{"id":"https://openalex.org/W2133532371","doi":"https://doi.org/10.1186/1471-2105-7-440","title":"A graph-search framework for associating gene identifiers with documents","display_name":"A graph-search framework for associating gene identifiers with documents","publication_year":2006,"publication_date":"2006-10-10","ids":{"openalex":"https://openalex.org/W2133532371","doi":"https://doi.org/10.1186/1471-2105-7-440","mag":"2133532371","pmid":"https://pubmed.ncbi.nlm.nih.gov/17032441"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-7-440","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-7-440","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-7-440","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":null,"license_id":null,"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/10.1186/1471-2105-7-440","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051617344","display_name":"William W. Cohen","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"William W Cohen","raw_affiliation_strings":["Department of Machine Learning, Carnegie Mellon University, 5000 Forbes Avenue, Pittsburgh, PA 15213, USA. wcohen@cs.cmu.edu","Department of Machine Learning, Carnegie Mellon University, 5000 Forbes Avenue, Pittsburgh, PA, 15213, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Machine Learning, Carnegie Mellon University, 5000 Forbes Avenue, Pittsburgh, PA 15213, USA. wcohen@cs.cmu.edu","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Department of Machine Learning, Carnegie Mellon University, 5000 Forbes Avenue, Pittsburgh, PA, 15213, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057700630","display_name":"Einat Minkov","orcid":"https://orcid.org/0000-0001-8421-5209"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Einat Minkov","raw_affiliation_strings":["Language Technology Institute, Carnegie Mellon University, 5000 Forbes Avenue, Pittsburgh, PA 15213, USA and","Language Technology Institute, Carnegie Mellon University, 5000 Forbes Avenue, Pittsburgh, PA, 15213, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technology Institute, Carnegie Mellon University, 5000 Forbes Avenue, Pittsburgh, PA 15213, USA and","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technology Institute, Carnegie Mellon University, 5000 Forbes Avenue, Pittsburgh, PA, 15213, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5051617344"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":1.5,"has_fulltext":true,"cited_by_count":45,"citation_normalized_percentile":{"value":0.81066696,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"7","issue":"1","first_page":"440","last_page":"440"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9575999975204468,"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":0.9575999975204468,"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":0.010599999688565731,"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/T11719","display_name":"Data Quality and Management","score":0.004999999888241291,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.809004545211792},{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.7183688879013062},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.6432784795761108},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.6181402206420898},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.6008168458938599},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4569838345050812},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4292856752872467},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4046303629875183},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35210171341896057},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2419709861278534},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.09739053249359131}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.809004545211792},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.7183688879013062},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.6432784795761108},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.6181402206420898},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.6008168458938599},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4569838345050812},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4292856752872467},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4046303629875183},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35210171341896057},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2419709861278534},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.09739053249359131},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003196","descriptor_name":"Computer Graphics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003196","descriptor_name":"Computer Graphics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003196","descriptor_name":"Computer Graphics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","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":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D051379","descriptor_name":"Mice","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D051379","descriptor_name":"Mice","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D051379","descriptor_name":"Mice","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":6,"locations":[{"id":"doi:10.1186/1471-2105-7-440","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-7-440","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-7-440","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:17032441","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/17032441","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:CiteSeerX.psu:10.1.1.142.3286","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.142.3286","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-2.cs.cmu.edu/~wcohen/postscript/normalize-preprint.pdf","raw_type":"text"},{"id":"pmh:oai:doaj.org/article:67bfaf51680e439db214680678acf1a8","is_oa":false,"landing_page_url":"https://doaj.org/article/67bfaf51680e439db214680678acf1a8","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 