{"id":"https://openalex.org/W2940574427","doi":"https://doi.org/10.1186/s12859-019-2752-2","title":"GO functional similarity clustering depends on similarity measure, clustering method, and annotation completeness","display_name":"GO functional similarity clustering depends on similarity measure, clustering method, and annotation completeness","publication_year":2019,"publication_date":"2019-03-27","ids":{"openalex":"https://openalex.org/W2940574427","doi":"https://doi.org/10.1186/s12859-019-2752-2","mag":"2940574427","pmid":"https://pubmed.ncbi.nlm.nih.gov/30917779"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-019-2752-2","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-019-2752-2","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-019-2752-2","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-019-2752-2","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100457483","display_name":"Meng Liu","orcid":"https://orcid.org/0000-0002-5893-2383"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Meng Liu","raw_affiliation_strings":["Department of Preventive Medicine, Keck School of Medicine, University of Southern California, Los Angeles, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Preventive Medicine, Keck School of Medicine, University of Southern California, Los Angeles, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016853551","display_name":"Paul D. Thomas","orcid":"https://orcid.org/0000-0002-9074-3507"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Paul D. Thomas","raw_affiliation_strings":["Department of Preventive Medicine, Keck School of Medicine, University of Southern California, Los Angeles, USA. pdthomas@usc.edu","Department of Preventive Medicine, Keck School of Medicine, University of Southern California, Los Angeles, USA"],"raw_orcid":"https://orcid.org/0000-0002-9074-3507","affiliations":[{"raw_affiliation_string":"Department of Preventive Medicine, Keck School of Medicine, University of Southern California, Los Angeles, USA. pdthomas@usc.edu","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Department of Preventive Medicine, Keck School of Medicine, University of Southern California, Los Angeles, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5016853551"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":1.4086,"has_fulltext":true,"cited_by_count":25,"citation_normalized_percentile":{"value":0.81402845,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"20","issue":"1","first_page":"155","last_page":"155"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9829999804496765,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9829999804496765,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.00860000029206276,"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/T10885","display_name":"Gene expression and cancer classification","score":0.0017999999690800905,"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/cluster-analysis","display_name":"Cluster analysis","score":0.7957497239112854},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.7222219705581665},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.581932008266449},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5795363187789917},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5361205339431763},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5331107378005981},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.5058531761169434},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4995396137237549},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4549611806869507},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40989258885383606},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.07782843708992004}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7957497239112854},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.7222219705581665},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.581932008266449},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5795363187789917},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5361205339431763},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5331107378005981},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.5058531761169434},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4995396137237549},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4549611806869507},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40989258885383606},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.07782843708992004}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","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":"D006801","descriptor_name":"Humans","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":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019540","descriptor_name":"Area Under Curve","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019540","descriptor_name":"Area Under Curve","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019540","descriptor_name":"Area Under Curve","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D063990","descriptor_name":"Gene Ontology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D063990","descriptor_name":"Gene Ontology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D063990","descriptor_name":"Gene Ontology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1186/s12859-019-2752-2","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-019-2752-2","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-019-2752-2","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:30917779","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/30917779","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,"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":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:6437941","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/6437941","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,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:2949b4a7929e47dc8d1946b2c6d9c104","is_oa":false,"landing_page_url":"https://doaj.org/article/2949b4a7929e47dc8d1946b2c6d9c104","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 20, Iss 1, Pp 1-15 (2019)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s12859-019-2752-2","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-019-2752-2","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-019-2752-2","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1819449706","display_name":null,"funder_award_id":"U41HG002273","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"},{"id":"https://openalex.org/G2820513190","display_name":null,"funder_award_id":"U41 HG002273","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2940574427.pdf","grobid_xml":"https://content.openalex.org/works/W2940574427.