{"id":"https://openalex.org/W2102461176","doi":"https://doi.org/10.1093/bioinformatics/btu739","title":"UniRef clusters: a comprehensive and scalable alternative for improving sequence similarity searches","display_name":"UniRef clusters: a comprehensive and scalable alternative for improving sequence similarity searches","publication_year":2014,"publication_date":"2014-11-13","ids":{"openalex":"https://openalex.org/W2102461176","doi":"https://doi.org/10.1093/bioinformatics/btu739","mag":"2102461176","pmid":"https://pubmed.ncbi.nlm.nih.gov/25398609"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btu739","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btu739","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/31/6/926/49011550/bioinformatics_31_6_926.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"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":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/31/6/926/49011550/bioinformatics_31_6_926.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042134761","display_name":"Bar\u0131\u015f Ethem S\u00fczek","orcid":"https://orcid.org/0000-0002-1521-4306"},"institutions":[{"id":"https://openalex.org/I12708293","display_name":"SIB Swiss Institute of Bioinformatics","ror":"https://ror.org/002n09z45","country_code":"CH","type":"nonprofit","lineage":["https://openalex.org/I12708293"]},{"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/I184565670","display_name":"Georgetown University","ror":"https://ror.org/05vzafd60","country_code":"US","type":"education","lineage":["https://openalex.org/I184565670"]},{"id":"https://openalex.org/I2799903593","display_name":"Georgetown University Medical Center","ror":"https://ror.org/00hjz7x27","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799903593"]},{"id":"https://openalex.org/I79946792","display_name":"Mu\u011fla University","ror":"https://ror.org/05n2cz176","country_code":"TR","type":"education","lineage":["https://openalex.org/I79946792"]}],"countries":["CH","GB","TR","US"],"is_corresponding":false,"raw_author_name":"Baris E. Suzek","raw_affiliation_strings":["1 Protein Information Resource, Georgetown University Medical Center, Washington, DC 20007, USA, 2Department of Computer Engineering, Mu\u011fla S\u0131tk\u0131 Ko\u00e7man University, Mu\u011fla 48000, Turkey, 3Center for Bioinformatics and Computational Biology and Protein Information Resource, University of Delaware, Newark, DE 19711, USA, 4European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, Cambridge CB10 1SD, UK and 5Swiss Institute of Bioinformatics, Centre Medical Universitaire, 1 rue Michel Servet, 1211 Geneva 4, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Protein Information Resource, Georgetown University Medical Center, Washington, DC 20007, USA, 2Department of Computer Engineering, Mu\u011fla S\u0131tk\u0131 Ko\u00e7man University, Mu\u011fla 48000, Turkey, 3Center for Bioinformatics and Computational Biology and Protein Information Resource, University of Delaware, Newark, DE 19711, USA, 4European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, Cambridge CB10 1SD, UK and 5Swiss Institute of Bioinformatics, Centre Medical Universitaire, 1 rue Michel Servet, 1211 Geneva 4, Switzerland","institution_ids":["https://openalex.org/I12708293","https://openalex.org/I1303153112","https://openalex.org/I184565670","https://openalex.org/I2799903593","https://openalex.org/I79946792"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100451675","display_name":"Yuqi Wang","orcid":"https://orcid.org/0000-0002-1703-3058"},"institutions":[{"id":"https://openalex.org/I12708293","display_name":"SIB Swiss Institute of Bioinformatics","ror":"https://ror.org/002n09z45","country_code":"CH","type":"nonprofit","lineage":["https://openalex.org/I12708293"]},{"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/I184565670","display_name":"Georgetown University","ror":"https://ror.org/05vzafd60","country_code":"US","type":"education","lineage":["https://openalex.org/I184565670"]},{"id":"https://openalex.org/I2799903593","display_name":"Georgetown University Medical Center","ror":"https://ror.org/00hjz7x27","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799903593"]},{"id":"https://openalex.org/I79946792","display_name":"Mu\u011fla University","ror":"https://ror.org/05n2cz176","country_code":"TR","type":"education","lineage":["https://openalex.org/I79946792"]}],"countries":["CH","GB","TR","US"],"is_corresponding":false,"raw_author_name":"Yuqi Wang","raw_affiliation_strings":["1 Protein Information Resource, Georgetown University Medical Center, Washington, DC 20007, USA, 2Department of Computer Engineering, Mu\u011fla S\u0131tk\u0131 Ko\u00e7man University, Mu\u011fla 48000, Turkey, 3Center for Bioinformatics and Computational Biology and Protein Information Resource, University of Delaware, Newark, DE 19711, USA, 4European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, Cambridge CB10 1SD, UK and 5Swiss Institute of Bioinformatics, Centre Medical Universitaire, 1 rue Michel Servet, 1211 Geneva 4, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Protein