{"id":"https://openalex.org/W1986347357","doi":"https://doi.org/10.1073/pnas.0905029106","title":"Nature of the protein universe","display_name":"Nature of the protein universe","publication_year":2009,"publication_date":"2009-06-18","ids":{"openalex":"https://openalex.org/W1986347357","doi":"https://doi.org/10.1073/pnas.0905029106","mag":"1986347357","pmid":"https://pubmed.ncbi.nlm.nih.gov/19541617","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/2698892"},"language":"en","primary_location":{"id":"doi:10.1073/pnas.0905029106","doi":"https://doi.org/10.1073/pnas.0905029106","is_oa":false,"landing_page_url":"https://doi.org/10.1073/pnas.0905029106","pdf_url":null,"source":{"id":"https://openalex.org/S125754415","display_name":"Proceedings of the National Academy of Sciences","issn_l":"0027-8424","issn":["0027-8424","1091-6490"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","dongbi-a","doyens","erih-plus","jufo-3","ki-jl-3","medline","norway-2","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320052","host_organization_name":"National Academy of Sciences","host_organization_lineage":["https://openalex.org/P4310320052"],"host_organization_lineage_names":["National Academy of Sciences"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the National Academy of Sciences","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC2698892/","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019080704","display_name":"Michael Levitt","orcid":"https://orcid.org/0000-0002-8414-7397","observed_orcids":["https://orcid.org/0000-0002-8414-7397"]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Michael Levitt","raw_affiliation_strings":["Department of Structural Biology, Stanford University, Stanford, CA 94305-5126","Department of Structural Biology, Stanford University, Stanford, CA 94305-5126, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Structural Biology, Stanford University, Stanford, CA 94305-5126","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Department of Structural Biology, Stanford University, Stanford, CA 94305-5126, USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5019080704"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":7.2936,"has_fulltext":false,"cited_by_count":319,"citation_normalized_percentile":{"value":0.98429109,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"106","issue":"27","first_page":"11079","last_page":"11084"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.7368000149726868,"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":0.7368000149726868,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.16930000483989716,"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/T11162","display_name":"Enzyme Structure and Function","score":0.03500000014901161,"subfield":{"id":"https://openalex.org/subfields/1315","display_name":"Structural 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/protein-families","display_name":"protein families","score":0.7590000033378601},{"id":"https://openalex.org/keywords/single-domain-proteins","display_name":"single-domain proteins","score":0.8090000152587891},{"id":"https://openalex.org/keywords/multidomain-proteins","display_name":"multidomain proteins","score":0.8539999723434448},{"id":"https://openalex.org/keywords/protein-domain-architecture","display_name":"protein domain architecture","score":0.6620000004768372},{"id":"https://openalex.org/keywords/sequence-profiles","display_name":"sequence profiles","score":0.7910000085830688},{"id":"https://openalex.org/keywords/protein-structure","display_name":"protein structure","score":0.5680000185966492},{"id":"https://openalex.org/keywords/protein-sequence-evolution","display_name":"protein sequence evolution","score":0.4869999885559082},{"id":"https://openalex.org/keywords/species-diversity","display_name":"species diversity","score":0.5379999876022339},{"id":"https://openalex.org/keywords/protein-structure-prediction","display_name":"protein structure prediction","score":0.4690000116825104}],"concepts":[{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6555399894714355},{"id":"https://openalex.org/C84999194","wikidata":"https://www.wikidata.org/wiki/Q1","display_name":"Universe","level":2,"score":0.6348840594291687},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5643343925476074},{"id":"https://openalex.org/C144292202","wikidata":"https://www.wikidata.org/wiki/Q898273","display_name":"Protein domain","level":3,"score":0.5335631370544434},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5328619480133057},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5134895443916321},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.4869919717311859},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.4571753144264221},{"id":"https://openalex.org/C47701112","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Protein structure","level":2,"score":0.4118138551712036},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4109093248844147},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.3720042109489441},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.2057066261768341},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16199180483818054},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.08422812819480896},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"score":0.0776522159576416},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005810","descriptor_name":"Multigene Family","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D017434","descriptor_name":"Protein