{"id":"https://openalex.org/W7212309255","doi":"https://doi.org/10.64898/2026.09.08.750172","title":"Causal variant underestimation is a major overlooked driver of sequence-to-function model underperformance","display_name":"Causal variant underestimation is a major overlooked driver of sequence-to-function model underperformance","publication_year":2026,"publication_date":"2026-09-11","ids":{"openalex":"https://openalex.org/W7212309255","doi":"https://doi.org/10.64898/2026.09.08.750172"},"language":"en","primary_location":{"id":"doi:10.64898/2026.09.08.750172","doi":"https://doi.org/10.64898/2026.09.08.750172","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.08.750172","pdf_url":null,"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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.64898/2026.09.08.750172","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058400785","display_name":"Shiron Drusinsky","orcid":"https://orcid.org/0000-0003-1184-8835","observed_orcids":["https://orcid.org/0000-0003-1184-8835"]},"institutions":[{"id":"https://openalex.org/I1321430492","display_name":"Gladstone Institutes","ror":"https://ror.org/038321296","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1321430492"]},{"id":"https://openalex.org/I180670191","display_name":"University of California, San Francisco","ror":"https://ror.org/043mz5j54","country_code":"US","type":"education","lineage":["https://openalex.org/I180670191"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shiron Drusinsky","raw_affiliation_strings":["University of California, San Francisco Gladstone Institutes"],"raw_orcid":"https://orcid.org/0000-0003-1184-8835","affiliations":[{"raw_affiliation_string":"University of California, San Francisco Gladstone Institutes","institution_ids":["https://openalex.org/I1321430492","https://openalex.org/I180670191"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005062415","display_name":"Katherine S. Pollard","orcid":"https://orcid.org/0000-0002-9870-6196","observed_orcids":["https://orcid.org/0000-0002-9870-6196"]},"institutions":[{"id":"https://openalex.org/I1321430492","display_name":"Gladstone Institutes","ror":"https://ror.org/038321296","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1321430492"]},{"id":"https://openalex.org/I180670191","display_name":"University of California, San Francisco","ror":"https://ror.org/043mz5j54","country_code":"US","type":"education","lineage":["https://openalex.org/I180670191"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Katherine S. Pollard","raw_affiliation_strings":["University of California, San Francisco Gladstone Institutes, Biohub SF"],"raw_orcid":"https://orcid.org/0000-0002-9870-6196","affiliations":[{"raw_affiliation_string":"University of California, San Francisco Gladstone Institutes, Biohub SF","institution_ids":["https://openalex.org/I1321430492","https://openalex.org/I180670191"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5058400785"],"corresponding_institution_ids":["https://openalex.org/I1321430492","https://openalex.org/I180670191"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"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/T10261","display_name":"Genetic Associations and Epidemiology","score":0.9526000022888184,"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/T10261","display_name":"Genetic Associations and Epidemiology","score":0.9526000022888184,"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/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.014999999664723873,"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/T11468","display_name":"Genetic Mapping and Diversity in Plants and Animals","score":0.005400000140070915,"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/expression-quantitative-trait-loci","display_name":"expression quantitative trait loci","score":0.9340000152587891},{"id":"https://openalex.org/keywords/fine-mapping","display_name":"fine mapping","score":0.8880000114440918},{"id":"https://openalex.org/keywords/alphagenome","display_name":"AlphaGenome","score":0.8790000081062317},{"id":"https://openalex.org/keywords/variant-effect-prediction","display_name":"variant effect prediction","score":0.781000018119812},{"id":"https://openalex.org/keywords/enhancer-activity","display_name":"enhancer