Information Resource, Georgetown University Medical Center, Washington, DC 20007, USA, 2Department of Computer Engineering, Mu\u011fla S\u0131tk\u0131 Ko\u00e7man University, Mu\u011fla 48000, Turkey, 3Center for Bioinformatics and Computational Biology and Protein Information Resource, University of Delaware, Newark, DE 19711, USA, 4European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, Cambridge CB10 1SD, UK and 5Swiss Institute of Bioinformatics, Centre Medical Universitaire, 1 rue Michel Servet, 1211 Geneva 4, Switzerland","institution_ids":["https://openalex.org/I12708293","https://openalex.org/I1303153112","https://openalex.org/I184565670","https://openalex.org/I2799903593","https://openalex.org/I79946792"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027838788","display_name":"Hongzhan Huang","orcid":"https://orcid.org/0000-0001-9594-9304"},"institutions":[{"id":"https://openalex.org/I12708293","display_name":"SIB Swiss Institute of Bioinformatics","ror":"https://ror.org/002n09z45","country_code":"CH","type":"nonprofit","lineage":["https://openalex.org/I12708293"]},{"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/I184565670","display_name":"Georgetown University","ror":"https://ror.org/05vzafd60","country_code":"US","type":"education","lineage":["https://openalex.org/I184565670"]},{"id":"https://openalex.org/I2799903593","display_name":"Georgetown University Medical Center","ror":"https://ror.org/00hjz7x27","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799903593"]},{"id":"https://openalex.org/I79946792","display_name":"Mu\u011fla University","ror":"https://ror.org/05n2cz176","country_code":"TR","type":"education","lineage":["https://openalex.org/I79946792"]}],"countries":["CH","GB","TR","US"],"is_corresponding":true,"raw_author_name":"Hongzhan Huang","raw_affiliation_strings":["1 Protein Information Resource, Georgetown University Medical Center, Washington, DC 20007, USA, 2Department of Computer Engineering, Mu\u011fla S\u0131tk\u0131 Ko\u00e7man University, Mu\u011fla 48000, Turkey, 3Center for Bioinformatics and Computational Biology and Protein Information Resource, University of Delaware, Newark, DE 19711, USA, 4European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, Cambridge CB10 1SD, UK and 5Swiss Institute of Bioinformatics, Centre Medical Universitaire, 1 rue Michel Servet, 1211 Geneva 4, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Protein Information Resource, Georgetown University Medical Center, Washington, DC 20007, USA, 2Department of Computer Engineering, Mu\u011fla S\u0131tk\u0131 Ko\u00e7man University, Mu\u011fla 48000, Turkey, 3Center for Bioinformatics and Computational Biology and Protein Information Resource, University of Delaware, Newark, DE 19711, USA, 4European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, Cambridge CB10 1SD, UK and 5Swiss Institute of Bioinformatics, Centre Medical Universitaire, 1 rue Michel Servet, 1211 Geneva 4, Switzerland","institution_ids":["https://openalex.org/I12708293","https://openalex.org/I1303153112","https://openalex.org/I184565670","https://openalex.org/I2799903593","https://openalex.org/I79946792"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082558927","display_name":"Peter B. McGarvey","orcid":"https://orcid.org/0000-0002-8312-6017"},"institutions":[{"id":"https://openalex.org/I12708293","display_name":"SIB Swiss Institute of Bioinformatics","ror":"https://ror.org/002n09z45","country_code":"CH","type":"nonprofit","lineage":["https://openalex.org/I12708293"]},{"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/I184565670","display_name":"Georgetown University","ror":"https://ror.org/05vzafd60","country_code":"US","type":"education","lineage":["https://openalex.org/I184565670"]},{"id":"https://openalex.org/I2799903593","display_name":"Georgetown University Medical Center","ror":"https://ror.org/00hjz7x27","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799903593"]},{"id":"https://openalex.org/I79946792","display_name":"Mu\u011fla University","ror":"https://ror.org/05n2cz176","country_code":"TR","type":"education","lineage":["https://openalex.org/I79946792"]}],"countries":["CH","GB","TR","US"],"is_corresponding":false,"raw_author_name":"Peter B. McGarvey","raw_affiliation_strings":["1 Protein Information Resource, Georgetown University Medical Center, Washington, DC 20007, USA, 2Department of Computer Engineering, Mu\u011fla S\u0131tk\u0131 Ko\u00e7man University, Mu\u011fla 48000, Turkey, 3Center for Bioinformatics and Computational Biology and Protein Information Resource, University of Delaware, Newark, DE 19711, USA, 4European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, Cambridge CB10 1SD, UK and 5Swiss Institute of Bioinformatics, Centre Medical Universitaire, 1 rue Michel Servet, 1211 Geneva 4, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Protein Information Resource, Georgetown University Medical Center, Washington, DC 20007, USA, 2Department of Computer Engineering, Mu\u011fla S\u0131tk\u0131 Ko\u00e7man University, Mu\u011fla 48000, Turkey, 