{"id":"https://openalex.org/W2107087429","doi":"https://doi.org/10.1093/bioinformatics/bti244","title":"On the quality of tree-based protein classification","display_name":"On the quality of tree-based protein classification","publication_year":2005,"publication_date":"2005-01-12","ids":{"openalex":"https://openalex.org/W2107087429","doi":"https://doi.org/10.1093/bioinformatics/bti244","mag":"2107087429","pmid":"https://pubmed.ncbi.nlm.nih.gov/15647305"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/bti244","doi":"https://doi.org/10.1093/bioinformatics/bti244","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bti244","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/21/9/1876/48972680/bioinformatics_21_9_1876.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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/21/9/1876/48972680/bioinformatics_21_9_1876.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081977293","display_name":"Betty Lazareva-Ulitsky","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"B. Lazareva-Ulitsky","raw_affiliation_strings":["Computational Biology Department, Applied Biosystems, Foster City, CA 94404, USA. betty.lazareva@fc.celera.com","Computational Biology Department, Applied Biosystems  850 Lincoln Centre Drive, Foster City, CA 94404, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Biology Department, Applied Biosystems, Foster City, CA 94404, USA. betty.lazareva@fc.celera.com","institution_ids":[]},{"raw_affiliation_string":"Computational Biology Department, Applied Biosystems  850 Lincoln Centre Drive, Foster City, CA 94404, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003251348","display_name":"Karen Diemer","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"K. Diemer","raw_affiliation_strings":["Computational Biology Department, Applied Biosystems 850 Lincoln Centre Drive, Foster City, CA 94404, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Biology Department, Applied Biosystems 850 Lincoln Centre Drive, Foster City, CA 94404, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016853551","display_name":"Paul D. Thomas","orcid":"https://orcid.org/0000-0002-9074-3507","observed_orcids":["https://orcid.org/0000-0002-9074-3507"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"P. D. Thomas","raw_affiliation_strings":["Computational Biology Department, Applied Biosystems 850 Lincoln Centre Drive, Foster City, CA 94404, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Biology Department, Applied Biosystems 850 Lincoln Centre Drive, Foster City, CA 94404, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5081977293"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8269,"has_fulltext":true,"cited_by_count":19,"citation_normalized_percentile":{"value":0.66985864,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":"21","issue":"9","first_page":"1876","last_page":"1890"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9955999851226807,"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":0.9955999851226807,"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":0.0008999999845400453,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.0007999999797903001,"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-family-classification","display_name":"protein family classification","score":0.7689999938011169},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"hierarchical clustering","score":0.7179999947547913},{"id":"https://openalex.org/keywords/panther","display_name":"panther","score":0.6729999780654907},{"id":"https://openalex.org/keywords/gene-ontology","display_name":"Gene Ontology","score":0.8050000071525574},{"id":"https://openalex.org/keywords/protein-function-annotation","display_name":"protein annotation","score":0.4659999907016754},{"id":"https://openalex.org/keywords/agglomerative-hierarchical-clustering","display_name":"agglomerative clustering","score":0.7639999985694885}],"concepts":[{"id":"https://openalex.org/C193252679","wikidata":"https://www.wikidata.org/wiki/Q242125","display_name":"Phylogenetic tree","level":3,"score":0.8464746475219727},{"id":"https://openalex.org/C26619641","wikidata":"https://www.wikidata.org/wiki/Q3142246","display_name":"Phylogenetic network","level":4,"score":0.6189298033714294},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.608953595161438},{"id":"https://openalex.org/C160525816","wikidata":"https://www.wikidata.org/wiki/Q208755","display_name":"Paraphyly","level":5,"score":0.574583113193512},{"id":"https://openalex.org/C53208351","wikidata":"https://www.wikidata.org/wiki/Q7837630","display_name":"Tree