{"id":"https://openalex.org/W1995530145","doi":"https://doi.org/10.1093/nar/gkr1027","title":"ProtoNet 6.0: organizing 10 million protein sequences in a compact hierarchical family tree","display_name":"ProtoNet 6.0: organizing 10 million protein sequences in a compact hierarchical family tree","publication_year":2011,"publication_date":"2011-11-25","ids":{"openalex":"https://openalex.org/W1995530145","doi":"https://doi.org/10.1093/nar/gkr1027","mag":"1995530145","pmid":"https://pubmed.ncbi.nlm.nih.gov/22121228"},"language":"en","primary_location":{"id":"doi:10.1093/nar/gkr1027","is_oa":true,"landing_page_url":"https://doi.org/10.1093/nar/gkr1027","pdf_url":"https://academic.oup.com/nar/article-pdf/40/D1/D313/9475078/gkr1027.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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","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/40/D1/D313/9475078/gkr1027.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080111333","display_name":"Nadav Rappoport","orcid":"https://orcid.org/0000-0002-7218-2558"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"N. Rappoport","raw_affiliation_strings":["School of Computer Science and Engineering, Institute of Life Sciences, The Sudarsky Center for Computational Biology, The Hebrew University of Jerusalem, 91904 Israel"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Institute of Life Sciences, The Sudarsky Center for Computational Biology, The Hebrew University of Jerusalem, 91904 Israel","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049067844","display_name":"Solange Karsenty","orcid":null},"institutions":[{"id":"https://openalex.org/I197251160","display_name":"Hebrew University of Jerusalem","ror":"https://ror.org/03qxff017","country_code":"IL","type":"education","lineage":["https://openalex.org/I197251160"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"S. Karsenty","raw_affiliation_strings":["School of Computer Science and Engineering and 2Deptartment of Biological Chemistry, Institute of Life Sciences, The Sudarsky Center for Computational Biology, The Hebrew University of Jerusalem, 91904, Israel"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering and 2Deptartment of Biological Chemistry, Institute of Life Sciences, The Sudarsky Center for Computational Biology, The Hebrew University of Jerusalem, 91904, Israel","institution_ids":["https://openalex.org/I197251160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018366916","display_name":"Ariel Dora Stern","orcid":"https://orcid.org/0000-0002-3586-1041"},"institutions":[{"id":"https://openalex.org/I197251160","display_name":"Hebrew University of Jerusalem","ror":"https://ror.org/03qxff017","country_code":"IL","type":"education","lineage":["https://openalex.org/I197251160"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"A. Stern","raw_affiliation_strings":["School of Computer Science and Engineering and 2Deptartment of Biological Chemistry, Institute of Life Sciences, The Sudarsky Center for Computational Biology, The Hebrew University of Jerusalem, 91904, Israel"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering and 2Deptartment of Biological Chemistry, Institute of Life Sciences, The Sudarsky Center for Computational Biology, The Hebrew University of Jerusalem, 91904, Israel","institution_ids":["https://openalex.org/I197251160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050009387","display_name":"Nathan Linial","orcid":null},"institutions":[{"id":"https://openalex.org/I197251160","display_name":"Hebrew University of Jerusalem","ror":"https://ror.org/03qxff017","country_code":"IL","type":"education","lineage":["https://openalex.org/I197251160"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"N. Linial","raw_affiliation_strings":["School of Computer Science and Engineering and 2Deptartment of Biological Chemistry, Institute of Life Sciences, The Sudarsky Center for Computational Biology, The Hebrew University of Jerusalem, 91904, Israel"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering and 2Deptartment of Biological Chemistry, Institute of Life Sciences, The Sudarsky Center for Computational Biology, The Hebrew University of Jerusalem, 91904, Israel","institution_ids":["https://openalex.org/I197251160"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085924022","display_name":"Michal Linial","orcid":"https://orcid.org/0000-0002-9357-4526"},"institutions":[{"id":"https://openalex.org/I197251160","display_name":"Hebrew