7, Iss 1, p 440 (2006)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:1337418","is_oa":true,"landing_page_url":"http://europepmc.org/articles/PMC1617121","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"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":"","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:1617121","is_oa":true,"landing_page_url":"http://doi.org/10.1186/1471-2105-7-440","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:10.1186/1471-2105-7-440","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-7-440","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-7-440","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":null,"license_id":null,"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/G4344409148","display_name":null,"funder_award_id":"K25 DA017357-01","funder_id":"https://openalex.org/F4320337347","funder_display_name":"National Institute on Drug Abuse"},{"id":"https://openalex.org/G5619622708","display_name":null,"funder_award_id":"K25 DA017357","funder_id":"https://openalex.org/F4320337347","funder_display_name":"National Institute on Drug Abuse"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320332815","display_name":"Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320337347","display_name":"National Institute on Drug Abuse","ror":"https://ror.org/00fq5cm18"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2133532371.pdf","grobid_xml":"https://content.openalex.org/works/W2133532371.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W14071851","https://openalex.org/W140600869","https://openalex.org/W634022085","https://openalex.org/W1527781663","https://openalex.org/W1603229901","https://openalex.org/W1646278814","https://openalex.org/W1954715867","https://openalex.org/W1979711143","https://openalex.org/W2008652694","https://openalex.org/W2012350188","https://openalex.org/W2018874418","https://openalex.org/W2023736097","https://openalex.org/W2035807240","https://openalex.org/W2040734632","https://openalex.org/W2044602212","https://openalex.org/W2058856481","https://openalex.org/W2061166439","https://openalex.org/W2094591616","https://openalex.org/W2103017472","https://openalex.org/W2126276057","https://openalex.org/W2139686264","https://openalex.org/W2141869602","https://openalex.org/W2150722176","https://openalex.org/W2156515921","https://openalex.org/W2157110051","https://openalex.org/W2166474856","https://openalex.org/W2168905447","https://openalex.org/W2169591950","https://openalex.org/W2197919320","https://openalex.org/W2314420468","https://openalex.org/W2560674852","https://openalex.org/W4247739775","https://openalex.org/W4251771625","https://openalex.org/W4290750029"],"related_works":["https://openalex.org/W5053386","https://openalex.org/W2138279922","https://openalex.org/W2947903144","https://openalex.org/W2949905168","https://openalex.org/W2051940813","https://openalex.org/W1551179054","https://openalex.org/W2121137269","https://openalex.org/W2133532371","https://openalex.org/W4293158981","https://openalex.org/W4311288223"],"abstract_inverted_index":{"BACKGROUND:":[0],"One":[1],"step":[2],"in":[3,22,36],"the":[4,16,23,87,106,109,157,160,186],"model":[5],"organism":[6],"database":[7],"curation":[8],"process":[9],"is":[10,40],"to":[11,62,218],"find,":[12],"for":[13,33,54,104,136,174],"each":[14,38],"article,":[15],"identifier":[17],"of":[18,29,46,77,89,98,108,144,159,167],"every":[19],"gene":[20,48,78],"discussed":[21],"article.":[24],"We":[25,113],"consider":[26],"a":[27,43,74,82,101,133,168],"relaxation":[28],"this":[30,56],"problem":[31],"suitable":[32],"semi-automated":[34],"systems,":[35,92,148],"which":[37,85],"article":[39],"associated":[41],"with":[42,73,121,132],"ranked":[44],"list":[45],"possible":[47],"identifiers,":[49],"and":[50,100,152],"experimentally":[51],"compare":[52],"methods":[53],"solving":[55],"geneId":[57],"ranking":[58,162],"problem.":[59],"In":[60],"addition":[61],"baseline":[63],"approaches":[64],"based":[65,212],"on":[66,213],"combining":[67,197],"named":[68,116,169],"entity":[69,117,170],"recognition":[70,118,171],"(NER)":[71,119,172],"systems":[72,120,192,208],"\"soft":[75],"dictionary\"":[76],"synonyms,":[79],"we":[80],"evaluate":[81],"graph-based":[83,110,139,161],"method":[84,103],"combines":[86],"outputs":[88],"multiple":[90],"NER":[91,147,199],"as":[93,95],"well":[94],"other":[96],"sources":[97],"information,":[99],"learning":[102,153],"reranking":[105],"output":[107],"method.":[111],"RESULTS:":[112],"show":[114],"that":[115],"similar":[122],"F-measure":[123],"performance":[124,129,158,189],"can":[125,141,154,209],"have":[126],"significantly":[127],"different":[128],"when":[130],"used":[131],"soft":[134],"dictionary":[135],"geneId-ranking.":[137],"The":[138,165],"approach":[140],"outperform":[142],"any":[143],"its":[145,182],"component":[146],"even":[149],"without":[150,216],"learning,":[151],"further":[155],"improve":[156],"approach.":[163],"CONCLUSION:":[164],"utility":[166],"system":[173],"geneId-finding":[175],"may":[176],"not":[177],"be":[178,210],"accurately":[179],"predicted":[180],"by":[181,196],"entity-level":[183],"F1":[184],"performance,":[185],"most":[187],"common":[188],"measure.":[190],"GeneId-ranking":[191],"are":[193],"best":[194],"implemented":[195],"several":[198],"systems.":[200],"With":[201],"appropriate":[202],"combination":[203],"methods,":[204],"usefully":[205],"accurate":[206],"geneId-ranking":[207],"constructed":[211],"easily-available":[214],"resources,":[215],"resorting":[217],"problem-specific,":[219],"engineered":[220],"components.":[221]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":18},{"year":2013,"cited_by_count":1}],"updated_date":"2026-06-24T13:16:06.693445","created_date":"2025-10-10T00:00:00"}