3Center for Bioinformatics and Computational Biology and Protein Information Resource, University of Delaware, Newark, DE 19711, USA, 4European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, Cambridge CB10 1SD, UK and 5Swiss Institute of Bioinformatics, Centre Medical Universitaire, 1 rue Michel Servet, 1211 Geneva 4, Switzerland","institution_ids":["https://openalex.org/I12708293","https://openalex.org/I1303153112","https://openalex.org/I184565670","https://openalex.org/I2799903593","https://openalex.org/I79946792"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053761444","display_name":"Cathy Wu","orcid":"https://orcid.org/0000-0001-6379-8601"},"institutions":[{"id":"https://openalex.org/I12708293","display_name":"SIB Swiss Institute of Bioinformatics","ror":"https://ror.org/002n09z45","country_code":"CH","type":"nonprofit","lineage":["https://openalex.org/I12708293"]},{"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/I184565670","display_name":"Georgetown University","ror":"https://ror.org/05vzafd60","country_code":"US","type":"education","lineage":["https://openalex.org/I184565670"]},{"id":"https://openalex.org/I2799903593","display_name":"Georgetown University Medical Center","ror":"https://ror.org/00hjz7x27","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799903593"]},{"id":"https://openalex.org/I79946792","display_name":"Mu\u011fla University","ror":"https://ror.org/05n2cz176","country_code":"TR","type":"education","lineage":["https://openalex.org/I79946792"]}],"countries":["CH","GB","TR","US"],"is_corresponding":false,"raw_author_name":"Cathy H. Wu","raw_affiliation_strings":["1 Protein Information Resource, Georgetown University Medical Center, Washington, DC 20007, USA, 2Department of Computer Engineering, Mu\u011fla S\u0131tk\u0131 Ko\u00e7man University, Mu\u011fla 48000, Turkey, 3Center for Bioinformatics and Computational Biology and Protein Information Resource, University of Delaware, Newark, DE 19711, USA, 4European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, Cambridge CB10 1SD, UK and 5Swiss Institute of Bioinformatics, Centre Medical Universitaire, 1 rue Michel Servet, 1211 Geneva 4, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Protein Information Resource, Georgetown University Medical Center, Washington, DC 20007, USA, 2Department of Computer Engineering, Mu\u011fla S\u0131tk\u0131 Ko\u00e7man University, Mu\u011fla 48000, Turkey, 3Center for Bioinformatics and Computational Biology and Protein Information Resource, University of Delaware, Newark, DE 19711, USA, 4European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, Cambridge CB10 1SD, UK and 5Swiss Institute of Bioinformatics, Centre Medical Universitaire, 1 rue Michel Servet, 1211 Geneva 4, Switzerland","institution_ids":["https://openalex.org/I12708293","https://openalex.org/I1303153112","https://openalex.org/I184565670","https://openalex.org/I2799903593","https://openalex.org/I79946792"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5027838788"],"corresponding_institution_ids":["https://openalex.org/I12708293","https://openalex.org/I1303153112","https://openalex.org/I184565670","https://openalex.org/I2799903593","https://openalex.org/I79946792"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":16.275,"has_fulltext":true,"cited_by_count":2168,"citation_normalized_percentile":{"value":0.99534935,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"31","issue":"6","first_page":"926","last_page":"932"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9998000264167786,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9998000264167786,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9976999759674072,"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":0.9959999918937683,"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/annotation","display_name":"Annotation","score":0.7258310317993164},{"id":"https://openalex.org/keywords/uniprot","display_name":"UniProt","score":0.714265763759613},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.687714159488678},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5922818183898926},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.578372597694397},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5754113793373108},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5267355442047119},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4900118410587311},{"id":"https://openalex.org/keywords/levenshtein-distance","display_name":"Levenshtein distance","score":0.46394869685173035},{"id":"https://openalex.org/keywords/gene-ontology","display_name":"Gene