rearrangement","level":4,"score":0.5623701214790344},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.49893665313720703},{"id":"https://openalex.org/C41168302","wikidata":"https://www.wikidata.org/wiki/Q3772859","display_name":"Computational phylogenetics","level":5,"score":0.4847087860107422},{"id":"https://openalex.org/C12326286","wikidata":"https://www.wikidata.org/wiki/Q210958","display_name":"Monophyly","level":5,"score":0.4820214509963989},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.47060924768447876},{"id":"https://openalex.org/C194898557","wikidata":"https://www.wikidata.org/wiki/Q1779497","display_name":"UPGMA","level":4,"score":0.4701005816459656},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.42384761571884155},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39974164962768555},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.35546785593032837},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3530700206756592},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34453627467155457},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.28639745712280273},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.19302862882614136},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.14433002471923828},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0846869945526123},{"id":"https://openalex.org/C44465124","wikidata":"https://www.wikidata.org/wiki/Q713623","display_name":"Clade","level":4,"score":0.0},{"id":"https://openalex.org/C135763542","wikidata":"https://www.wikidata.org/wiki/Q106016","display_name":"Genotype","level":3,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","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":false},{"descriptor_ui":"D012984","descriptor_name":"Software","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":"D017386","descriptor_name":"Sequence Homology, Amino Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019143","descriptor_name":"Evolution, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/bti244","doi":"https://doi.org/10.1093/bioinformatics/bti244","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bti244","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/21/9/1876/48972680/bioinformatics_21_9_1876.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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:15647305","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/15647305","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":"Comparative Study"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.101.1273","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.101.1273","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/cgi/reprint/bti244v1.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/bti244","doi":"https://doi.org/10.1093/bioinformatics/bti244","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bti244","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/21/9/1876/48972680/bioinformatics_21_9_1876.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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2107087429.pdf","grobid_xml":"https://content.openalex.org/works/W2107087429.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W1546639740","https://openalex.org/W1969051510","https://openalex.org/W1969153299","https://openalex.org/W1970999032","https://openalex.org/W1997268601","https://openalex.org/W2041862730","https://openalex.org/W2066737015","https://openalex.org/W2086062742","https://openalex.org/W2097706568","https://openalex.org/W2097874946","https://openalex.org/W2103017472","https://openalex.org/W2107302432","https://openalex.org/W2112162865","https://openalex.org/W2122665495","https://openalex.org/W2124105487","https://openalex.org/W2132926880","https://openalex.org/W2137488129","https://openalex.org/W2139919097","https://openalex.org/W2150452501","https://openalex.org/W2158749079","https://openalex.org/W2167188257","https://openalex.org/W2169929748","https://openalex.org/W2229908198","https://openalex.org/W2764687937","https://openalex.org/W3199943451","https://openalex.org/W7096257995","https://openalex.org/W7099253376"],"related_works":["https://openalex.org/W1520080638","https://openalex.org/W7097028661","https://openalex.org/W7096571450","https://openalex.org/W1198143361","https://openalex.org/W2204256303","https://openalex.org/