{"id":"https://openalex.org/W2054518234","doi":"https://doi.org/10.1186/1471-2105-9-69","title":"The strength of co-authorship in gene name disambiguation","display_name":"The strength of co-authorship in gene name disambiguation","publication_year":2008,"publication_date":"2008-01-29","ids":{"openalex":"https://openalex.org/W2054518234","doi":"https://doi.org/10.1186/1471-2105-9-69","mag":"2054518234","pmid":"https://pubmed.ncbi.nlm.nih.gov/18230174"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-9-69","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-9-69","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-9-69","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/10.1186/1471-2105-9-69","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076395593","display_name":"Rich\u00e1rd Farkas","orcid":"https://orcid.org/0000-0001-7019-2632"},"institutions":[{"id":"https://openalex.org/I4210152167","display_name":"MTA-SZTE Research Group on Artificial Intelligence","ror":"https://ror.org/0507fk326","country_code":"HU","type":"facility","lineage":["https://openalex.org/I227486990","https://openalex.org/I4210152167","https://openalex.org/I7597260"]}],"countries":["HU"],"is_corresponding":true,"raw_author_name":"Rich\u00e1rd Farkas","raw_affiliation_strings":["Hungarian Academy of Science, Research Group on Artificial Intelligence, Aradi vertanuk tere, Szeged, Hungary. rfarkas@inf.u-szeged.hu","Hungarian Academy of Science, Research Group on Artificial Intelligence, Aradi vertanuk tere, Szeged, Hungary"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hungarian Academy of Science, Research Group on Artificial Intelligence, Aradi vertanuk tere, Szeged, Hungary. rfarkas@inf.u-szeged.hu","institution_ids":["https://openalex.org/I4210152167"]},{"raw_affiliation_string":"Hungarian Academy of Science, Research Group on Artificial Intelligence, Aradi vertanuk tere, Szeged, Hungary","institution_ids":["https://openalex.org/I4210152167"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5076395593"],"corresponding_institution_ids":["https://openalex.org/I4210152167"],"apc_list":{"value":2790,"currency":"USD","value_usd":2790},"apc_paid":{"value":2790,"currency":"USD","value_usd":2790},"fwci":1.6896,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.83187709,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"9","issue":"1","first_page":"69","last_page":"69"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9528999924659729,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9528999924659729,"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":0.02370000071823597,"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/T11642","display_name":"Genomics and Rare Diseases","score":0.004000000189989805,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/computer-science","display_name":"Computer science","score":0.7445455193519592},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5778592228889465},{"id":"https://openalex.org/keywords/unique-identifier","display_name":"Unique identifier","score":0.5249440670013428},{"id":"https://openalex.org/keywords/gene-nomenclature","display_name":"Gene nomenclature","score":0.5001943111419678},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.48976945877075195},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44772958755493164},{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.43493422865867615},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4054034650325775},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.20331069827079773},{"id":"https://openalex.org/keywords/taxonomy","display_name":"Taxonomy (biology)","score":0.14071020483970642},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.13987493515014648}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7445455193519592},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5778592228889465},{"id":"https://openalex.org/C119839945","wikidata":"https://www.wikidata.org/wiki/Q6545185","display_name":"Unique identifier","level":3,"score":0.5249440670013428},{"id":"https://openalex.org/C62177273","wikidata":"https://www.wikidata.org/wiki/Q5531556","display_name":"Gene nomenclature","level":4,"score":0.5001943111419678},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.48976945877075195},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44772958755493164},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.43493422865867615},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4054034650325775},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.20331069827079773},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.14071020483970642},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.13987493515014648},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C514705636","wikidata":"https://www.wikidata.org/wiki/Q863247","display_name":"Nomenclature","level":3,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D001319","descriptor_name":"Authorship","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001319","descriptor_name":"Authorship","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001319","descriptor_name":"Authorship","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D002965","descriptor_name":"Classification","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D002965","descriptor_name":"Classification","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D002965","descriptor_name":"Classification","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D003663","descriptor_name":"Decision Trees","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003663","descriptor_name":"Decision Trees","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003663","descriptor_name":"Decision