{"id":"https://openalex.org/W7223247149","doi":"https://doi.org/10.64898/2026.10.16.759653","title":"Population-scale drug target and variant prioritization with Varformer","display_name":"Population-scale drug target and variant prioritization with Varformer","publication_year":2026,"publication_date":"2026-10-22","ids":{"openalex":"https://openalex.org/W7223247149","doi":"https://doi.org/10.64898/2026.10.16.759653"},"language":"en","primary_location":{"id":"doi:10.64898/2026.10.16.759653","doi":"https://doi.org/10.64898/2026.10.16.759653","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.16.759653","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/22/2026.10.16.759653.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/22/2026.10.16.759653.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093850003","display_name":"Aaron Wenteler","orcid":"https://orcid.org/0000-0002-0851-1564","observed_orcids":["https://orcid.org/0000-0002-0851-1564"]},"institutions":[{"id":"https://openalex.org/I1285764155","display_name":"Merck & Co., Inc., Rahway, NJ, USA (United States)","ror":"https://ror.org/02891sr49","country_code":"US","type":"company","lineage":["https://openalex.org/I1285764155"]},{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]},{"id":"https://openalex.org/I4210149920","display_name":"William Harvey Research Institute","ror":"https://ror.org/0574dzy90","country_code":"GB","type":"facility","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079","https://openalex.org/I4210149920"]}],"countries":["GB","US"],"is_corresponding":true,"raw_author_name":"Aaron Wenteler","raw_affiliation_strings":["Data, AI & Genome Sciences, Merck & Co., Inc., Cambridge, MA, United States of America","Digital Environment Research Institute, Queen Mary University of London, London, United Kingdom","William Harvey Research Institute, Queen Mary University of London, London, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-0851-1564","affiliations":[{"raw_affiliation_string":"Data, AI & Genome Sciences, Merck & Co., Inc., Cambridge, MA, United States of America","institution_ids":["https://openalex.org/I1285764155"]},{"raw_affiliation_string":"Digital Environment Research Institute, Queen Mary University of London, London, United Kingdom","institution_ids":["https://openalex.org/I166337079"]},{"raw_affiliation_string":"William Harvey Research Institute, Queen Mary University of London, London, United Kingdom","institution_ids":["https://openalex.org/I166337079","https://openalex.org/I4210149920"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035143106","display_name":"Victor Neduva","orcid":"https://orcid.org/0000-0001-9069-6440","observed_orcids":["https://orcid.org/0000-0001-9069-6440"]},"institutions":[{"id":"https://openalex.org/I118019719","display_name":"F. Hoffmann-La Roche AG","ror":"https://ror.org/00by1q217","country_code":"CH","type":"company","lineage":["https://openalex.org/I118019719"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Victor Neduva","raw_affiliation_strings":["Roche Innovation Center, F. Hoffmann-La Roche Ltd, Basel, Switzerland"],"raw_orcid":"https://orcid.org/0000-0001-9069-6440","affiliations":[{"raw_affiliation_string":"Roche Innovation Center, F. Hoffmann-La Roche Ltd, Basel, Switzerland","institution_ids":["https://openalex.org/I118019719"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055915688","display_name":"Claudia Cabrera","orcid":"https://orcid.org/0000-0002-2205-5315","observed_orcids":["https://orcid.org/0000-0002-2205-5315"]},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]},{"id":"https://openalex.org/I4210149920","display_name":"William Harvey Research Institute","ror":"https://ror.org/0574dzy90","country_code":"GB","type":"facility","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079","https://openalex.org/I4210149920"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Claudia P. Cabrera","raw_affiliation_strings":["Digital Environment Research Institute, Queen Mary University of London, London, United Kingdom","NIHR Barts Cardiovascular Biomedical Research Centre, Queen Mary University of London, London, United Kingdom","William Harvey Research Institute, Queen Mary University of London, London, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-2205-5315","affiliations":[{"raw_affiliation_string":"Digital Environment Research Institute, Queen Mary University of London, London, United Kingdom","institution_ids":["https://openalex.org/I166337079"]},{"raw_affiliation_string":"NIHR Barts Cardiovascular Biomedical Research Centre, Queen Mary University of London, London, United Kingdom","institution_ids":["https://openalex.org/I166337079"]},{"raw_affiliation_string":"William Harvey Research Institute, Queen Mary University of London, London, United Kingdom","institution_ids":["https://openalex.org/I166337079","https://openalex.org/I4210149920"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100323702","display_name":"Wei Wei","orcid":"https://orcid.org/0000-0002-2945-3543","observed_orcids":["https://orcid.org/0000-0002-2945-3543"]},"institutions":[{"id":"https://openalex.org/I1285764155","display_name":"Merck & Co., Inc., Rahway, NJ, USA (United