{"id":"https://openalex.org/W2116377237","doi":"https://doi.org/10.1093/bioinformatics/bti627","title":"Statistical evaluation of pairwise protein sequence comparison with the Bayesian bootstrap","display_name":"Statistical evaluation of pairwise protein sequence comparison with the Bayesian bootstrap","publication_year":2005,"publication_date":"2005-08-16","ids":{"openalex":"https://openalex.org/W2116377237","doi":"https://doi.org/10.1093/bioinformatics/bti627","mag":"2116377237","pmid":"https://pubmed.ncbi.nlm.nih.gov/16105900"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/bti627","doi":"https://doi.org/10.1093/bioinformatics/bti627","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bti627","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/21/20/3824/48981123/bioinformatics_21_20_3824.pdf","source":{"id":"https://openalex.org/S4210188263","display_name":"Computer applications in the biosciences","issn_l":"0266-7061","issn":["0266-7061","1460-2059"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["abdc-a","cwts-core","poland-200"],"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/21/20/3824/48981123/bioinformatics_21_20_3824.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"G. A. Price","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"G. A. Price","raw_affiliation_strings":["Department of Bioengineering, University of California, Berkeley, 94720, USA","Department of Bioengineering, University of California Berkeley, CA 94720, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Bioengineering, University of California, Berkeley, 94720, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"Department of Bioengineering, University of California Berkeley, CA 94720, USA#TAB#","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056143270","display_name":"Gavin E. Crooks","orcid":"https://orcid.org/0000-0002-6870-7956","observed_orcids":["https://orcid.org/0000-0002-6870-7956"]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"G. E. Crooks","raw_affiliation_strings":["Department of Plant and Microbial Biology, University of California, Berkeley CA 94720, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Plant and Microbial Biology, University of California, Berkeley CA 94720, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038814932","display_name":"Richard Edward Green","orcid":"https://orcid.org/0000-0003-0516-5827","observed_orcids":["https://orcid.org/0000-0003-0516-5827"]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"R. E. Green","raw_affiliation_strings":["Department of Plant and Microbial Biology, University of California, Berkeley CA 94720, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Plant and Microbial Biology, University of California, Berkeley CA 94720, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046334676","display_name":"Steven E. Brenner","orcid":"https://orcid.org/0000-0001-7559-6185","observed_orcids":["https://orcid.org/0000-0001-7559-6185"]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"S. E. Brenner","raw_affiliation_strings":["Department of Bioengineering and","Department of Plant and Microbial Biology , University of California , Berkeley , CA 94720 , USA","Department of Bioengineering, University of California Berkeley, CA 94720, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Bioengineering and","institution_ids":[]},{"raw_affiliation_string":"Department of Plant and Microbial Biology , University of California , Berkeley , CA 94720 , USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"Department of Bioengineering, University of California Berkeley, CA 94720, USA#TAB#","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":0.6275,"has_fulltext":true,"cited_by_count":26,"citation_normalized_percentile":{"value":0.64836559,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":"21","issue":"20","first_page":"3824","last_page":"3831"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.8999000191688538,"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":0.8999000191688538,"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":0.029600000008940697,"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/T12946","display_name":"Fractal and DNA sequence analysis","score":0.02070000022649765,"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":0.8349999785423279},{"id":"https://openalex.org/keywords/bayesian-bootstrap","display_name":"Bayesian bootstrap","score":0.953000009059906},{"id":"https://openalex.org/keywords/amino-acid-substitution-matrices","display_name":"amino acid substitution matrices","score":0.9359999895095825},{"id":"https://openalex.org/keywords/remote-homology-detection","display_name":"remote homology detection","score":0.8999999761581421}],"concepts":[{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.7622460722923279},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.6260303854942322},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5885699987411499},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5397094488143921},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.41990065574645996},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3637283444404602},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3126222491264343},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.16576802730560303},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.11026111245155334}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001499","descriptor_name":"Bayes Theorem","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003627","descriptor_name":"Data Interpretation, Statistical","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":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000032","qualifier_name":"analysis","is_major_topic":false},{"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":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/bti627","doi":"https://doi.org/10.1093/bioinformatics/bti627","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bti627","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/21/20/3824/48981123/bioinformatics_21_20_3824.pdf","source":{"id":"https://openalex.org/S4210188263","display_name":"Computer applications in the biosciences","issn_l":"0266-7061","issn":["0266-7061","1460-2059"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["abdc-a","cwts-core","poland-200"],"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:16105900","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/16105900","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":"Bioinformatics (Oxford, England)","raw_type":"Evaluation Study"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.324.1314","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.324.1314","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://bioinformatics.oxfordjournals.org/content/early/2005/08/16/bioinformatics.bti627.full.