University of Jerusalem","ror":"https://ror.org/03qxff017","country_code":"IL","type":"education","lineage":["https://openalex.org/I197251160"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"M. Linial","raw_affiliation_strings":["School of Computer Science and Engineering and 2Deptartment of Biological Chemistry, Institute of Life Sciences, The Sudarsky Center for Computational Biology, The Hebrew University of Jerusalem, 91904, Israel"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering and 2Deptartment of Biological Chemistry, Institute of Life Sciences, The Sudarsky Center for Computational Biology, The Hebrew University of Jerusalem, 91904, Israel","institution_ids":["https://openalex.org/I197251160"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5080111333"],"corresponding_institution_ids":[],"apc_list":{"value":3630,"currency":"USD","value_usd":3630},"apc_paid":{"value":3630,"currency":"USD","value_usd":3630},"fwci":1.6937,"has_fulltext":false,"cited_by_count":50,"citation_normalized_percentile":{"value":0.83183787,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"40","issue":"D1","first_page":"D313","last_page":"D320"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9995999932289124,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9993000030517578,"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/biology","display_name":"Biology","score":0.9332709908485413},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5558242201805115},{"id":"https://openalex.org/keywords/family-tree","display_name":"Family tree","score":0.45128071308135986},{"id":"https://openalex.org/keywords/evolutionary-biology","display_name":"Evolutionary biology","score":0.43027615547180176},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.3668694794178009},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.32430458068847656},{"id":"https://openalex.org/keywords/genealogy","display_name":"Genealogy","score":0.2854236960411072},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.13364338874816895}],"concepts":[{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.9332709908485413},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5558242201805115},{"id":"https://openalex.org/C80429922","wikidata":"https://www.wikidata.org/wiki/Q189977","display_name":"Family tree","level":2,"score":0.45128071308135986},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.43027615547180176},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3668694794178009},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.32430458068847656},{"id":"https://openalex.org/C53553401","wikidata":"https://www.wikidata.org/wiki/Q47307","display_name":"Genealogy","level":1,"score":0.2854236960411072},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.13364338874816895},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","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":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020407","descriptor_name":"Internet","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020407","descriptor_name":"Internet","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020407","descriptor_name":"Internet","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"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":"D054892","descriptor_name":"Metagenome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D054892","descriptor_name":"Metagenome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D054892","descriptor_name":"Metagenome","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":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1093/nar/gkr1027","is_oa":true,"landing_page_url":"https://doi.org/10.1093/nar/gkr1027","pdf_url":"https://academic.oup.com/nar/article-pdf/40/D1/D313/9475078/gkr1027.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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nucleic Acids Research","raw_type":"journal-article"},{"id":"pmid:22121228","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/22121228","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:pubmedcentral.nih.gov:3245180","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3245180","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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 Res","raw_type":"Text"},{"id":"pmh:oai:open-archive.highwire.org:nar:40/D1/D313","is_oa":false,"landing_page_url":"http://nar.oxfordjournals.org/cgi/content/short/40/D1/D313","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"}],"best_oa_location":{"id":"doi:10.1093/nar/gkr1027","is_oa":true,"landing_page_url":"https://doi.org/10.1093/nar/gkr1027","pdf_url":"https://academic.oup.com/nar/article-pdf/40/D1/D313/9475078/gkr1027.