{"id":"https://openalex.org/W2005049999","doi":"https://doi.org/10.1073/pnas.95.11.5913","title":"A unified statistical framework for sequence comparison and structure comparison","display_name":"A unified statistical framework for sequence comparison and structure comparison","publication_year":1998,"publication_date":"1998-05-26","ids":{"openalex":"https://openalex.org/W2005049999","doi":"https://doi.org/10.1073/pnas.95.11.5913","mag":"2005049999","pmid":"https://pubmed.ncbi.nlm.nih.gov/9600892","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/34495"},"language":"en","primary_location":{"id":"doi:10.1073/pnas.95.11.5913","doi":"https://doi.org/10.1073/pnas.95.11.5913","is_oa":false,"landing_page_url":"https://doi.org/10.1073/pnas.95.11.5913","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":"http://europepmc.org/pmc/articles/PMC34495","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/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]},{"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":false,"raw_author_name":"Michael Levitt","raw_affiliation_strings":["Department of Structural Biology, Stanford University, Stanford,\r CA 94305; and Molecular Biophysics and Biochemistry\r Department, P.O. Box 208114, Yale University, New Haven, CT\r 06520-8114"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Structural Biology, Stanford University, Stanford,\r CA 94305; and Molecular Biophysics and Biochemistry\r Department, P.O. Box 208114, Yale University, New Haven, CT\r 06520-8114","institution_ids":["https://openalex.org/I32971472","https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042321575","display_name":"Mark Gerstein","orcid":"https://orcid.org/0000-0002-9746-3719","observed_orcids":["https://orcid.org/0000-0002-9746-3719"]},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]},{"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":false,"raw_author_name":"Mark Gerstein","raw_affiliation_strings":["Department of Structural Biology, Stanford University, Stanford,\r CA 94305; and Molecular Biophysics and Biochemistry\r Department, P.O. Box 208114, Yale University, New Haven, CT\r 06520-8114"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Structural Biology, Stanford University, Stanford,\r CA 94305; and Molecular Biophysics and Biochemistry\r Department, P.O. Box 208114, Yale University, New Haven, CT\r 06520-8114","institution_ids":["https://openalex.org/I32971472","https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.36,"has_fulltext":false,"cited_by_count":301,"citation_normalized_percentile":{"value":0.95646052,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"95","issue":"11","first_page":"5913","last_page":"5920"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.8227999806404114,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.8227999806404114,"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":0.08449999988079071,"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"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.05730000138282776,"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/protein-sequence-comparison","display_name":"protein sequence comparison","score":0.8600000143051147},{"id":"https://openalex.org/keywords/protein-structure-comparison","display_name":"protein structure comparison","score":0.9929999709129333},{"id":"https://openalex.org/keywords/extreme-value-distribution","display_name":"extreme value distribution","score":0.9089999794960022},{"id":"https://openalex.org/keywords/p-values","display_name":"p-values","score":0.5950000286102295},{"id":"https://openalex.org/keywords/protein-domains","display_name":"protein domains","score":0.7009999752044678},{"id":"https://openalex.org/keywords/rms-deviation","display_name":"RMS deviation","score":0.7020000219345093},{"id":"https://openalex.org/keywords/scop","display_name":"SCOP","score":0.4659999907016754},{"id":"https://openalex.org/keywords/blast","display_name":"BLAST","score":0.5360000133514404},{"id":"https://openalex.org/keywords/fasta","display_name":"FASTA","score":0.9760000109672546}],"concepts":[{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.631647527217865},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6239433884620667},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.5348753929138184},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.47381889820098877},{"id":"https://openalex.org/C169707849","wikidata":"https://www.wikidata.org/wiki/Q1617240","display_name":"Generalized extreme value distribution","level":3,"score":0.4702683091163635},{"id":"https://openalex.org/C147581598","wikidata":"https://www.wikidata.org/wiki/Q729429","display_name":"Extreme value theory","level":2,"score":0.46574366092681885},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.42603030800819397},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4241354763507843},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.411123126745224},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4060615599155426},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3463493585586548},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3275071978569031},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2860344648361206},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.22491031885147095},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.12674462795257568},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.07927742600440979},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000818","descriptor_name":"Animals","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":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017421","descriptor_name":"Sequence Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017510","descriptor_name":"Protein