Structure, Tertiary","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019143","descriptor_name":"Evolution, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D040681","descriptor_name":"Structural Homology, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1073/pnas.0905029106","doi":"https://doi.org/10.1073/pnas.0905029106","is_oa":false,"landing_page_url":"https://doi.org/10.1073/pnas.0905029106","pdf_url":null,"source":{"id":"https://openalex.org/S125754415","display_name":"Proceedings of the National Academy of Sciences","issn_l":"0027-8424","issn":["0027-8424","1091-6490"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","dongbi-a","doyens","erih-plus","jufo-3","ki-jl-3","medline","norway-2","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320052","host_organization_name":"National Academy of Sciences","host_organization_lineage":["https://openalex.org/P4310320052"],"host_organization_lineage_names":["National Academy of Sciences"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the National Academy of Sciences","raw_type":"journal-article"},{"id":"pmid:19541617","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/19541617","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the National Academy of Sciences of the United States of America","raw_type":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:2698892","doi":null,"is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC2698892/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proc Natl Acad Sci U S A","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:2698892","doi":null,"is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC2698892/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proc Natl Acad Sci U S A","raw_type":"Text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G5612071531","display_name":"Accurate Modeling in Structural Genomics","funder_award_id":"R01GM063817","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"}],"funders":[{"id":"https://openalex.org/F4320324887","display_name":"Shandong Academy of Sciences","ror":"https://ror.org/04y8d6y55"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W79627341","https://openalex.org/W1791999417","https://openalex.org/W1913745973","https://openalex.org/W1947762817","https://openalex.org/W1969460352","https://openalex.org/W1971921744","https://openalex.org/W1974160388","https://openalex.org/W1977922844","https://openalex.org/W2010458285","https://openalex.org/W2011235285","https://openalex.org/W2017699309","https://openalex.org/W2018410079","https://openalex.org/W2019076206","https://openalex.org/W2023790301","https://openalex.org/W2041916700","https://openalex.org/W2043092219","https://openalex.org/W2045839655","https://openalex.org/W2055043387","https://openalex.org/W2056788931","https://openalex.org/W2058336694","https://openalex.org/W2085277871","https://openalex.org/W2102122585","https://openalex.org/W2102882929","https://openalex.org/W2108211735","https://openalex.org/W2115843776","https://openalex.org/W2115864800","https://openalex.org/W2116435022","https://openalex.org/W2121520117","https://openalex.org/W2124871329","https://openalex.org/W2134156588","https://openalex.org/W2141920824","https://openalex.org/W2144494426","https://openalex.org/W2148950394","https://openalex.org/W2158714788","https://openalex.org/W2159266221","https://openalex.org/W2161033884","https://openalex.org/W3147254695","https://openalex.org/W4232639155"],"related_works":["https://openalex.org/W2036845870","https://openalex.org/W1964903151","https://openalex.org/W1574088300","https://openalex.org/W2030040914","https://openalex.org/W2163363312","https://openalex.org/W2290774513","https://openalex.org/W2133070552","https://openalex.org/W7100026309","https://openalex.org/W2121481607","https://openalex.org/W7100757395"],"abstract_inverted_index":{"The":[0],"protein":[1],"universe":[2],"is":[3,42],"the":[4,70,93],"set":[5],"of":[6,9,21,38,56,73,92,98],"all":[7,10,13,46,99],"proteins":[8],"organisms.":[11],"Here,":[12],"currently":[14],"known":[15,34,87],"sequences":[16,100],"are":[17,54,66,78,86],"analyzed":[18],"in":[19,109],"terms":[20],"families":[22,41,65],"that":[23,53],"have":[24,32],"single-domain":[25,40,94],"or":[26],"multidomain":[27,51,76],"architectures":[28,52,77],"and":[29,80,96],"whether":[30],"they":[31],"a":[33,90],"three-dimensional":[35],"structure.":[36],"Growth":[37],"new":[39,50],"very":[43],"slow:":[44],"Almost":[45],"growth":[47],"comes":[48],"from":[49],"combinations":[55],"domains":[57],"characterized":[58],"by":[59,69],"approximately":[60],"15,000":[61],"sequence":[62],"profiles.":[63],"Single-domain":[64],"mostly":[67],"shared":[68],"major":[71],"groups":[72],"organisms,":[74],"whereas":[75],"specific":[79],"account":[81],"for":[82,89],"species":[83],"diversity.":[84],"There":[85],"structures":[88],"quarter":[91],"families,":[95],">70%":[97],"can":[101],"be":[102],"partially":[103],"modeled":[104],"thanks":[105],"to":[106],"their":[107],"membership":[108],"these":[110],"families.":[111]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":24},{"year":2020,"cited_by_count":24},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":21},{"year":2017,"cited_by_count":27},{"year":2016,"cited_by_count":16},{"year":2015,"cited_by_count":17},{"year":2014,"cited_by_count":28},{"year":2013,"cited_by_count":23},{"year":2012,"cited_by_count":30}],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2016-06-24T00:00:00"}