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1490161904","https://openalex.org/W1583837637","https://openalex.org/W1647729745","https://openalex.org/W1964673897","https://openalex.org/W1969353942","https://openalex.org/W1999722941","https://openalex.org/W2008830098","https://openalex.org/W2016381774","https://openalex.org/W2037027640","https://openalex.org/W2061615066","https://openalex.org/W2077940944","https://openalex.org/W2081741335","https://openalex.org/W2084168100","https://openalex.org/W2097624459","https://openalex.org/W2100761975","https://openalex.org/W2100935296","https://openalex.org/W2103017472","https://openalex.org/W2113891856","https://openalex.org/W2121343862","https://openalex.org/W2127536416","https://openalex.org/W2127563440","https://openalex.org/W2130410032","https://openalex.org/W2134868174","https://openalex.org/W2136345497","https://openalex.org/W2149911752","https://openalex.org/W2154536013","https://openalex.org/W2157471305","https://openalex.org/W2162891889","https://openalex.org/W2514630101","https://openalex.org/W2559466477","https://openalex.org/W2560868163","https://openalex.org/W2563661043","https://openalex.org/W2953332543"],"related_works":["https://openalex.org/W2361861616","https://openalex.org/W2263699433","https://openalex.org/W2377979023","https://openalex.org/W2218034408","https://openalex.org/W2392921965","https://openalex.org/W2226024386","https://openalex.org/W2380654781","https://openalex.org/W2114797768","https://openalex.org/W2516873349","https://openalex.org/W2176214140"],"abstract_inverted_index":{"BACKGROUND:":[0],"Biological":[1],"knowledge,":[2],"and":[3,67,92,108,159,186,209,218,234,285,306],"therefore":[4],"Gene":[5],"Ontology":[6],"annotation":[7,99,111,203,232,274,317],"sets,":[8],"for":[9,133,227,243,312,336],"human":[10,127],"genes":[11],"is":[12,35,78,258],"incomplete.":[13,187],"Recent":[14],"studies":[15],"have":[16],"reported":[17],"that":[18,192,242,309],"biases":[19],"in":[20,25,47,57,177,231],"available":[21],"GO":[22,110,119,179,237,254,333],"annotations":[23,116,334],"result":[24],"biased":[26],"estimates":[27],"of":[28,31,41,50,60,71,105,126,139,236,252,273,279,299,319,328,332,340],"functional":[29,72,313],"similarities":[30,54,132],"genes,":[32],"but":[33,76],"it":[34,77],"still":[36],"unclear":[37],"what":[38],"the":[39,48,68,94,118,124,146,160,165,182,224,247,253,264,271,277,289,326,330],"effect":[40],"incompleteness":[42,125],"itself":[43],"may":[44],"be,":[45],"even":[46],"absence":[49],"bias.":[51],"Pairwise":[52],"gene":[53,63,128,196,281,314,341],"are":[55,96,184],"used":[56],"a":[58,137,194,210,228],"number":[59],"contexts,":[61],"including":[62],"\"functional":[64],"similarity\"":[65],"clustering":[66,86,155,176,307,315],"related":[69],"problem":[70],"ontology":[73,257],"structure":[74],"inference,":[75],"not":[79],"known":[80],"how":[81,93],"different":[82,140,154],"similarity":[83,197,283,301],"measures":[84,151],"or":[85],"methods":[87,305],"perform":[88,310],"on":[89,114,276,288],"this":[90],"task,":[91],"clusters":[95,147,290],"affected":[97],"by":[98,198],"completeness.":[100,321],"RESULTS:":[101],"We":[102,143,163,269],"developed":[103],"representations":[104],"both":[106,180],"\"complete\"":[107],"\"incomplete\"":[109],"datasets":[112],"based":[113],"experimentally-supported":[115],"from":[117,149,292],"database-specifically":[120],"designed":[121],"to":[122,261,335],"model":[123],"annotations-and":[129],"computed":[130],"semantic":[131,244,282,300],"each":[134],"set":[135],"using":[136,152,316],"variety":[138],"published":[141],"measures.":[142],"then":[144],"assessed":[145,270],"derived":[148,291],"these":[150,293],"two":[153],"methods:":[156],"hierarchical":[157,175],"clustering,":[158,246],"CliXO":[161,166],"algorithm.":[162],"find":[164],"algorithm,":[167],"combined":[168],"with":[169],"appropriate":[170],"measures,":[171,189,212,302],"performs":[172],"better":[173],"than":[174,263],"reconstructing":[178],"when":[181],"data":[183],"complete,":[185],"Some":[188],"particularly":[190],"those":[191],"create":[193],"pairwise":[195,202,280],"averaging":[199],"over":[200],"all":[201],"similarities,":[204],"had":[205],"consistently":[206],"poor":[207],"performance,":[208],"few":[211],"such":[213],"as":[214],"Lin":[215],"best-matched":[216],"average":[217],"Relevance":[219],"maximum,":[220],"were":[221],"generally":[222],"among":[223],"best":[225,311],"performers":[226],"broad":[229],"range":[230],"completeness":[233,275,331],"types":[235],"classes.":[238],"Finally,":[239],"we":[240],"show":[241],"similarity-based":[245],"multicellular":[248],"organism":[249],"process":[250,256,266],"branch":[251],"biological":[255],"more":[259],"challenging":[260],"represent":[262],"cellular":[265],"branch.":[267],"CONCLUSIONS:":[268],"effects":[272,287],"distribution":[278],"scores,":[284],"subsequent":[286],"scores.":[294],"Our":[295],"results":[296,324],"suggest":[297],"combinations":[298],"gene-level":[303],"scoring":[304],"method":[308],"sets":[318],"varying":[320],"Overall,":[322],"our":[323],"underscore":[325],"importance":[327],"increasing":[329],"supporting":[337],"computational":[338],"analyses":[339],"function.":[342]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":4}],"updated_date":"2026-06-19T15:47:20.252518","created_date":"2025-10-10T00:00:00"}