{"id":"https://openalex.org/W4393873085","doi":"https://doi.org/10.5281/zenodo.5911097","title":"TBGA: A Large-Scale Gene-Disease Association Dataset for Biomedical Relation Extraction","display_name":"TBGA: A Large-Scale Gene-Disease Association Dataset for Biomedical Relation Extraction","publication_year":2022,"publication_date":"2022-01-27","ids":{"openalex":"https://openalex.org/W4393873085","doi":"https://doi.org/10.5281/zenodo.5911097"},"language":"en","primary_location":{"id":"pmh:oai:zenodo.org:5911097","is_oa":true,"landing_page_url":"https://zenodo.org/record/5911097","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://zenodo.org/record/5911097","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003820981","display_name":"Stefano Marchesin","orcid":"https://orcid.org/0000-0003-0362-5893"},"institutions":[{"id":"https://openalex.org/I138689650","display_name":"University of Padua","ror":"https://ror.org/00240q980","country_code":"IT","type":"education","lineage":["https://openalex.org/I138689650"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Marchesin, Stefano","raw_affiliation_strings":["University of Padua"],"raw_orcid":"https://orcid.org/0000-0003-0362-5893","affiliations":[{"raw_affiliation_string":"University of Padua","institution_ids":["https://openalex.org/I138689650"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078254809","display_name":"Gianmaria Silvello","orcid":"https://orcid.org/0000-0003-4970-4554"},"institutions":[{"id":"https://openalex.org/I138689650","display_name":"University of Padua","ror":"https://ror.org/00240q980","country_code":"IT","type":"education","lineage":["https://openalex.org/I138689650"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Silvello, Gianmaria","raw_affiliation_strings":["University of Padua"],"raw_orcid":"https://orcid.org/0000-0003-4970-4554","affiliations":[{"raw_affiliation_string":"University of Padua","institution_ids":["https://openalex.org/I138689650"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I138689650"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.948199987411499,"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":0.948199987411499,"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":0.9384999871253967,"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":0.9041000008583069,"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/association","display_name":"Association (psychology)","score":0.6310296058654785},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.6035934686660767},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.6017932891845703},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.4501514136791229},{"id":"https://openalex.org/keywords/disease","display_name":"Disease","score":0.440391480922699},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.31754571199417114},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3135160207748413},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.3075287938117981},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.25236353278160095},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.1903705596923828},{"id":"https://openalex.org/keywords/internal-medicine","display_name":"Internal medicine","score":0.14292463660240173},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.13019469380378723},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.12198492884635925}],"concepts":[{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.6310296058654785},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.6035934686660767},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.6017932891845703},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4501514136791229},{"id":"https://openalex.org/C2779134260","wikidata":"https://www.wikidata.org/wiki/Q12136","display_name":"Disease","level":2,"score":0.440391480922699},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.31754571199417114},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3135160207748413},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3075287938117981},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.25236353278160095},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.1903705596923828},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.14292463660240173},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.13019469380378723},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.12198492884635925},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:zenodo.org:5911097","is_oa":true,"landing_page_url":"https://zenodo.org/record/5911097","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"dataset"},{"id":"doi:10.5281/zenodo.5911097","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.5911097","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:5911097","is_oa":true,"landing_page_url":"https://zenodo.org/record/5911097","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"dataset"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5113281195","display_name":"EXtreme-scale Analytics via Multimodal Ontology Discovery & Enhancement","funder_award_id":"825292","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4234874385","https://openalex.org/W2323648130","https://openalex.org/W2157140558","https://openalex.org/W2378782423","https://openalex.org/W2388988621","https://openalex.org/W2357797405","https://openalex.org/W2366623913","https://openalex.org/W2374905595","https://openalex.org/W2516693588","https://openalex.org/W2116112408"],"abstract_inverted_index":{"This":[0],"repository":[1],"contains":[2,171],"the":[3,38,69,76,85,92,103,113,125,134,144,153,165,188,192,203],"TBGA":[4,6,170,206,213],"dataset.":[5,193],"is":[7,215],"a":[8,55,60],"large-scale,":[9],"semi-automatically":[10],"annotated":[11],"dataset":[12,19],"for":[13],"Gene-Disease":[14],"Association":[15],"(GDA)":[16],"extraction.":[17],"The":[18,178],"consists":[20,181],"of":[21,119,124,159,164,182],"three":[22],"text":[23],"files,":[24],"corresponding":[25,190],"to":[26,54,191],"train,":[27,48],"validation,":[28,49],"and":[29,43,122,162,175],"test":[30,51],"sets,":[31],"plus":[32],"an":[33],"additional":[34],"JSON":[35,66,131],"file":[36,180],"containing":[37,187],"mapping":[39],"between":[40],"relation":[41,81],"names":[42],"IDs.":[44],"Each":[45],"record":[46],"in":[47],"or":[50,197],"files":[52,189],"corresponds":[53],"single":[56],"GDA":[57,77],"extracted":[58],"from":[59,74],"sentence.":[61],"Records":[62],"are":[63],"represented":[64],"as":[65],"objects":[67],"with":[68,84,102,112,143,152],"following":[70],"structure:":[71],"<strong>text:</strong>":[72],"sentence":[73],"which":[75],"was":[78],"extracted.":[79],"<strong>relation:</strong>":[80],"name":[82],"associated":[83,101,111,142,151],"given":[86],"GDA.":[87],"<strong>h:":[88],"</strong>JSON":[89],"object":[90,132],"representing":[91,133],"gene":[93,104,109,114,126],"entity,":[94,136],"composed":[95,137],"of:":[96,138],"<strong>id:":[97,139],"</strong>NCBI":[98],"Entrez":[99],"ID":[100],"entity.":[105,115,146,155],"<strong>name:</strong>":[106,147],"NCBI":[107],"official":[108],"symbol":[110],"<strong>pos:":[116],"</strong>list":[117],"consisting":[118,158],"starting":[120,160],"position":[121,161],"length":[123,163],"mention":[127,167],"within":[128,168],"text.":[129,169],"<strong>t:</strong>":[130],"disease":[135,145,154,166],"</strong>UMLS":[140],"CUI":[141],"UMLS":[148],"preferred":[149],"term":[150],"<strong>pos:</strong>":[156],"list":[157],"over":[172],"200,000":[173],"instances":[174],"100,000":[176],"bags.<br>":[177],"zip":[179],"one":[183],"folder,":[184],"named":[185],"TBGA,":[186],"If":[194],"you":[195],"use":[196],"extend":[198],"our":[199],"work,":[200],"please":[201],"cite":[202],"following:":[204],"https://bmcbioinformatics.biomedcentral.com/articles/10.1186/s12859-022-04646-6#citeas<br>":[205],"paper":[207],"can":[208],"be":[209],"found":[210],"at:":[211,217],"https://rdcu.be/cKkY2<br>":[212],"code":[214],"available":[216],"https://github.com/GDAMining/gda-extraction":[218]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-10T00:00:00"}
