{"id":"https://openalex.org/W4387698279","doi":"https://doi.org/10.1145/3603765.3603771","title":"Applying BioBERT to Extract Germline Gene-Disease Associations for Building a Knowledge Graph from the Biomedical Literature","display_name":"Applying BioBERT to Extract Germline Gene-Disease Associations for Building a Knowledge Graph from the Biomedical Literature","publication_year":2023,"publication_date":"2023-05-10","ids":{"openalex":"https://openalex.org/W4387698279","doi":"https://doi.org/10.1145/3603765.3603771"},"language":"en","primary_location":{"id":"doi:10.1145/3603765.3603771","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3603765.3603771","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 the 7th International Conference on Information System and Data Mining (ICISDM)","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/A5011569387","display_name":"A. Gonz\u00e1lez","orcid":"https://orcid.org/0000-0002-4061-1880"},"institutions":[{"id":"https://openalex.org/I171231263","display_name":"Charleston Southern University","ror":"https://ror.org/03mwnnn55","country_code":"US","type":"education","lineage":["https://openalex.org/I171231263"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Armando D. Diaz Gonzalez","raw_affiliation_strings":["Department of Computing Science, Charleston Southern University, United States"],"raw_orcid":"https://orcid.org/0000-0002-4061-1880","affiliations":[{"raw_affiliation_string":"Department of Computing Science, Charleston Southern University, United States","institution_ids":["https://openalex.org/I171231263"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025382374","display_name":"Kevin S. Hughes","orcid":"https://orcid.org/0000-0003-4084-6484"},"institutions":[{"id":"https://openalex.org/I153297377","display_name":"Medical University of South Carolina","ror":"https://ror.org/012jban78","country_code":"US","type":"education","lineage":["https://openalex.org/I153297377"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin S. Hughes","raw_affiliation_strings":["Department of Surgery, Medical University of South Carolina, United States"],"raw_orcid":"https://orcid.org/0000-0003-4084-6484","affiliations":[{"raw_affiliation_string":"Department of Surgery, Medical University of South Carolina, United States","institution_ids":["https://openalex.org/I153297377"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044260725","display_name":"Songhui Yue","orcid":"https://orcid.org/0009-0002-0945-3105"},"institutions":[{"id":"https://openalex.org/I171231263","display_name":"Charleston Southern University","ror":"https://ror.org/03mwnnn55","country_code":"US","type":"education","lineage":["https://openalex.org/I171231263"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Songhui Yue","raw_affiliation_strings":["Department of Computing Science, Charleston Southern University, United States"],"raw_orcid":"https://orcid.org/0009-0002-0945-3105","affiliations":[{"raw_affiliation_string":"Department of Computing Science, Charleston Southern University, United States","institution_ids":["https://openalex.org/I171231263"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090423231","display_name":"Sean T. Hayes","orcid":"https://orcid.org/0000-0003-3631-7782"},"institutions":[{"id":"https://openalex.org/I171231263","display_name":"Charleston Southern University","ror":"https://ror.org/03mwnnn55","country_code":"US","type":"education","lineage":["https://openalex.org/I171231263"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sean T. Hayes","raw_affiliation_strings":["Department of Computing Science, Charleston Southern University, United States"],"raw_orcid":"https://orcid.org/0000-0003-3631-7782","affiliations":[{"raw_affiliation_string":"Department of Computing Science, Charleston Southern University, United States","institution_ids":["https://openalex.org/I171231263"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5011569387"],"corresponding_institution_ids":["https://openalex.org/I171231263"],"apc_list":null,"apc_paid":null,"fwci":0.5998,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.70508716,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"37","last_page":"42"},"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/T10028","display_name":"Topic Modeling","score":0.9988999962806702,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9961000084877014,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7169044613838196},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.6324710249900818},{"id":"https://openalex.org/keywords/knowledge-representation-and-reasoning","display_name":"Knowledge representation and reasoning","score":0.5698360204696655},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5053332448005676},{"id":"https://openalex.org/keywords/ontology","display_name":"Ontology","score":0.4587448239326477},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.43165507912635803},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41592133045196533},{"id":"https://openalex.org/keywords/relationship-extraction","display_name":"Relationship