Folding","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019143","descriptor_name":"Evolution, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":6,"locations":[{"id":"doi:10.1073/pnas.95.11.5913","doi":"https://doi.org/10.1073/pnas.95.11.5913","is_oa":false,"landing_page_url":"https://doi.org/10.1073/pnas.95.11.5913","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":"pmh:oai:europepmc.org:192486","doi":null,"is_oa":true,"landing_page_url":"http://europepmc.org/pmc/articles/PMC34495","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:34495","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/34495","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"},{"id":"pmid:9600892","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/9600892","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:CiteSeerX.psu:10.1.1.21.582","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.21.582","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://bioinfo.mbb.yale.edu/~mbg/preprint/stat-framework-pnas-preprint.pdf","raw_type":"text"},{"id":"mag:2319435119","doi":null,"is_oa":false,"landing_page_url":"http://papers.gersteinlab.org/e-print/statframe-pnas-reprint.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:europepmc.org:192486","doi":null,"is_oa":true,"landing_page_url":"http://europepmc.org/pmc/articles/PMC34495","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W146195030","https://openalex.org/W1484548732","https://openalex.org/W1513073936","https://openalex.org/W1536270671","https://openalex.org/W1551915691","https://openalex.org/W1571578421","https://openalex.org/W1605134757","https://openalex.org/W1659313070","https://openalex.org/W1901470441","https://openalex.org/W1965910641","https://openalex.org/W1965998064","https://openalex.org/W1966041739","https://openalex.org/W1979147581","https://openalex.org/W1986825290","https://openalex.org/W1986850860","https://openalex.org/W1988461381","https://openalex.org/W1989447327","https://openalex.org/W2000468790","https://openalex.org/W2002180966","https://openalex.org/W2012744602","https://openalex.org/W2015292449","https://openalex.org/W2022058405","https://openalex.org/W2023790301","https://openalex.org/W2029195137","https://openalex.org/W2037357509","https://openalex.org/W2045501609","https://openalex.org/W2054453390","https://openalex.org/W2065117679","https://openalex.org/W2074231493","https://openalex.org/W2084367350","https://openalex.org/W2085277871","https://openalex.org/W2087064593","https://openalex.org/W2094519647","https://openalex.org/W2102475449","https://openalex.org/W2108138353","https://openalex.org/W2117077088","https://openalex.org/W2118404357","https://openalex.org/W2131202198","https://openalex.org/W2131851875","https://openalex.org/W2136567909","https://openalex.org/W2141414410","https://openalex.org/W2157975034","https://openalex.org/W2158714788","https://openalex.org/W2166905169","https://openalex.org/W4298086639"],"related_works":["https://openalex.org/W2319435119","https://openalex.org/W2157975034","https://openalex.org/W2043491405","https://openalex.org/W2148376194","https://openalex.org/W7098437041","https://openalex.org/W7098741194","https://openalex.org/W2368300829","https://openalex.org/W1972718882","https://openalex.org/W7097893793","https://openalex.org/W7100828401"],"abstract_inverted_index":{"We":[0,157],"present":[1],"an":[2,27,96,130],"approach":[3],"for":[4,19,92,200],"assessing":[5],"the":[6,36,51,69,75,90,103,134,146,160,166,189,195,227],"significance":[7,63],"of":[8,30,39,71,140,148,163,180,194,202,246,259],"sequence":[9,21,93,196,224,247],"and":[10,22,43,112,120,182,197],"structure":[11,198,250,260],"comparisons":[12],"by":[13,83,115],"using":[14,55],"nearly":[15],"identical":[16],"statistical":[17,62],"formalisms":[18],"both":[20],"structure.":[23],"Doing":[24],"so":[25],"involves":[26],"all-vs.-all":[28],"comparison":[29,66,126,212,225,232],"protein":[31],"domains":[32],"[taken":[33],"here":[34],"from":[35,109],"Structural":[37],"Classification":[38],"Proteins":[40],"(scop)":[41],"database]":[42],"then":[44],"fitting":[45,173],"a":[46,61,72,78,141,177],"simple":[47],"distribution":[48,111,132,179],"function":[49],"to":[50,64,205,215],"observed":[52],"scores.":[53],"By":[54],"this":[56,110],"distribution,":[57],"we":[58,87,107],"can":[59],"attach":[60],"each":[65],"score":[67,80,144],"in":[68,138,169,244,257],"form":[70],"P":[73,104],"value,":[74],"probability":[76],"that":[77,89,106,159,210,235],"better":[79],"would":[81],"occur":[82],"chance.":[84],"As":[85],"expected,":[86],"find":[88,158],"scores":[91,127,181],"matching":[94],"follow":[95,129],"extreme-value":[97,131],"distribution.":[98],"The":[99,231],"agreement,":[100],"moreover,":[101],"between":[102,151],"values":[105],"derive":[108],"those":[113],"reported":[114],"standard":[116],"programs":[117],"(e.g.,":[118],"BLAST":[119],"FASTA":[121],"validates":[122],"our":[123],"approach.":[124],"Structure":[125],"also":[128,233],"when":[133],"statistics":[135,199],"are":[136,237],"expressed":[137],"terms":[139,245,258],"structural":[142,164,190,211],"alignment":[143,191],"(essentially":[145],"sum":[147],"reciprocated":[149],"distances":[150],"aligned":[152,174],"atoms":[153],"minus":[154],"gap":[155],"penalties).":[156],"traditional":[161],"metric":[162],"similarity,":[165],"rms":[167],"deviation":[168],"atom":[170],"positions":[171],"after":[172],"atoms,":[175],"follows":[176],"different":[178],"does":[183],"not":[184,249,262],"perform":[185],"as":[186,188,219,223],"well":[187],"score.":[192],"Comparison":[193],"pairs":[201,240,253],"proteins":[203],"known":[204],"be":[206],"related":[207],"distantly":[208],"shows":[209],"is":[213],"able":[214],"detect":[216],"approximately":[217],"twice":[218],"many":[220,252],"distant":[221],"relationships":[222],"at":[226],"same":[228],"error":[229],"rate.":[230],"indicates":[234],"there":[236],"very":[238],"few":[239],"with":[241],"significant":[242,255],"similarity":[243,256],"but":[248,261],"whereas":[251],"have":[254],"sequence.":[263]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":10},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":10}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2016-06-24T00:00:00"}
