{"id":"https://openalex.org/W7171557264","doi":"https://doi.org/10.1145/3807503.3816791","title":"Synthetic Germline VCF Generation for Rare Diseases: Case Study in NF1","display_name":"Synthetic Germline VCF Generation for Rare Diseases: Case Study in NF1","publication_year":2026,"publication_date":"2026-06-30","ids":{"openalex":"https://openalex.org/W7171557264","doi":"https://doi.org/10.1145/3807503.3816791"},"language":null,"primary_location":{"id":"doi:10.1145/3807503.3816791","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3807503.3816791","pdf_url":null,"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 17th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3807503.3816791","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055498873","display_name":"Sikha Pentyala","orcid":"https://orcid.org/0000-0001-7486-6016"},"institutions":[{"id":"https://openalex.org/I4210150356","display_name":"University of Washington Tacoma","ror":"https://ror.org/05n8t2628","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701","https://openalex.org/I4210150356"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sikha Pentyala","raw_affiliation_strings":["School of Engineering and Technology, University of Washington Tacoma, Tacoma, Washington, USA"],"raw_orcid":"https://orcid.org/0000-0001-7486-6016","affiliations":[{"raw_affiliation_string":"School of Engineering and Technology, University of Washington Tacoma, Tacoma, Washington, USA","institution_ids":["https://openalex.org/I4210150356"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072958883","display_name":"Ziwei Pan","orcid":"https://orcid.org/0000-0003-0533-1995"},"institutions":[{"id":"https://openalex.org/I1323236076","display_name":"Sage Bionetworks","ror":"https://ror.org/049ncjx51","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1323236076"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ziwei Pan","raw_affiliation_strings":["Sage Bionetworks, Seattle, Washington, USA"],"raw_orcid":"https://orcid.org/0000-0003-0533-1995","affiliations":[{"raw_affiliation_string":"Sage Bionetworks, Seattle, Washington, USA","institution_ids":["https://openalex.org/I1323236076"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108511548","display_name":"Patrick J. McKeever","orcid":null},"institutions":[{"id":"https://openalex.org/I4210150356","display_name":"University of Washington Tacoma","ror":"https://ror.org/05n8t2628","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701","https://openalex.org/I4210150356"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Patrick J McKeever","raw_affiliation_strings":["University of Washington Tacoma, Tacoma, Washington, USA"],"raw_orcid":"https://orcid.org/0009-0000-2845-7107","affiliations":[{"raw_affiliation_string":"University of Washington Tacoma, Tacoma, Washington, USA","institution_ids":["https://openalex.org/I4210150356"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045731311","display_name":"Jineta Banerjee","orcid":"https://orcid.org/0000-0002-1775-3645"},"institutions":[{"id":"https://openalex.org/I1323236076","display_name":"Sage Bionetworks","ror":"https://ror.org/049ncjx51","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1323236076"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jineta Banerjee","raw_affiliation_strings":["Sage Bionetworks, Seattle, Washington, USA"],"raw_orcid":"https://orcid.org/0000-0002-1775-3645","affiliations":[{"raw_affiliation_string":"Sage Bionetworks, Seattle, Washington, USA","institution_ids":["https://openalex.org/I1323236076"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003370572","display_name":"Luca Foschini","orcid":"https://orcid.org/0000-0003-1409-3570"},"institutions":[{"id":"https://openalex.org/I1323236076","display_name":"Sage Bionetworks","ror":"https://ror.org/049ncjx51","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1323236076"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luca Foschini","raw_affiliation_strings":["Sage Bionetworks, Seattle, Washington, USA"],"raw_orcid":"https://orcid.org/0000-0003-1409-3570","affiliations":[{"raw_affiliation_string":"Sage Bionetworks, Seattle, Washington, USA","institution_ids":["https://openalex.org/I1323236076"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056749857","display_name":"Martine De