States)","ror":"https://ror.org/02891sr49","country_code":"US","type":"company","lineage":["https://openalex.org/I1285764155"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Wei","raw_affiliation_strings":["Data, AI & Genome Sciences, Merck & Co., Inc., Cambridge, MA, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-2945-3543","affiliations":[{"raw_affiliation_string":"Data, AI & Genome Sciences, Merck & Co., Inc., Cambridge, MA, United States of America","institution_ids":["https://openalex.org/I1285764155"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104831267","display_name":"Michael R. Barnes","orcid":"https://orcid.org/0000-0001-9097-7381","observed_orcids":["https://orcid.org/0000-0001-9097-7381","https://orcid.org/0000-0003-1981-2220"]},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]},{"id":"https://openalex.org/I4210128584","display_name":"The Alan Turing Institute","ror":"https://ror.org/035dkdb55","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210128584"]},{"id":"https://openalex.org/I4210149920","display_name":"William Harvey Research Institute","ror":"https://ror.org/0574dzy90","country_code":"GB","type":"facility","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079","https://openalex.org/I4210149920"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Michael R. Barnes","raw_affiliation_strings":["Digital Environment Research Institute, Queen Mary University of London, London, United Kingdom","NIHR Barts Cardiovascular Biomedical Research Centre, Queen Mary University of London, London, United Kingdom","The Alan Turing Institute, London, United Kingdom","William Harvey Research Institute, Queen Mary University of London, London, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0001-9097-7381","affiliations":[{"raw_affiliation_string":"Digital Environment Research Institute, Queen Mary University of London, London, United Kingdom","institution_ids":["https://openalex.org/I166337079"]},{"raw_affiliation_string":"NIHR Barts Cardiovascular Biomedical Research Centre, Queen Mary University of London, London, United Kingdom","institution_ids":["https://openalex.org/I166337079"]},{"raw_affiliation_string":"The Alan Turing Institute, London, United Kingdom","institution_ids":["https://openalex.org/I4210128584"]},{"raw_affiliation_string":"William Harvey Research Institute, Queen Mary University of London, London, United Kingdom","institution_ids":["https://openalex.org/I166337079","https://openalex.org/I4210149920"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5093850003"],"corresponding_institution_ids":["https://openalex.org/I1285764155","https://openalex.org/I166337079","https://openalex.org/I4210149920"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T11642","display_name":"Genomics and Rare Diseases","score":0.9599999785423279,"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"}},"topics":[{"id":"https://openalex.org/T11642","display_name":"Genomics and Rare Diseases","score":0.9599999785423279,"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.018300000578165054,"subfield":{"id":"https://openalex.org/subfields/3002","display_name":"Drug Discovery"},"field":{"id":"https://openalex.org/fields/30","display_name":"Pharmacology, Toxicology and Pharmaceutics"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10261","display_name":"Genetic Associations and Epidemiology","score":0.013799999840557575,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/drug-target-prioritization","display_name":"drug target prioritization","score":0.9679999947547913},{"id":"https://openalex.org/keywords/missense-mutations","display_name":"missense mutations","score":0.9089999794960022},{"id":"https://openalex.org/keywords/multimodal-transformer","display_name":"multimodal transformer","score":0.9330000281333923},{"id":"https://openalex.org/keywords/cross-modal-attention","display_name":"cross-modal attention","score":0.9860000014305115},{"id":"https://openalex.org/keywords/positive-unlabeled-learning","display_name":"positive-unlabeled learning","score":0.9700000286102295},{"id":"https://openalex.org/keywords/human-genetic-variation","display_name":"human genetic variation","score":0.6340000033378601},{"id":"https://openalex.org/keywords/pathogenic-variants","display_name":"pathogenic variants","score":0.5709999799728394}],"concepts":[{"id":"https://openalex.org/C2989108626","wikidata":"https://www.wikidata.org/wiki/Q904407","display_name":"Drug target","level":2,"score":0.6773999929428101},{"id":"https://openalex.org/C2777615720","wikidata":"https://www.wikidata.org/wiki/Q11888847","display_name":"Prioritization","level":2,"score":0.5443999767303467},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4796999990940094},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.47429999709129333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4724000096321106},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.45680001378059387},{"id":"https://openalex.org/C151956035","wikidata":"https://www.wikidata.org/wiki/Q1132755","display_name":"Logistic regression","level":2,"score":0.4381999969482422},{"id":"https://openalex.org/C68873052","wikidata":"https://www.wikidata.org/wiki/Q349856","display_name":"Genetic