ontology","score":0.4317566156387329},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.4237220883369446},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3613361418247223},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2643286883831024},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.1723775863647461},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.1504121720790863},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.10996606945991516}],"concepts":[{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.7258310317993164},{"id":"https://openalex.org/C202264299","wikidata":"https://www.wikidata.org/wiki/Q905695","display_name":"UniProt","level":3,"score":0.714265763759613},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.687714159488678},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5922818183898926},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.578372597694397},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5754113793373108},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5267355442047119},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4900118410587311},{"id":"https://openalex.org/C2777515626","wikidata":"https://www.wikidata.org/wiki/Q496939","display_name":"Levenshtein distance","level":2,"score":0.46394869685173035},{"id":"https://openalex.org/C2987395477","wikidata":"https://www.wikidata.org/wiki/Q135085","display_name":"Gene ontology","level":4,"score":0.4317566156387329},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4237220883369446},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3613361418247223},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2643286883831024},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.1723775863647461},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1504121720790863},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.10996606945991516},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.0}],"mesh":[{"descriptor_ui":"D000071502","descriptor_name":"AlkB Homolog 5, RNA Demethylase","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000071502","descriptor_name":"AlkB Homolog 5, RNA Demethylase","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000071502","descriptor_name":"AlkB Homolog 5, RNA Demethylase","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008565","descriptor_name":"Membrane Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D008565","descriptor_name":"Membrane Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D008565","descriptor_name":"Membrane Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D008565","descriptor_name":"Membrane Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D008565","descriptor_name":"Membrane Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D008565","descriptor_name":"Membrane Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D008565","descriptor_name":"Membrane Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D008565","descriptor_name":"Membrane Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D008565","descriptor_name":"Membrane Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"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":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D049308","descriptor_name":"Dioxygenases","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D049308","descriptor_name":"Dioxygenases","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D049308","descriptor_name":"Dioxygenases","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D049308","descriptor_name":"Dioxygenases","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D049308","descriptor_name":"Dioxygenases","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D049308","descriptor_name":"Dioxygenases","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D049308","descriptor_name":"Dioxygenases","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D049308","descriptor_name":"Dioxygenases","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D049308","descriptor_name":"Dioxygenases","qualifier_ui":"Q000737","qualifier_name":"chemistry","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":"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}],"locations_count":4,"locations":[{"id":"doi:10.1093/bioinformatics/btu739","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btu739","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/31/6/926/49011550/bioinformatics_31_6_926.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"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":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:25398609","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/25398609","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":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:oai:doc.rero.ch:299491","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400148","display_name":"reroDoc Digital Library","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:4375400","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4375400","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":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btu739","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btu739","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/31/6/926/49011550/bioinformatics_31_6_926.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"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":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G205811794","display_name":null,"funder_award_id":"U41 HG006104","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"},{"id":"https://openalex.org/G4750929100","display_name":null,"funder_award_id":"U41 HG007822","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"}],"funders":[{"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/W2102461176.pdf","grobid_xml":"https://content.openalex.org/works/W2102461176.