extraction","score":0.41523343324661255},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.40705418586730957},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.3783433437347412},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35016724467277527},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.262004554271698}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7169044613838196},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.6324710249900818},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.5698360204696655},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5053332448005676},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.4587448239326477},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.43165507912635803},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41592133045196533},{"id":"https://openalex.org/C153604712","wikidata":"https://www.wikidata.org/wiki/Q7310755","display_name":"Relationship extraction","level":3,"score":0.41523343324661255},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40705418586730957},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.3783433437347412},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35016724467277527},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.262004554271698},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3603765.3603771","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3603765.3603771","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 the 7th International Conference on Information System and Data Mining (ICISDM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8100000023841858,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W2018064805","https://openalex.org/W2037450062","https://openalex.org/W2067792343","https://openalex.org/W2123152121","https://openalex.org/W2133656631","https://openalex.org/W2146954401","https://openalex.org/W2154142897","https://openalex.org/W2156235098","https://openalex.org/W2169099542","https://openalex.org/W2343954916","https://openalex.org/W2562426122","https://openalex.org/W2761714433","https://openalex.org/W2775521672","https://openalex.org/W2806882588","https://openalex.org/W2888113858","https://openalex.org/W2896457183","https://openalex.org/W2906635035","https://openalex.org/W2911489562","https://openalex.org/W2945273730","https://openalex.org/W2970771982","https://openalex.org/W3006227201","https://openalex.org/W3093934881","https://openalex.org/W3103412787","https://openalex.org/W3120941101","https://openalex.org/W3184399081","https://openalex.org/W3187852182","https://openalex.org/W3205802642","https://openalex.org/W4210800588","https://openalex.org/W4224939608","https://openalex.org/W4246866390","https://openalex.org/W4282960293","https://openalex.org/W4283318325","https://openalex.org/W4291745514","https://openalex.org/W4295736374","https://openalex.org/W4303685003","https://openalex.org/W4303857545","https://openalex.org/W4307838179","https://openalex.org/W4309004304","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W842810586","https://openalex.org/W4319940250","https://openalex.org/W2352298027","https://openalex.org/W2092919065","https://openalex.org/W3138801416","https://openalex.org/W4236762297","https://openalex.org/W2444550338","https://openalex.org/W2369351710","https://openalex.org/W2594363579","https://openalex.org/W2169232658"],"abstract_inverted_index":{"Published":[0],"biomedical":[1,29,95],"information":[2],"has":[3,54],"and":[4,26,36,62,78,85,101,106,116,132,148,166],"continues":[5],"to":[6,104,124,150,173],"rapidly":[7],"increase.":[8],"The":[9],"recent":[10],"advancements":[11],"in":[12,21,43,57,135],"Natural":[13],"Language":[14],"Processing":[15],"(NLP),":[16],"have":[17],"generated":[18],"considerable":[19],"interest":[20],"automating":[22],"the":[23,44,50,81,143,152,175],"extraction,":[24],"normalization,":[25],"representation":[27],"of":[28,46,49,83,155],"knowledge":[30,47,70,138,144,159],"about":[31],"entities":[32],"such":[33],"as":[34],"genes":[35,61,77,84],"diseases.":[37,63,79],"Our":[38,158],"study":[39],"analyzes":[40],"germline":[41,76,156],"abstracts":[42],"construction":[45,72],"graphs":[48],"immense":[51],"work":[52],"that":[53,74],"been":[55],"done":[56],"this":[58],"area":[59],"for":[60],"This":[64],"paper":[65],"presents":[66],"SimpleGermKG,":[67],"an":[68,99],"automatic":[69],"graph":[71,145,160],"approach":[73,123],"connects":[75],"For":[80,110],"extraction":[82],"diseases,":[86,117,165],"we":[87,118,141],"employ":[88],"BioBERT,":[89],"a":[90,120,136],"pre-trained":[91],"BERT":[92],"model":[93],"on":[94],"corpora.":[96,157],"We":[97],"propose":[98],"ontology-based":[100],"rule-based":[102],"algorithm":[103],"standardize":[105],"disambiguate":[107],"medical":[108],"terms.":[109],"semantic":[111],"relationships":[112],"between":[113],"articles,":[114],"genes,":[115,163],"implemented":[119],"part-whole":[121],"relation":[122],"connect":[125],"each":[126],"entity":[127],"with":[128],"its":[129],"data":[130],"source":[131],"visualize":[133],"them":[134],"graph-based":[137],"representation.":[139],"Lastly,":[140],"discuss":[142],"applications,":[146],"limitations,":[147],"challenges":[149],"inspire":[151],"future":[153],"research":[154],"contains":[161],"297":[162],"130":[164],"46,747":[167],"triples.":[168],"Graph-based":[169],"visualizations":[170],"are":[171],"used":[172],"show":[174],"results.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}