Cock","orcid":"https://orcid.org/0000-0001-7917-0771"},"institutions":[{"id":"https://openalex.org/I4210150356","display_name":"University of Washington Tacoma","ror":"https://ror.org/05n8t2628","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701","https://openalex.org/I4210150356"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Martine De Cock","raw_affiliation_strings":["University of Washington Tacoma, Tacoma, Washington, USA"],"raw_orcid":"https://orcid.org/0000-0001-7917-0771","affiliations":[{"raw_affiliation_string":"University of Washington Tacoma, Tacoma, Washington, USA","institution_ids":["https://openalex.org/I4210150356"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":"1","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/germline","display_name":"Germline","score":0.5698000192642212},{"id":"https://openalex.org/keywords/mutation","display_name":"Mutation","score":0.3540000021457672},{"id":"https://openalex.org/keywords/disease","display_name":"Disease","score":0.2842999994754791},{"id":"https://openalex.org/keywords/frameshift-mutation","display_name":"Frameshift mutation","score":0.2614000141620636}],"concepts":[{"id":"https://openalex.org/C109825262","wikidata":"https://www.wikidata.org/wiki/Q1139164","display_name":"Germline","level":3,"score":0.5698000192642212},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.44359999895095825},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.42980000376701355},{"id":"https://openalex.org/C501734568","wikidata":"https://www.wikidata.org/wiki/Q42918","display_name":"Mutation","level":3,"score":0.3540000021457672},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.34860000014305115},{"id":"https://openalex.org/C502942594","wikidata":"https://www.wikidata.org/wiki/Q3421914","display_name":"Cancer research","level":1,"score":0.32670000195503235},{"id":"https://openalex.org/C2779134260","wikidata":"https://www.wikidata.org/wiki/Q12136","display_name":"Disease","level":2,"score":0.2842999994754791},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.2702000141143799},{"id":"https://openalex.org/C29906990","wikidata":"https://www.wikidata.org/wiki/Q1440688","display_name":"Frameshift mutation","level":4,"score":0.2614000141620636},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.24040000140666962}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3807503.3816791","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3807503.3816791","pdf_url":null,"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 17th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3807503.3816791","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3807503.3816791","pdf_url":null,"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 17th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8665234596","display_name":"EAGER: NAIRR Pilot: Making Biomedical Data FAIR on the NAIRR","funder_award_id":"2451163","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W4386268652","https://openalex.org/W4412454169","https://openalex.org/W4413102667"],"related_works":[],"abstract_inverted_index":{"Synthetic":[0],"data":[1,13,52],"generation":[2,60],"(SDG)":[3],"holds":[4],"promise":[5],"for":[6,26,35,82],"rare":[7,83],"disease":[8,84],"research":[9],"by":[10],"enabling":[11],"privacy-conscious":[12],"sharing":[14],"and":[15,67],"AI":[16],"model":[17],"training":[18],"on":[19,48,92],"limited":[20],"cohorts.":[21],"We":[22],"present":[23],"a":[24,44],"framework":[25],"generating":[27],"synthetic":[28,75],"germline":[29,76],"variant":[30],"call":[31],"format":[32],"(VCF)":[33],"datasets":[34],"Neurofibromatosis":[36],"type":[37],"1":[38],"(NF1),":[39],"combining":[40],"domain":[41],"knowledge":[42],"with":[43,86],"CART-based":[45],"generator":[46],"trained":[47],"whole":[49],"exome":[50],"sequencing":[51],"from":[53],"182":[54],"NF1":[55],"patients.":[56],"Three":[57],"progressively":[58],"refined":[59],"strategies":[61],"are":[62],"evaluated":[63],"across":[64],"fidelity,":[65],"utility,":[66],"privacy":[68,94],"dimensions.":[69],"Our":[70],"results":[71],"demonstrate":[72],"that":[73],"realistic":[74],"VCF":[77],"cohorts":[78],"can":[79],"be":[80],"generated":[81],"research,":[85],"privacy\u2013fidelity":[87],"tradeoffs":[88],"motivating":[89],"future":[90],"work":[91],"formal":[93],"guarantees.":[95]},"counts_by_year":[],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2026-07-29T00:00:00"}