variation","level":3,"score":0.4235999882221222},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.41659998893737793},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.3653999865055084},{"id":"https://openalex.org/C2993967602","wikidata":"https://www.wikidata.org/wiki/Q5532932","display_name":"Genetic variants","level":4,"score":0.365200012922287},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.35830000042915344},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.34619998931884766},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.3264000117778778},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.32280001044273376},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.3165999948978424},{"id":"https://openalex.org/C186413461","wikidata":"https://www.wikidata.org/wiki/Q744727","display_name":"Genetic association","level":5,"score":0.28459998965263367},{"id":"https://openalex.org/C2994119904","wikidata":"https://www.wikidata.org/wiki/Q1251001","display_name":"Drug response","level":3,"score":0.2777000069618225},{"id":"https://openalex.org/C75563809","wikidata":"https://www.wikidata.org/wiki/Q2656896","display_name":"Missense mutation","level":4,"score":0.271699994802475},{"id":"https://openalex.org/C58041806","wikidata":"https://www.wikidata.org/wiki/Q1660484","display_name":"Imputation (statistics)","level":3,"score":0.2662999927997589},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.26579999923706055},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2596000134944916},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.25529998540878296}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.10.16.759653","doi":"https://doi.org/10.64898/2026.10.16.759653","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.16.759653","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/22/2026.10.16.759653.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.10.16.759653","doi":"https://doi.org/10.64898/2026.10.16.759653","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.16.759653","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/22/2026.10.16.759653.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being","score":0.9537000060081482}],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334629","display_name":"Biotechnology and Biological Sciences Research Council","ror":"https://ror.org/00cwqg982"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7223247149.pdf","grobid_xml":"https://content.openalex.org/works/W7223247149.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W2131319167","https://openalex.org/W2610439248","https://openalex.org/W2951276412","https://openalex.org/W3094762523","https://openalex.org/W3095583226","https://openalex.org/W4386861232","https://openalex.org/W4405224584","https://openalex.org/W4406448936"],"related_works":["https://openalex.org/W7079560898","https://openalex.org/W4415779810","https://openalex.org/W4214674964","https://openalex.org/W2806311302","https://openalex.org/W7134277999","https://openalex.org/W4412935006","https://openalex.org/W7028447726","https://openalex.org/W1968107700","https://openalex.org/W4414055741","https://openalex.org/W4399045484"],"abstract_inverted_index":{"Abstract":[0],"Human":[1],"genetic":[2,63,104],"variation":[3],"is":[4,140],"a":[5,36,68,83],"powerful":[6],"driver":[7],"of":[8,20,30,47,70,78,137],"therapeutic":[9],"target":[10,148],"prioritization,":[11],"yet":[12],"current":[13],"models":[14],"struggle":[15],"to":[16,43],"aggregate":[17],"variable":[18],"numbers":[19],"variants":[21,49],"per":[22],"gene":[23],"and":[24,73,89,149],"are":[25],"bottlenecked":[26],"by":[27,87,91],"the":[28,94,126,131],"scarcity":[29],"validated":[31,59],"targets.":[32],"We":[33],"present":[34],"Varformer,":[35],"multimodal":[37],"transformer":[38],"that":[39],"uses":[40],"cross-modal":[41],"attention":[42],"integrate":[44],"contextual":[45],"representations":[46],"missense":[48],"with":[50,102],"gene-level":[51],"features.":[52],"Trained":[53],"via":[54],"positive-unlabeled":[55],"learning":[56],"on":[57,93],"clinically":[58],"targets":[60,101],"across":[61,75,106],"four":[62],"ancestry":[64,107],"groups,":[65],"Varformer":[66,124,139],"achieves":[67],"precision@20":[69],"0.95,":[71],"0.86,":[72],"0.48":[74],"three":[76],"benchmarks":[77],"increasing":[79],"difficulty.":[80],"It":[81],"surpasses":[82],"logistic":[84],"regression":[85],"ablation":[86],"20%":[88],"DrugnomeAI":[90],"23%":[92],"hardest":[95],"benchmark.":[96],"Cross-population":[97],"rank":[98],"normalization":[99],"isolates":[100],"consistent":[103],"support":[105],"groups.":[108],"The":[109],"variant":[110,129,150],"encoder":[111],"also":[112],"scores":[113],"individual":[114],"variants.":[115],"Across":[116],"1,164":[117],"carrier\u2013variant":[118],"pairs":[119],"in":[120,130,135],"Genes":[121],"&":[122],"Health,":[123],"ranked":[125],"known":[127],"pathogenic":[128],"carrier\u2019s":[132],"top":[133],"20":[134],"57%":[136],"pairs.":[138],"available":[141],"as":[142],"an":[143],"open-source":[144],"framework":[145],"for":[146],"unified":[147],"prioritization.":[151]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-10-23T00:00:00"}
