{"id":"https://openalex.org/W2017777683","doi":"https://doi.org/10.1126/science.1158395","title":"Phylogeny-Aware Gap Placement Prevents Errors in Sequence Alignment and Evolutionary Analysis","display_name":"Phylogeny-Aware Gap Placement Prevents Errors in Sequence Alignment and Evolutionary Analysis","publication_year":2008,"publication_date":"2008-06-19","ids":{"openalex":"https://openalex.org/W2017777683","doi":"https://doi.org/10.1126/science.1158395","mag":"2017777683","pmid":"https://pubmed.ncbi.nlm.nih.gov/18566285"},"language":"en","primary_location":{"id":"doi:10.1126/science.1158395","doi":"https://doi.org/10.1126/science.1158395","is_oa":false,"landing_page_url":"https://doi.org/10.1126/science.1158395","pdf_url":null,"source":{"id":"https://openalex.org/S3880285","display_name":"Science","issn_l":"0036-8075","issn":["0036-8075","0193-4511","1095-9203"],"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/P4310315823","host_organization_name":"American Association for the Advancement of Science","host_organization_lineage":["https://openalex.org/P4310315823"],"host_organization_lineage_names":["American Association for the Advancement of Science"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Science","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000878403","display_name":"Ari L\u00f6ytynoja","orcid":"https://orcid.org/0000-0001-5389-6611","observed_orcids":["https://orcid.org/0000-0001-5389-6611"]},"institutions":[{"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/I87048295","display_name":"Wellcome Trust","ror":"https://ror.org/029chgv08","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I87048295"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Ari Lo\u0308ytynoja","raw_affiliation_strings":["European Molecular Biology Laboratory\u2014European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton CB10 1SD, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"European Molecular Biology Laboratory\u2014European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton CB10 1SD, UK","institution_ids":["https://openalex.org/I1303153112","https://openalex.org/I87048295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020967139","display_name":"Nick Goldman","orcid":"https://orcid.org/0000-0001-8486-2211","observed_orcids":["https://orcid.org/0000-0001-8486-2211"]},"institutions":[{"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/I87048295","display_name":"Wellcome Trust","ror":"https://ror.org/029chgv08","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I87048295"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nick Goldman","raw_affiliation_strings":["European Molecular Biology Laboratory\u2014European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton CB10 1SD, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"European Molecular Biology Laboratory\u2014European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton CB10 1SD, UK","institution_ids":["https://openalex.org/I1303153112","https://openalex.org/I87048295"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5000878403"],"corresponding_institution_ids":["https://openalex.org/I1303153112","https://openalex.org/I87048295"],"apc_list":null,"apc_paid":null,"fwci":13.858,"has_fulltext":false,"cited_by_count":815,"citation_normalized_percentile":{"value":0.9950586,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"320","issue":"5883","first_page":"1632","last_page":"1635"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9984999895095825,"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":0.9984999895095825,"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":0.0005000000237487257,"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":0.00019999999494757503,"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/multiple-sequence-alignment","display_name":"multiple sequence alignment","score":0.8270000219345093},{"id":"https://openalex.org/keywords/phylogenetic-alignment","display_name":"phylogenetic alignment","score":0.6380000114440918},{"id":"https://openalex.org/keywords/indels","display_name":"indels","score":0.9459999799728394},{"id":"https://openalex.org/keywords/insertion-deletion-events","display_name":"insertion-deletion events","score":0.7900000214576721},{"id":"https://openalex.org/keywords/alignment-errors","display_name":"alignment errors","score":0.609000027179718},{"id":"https://openalex.org/keywords/evolutionary-events","display_name":"evolutionary events","score":0.4320000112056732},{"id":"https://openalex.org/keywords/alignment-bias","display_name":"alignment bias","score":0.4699999988079071},{"id":"https://openalex.org/keywords/sequence-evolution","display_name":"sequence evolution","score":0.4440000057220459}],"concepts":[{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.7414731383323669},{"id":"https://openalex.org/C180384323","wikidata":"https://www.wikidata.org/wiki/Q16335137","display_name":"Alignment-free sequence analysis","level":5,"score":0.7269311547279358},{"id":"https://openalex.org/C193252679","wikidata":"https://www.wikidata.org/wiki/Q242125","display_name":"Phylogenetic tree","level":3,"score":0.641720175743103},{"id":"https://openalex.org/C88031987","wikidata":"https://www.wikidata.org/wiki/Q1377767","display_name":"Multiple sequence alignment","level":5,"score":0.6102239489555359},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.5757766962051392},{"id":"https://openalex.org/C90132467","wikidata":"https://www.wikidata.org/wiki/Q171184","display_name":"Phylogenetics","level":3,"score":0.5732536315917969},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.5717955231666565},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5686469078063965},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.528819739818573},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.44743648171424866},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.3737184703350067},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.1345130205154419},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.117654949426651}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006678","descriptor_name":"HIV","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D006678","descriptor_name":"HIV","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D006678","descriptor_name":"HIV","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D008562","descriptor_name":"Membrane Glycoproteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D008562","descriptor_name":"Membrane Glycoproteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D014759","descriptor_name":"Viral Envelope Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D014759","descriptor_name":"Viral Envelope Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D015302","descriptor_name":"Simian Immunodeficiency Virus","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D015302","descriptor_name":"Simian Immunodeficiency Virus","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D015302","descriptor_name":"Simian Immunodeficiency Virus","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D015497","descriptor_name":"HIV-1","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D015497","descriptor_name":"HIV-1","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D015497","descriptor_name":"HIV-1","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D015699","descriptor_name":"HIV Envelope Protein gp120","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D015699","descriptor_name":"HIV Envelope Protein gp120","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D016254","descriptor_name":"Mutagenesis, Insertional","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":"D017384","descriptor_name":"Sequence Deletion","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":true}],"locations_count":2,"locations":[{"id":"doi:10.1126/science.1158395","doi":"https://doi.org/10.1126/science.1158395","is_oa":false,"landing_page_url":"https://doi.org/10.1126/science.1158395","pdf_url":null,"source":{"id":"https://openalex.org/S3880285","display_name":"Science","issn_l":"0036-8075","issn":["0036-8075","0193-4511","1095-9203"],"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/P4310315823","host_organization_name":"American Association for the Advancement of Science","host_organization_lineage":["https://openalex.org/P4310315823"],"host_organization_lineage_names":["American Association for the Advancement of Science"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Science","raw_type":"journal-article"},{"id":"pmid:18566285","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/18566285","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":"Science (New York, N.Y.)","raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G7332663836","display_name":null,"funder_award_id":"GR078968","funder_id":"https://openalex.org/F4320311904","funder_display_name":"Wellcome Trust"}],"funders":[{"id":"https://openalex.org/F4320311904","display_name":"Wellcome Trust","ror":"https://ror.org/029chgv08"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1519266993","https://openalex.org/W1646393397","https://openalex.org/W1791659070","https://openalex.org/W1866488244","https://openalex.org/W2005925428","https://openalex.org/W2076195270","https://openalex.org/W2097040991","https://openalex.org/W2099381548","https://openalex.org/W2102304447","https://openalex.org/W2102502076","https://openalex.org/W2106882534","https://openalex.org/W2118533197","https://openalex.org/W2125548284","https://openalex.org/W2126887491","https://openalex.org/W2127146638","https://openalex.org/W2127688908","https://openalex.org/W2130044459","https://openalex.org/W2144362290","https://openalex.org/W2144413761"],"related_works":["https://openalex.org/W3111451490","https://openalex.org/W128985141","https://openalex.org/W1646393397","https://openalex.org/W2066615914","https://openalex.org/W2183485040","https://openalex.org/W1995318306","https://openalex.org/W2128201162","https://openalex.org/W1999707793","https://openalex.org/W7097351283","https://openalex.org/W7014440247"],"abstract_inverted_index":{"Genetic":[0],"sequence":[1,29,88,107,122],"alignment":[2,30,99],"is":[3,113],"the":[4,20,33,85,118],"basis":[5],"of":[6,22,36,87,97,121,126],"many":[7],"evolutionary":[8,23,75],"and":[9,12,42,50,55,71,80,90,106,116,124,128],"comparative":[10],"studies,":[11],"errors":[13,18,67],"in":[14,19,25],"alignments":[15,46,89],"lead":[16],"to":[17],"interpretation":[21],"information":[24],"genomes.":[26],"Traditional":[27],"multiple":[28],"methods":[31],"disregard":[32],"phylogenetic":[34],"implications":[35],"gap":[37],"patterns":[38],"that":[39,63,82,104],"they":[40],"create":[41],"infer":[43],"systematically":[44],"biased":[45],"with":[47],"excess":[48],"deletions":[49,72],"substitutions,":[51],"too":[52],"few":[53],"insertions,":[54],"implausible":[56],"insertion-deletion-event":[57],"histories.":[58],"We":[59,77],"present":[60],"a":[61,94],"method":[62],"prevents":[64],"these":[65],"systematic":[66],"by":[68],"recognizing":[69],"insertions":[70,105],"as":[73],"distinct":[74],"events.":[76],"show":[78],"theoretically":[79],"practically":[81],"this":[83],"improves":[84],"quality":[86],"downstream":[91],"analyses":[92],"over":[93],"wide":[95],"range":[96],"realistic":[98],"problems.":[100],"These":[101],"results":[102],"suggest":[103],"turnover":[108],"are":[109],"more":[110],"common":[111],"than":[112],"currently":[114],"thought":[115],"challenge":[117],"conventional":[119],"picture":[120],"evolution":[123],"mechanisms":[125],"functional":[127],"structural":[129],"changes.":[130]},"counts_by_year":[{"year":2026,"cited_by_count":26},{"year":2025,"cited_by_count":25},{"year":2024,"cited_by_count":30},{"year":2023,"cited_by_count":27},{"year":2022,"cited_by_count":32},{"year":2021,"cited_by_count":37},{"year":2020,"cited_by_count":45},{"year":2019,"cited_by_count":48},{"year":2018,"cited_by_count":66},{"year":2017,"cited_by_count":55},{"year":2016,"cited_by_count":52},{"year":2015,"cited_by_count":68},{"year":2014,"cited_by_count":66},{"year":2013,"cited_by_count":57},{"year":2012,"cited_by_count":52}],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2016-06-24T00:00:00"}