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/bti627","doi":"https://doi.org/10.1093/bioinformatics/bti627","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bti627","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/21/20/3824/48981123/bioinformatics_21_20_3824.pdf","source":{"id":"https://openalex.org/S4210188263","display_name":"Computer applications in the biosciences","issn_l":"0266-7061","issn":["0266-7061","1460-2059"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["abdc-a","cwts-core","poland-200"],"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G5088157245","display_name":"COMPUTATIONAL STRUCTURAL AND FUNCTIONAL GENOMICS","funder_award_id":"K22HG000056","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"},{"id":"https://openalex.org/G9000892114","display_name":"Berkeley Training Program in Genomics and Computational Biology","funder_award_id":"T32HG000047","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/W2116377237.pdf","grobid_xml":"https://content.openalex.org/works/W2116377237.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W21816278","https://openalex.org/W1502621331","https://openalex.org/W1526255571","https://openalex.org/W1536270671","https://openalex.org/W1964145490","https://openalex.org/W1969460352","https://openalex.org/W1988461381","https://openalex.org/W1995945562","https://openalex.org/W1996357466","https://openalex.org/W2001994823","https://openalex.org/W2003443426","https://openalex.org/W2009570821","https://openalex.org/W2015292449","https://openalex.org/W2018220145","https://openalex.org/W2026881360","https://openalex.org/W2029372233","https://openalex.org/W2044128233","https://openalex.org/W2055043387","https://openalex.org/W2058336694","https://openalex.org/W2068448872","https://openalex.org/W2074231493","https://openalex.org/W2084787613","https://openalex.org/W2085277871","https://openalex.org/W2087064593","https://openalex.org/W2089499735","https://openalex.org/W2090424274","https://openalex.org/W2095595785","https://openalex.org/W2097818324","https://openalex.org/W2112452502","https://openalex.org/W2113398700","https://openalex.org/W2117249420","https://openalex.org/W2117897510","https://openalex.org/W2118475569","https://openalex.org/W2126377763","https://openalex.org/W2131724426","https://openalex.org/W2133312664","https://openalex.org/W2133571659","https://openalex.org/W2133657429","https://openalex.org/W2135112949","https://openalex.org/W2139621307","https://openalex.org/W2140244239","https://openalex.org/W2140540327","https://openalex.org/W2143210482","https://openalex.org/W2145358391","https://openalex.org/W2157975034","https://openalex.org/W2163694519","https://openalex.org/W2171280596"],"related_works":["https://openalex.org/W7096487995","https://openalex.org/W7095699568","https://openalex.org/W2118475569","https://openalex.org/W2157975034","https://openalex.org/W2113398700","https://openalex.org/W2132015821","https://openalex.org/W1502621331","https://openalex.org/W6987361501","https://openalex.org/W2319435119","https://openalex.org/W2133927913"],"abstract_inverted_index":{"MOTIVATION:":[0],"Protein":[1],"sequence":[2,49,101,171],"comparison":[3,50,102],"methods":[4],"are":[5,179],"routinely":[6],"used":[7,95],"to":[8,27,57,63,84,124,133],"infer":[9],"the":[10,18,29,37,65,73,88,97,116,125,134,163],"intricate":[11],"network":[12],"of":[13,22,33,46,67,99,137],"evolutionary":[14],"relationships":[15],"found":[16],"within":[17,76],"rapidly":[19],"growing":[20],"library":[21],"protein":[23,48],"sequences,":[24],"and":[25,31,62,143,166,173],"thereby":[26],"predict":[28],"structure":[30,75],"function":[32],"uncharacterized":[34],"proteins.":[35],"In":[36],"present":[38],"study,":[39],"we":[40],"detail":[41],"an":[42,108,110],"improved":[43],"statistical":[44,60,112],"benchmark":[45,77],"pairwise":[47],"algorithms.":[51],"We":[52,70,104,129],"use":[53],"bootstrap":[54,83,90],"resampling":[55,120],"techniques":[56],"determine":[58],"standard":[59,89,126],"errors":[61],"estimate":[64],"confidence":[66],"our":[68,131],"conclusions.":[69],"show":[71],"that":[72,145],"underlying":[74],"databases":[78],"causes":[79],"Efron's":[80],"standard,":[81],"non-parametric":[82],"be":[85],"biased.":[86],"Consequently,":[87],"underpredicts":[91],"average":[92],"performance":[93],"when":[94],"in":[96,150,157],"context":[98],"evaluating":[100],"methods.":[103],"have":[105],"developed,":[106],"as":[107],"alternative,":[109],"unbiased":[111],"evaluation":[113],"based":[114],"on":[115],"Bayesian":[117],"bootstrap,":[118],"a":[119,151],"method":[121],"operationally":[122],"similar":[123],"bootstrap.":[127],"RESULTS:":[128],"apply":[130],"analysis":[132],"comparative":[135],"study":[136],"amino":[138],"acid":[139],"substitution":[140],"matrix":[141],"families":[142],"find":[144],"using":[146],"modern":[147],"matrices":[148],"results":[149],"small,":[152],"but":[153],"statistically":[154],"significant":[155],"improvement":[156],"remote":[158],"homology":[159],"detection":[160],"compared":[161],"with":[162],"classic":[164],"PAM":[165],"BLOSUM":[167],"matrices.":[168],"AVAILABILITY:":[169],"The":[170],"sets":[172],"code":[174],"for":[175],"performing":[176],"these":[177],"analyses":[178],"available":[180],"from":[181],"http://compbio.berkeley.edu/.":[182],"CONTACT:":[183],"brenner@compbio.berkeley.edu.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-11-01T11:40:01.658920","created_date":"2016-06-24T00:00:00"}