Trees","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005796","descriptor_name":"Genes","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D005796","descriptor_name":"Genes","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D005796","descriptor_name":"Genes","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"D016239","descriptor_name":"MEDLINE","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016239","descriptor_name":"MEDLINE","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016239","descriptor_name":"MEDLINE","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1186/1471-2105-9-69","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-9-69","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-9-69","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:18230174","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/18230174","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:doaj.org/article:deddc69fa1084b7cad3460733cc992cf","is_oa":false,"landing_page_url":"https://doaj.org/article/deddc69fa1084b7cad3460733cc992cf","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 9, Iss 1, p 69 (2008)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:2262057","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/2262057","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/1471-2105-9-69","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-9-69","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-9-69","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":[{"score":0.4399999976158142,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2054518234.pdf","grobid_xml":"https://content.openalex.org/works/W2054518234.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W170684085","https://openalex.org/W1512170015","https://openalex.org/W1532254950","https://openalex.org/W1570448133","https://openalex.org/W1959755538","https://openalex.org/W1987281569","https://openalex.org/W1988946940","https://openalex.org/W2000862718","https://openalex.org/W2037987185","https://openalex.org/W2061166439","https://openalex.org/W2097106271","https://openalex.org/W2107580398","https://openalex.org/W2123504579","https://openalex.org/W2125055259","https://openalex.org/W2127112494","https://openalex.org/W2129267433","https://openalex.org/W2141869602","https://openalex.org/W2145845082","https://openalex.org/W2157870551","https://openalex.org/W2466512847","https://openalex.org/W2799321649","https://openalex.org/W3100447784","https://openalex.org/W4247469419"],"related_works":["https://openalex.org/W2099409622","https://openalex.org/W4252772812","https://openalex.org/W2809881945","https://openalex.org/W1882848237","https://openalex.org/W2172533829","https://openalex.org/W4378715759","https://openalex.org/W3087323585","https://openalex.org/W4291327337","https://openalex.org/W4281775131","https://openalex.org/W3194702611"],"abstract_inverted_index":{"BACKGROUND:":[0],"A":[1],"biomedical":[2,74,329],"entity":[3],"mention":[4],"in":[5,59,72,212,242,249],"articles":[6,96,166,181,317],"and":[7,63,132,167,176,248,259,266,287,318],"other":[8,328],"free":[9],"texts":[10],"is":[11,46,118,169],"often":[12],"ambiguous.":[13],"For":[14],"example,":[15],"13%":[16],"of":[17,31,40,85,90,94,101,143,160,197,214,255,290,297,302,310],"the":[18,73,82,86,91,99,102,111,136,144,151,161,179,195,200,229,235,262,275,284,288,291,295,298,300,320],"gene":[19,51,56,126,130],"names":[20],"(aliases)":[21],"might":[22],"refer":[23],"to":[24,47,123,149,244],"more":[25],"than":[26],"one":[27,89],"gene.":[28],"The":[29,158],"task":[30],"Gene":[32],"Symbol":[33],"Disambiguation":[34,43],"(GSD)":[35],"-":[36,45,88,97],"a":[37,49,120,128,183,206,306],"special":[38,92],"case":[39],"Word":[41],"Sense":[42],"(WSD)":[44],"assign":[48],"unique":[50],"identifier":[52],"for":[53,110,135,199,327],"all":[54],"identified":[55],"name":[57],"aliases":[58],"biology-related":[60],"articles.":[61],"Supervised":[62],"unsupervised":[64],"machine":[65],"learning":[66],"WSD":[67],"techniques":[68],"have":[69,182],"been":[70],"applied":[71],"field":[75],"with":[76,216],"promising":[77,276],"results.":[78],"We":[79,186,203,233],"examine":[80],"here":[81,188,323],"utilisation":[83],"potential":[84],"fact":[87],"features":[93],"biological":[95,316],"that":[98,119,205,283],"authors":[100],"documents":[103],"are":[104,165],"known":[105],"through":[106],"graph-based":[107],"semi-supervised":[108],"methods":[109,190,321],"GSD":[112,201,240,268],"task.":[113,202],"RESULTS:":[114],"Our":[115],"key":[116],"hypothesis":[117],"biologist":[121],"refers":[122],"each":[124],"particular":[125],"by":[127,224],"fixed":[129],"alias":[131],"this":[133],"holds":[134],"co-authors":[137],"as":[138,340],"well.":[139,341],"To":[140],"make":[141],"use":[142],"co-authorship":[145,236,285],"information":[146,226,237,286],"we":[147,281],"decided":[148],"build":[150],"inverse":[152,162,230],"co-author":[153,163,231],"graph":[154,164],"on":[155,194,261,274],"MedLine":[156],"abstracts.":[157],"nodes":[159,174],"there":[168],"an":[170,217],"edge":[171],"between":[172],"two":[173,180,189,239],"if":[175,178],"only":[177],"mutual":[184],"author.":[185],"introduce":[187],"using":[191,225],"distances":[192],"(based":[193],"graph)":[196],"abstracts":[198],"found":[204],"disambiguation":[207],"decision":[208],"can":[209,304],"be":[210,305,325],"made":[211],"85%":[213],"cases":[215],"extremely":[218],"high":[219],"(99.5%)":[220],"precision":[221,254],"rate":[222],"just":[223],"obtained":[227,278],"from":[228],"graph.":[232],"incorporated":[234],"into":[238],"systems":[241],"order":[243],"attain":[245],"full":[246],"coverage":[247],"experiments":[250],"our":[251],"procedure":[252],"achieved":[253],"94.3%,":[256],"98.85%,":[257],"96.05%":[258],"99.63%":[260],"human,":[263],"mouse,":[264],"fly":[265],"yeast":[267],"evaluation":[269],"sets,":[270],"respectively.":[271],"CONCLUSION:":[272],"Based":[273],"results":[277],"so":[279],"far":[280],"suggest":[282],"circumstances":[289],"articles'":[292],"release":[293],"(like":[294,334],"title":[296],"journal,":[299],"year":[301],"publication)":[303],"crucial":[307],"building":[308],"block":[309],"any":[311],"sophisticated":[312],"similarity":[313],"measure":[314],"among":[315],"hence":[319],"introduced":[322],"should":[324],"useful":[326],"natural":[330],"language":[331],"processing":[332],"tasks":[333],"organism":[335],"or":[336],"target":[337],"disease":[338],"detection)":[339]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}