activity","score":0.8130000233650208},{"id":"https://openalex.org/keywords/gene-expression-prediction","display_name":"gene expression prediction","score":0.7379999756813049}],"concepts":[{"id":"https://openalex.org/C168393362","wikidata":"https://www.wikidata.org/wiki/Q5421706","display_name":"Expression quantitative trait loci","level":5,"score":0.5766000151634216},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.49900001287460327},{"id":"https://openalex.org/C106934330","wikidata":"https://www.wikidata.org/wiki/Q1971873","display_name":"Trait","level":2,"score":0.48669999837875366},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.4607999920845032},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.42570000886917114},{"id":"https://openalex.org/C81941488","wikidata":"https://www.wikidata.org/wiki/Q853421","display_name":"Quantitative trait locus","level":3,"score":0.4034000039100647},{"id":"https://openalex.org/C64357122","wikidata":"https://www.wikidata.org/wiki/Q1149766","display_name":"Causality (physics)","level":2,"score":0.39320001006126404},{"id":"https://openalex.org/C84597430","wikidata":"https://www.wikidata.org/wiki/Q106227","display_name":"Locus (genetics)","level":3,"score":0.3896999955177307},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.38179999589920044},{"id":"https://openalex.org/C2993967602","wikidata":"https://www.wikidata.org/wiki/Q5532932","display_name":"Genetic variants","level":4,"score":0.37860000133514404},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.3763999938964844},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3709999918937683},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.3677000105381012},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.3553999960422516},{"id":"https://openalex.org/C61727976","wikidata":"https://www.wikidata.org/wiki/Q751748","display_name":"Epistasis","level":3,"score":0.34439998865127563},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.3343999981880188},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.3301999866962433},{"id":"https://openalex.org/C119043178","wikidata":"https://www.wikidata.org/wiki/Q320723","display_name":"Covariate","level":2,"score":0.3280999958515167},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.32170000672340393},{"id":"https://openalex.org/C111936080","wikidata":"https://www.wikidata.org/wiki/Q913367","display_name":"Enhancer","level":4,"score":0.27549999952316284},{"id":"https://openalex.org/C106208931","wikidata":"https://www.wikidata.org/wiki/Q1098876","display_name":"Genome-wide association study","level":5,"score":0.2614000141620636},{"id":"https://openalex.org/C163175372","wikidata":"https://www.wikidata.org/wiki/Q3339222","display_name":"Linear model","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C2987525970","wikidata":"https://www.wikidata.org/wiki/Q96374569","display_name":"Causal analysis","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C67339327","wikidata":"https://www.wikidata.org/wiki/Q1502576","display_name":"Gene regulatory network","level":4,"score":0.25459998846054077}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.09.08.750172","doi":"https://doi.org/10.64898/2026.09.08.750172","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.08.750172","pdf_url":null,"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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.09.08.750172","doi":"https://doi.org/10.64898/2026.09.08.750172","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.08.750172","pdf_url":null,"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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[{"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3","score":0.6240000128746033}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1981041672","https://openalex.org/W2024933578","https://openalex.org/W2025943989","https://openalex.org/W2099085143","https://openalex.org/W2181523240","https://openalex.org/W2209106767","https://openalex.org/W2901749533","https://openalex.org/W2991283206","https://openalex.org/W3133859624","https://openalex.org/W3196426274","https://openalex.org/W3203588026","https://openalex.org/W4285006295","https://openalex.org/W4320726002","https://openalex.org/W4361001523","https://openalex.org/W4389174422","https://openalex.org/W4389174423","https://openalex.org/W4389174513","https://openalex.org/W4390139716","https://openalex.org