{"id":"https://openalex.org/W4393896657","doi":"https://doi.org/10.5281/zenodo.5113853","title":"Building Large-Scale Gene-Disease Association Datasets for Biomedical Relation Extraction","display_name":"Building Large-Scale Gene-Disease Association Datasets for Biomedical Relation Extraction","publication_year":2021,"publication_date":"2021-07-19","ids":{"openalex":"https://openalex.org/W4393896657","doi":"https://doi.org/10.5281/zenodo.5113853"},"language":"en","primary_location":{"id":"pmh:oai:zenodo.org:5113853","is_oa":true,"landing_page_url":"https://zenodo.org/record/5113853","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","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/5113853","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":0,"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":0.9534000158309937,"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":0.9534000158309937,"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":0.935699999332428,"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/T13937","display_name":"Genetics, Bioinformatics, and Biomedical Research","score":0.9236999750137329,"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/relation","display_name":"Relation (database)","score":0.639861524105072},{"id":"https://openalex.org/keywords/association","display_name":"Association (psychology)","score":0.5911139249801636},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5866689682006836},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.4696594476699829},{"id":"https://openalex.org/keywords/relationship-extraction","display_name":"Relationship extraction","score":0.4261378049850464},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.3541182577610016},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3364984095096588},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3189413547515869},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.31163057684898376},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.23125240206718445},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.11623203754425049},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09145531058311462}],"concepts":[{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.639861524105072},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.5911139249801636},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5866689682006836},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4696594476699829},{"id":"https://openalex.org/C153604712","wikidata":"https://www.wikidata.org/wiki/Q7310755","display_name":"Relationship extraction","level":3,"score":0.4261378049850464},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3541182577610016},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3364984095096588},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3189413547515869},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.31163057684898376},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.23125240206718445},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.11623203754425049},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09145531058311462},{"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:5113853","is_oa":true,"landing_page_url":"https://zenodo.org/record/5113853","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"dataset"},{"id":"doi:10.5281/zenodo.5113853","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.5113853","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:5113853","is_oa":true,"landing_page_url":"https://zenodo.org/record/5113853","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2976808399","https://openalex.org/W2609844752","https://openalex.org/W2981341912","https://openalex.org/W4285246823","https://openalex.org/W4226278302","https://openalex.org/W4385734297","https://openalex.org/W2547211086","https://openalex.org/W4221160509","https://openalex.org/W4380551175","https://openalex.org/W2538200646"],"abstract_inverted_index":{"This":[0],"repository":[1],"contains":[2],"the":[3,44,75,82,91,98,108,117,129,138,148,157,169,194,198],"GDAb":[4,8,190],"and":[5,9,15,35,49,126,166,180,191],"GDAt":[6,10],"datasets.":[7],"are":[11,69],"large-scale,":[12],"distantly":[13],"supervised,":[14],"manually":[16],"enhanced":[17],"datasets":[18,175],"for":[19],"Gene-Disease":[20],"Association":[21],"(GDA)":[22],"extraction.":[23],"Each":[24,51],"dataset":[25],"consists":[26,186],"of":[27,123,128,163,168,187],"three":[28],"text":[29],"files,":[30],"corresponding":[31,196],"to":[32,60,90,107,116,147,156,197],"train,":[33,54],"validation,":[34,55],"test":[36,57],"sets,":[37],"plus":[38],"an":[39],"additional":[40],"JSON":[41,72,135],"file":[42,185],"containing":[43,193],"mapping":[45],"between":[46],"relation":[47,87],"names":[48],"IDs.":[50],"record":[52],"in":[53],"or":[56],"files":[58,195],"corresponds":[59],"a":[61,66],"single":[62],"GDA":[63,83],"extracted":[64],"from":[65,80],"sentence.":[67],"Records":[68],"represented":[70],"as":[71],"objects":[73],"with":[74],"following":[76],"structure:":[77],"<strong>text:</strong>":[78],"sentence":[79],"which":[81],"was":[84],"extracted.":[85],"<strong>relation:</strong>":[86],"name":[88,114,154],"associated":[89,106,115,146,155],"given":[92],"GDA.":[93],"<strong>h:":[94],"</strong>JSON":[95],"object":[96,136],"representing":[97,137],"gene":[99,109,118,130],"entity,":[100,140],"composed":[101,141],"of:":[102,142],"<strong>id:":[103,143],"</strong>UMLS":[104,144],"CUI":[105,145],"entity.":[110,119,150,159],"<strong>name:</strong>":[111,151],"UMLS":[112,152],"preferred":[113,153],"<strong>pos:":[120],"</strong>list":[121],"consisting":[122,162],"starting":[124,164],"position":[125,165],"length":[127,167],"mention":[131,171],"within":[132,172],"text.":[133,173],"<strong>t:</strong>":[134],"disease":[139,149,158,170],"<strong>pos:</strong>":[160],"list":[161],"Both":[174],"contain":[176],"over":[177],"2,500,000":[178],"sentences":[179],"500,000":[181],"bags.<br>":[182],"The":[183],"zip":[184],"two":[188,199],"folders,":[189],"GDAt,":[192],"datasets,":[200],"respectively.":[201]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-10T00:00:00"}