W7099644610","https://openalex.org/W2063050469","https://openalex.org/W4313302964","https://openalex.org/W2187007606","https://openalex.org/W2536038384"],"abstract_inverted_index":{"MOTIVATION:":[0],"Phylogenetic":[1,65],"analysis":[2,66,256],"of":[3,15,28,67,93,156,207,216,222,260,327,378,398],"protein":[4,10,29,62,104,142,158,251,262,277,336,354,365],"sequences":[5,105,159],"is":[6,269,320,331,347,400],"widely":[7],"used":[8,295,349],"in":[9,25,61,136,325,350],"function":[11,37,224],"classification":[12,210,328,355,379],"and":[13,73,109,195,238,264,274,288,330,343,375],"delineation":[14],"subfamilies":[16],"within":[17],"larger":[18],"families.":[19,337],"In":[20],"addition,":[21],"the":[22,26,39,107,178,189,192,196,201,205,214,243,290,351,383,388,396],"recent":[23],"increase":[24],"number":[27],"sequence":[30],"entries":[31],"with":[32,120,242,281,286,311,322,387],"controlled":[33],"vocabulary":[34],"terms":[35,51,326],"describing":[36,165],"(e.g.":[38,168],"Gene":[40],"Ontology)":[41],"suggests":[42,266],"that":[43,267,275,394],"it":[44],"may":[45],"be":[46,134,368],"possible":[47],"to":[48,55,102,139,187,219,234,298,301,339],"overlay":[49],"these":[50,132],"onto":[52],"phylogenetic":[53,79,114,170,240,323],"trees":[54,127,133,241,244,285,358],"automatically":[56],"locate":[57],"functional":[58],"divergence":[59],"events":[60],"family":[63,108],"evolution.":[64],"large":[68,84,335],"datasets":[69,85],"requires":[70],"fast":[71],"algorithms;":[72],"even":[74],"'fast',":[75],"approximate":[76],"distance":[77,122],"matrix-based":[78],"algorithms":[80,324,362],"are":[81],"slow":[82],"on":[83,106,257,308,334],"since":[86],"they":[87],"involve":[88],"calculating":[89],"maximum":[90],"likelihood":[91],"estimates":[92],"pairwise":[94],"evolutionary":[95],"distances.":[96],"There":[97],"have":[98],"been":[99],"many":[100],"attempts":[101],"classify":[103,141],"subfamily":[110],"level":[111,377],"without":[112],"reconstructing":[113],"trees,":[115],"but":[116],"using":[117,249],"hierarchical":[118,247,282],"clustering":[119,248,283,310],"simpler":[121],"measures,":[123],"which":[124,212],"also":[125],"produce":[126,284],"or":[128,149,182,227],"dendrograms.":[129],"How":[130],"can":[131,367],"compared":[135],"their":[137,166],"ability":[138,215],"accurately":[140],"sequences?":[143],"RESULTS:":[144],"Given":[145],"a":[146,154,163,169,174,208,217,258,304,312],"'reference":[147],"classification'":[148],"'group":[150],"membership":[151],"labels'":[152],"for":[153,176,363],"set":[155,259],"related":[157],"as":[160,162,186],"well":[161],"tree":[164,179,218,374],"relationships":[167],"tree),":[171],"we":[172,381],"propose":[173],"method":[175],"dividing":[177],"into":[180,225],"monophyletic":[181,226],"paraphyletic":[183,228],"groups":[184,194],"so":[185],"optimize":[188],"correspondence":[190,204],"between":[191],"reference":[193,389],"tree-derived":[197],"groups.":[198,229],"We":[199,230,294],"call":[200],"achieved":[202],"optimal":[203,384],"'accuracy":[206],"tree-based":[209],"(TBC)',":[211],"measures":[213,279],"separate":[220],"proteins":[221],"similar":[223],"apply":[231],"this":[232],"measure":[233,297,314],"compare":[235],"classical":[236],"NJ":[237],"UPGMA":[239],"obtained":[245],"from":[246,316],"different":[250,361,364],"similarity":[252,278,313],"measures.":[253],"Our":[254],"preliminary":[255],"expert-curated":[261],"families":[263,366],"alignments":[265],"there":[268],"no":[270],"uniformly":[271],"superior":[272],"algorithm,":[273,306],"simple":[276],"combined":[280],"reasonable":[287],"often":[289],"most":[291],"accurate":[292],"TBC.":[293],"our":[296],"help":[299],"us":[300],"design":[302],"TIPS,":[303],"tree-building":[305],"based":[307],"agglomerative":[309],"derived":[315],"profile":[317],"scoring.":[318],"TIPS":[319,346],"comparable":[321],"accuracy":[329,397],"much":[332],"faster":[333],"Due":[338],"its":[340],"time":[341],"scalability":[342],"acceptable":[344],"accuracy,":[345],"being":[348],"large-scale":[352],"PANTHER":[353],"project.":[356],"The":[357,392],"produced":[359],"by":[360],"viewed":[369],"at":[370,402],"http://panther.appliedbiosystems.com/pub/tree_quality/trees.jsp.":[371],"For":[372],"every":[373,376],"granularity":[380],"provide":[382],"TBC":[385,399],"along":[386],"classification.":[390],"AVAILABILITY:":[391],"script":[393],"evaluates":[395],"available":[401],"http://panther.appliedbiosystems.com/pub/tree_quality/index.jsp":[403]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}