/W4402826099","https://openalex.org/W4404535307","https://openalex.org/W4405829527","https://openalex.org/W4406178430","https://openalex.org/W4407553679","https://openalex.org/W4410851723","https://openalex.org/W4412400843","https://openalex.org/W6968220914","https://openalex.org/W7118514966","https://openalex.org/W7125967877","https://openalex.org/W7128294649","https://openalex.org/W7163911915","https://openalex.org/W7171362730"],"related_works":["https://openalex.org/W7166328984","https://openalex.org/W7223629431","https://openalex.org/W7127293915","https://openalex.org/W3168560461","https://openalex.org/W7128294649","https://openalex.org/W4403547222","https://openalex.org/W7162571144","https://openalex.org/W7163911915","https://openalex.org/W2093592848","https://openalex.org/W7167642065"],"abstract_inverted_index":{"Abstract":[0],"Deep":[1],"learning":[2],"sequence-to-function":[3],"(S2F)":[4],"models":[5,33,215],"represent":[6],"tremendous":[7],"promise":[8],"for":[9,97,125,218,232,247],"functionally":[10],"fine-mapping":[11,219,230],"causal":[12,39,114,161,226,248,271],"variants":[13,80,115,162,189,249],"associated":[14],"with":[15,250,282],"traits":[16],"and":[17,116,135,291],"disease.":[18],"Yet":[19],"it":[20],"remains":[21],"unclear":[22],"precisely":[23],"how":[24],"effective":[25],"they":[26,222],"are":[27,148,163,190,207,216,244,255,264],"at":[28,36,51],"this":[29,126],"task.":[30],"Generally,":[31],"S2F":[32,88,145,214,279],"perform":[34],"well":[35],"classifying":[37],"putatively":[38,102],"expression":[40,56,146,280],"quantitative":[41],"trait":[42],"loci":[43,124],"(eQTL)":[44],"SNVs,":[45,104],"yet":[46],"dramatically":[47],"underperform":[48],"linear":[49],"baselines":[50],"ranking":[52],"different":[53],"individuals\u2019":[54],"gene":[55,82],"values":[57],"from":[58,193],"their":[59,68,194],"whole":[60],"genome":[61],"sequence,":[62],"which":[63],"directly":[64],"calls":[65],"into":[66],"question":[67],"ability":[69],"to":[70,100,118,171],"fine-map":[71,120],"a":[72,153,169,180,275],"locus":[73],"by":[74],"properly":[75],"weighting":[76],"the":[77,86,110,235],"effects":[78,111,175,206],"of":[79,112,156,182],"onto":[81,176],"expression.":[83],"Here,":[84],"using":[85],"state-of-the-art":[87],"model":[89,258],"AlphaGenome,":[90],"we":[91,185],"systematically":[92],"compared":[93],"predicted":[94],"effect":[95,133,242],"sizes":[96],"fine-mapped":[98],"eQTLs":[99,121],"nearby":[101],"non-causal":[103],"finding":[105],"that":[106,130,168,187,254,270],"AlphaGenome":[107],"pervasively":[108,223],"underestimates":[109],"most":[113,123,225,233,239],"fails":[117],"successfully":[119],"in":[122],"reason.":[127],"We":[128],"show":[129],"misdirected":[131],"variant":[132,174,241,272],"predictions":[134,243,253,263],"negative":[136],"cross-individual":[137],"correlations,":[138],"widely":[139],"cited":[140],"as":[141],"major":[142],"challenges":[143],"facing":[144,278],"modeling,":[147],"not":[149],"egregious":[150],"errors":[151],"but":[152],"chance":[154],"consequence":[155],"weak,":[157],"noisy":[158],"attributions":[159],"when":[160,204,213],"underestimated.":[164],"Our":[165,267],"results":[166,211,268],"suggest":[167],"failure":[170],"detect":[172],"local":[173,205,288],"enhancer":[177],"activity":[178,289],"is":[179,274],"cause":[181],"underestimation.":[183],"Additionally,":[184],"find":[186],"underestimated":[188],"enriched":[191,246],"far":[192],"target":[195],"gene,":[196],"suggesting":[197,260],"inadequate":[198],"enhancer-gene":[199,292],"linking":[200],"causes":[201],"underestimation":[202,273],"even":[203],"well-detected.":[208],"Finally,":[209],"our":[210],"clarify":[212],"reliable":[217],"objectives:":[220],"while":[221],"underestimate":[224],"variants,":[227],"demonstrating":[228],"limited":[229],"utility":[231],"loci,":[234],"top":[236],"\u223c":[237],"0.1%":[238],"prominent":[240],"strongly":[245],"directionally":[251],"correct":[252],"consistent":[256],"across":[257],"replicates,":[259],"extremely":[261],"strong":[262],"broadly":[265],"trustworthy.":[266],"demonstrate":[269],"core":[276],"issue":[277],"predictors,":[281],"future":[283],"improvements":[284],"dependent":[285],"on":[286],"better":[287],"detection":[290],"linking.":[293]},"counts_by_year":[{"year":2026,"cited_by_count":4}],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2026-09-12T00:00:00"}
