.2651871144771576},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.23793888092041016},{"id":"https://openalex.org/keywords/protein-structure","display_name":"Protein structure","score":0.215071439743042},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.1877460777759552},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.10538274049758911}],"concepts":[{"id":"https://openalex.org/C202264299","wikidata":"https://www.wikidata.org/wiki/Q905695","display_name":"UniProt","level":3,"score":0.9720085263252258},{"id":"https://openalex.org/C41584329","wikidata":"https://www.wikidata.org/wiki/Q175902","display_name":"Sequence database","level":3,"score":0.7882665991783142},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.6595702767372131},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5930303335189819},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.5527328252792358},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5298866033554077},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4741770029067993},{"id":"https://openalex.org/C88031987","wikidata":"https://www.wikidata.org/wiki/Q1377767","display_name":"Multiple sequence alignment","level":5,"score":0.4636681377887726},{"id":"https://openalex.org/C151810110","wikidata":"https://www.wikidata.org/wiki/Q7307074","display_name":"RefSeq","level":4,"score":0.45485639572143555},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4449133276939392},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.44176965951919556},{"id":"https://openalex.org/C207060522","wikidata":"https://www.wikidata.org/wiki/Q7251473","display_name":"Protein function prediction","level":4,"score":0.44163304567337036},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.4251306354999542},{"id":"https://openalex.org/C72802188","wikidata":"https://www.wikidata.org/wiki/Q1683352","display_name":"Smith\u2013Waterman algorithm","level":5,"score":0.41999128460884094},{"id":"https://openalex.org/C65556437","wikidata":"https://www.wikidata.org/wiki/Q766195","display_name":"Protein Data Bank (RCSB PDB)","level":2,"score":0.4198365807533264},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4180552661418915},{"id":"https://openalex.org/C2779315201","wikidata":"https://www.wikidata.org/wiki/Q414601","display_name":"Sequence homology","level":4,"score":0.4176395535469055},{"id":"https://openalex.org/C61053724","wikidata":"https://www.wikidata.org/wiki/Q1154615","display_name":"Sequence analysis","level":3,"score":0.4154930114746094},{"id":"https://openalex.org/C58773245","wikidata":"https://www.wikidata.org/wiki/Q4832556","display_name":"Structural Classification of Proteins database","level":3,"score":0.414957195520401},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.3111761808395386},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.2876128554344177},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.2689581513404846},{"id":"https://openalex.org/C2986374874","wikidata":"https://www.wikidata.org/wiki/Q8054","display_name":"Protein function","level":3,"score":0.2651871144771576},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.23793888092041016},{"id":"https://openalex.org/C47701112","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Protein structure","level":2,"score":0.215071439743042},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.1877460777759552},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.10538274049758911},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D030561","descriptor_name":"Databases, Nucleic Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030561","descriptor_name":"Databases, Nucleic Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030561","descriptor_name":"Databases, Nucleic Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D063990","descriptor_name":"Gene Ontology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D063990","descriptor_name":"Gene Ontology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D063990","descriptor_name":"Gene Ontology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D064878","descriptor_name":"Web Browser","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D064878","descriptor_name":"Web Browser","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D064878","descriptor_name":"Web Browser","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":8,"locations":[{"id":"doi:10.1093/nar/gkw1081","is_oa":true,"landing_page_url":"https://doi.org/10.1093/nar/gkw1081","pdf_url":"https://academic.oup.com/nar/article-pdf/45/D1/D170/8846789/gkw1081.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":true,"is_in_doaj":true,"is_core":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nucleic Acids Research","raw_type":"journal-article"},{"id":"pmid:27899574","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/27899574","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,"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":null},{"id":"pmh:oai:pure.mpg.de:item_2368324","is_oa":true,"landing_page_url":"https://hdl.handle.net/11858/00-001M-0000-002C-1521-2","pdf_url":"http://hdl.handle.net/11858/00-001M-0000-002C-1521-2","source":{"id":"https://openalex.org/S4306400654","display_name":"MPG.PuRe (Max Planck Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149899117","host_organization_name":"Max Planck Society","host_organization_lineage":["https://openalex.org/I149899117"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Nucleic Acids Research","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:pubmedcentral.nih.gov:5614098","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/5614098","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,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Nucleic Acids Res","raw_type":"Text"},{"id":"pmh:oai:HAL:hal-02088268v1","is_oa":false,"landing_page_url":"https://hal.science/hal-02088268","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Nucleic Acids Research, 2017, 45 (D1), pp.D170-D176. ⟨10.1093/nar/gkw1081⟩","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:escidoc.org:escidoc:2368324","is_oa":true,"landing_page_url":"http://hdl.handle.net/11858/00-001M-0000-002C-1521-2","pdf_url":null,"source":{"id":"https://openalex.org/S7407052962","display_name":"Max Planck Digital Library","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210088280","host_organization_name":"Max Planck Digital Library","host_organization_lineage":["https://openalex.org/I4210088280"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:open-archive.highwire.org:nar:45/D1/D170","is_oa":false,"landing_page_url":"http://nar.oxfordjournals.org/cgi/content/short/45/D1/D170","pdf_url":null,"source":{"id":"https://openalex.org/S4406923041","display_name":"HighWire Press Open Archive","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"TEXT"},{"id":"pmh:oai:s-space.snu.ac.kr:10371/202610","is_oa":false,"landing_page_url":"https://hdl.handle.net/10371/202610","pdf_url":null,"source":{"id":"https://openalex.org/S4306401345","display_name":"Seoul National University Open Repository (Seoul National University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139264467","host_organization_name":"Seoul National University","host_organization_lineage":["https://openalex.org/I139264467"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":{"id":"doi:10.1093/nar/gkw1081","is_oa":true,"landing_page_url":"https://doi.org/10.1093/nar/gkw1081","pdf_url":"https://academic.oup.com/nar/article-pdf/45/D1/D170/8846789/gkw1081.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":true,"is_in_doaj":true,"is_core":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nucleic Acids Research","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4671512033","display_name":null,"funder_award_id":"685778","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"}],"funders":[{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"},{"id":"https://openalex.org/F4320322434","display_name":"Max-Planck-Gesellschaft","ror":"https://ror.org/01hhn8329"},{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2557595285.pdf","grobid_xml":"https://content.openalex.org/works/W2557595285.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1490161904","https://openalex.org/W1647729745","https://openalex.org/W1987916789","https://openalex.org/W1995808589","https://openalex.org/W2051210555","https://openalex.org/W2055043387","https://openalex.org/W2102461176","https://openalex.org/W2117077088","https://openalex.org/W2118597789","https://openalex.org/W2121013757","https://openalex.org/W2127261350","https://openalex.org/W2127322768","https://openalex.org/W2132819807","https://openalex.org/W2135415614","https://openalex.org/W2152882637","https://openalex.org/W2155520400","https://openalex.org/W2156125289","https://openalex.org/W2167406239","https://openalex.org/W2224056471","https://openalex.org/W2277953252","https://openalex.org/W2303521084","https://openalex.org/W2466387107","https://openalex.org/W2683236244","https://openalex.org/W2739999456","https://openalex.org/W4236236547","https://openalex.org/W4242729757"],"related_works":["https://openalex.org/W2136456075","https://openalex.org/W2110847899","https://openalex.org/W4230932396","https://openalex.org/W2107903949","https://openalex.org/W3100584158","https://openalex.org/W2136785696","https://openalex.org/W1496233740","https://openalex.org/W2339549279","https://openalex.org/W2066737015","https://openalex.org/W1490120815"],"abstract_inverted_index":{"We":[0],"present":[1],"three":[2,11,126],"clustered":[3],"protein":[4,26,83],"sequence":[5,15,27,32,49,84,137],"databases,":[6],"Uniclust90,":[7],"Uniclust50,":[8],"Uniclust30":[9,133],"and":[10,20,31,46,52,65,81,86,98,162,168],"databases":[12,36,146],"of":[13,43,58,63,125],"multiple":[14],"alignments":[16],"(MSAs),":[17],"Uniboost10,":[18],"Uniboost20":[19],"Uniboost30,":[21],"as":[22],"a":[23],"resource":[24],"for":[25,79],"analysis,":[28],"function":[29],"prediction":[30],"searches.":[33],"The":[34],"Uniclust":[35,88,114,152,170],"cluster":[37],"UniProtKB":[38],"sequences":[39,89],"at":[40,154],"the":[41,101,132,151,177],"level":[42],"90%,":[44],"50%":[45],"30%":[47],"pairwise":[48],"identity.":[50],"Uniclust90":[51],"Uniclust50":[53],"clusters":[54,159],"showed":[55],"better":[56],"consistency":[57],"functional":[59],"annotation":[60],"than":[61,121],"those":[62],"UniRef90":[64],"UniRef50,":[66],"owing":[67],"to":[68,94,110],"an":[69],"optimised":[70],"clustering":[71],"pipeline":[72],"that":[73],"runs":[74],"with":[75,92,135,176],"our":[76,104],"MMseqs2":[77,140],"software":[78],"fast":[80],"sensitive":[82],"searching":[85],"clustering.":[87],"are":[90,128],"annotated":[91],"matches":[93,138],"Pfam,":[95],"SCOP":[96],"domains,":[97],"proteins":[99],"in":[100],"PDB,":[102],"using":[103],"HHblits":[105],"homology":[106],"detection":[107],"tool.":[108],"Due":[109],"its":[111],"high":[112],"sensitivity,":[113],"contains":[115],"17%":[116],"more":[117],"Pfam":[118],"domain":[119],"annotations":[120],"UniProt.":[122],"Uniboost":[123],"MSAs":[124,134],"diversities":[127],"built":[129],"by":[130,160],"enriching":[131],"local":[136],"from":[139,150],"profile":[141],"searches":[142],"through":[143],"Uniclust30.":[144],"All":[145],"can":[147,157],"be":[148],"downloaded":[149],"server":[153],"uniclust.mmseqs.com.":[155],"Users":[156],"search":[158],"keywords":[161],"explore":[163],"their":[164],"MSAs,":[165],"taxonomic":[166],"representation,":[167],"annotations.":[169],"is":[171],"updated":[172],"every":[173],"two":[174],"months":[175],"new":[178],"UniProt":[179],"release.":[180]},"counts_by_year":[{"year":2026,"cited_by_count":42},{"year":2025,"cited_by_count":127},{"year":2024,"cited_by_count":163},{"year":2023,"cited_by_count":162},{"year":2022,"cited_by_count":158},{"year":2021,"cited_by_count":156},{"year":2020,"cited_by_count":58},{"year":2019,"cited_by_count":33},{"year":2018,"cited_by_count":13},{"year":2017,"cited_by_count":5}],"updated_date":"2026-08-13T07:04:57.449891","created_date":"2025-10-10T00:00:00"}