{"id":"https://openalex.org/W2009542214","doi":"https://doi.org/10.1145/1183614.1183639","title":"Validating associations in biological databases","display_name":"Validating associations in biological databases","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W2009542214","doi":"https://doi.org/10.1145/1183614.1183639","mag":"2009542214"},"language":"en","primary_location":{"id":"doi:10.1145/1183614.1183639","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1183614.1183639","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th ACM international conference on Information and knowledge management  - CIKM '06","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5014333753","display_name":"Francisco M. Couto","orcid":"https://orcid.org/0000-0003-0627-1496"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Francisco M. Couto","raw_affiliation_strings":["University of Lisboa"],"affiliations":[{"raw_affiliation_string":"University of Lisboa","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043057704","display_name":"M\u00e1rio J. Silva","orcid":"https://orcid.org/0000-0002-5452-6185"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"M\u00e1rio J. Silva","raw_affiliation_strings":["University of Lisboa"],"affiliations":[{"raw_affiliation_string":"University of Lisboa","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102987146","display_name":"Pedro M. Coutinho","orcid":"https://orcid.org/0000-0003-3992-0384"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Pedro M. Coutinho","raw_affiliation_strings":["Centre National de la Recherche Scientifique","Centre National De La: Recherche Scientifique"],"affiliations":[{"raw_affiliation_string":"Centre National de la Recherche Scientifique","institution_ids":["https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Centre National De La: Recherche Scientifique","institution_ids":["https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5014333753"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.07928547,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"142","last_page":"142"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9998000264167786,"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":0.9998000264167786,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9933000206947327,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9927999973297119,"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/computer-science","display_name":"Computer science","score":0.7525460720062256},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.7124375104904175},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.5292151570320129},{"id":"https://openalex.org/keywords/association","display_name":"Association (psychology)","score":0.511401355266571},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5113617777824402},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4958396852016449},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.44979381561279297},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.41964423656463623},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4091198146343231},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3953336477279663},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32036101818084717}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7525460720062256},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.7124375104904175},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.5292151570320129},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.511401355266571},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5113617777824402},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4958396852016449},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.44979381561279297},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.41964423656463623},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4091198146343231},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3953336477279663},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32036101818084717},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1183614.1183639","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1183614.1183639","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th ACM international conference on Information and knowledge management  - CIKM '06","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Partnerships for the goals","score":0.5400000214576721,"id":"https://metadata.un.org/sdg/17"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1523150955","https://openalex.org/W1527927437","https://openalex.org/W1529522905","https://openalex.org/W1569415500","https://openalex.org/W1603063797","https://openalex.org/W1967376701","https://openalex.org/W1970863518","https://openalex.org/W1976097579","https://openalex.org/W2032838501","https://openalex.org/W2040778567","https://openalex.org/W2056119436","https://openalex.org/W2060948468","https://openalex.org/W2061327015","https://openalex.org/W2079665010","https://openalex.org/W2091978351","https://openalex.org/W2092795373","https://openalex.org/W2099100406","https://openalex.org/W2100935296","https://openalex.org/W2108491719","https://openalex.org/W2112441656","https://openalex.org/W2117805756","https://openalex.org/W2121940249","https://openalex.org/W2123273303","https://openalex.org/W2126276057","https://openalex.org/W2132290594","https://openalex.org/W2134226301","https://openalex.org/W2141885858","https://openalex.org/W2154139219","https://openalex.org/W2164004716","https://openalex.org/W2166711445"],"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/W2358755282","https://openalex.org/W2625833328","https://openalex.org/W2358294942","https://openalex.org/W2405355225","https://openalex.org/W4367460280"],"abstract_inverted_index":{"Erroneous":[0],"data":[1],"can":[2,101],"often":[3],"be":[4,102],"found":[5],"in":[6,70,128,153,159],"databases,":[7],"and":[8,34,51,137,170,178],"detecting":[9],"it":[10],"is":[11,45,92],"normally":[12],"a":[13,29,49,52,61,76,93,141,150,156],"non-trivial":[14],"task.":[15],"For":[16,161],"example,":[17,162],"To":[18],"cope":[19],"with":[20],"the":[21,111,114,173,181,200],"large":[22,157],"amount":[23],"of":[24,32,64,124,134,172,180,199],"biological":[25,71],"sequences":[26],"being":[27],"produced,":[28],"significant":[30,62],"number":[31,63],"genes":[33],"proteins":[35],"have":[36,59,148],"been":[37],"annotated":[38],"by":[39,83,196],"automated":[40,115],"tools.":[41],"A":[42],"protein":[43,50,116],"annotation":[44],"an":[46,121],"association":[47,91],"between":[48],"term":[53],"describing":[54],"its":[55],"role.":[56],"These":[57],"tools":[58],"produced":[60],"misannotations":[65],"that":[66,95],"are":[67],"now":[68],"present":[69],"databases.":[72],"This":[73],"paper":[74],"proposes":[75],"new":[77],"method":[78,112,131],"for":[79,155],"automatically":[80],"scoring":[81],"associations":[82],"comparing":[84],"them":[85],"to":[86,104,119,166,189,194],"preexisting":[87],"curated":[88],"associations.":[89],"An":[90],"pair":[94],"links":[96],"two":[97],"entities.":[98],"The":[99,130,146],"score":[100],"used":[103],"filter":[105],"incorrect":[106],"or":[107],"uncommon":[108],"associations.We":[109],"evaluated":[110],"using":[113],"annotations":[117,136],"submitted":[118],"BioCreAtIvE,":[120],"international":[122],"evaluation":[123],"state-of-the-art":[125],"text-mining":[126],"systems":[127],"Biology.":[129],"scored":[132,139],"each":[133,191],"these":[135],"those":[138],"below":[140],"certain":[142],"threshold":[143],"were":[144,164,187],"discarded.":[145],"results":[147],"shown":[149],"small":[151],"trade-off":[152],"recall":[154],"improvement":[158],"precision.":[160],"we":[163,186],"able":[165,188],"discard":[167],"44.6%,":[168],"66.8%":[169],"81%":[171],"misannotations,":[174],"maintaining":[175],"96.9%,":[176],"84.2%,":[177],"47.8%":[179],"correct":[182],"annotations,":[183],"respectively.":[184],"Moreover,":[185],"outperform":[190],"individual":[192],"submission":[193],"BioCreAtIvE":[195],"proper":[197],"adjustment":[198],"threshold.":[201]},"counts_by_year":[{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