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1964903151","https://openalex.org/W1976369037","https://openalex.org/W1982265452","https://openalex.org/W2035876071","https://openalex.org/W2055043387","https://openalex.org/W2056560532","https://openalex.org/W2062758748","https://openalex.org/W2064795263","https://openalex.org/W2065262208","https://openalex.org/W2076048958","https://openalex.org/W2076735582","https://openalex.org/W2084787613","https://openalex.org/W2103017472","https://openalex.org/W2107644675","https://openalex.org/W2108211735","https://openalex.org/W2111823792","https://openalex.org/W2112037121","https://openalex.org/W2118597789","https://openalex.org/W2123076448","https://openalex.org/W2127322768","https://openalex.org/W2137886330","https://openalex.org/W2141885858","https://openalex.org/W2144616092","https://openalex.org/W2145010684","https://openalex.org/W2150249052","https://openalex.org/W2151370125","https://openalex.org/W2155520400","https://openalex.org/W2156125289","https://openalex.org/W2161241566","https://openalex.org/W2276605232","https://openalex.org/W2605068739","https://openalex.org/W4212920271","https://openalex.org/W4320301318","https://openalex.org/W6681840848"],"related_works":["https://openalex.org/W2102027645","https://openalex.org/W2107785922","https://openalex.org/W2035528219","https://openalex.org/W2402478170","https://openalex.org/W2999847357","https://openalex.org/W2946410450","https://openalex.org/W2901823680","https://openalex.org/W4225740479","https://openalex.org/W2106830745","https://openalex.org/W2941245232"],"abstract_inverted_index":{"Abstract":[0],"Motivation:":[1],"UniRef":[2,28,78,171,213],"databases":[3,182],"provide":[4],"full-scale":[5],"clustering":[6],"of":[7,17,51,58,71,83,91,123,157,170],"UniProtKB":[8,136],"sequences":[9],"and":[10,24,49,54,101,152,176,186,196,200,208],"are":[11,97,140,214],"utilized":[12],"for":[13,99,183,190],"a":[14,34,174],"broad":[15],"range":[16],"applications,":[18],"particularly":[19],"similarity-based":[20],"functional":[21,193],"annotation.":[22,194],"Non-redundancy":[23],"intra-cluster":[25],"homogeneity":[26],"in":[27,87,113,155,192],"were":[29],"recently":[30],"improved":[31],"by":[32,69,121],"adding":[33],"sequence":[35,181],"length":[36],"overlap":[37],"threshold.":[38],"Our":[39,165],"hypothesis":[40],"is":[41],"that":[42,77,95],"these":[43],"improvements":[44],"would":[45],"enhance":[46],"the":[47,56,92,124,138,168],"speed":[48],"sensitivity":[50],"similarity":[52,114,184],"searches":[53,117,134,139,185,211],"improve":[55],"consistency":[57,66],"annotation":[59,100,108],"within":[60],"clusters.":[61],"Results:":[62],"Intra-cluster":[63],"molecular":[64,85],"function":[65,86],"was":[67],"examined":[68],"analysis":[70],"Gene":[72],"Ontology":[73],"terms.":[74],"Results":[75],"show":[76],"clusters":[79,96,172],"bring":[80],"together":[81],"proteins":[82],"identical":[84],"more":[88,153],"than":[89],"97%":[90],"clusters,":[93],"implying":[94],"useful":[98],"can":[102],"also":[103],"be":[104],"used":[105],"to":[106,179],"detect":[107],"inconsistencies.":[109],"To":[110],"examine":[111],"coverage":[112],"results,":[115],"BLASTP":[116],"against":[118,135,212],"UniRef50":[119],"followed":[120],"expansion":[122],"hit":[125,145],"lists":[126],"with":[127,133],"cluster":[128],"members":[129],"demonstrated":[130],"advantages":[131],"compared":[132],"sequences;":[137],"concise":[141],"(\u223c7":[142],"times":[143],"shorter":[144],"list":[146],"before":[147],"expansion),":[148],"faster":[149],"(\u223c6":[150],"times)":[151],"sensitive":[154],"detection":[156],"remote":[158],"similarities":[159],"(&amp;gt;96%":[160],"recall":[161],"at":[162,206,216],"e-value":[163],"&amp;lt;0.0001).":[164],"results":[166],"support":[167],"use":[169,191],"as":[173],"comprehensive":[175],"scalable":[177],"alternative":[178],"native":[180],"reinforces":[187],"its":[188],"reliability":[189],"Availability":[195],"implementation:":[197],"Web":[198],"access":[199],"file":[201],"download":[202],"from":[203],"UniProt":[204],"website":[205],"http://www.uniprot.org/uniref":[207],"ftp://ftp.uniprot.org/pub/databases/uniprot/uniref.":[209],"BLAST":[210],"available":[215],"http://www.uniprot.org/blast/":[217],"Contact:":[218],"huang@dbi.udel.edu":[219]},"counts_by_year":[{"year":2026,"cited_by_count":151},{"year":2025,"cited_by_count":318},{"year":2024,"cited_by_count":374},{"year":2023,"cited_by_count":298},{"year":2022,"cited_by_count":270},{"year":2021,"cited_by_count":267},{"year":2020,"cited_by_count":159},{"year":2019,"cited_by_count":109},{"year":2018,"cited_by_count":95},{"year":2017,"cited_by_count":71},{"year":2016,"cited_by_count":41},{"year":2015,"cited_by_count":13},{"year":2012,"cited_by_count":1}],"updated_date":"2026-08-08T07:41:36.138363","created_date":"2025-10-10T00:00:00"}
