{"id":"https://openalex.org/W4387346456","doi":"https://doi.org/10.1145/3584371.3612995","title":"Large-scale Dataset and Effective Model for Variant-Disease Associations Extraction","display_name":"Large-scale Dataset and Effective Model for Variant-Disease Associations Extraction","publication_year":2023,"publication_date":"2023-09-03","ids":{"openalex":"https://openalex.org/W4387346456","doi":"https://doi.org/10.1145/3584371.3612995"},"language":"en","primary_location":{"id":"doi:10.1145/3584371.3612995","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3584371.3612995","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3584371.3612995","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3584371.3612995","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030867642","display_name":"Lei Chen","orcid":"https://orcid.org/0000-0002-9727-0714"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Lei Chen","raw_affiliation_strings":["Department of Computer Science, The University of Hong Kong, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-9727-0714","affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043198787","display_name":"Junhao Su","orcid":"https://orcid.org/0000-0002-8560-3999"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Junhao Su","raw_affiliation_strings":["Department of Computer Science, The University of Hong Kong, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-8560-3999","affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008837884","display_name":"Zhenxian Zheng","orcid":"https://orcid.org/0000-0002-6546-2324"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhenxian Zheng","raw_affiliation_strings":["Department of Computer Science, The University of Hong Kong, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-6546-2324","affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077116003","display_name":"Tak\u2010Wah Lam","orcid":"https://orcid.org/0000-0003-4676-8587"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Tak-Wah Lam","raw_affiliation_strings":["Department of Computer Science, The University of Hong Kong, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0003-4676-8587","affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027440970","display_name":"Ruibang Luo","orcid":"https://orcid.org/0000-0001-9711-6533"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ruibang Luo","raw_affiliation_strings":["Department of Computer Science, The University of Hong Kong, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0001-9711-6533","affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5030867642"],"corresponding_institution_ids":["https://openalex.org/I889458895"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29473751,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9850999712944031,"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"}},{"id":"https://openalex.org/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9588000178337097,"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":0.7993119955062866},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6732999086380005},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5990213751792908},{"id":"https://openalex.org/keywords/biomedical-text-mining","display_name":"Biomedical text mining","score":0.5186814069747925},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4997375011444092},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4990270137786865},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46280449628829956},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.45969879627227783},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4510273039340973},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43896251916885376},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.43860673904418945},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4264174699783325},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.36172932386398315},{"id":"https://openalex.org/keywords/text-mining","display_name":"Text mining","score":0.14312392473220825}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7993119955062866},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6732999086380005},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5990213751792908},{"id":"https://openalex.org/C165141518","wikidata":"https://www.wikidata.org/wiki/Q4915126","display_name":"Biomedical text mining","level":3,"score":0.5186814069747925},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4997375011444092},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4990270137786865},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46280449628829956},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.45969879627227783},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4510273039340973},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43896251916885376},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.43860673904418945},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4264174699783325},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36172932386398315},{"id":"https://openalex.org/C71472368","wikidata":"https://www.wikidata.org/wiki/Q676880","display_name":"Text mining","level":2,"score":0.14312392473220825},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3584371.3612995","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3584371.3612995","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3584371.3612995","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3584371.3612995","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3584371.3612995","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3584371.3612995","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.6600000262260437}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387346456.pdf","grobid_xml":"https://content.openalex.org/works/W4387346456.grobid-xml"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W2029017735","https://openalex.org/W2155518941","https://openalex.org/W2911489562","https://openalex.org/W3046375318"],"related_works":["https://openalex.org/W2916147465","https://openalex.org/W1757434866","https://openalex.org/W3004288456","https://openalex.org/W4362496998","https://openalex.org/W2184397297","https://openalex.org/W2251431888","https://openalex.org/W1663435917","https://openalex.org/W2810079151","https://openalex.org/W2572241437","https://openalex.org/W2164881856"],"abstract_inverted_index":{"Extracting":[0],"variant-disease":[1],"associations":[2,56,210],"(VDAs)":[3],"from":[4,65,101,128,177],"the":[5,23,30,60,66,81,102,129,136,143,157,166,178,196,201,204,209,220,228],"biomedical":[6,13,36,103,130,179],"literature":[7,37,67,131],"is":[8,38,68,87,163],"a":[9,39,47,69,88,108,120,185,234],"critical":[10],"task":[11],"in":[12],"and":[14,28,41,54,71,98,105,150,187,214,244],"genomics":[15],"research,":[16],"as":[17],"it":[18,75],"provides":[19],"valuable":[20],"insights":[21],"into":[22,203],"genetic":[24,52,212],"basis":[25],"of":[26,32,44,49,63,142,148,159,165,200],"diseases":[27],"facilitates":[29],"development":[31],"precision":[33],"medicine.":[34],"The":[35],"vast":[40],"growing":[42],"source":[43],"information":[45],"containing":[46,172],"wealth":[48],"knowledge":[50],"on":[51,135,219],"variants":[53,151,202,213],"their":[55],"with":[57,80,153],"diseases.":[58,155,216],"However,":[59],"manual":[61],"extraction":[62,127],"VDAs":[64,100],"time-consuming":[70],"labor-intensive":[72],"process,":[73],"making":[74],"challenging":[76],"to":[77,91,106,206],"keep":[78],"up":[79],"rapidly":[82],"expanding":[83],"literature.":[84],"Therefore,":[85],"there":[86],"pressing":[89],"need":[90],"develop":[92],"computational":[93],"methods":[94],"for":[95,111,125,169,237],"effectively":[96],"extracting":[97],"curating":[99],"literature,":[104],"build":[107],"comprehensive":[109],"dataset":[110,124,222],"this":[112,116],"significant":[113],"task.":[114],"In":[115,181],"paper,":[117],"we":[118,183],"present":[119],"large-scale,":[121],"semi-automatically":[122],"annotated":[123],"VDA":[126,170,238],"(called":[132],"VDAL)":[133],"based":[134],"DisGeNet":[137],"platform":[138],"which":[139,194],"contains":[140],"one":[141,164],"largest":[144,167],"publicly":[145],"available":[146,247],"collections":[147],"genes":[149],"associated":[152],"human":[154,215],"To":[156],"best":[158],"our":[160,242],"knowledge,":[161],"VDAL":[162],"datasets":[168],"extraction,":[171],"9,362":[173],"related":[174],"PubMed":[175],"documents":[176],"domain.":[180],"addition,":[182],"propose":[184],"novel":[186],"simple":[188],"yet":[189],"effective":[190],"model,":[191],"called":[192],"VDANet,":[193],"incorporates":[195],"corresponding":[197],"gene":[198],"embeddings":[199],"model":[205],"better":[207],"explore":[208],"between":[211],"Extensive":[217],"experiments":[218],"constructed":[221],"show":[223],"that":[224],"VDANet":[225],"significantly":[226],"outperforms":[227],"state-of-the-art":[229],"baseline":[230],"methods,":[231],"thus":[232],"establishing":[233],"new":[235],"benchmark":[236],"extraction.":[239],"For":[240],"reproducibility,":[241],"code":[243],"data":[245],"are":[246],"at":[248],"https://github.com/JasonCLEI/VDANet.":[249]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}