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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nucleic Acids Research","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1995530145.pdf","grobid_xml":"https://content.openalex.org/works/W1995530145.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1791999417","https://openalex.org/W1993731989","https://openalex.org/W2008116827","https://openalex.org/W2014719716","https://openalex.org/W2027542060","https://openalex.org/W2033441138","https://openalex.org/W2037993016","https://openalex.org/W2069399904","https://openalex.org/W2076048958","https://openalex.org/W2081269341","https://openalex.org/W2083654996","https://openalex.org/W2096039184","https://openalex.org/W2096939566","https://openalex.org/W2108366237","https://openalex.org/W2108758729","https://openalex.org/W2110115297","https://openalex.org/W2111973517","https://openalex.org/W2116423958","https://openalex.org/W2117249420","https://openalex.org/W2118619377","https://openalex.org/W2119027485","https://openalex.org/W2128653811","https://openalex.org/W2133892581","https://openalex.org/W2141885858","https://openalex.org/W2151370125","https://openalex.org/W2154205489","https://openalex.org/W2155744824","https://openalex.org/W2158714788","https://openalex.org/W2161241566","https://openalex.org/W2163105490","https://openalex.org/W2163895365","https://openalex.org/W2171097261","https://openalex.org/W2772934464","https://openalex.org/W4210623056"],"related_works":["https://openalex.org/W2390982513","https://openalex.org/W2385089581","https://openalex.org/W643262219","https://openalex.org/W2356893721","https://openalex.org/W2942942420","https://openalex.org/W2481589910","https://openalex.org/W2383222704","https://openalex.org/W2391839550","https://openalex.org/W3113684560","https://openalex.org/W3130260659"],"abstract_inverted_index":{"ProtoNet":[0,44,119,156,178],"6.0":[1,120,179],"(http://www.protonet.cs.huji.ac.il)":[2],"is":[3,68,95],"a":[4,34,97,123,138],"data":[5,133],"structure":[6,67,134],"of":[7,31,53,74,78,105,140,148,155,165,172,187],"protein":[8,13,40,166],"families":[9,17,167],"that":[10,37,99],"cover":[11],"the":[12,60,85,101,129,136,141,173,185],"sequence":[14,174],"space.":[15],"These":[16,108],"are":[18,110,157],"generated":[19],"through":[20],"an":[21,71],"unsupervised":[22],"bottom-up":[23],"clustering":[24],"algorithm.":[25],"This":[26],"algorithm":[27],"organizes":[28],"large":[29],"sets":[30],"proteins":[32,52],"in":[33,122,128],"hierarchical":[35,65],"tree":[36,47,66,86,143],"yields":[38],"high-quality":[39,93],"families.":[41],"The":[42,64],"2012":[43],"(Version":[45],"6.0)":[46],"includes":[48],"over":[49],"9":[50],"million":[51,76],"which":[54],"5.5%":[55],"come":[56],"from":[57,62],"UniProtKB/SwissProt":[58],"and":[59,117],"rest":[61],"UniProtKB/TrEMBL.":[63],"based":[69],"on":[70],"all-against-all":[72],"comparison":[73],"2.5":[75],"representatives":[77],"UniRef50.":[79],"Rigorous":[80],"annotation-based":[81],"quality":[82],"tests":[83],"prune":[84],"to":[87,183],"most":[88,102],"informative":[89],"162,088":[90],"clusters.":[91,188],"Every":[92],"cluster":[94],"assigned":[96],"ProtoName":[98],"reflects":[100],"significant":[103],"annotations":[104,109],"its":[106],"proteins.":[107],"dominated":[111],"by":[112],"GO":[113],"terms,":[114],"UniProt/Swiss-Prot":[115],"keywords":[116],"InterPro.":[118],"operates":[121],"default":[124],"mode.":[125],"When":[126],"used":[127],"advanced":[130],"mode,":[131],"this":[132],"offers":[135],"user":[137],"view":[139,164],"family":[142],"at":[144],"any":[145],"desired":[146],"level":[147],"resolution.":[149],"Systematic":[150],"comparisons":[151],"with":[152],"previous":[153],"versions":[154],"carried":[158],"out.":[159],"They":[160],"show":[161],"how":[162],"our":[163],"evolves,":[168],"as":[169],"larger":[170],"parts":[171],"space":[175],"become":[176],"known.":[177],"provides":[180],"numerous":[181],"tools":[182],"navigate":[184],"hierarchy":[186]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":7},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":1}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}
