{"id":"https://openalex.org/W7204118510","doi":"https://doi.org/10.64898/2026.08.20.745945","title":"Trust-Aware Sequence-to-Function Modelling in Regulatory Genomics","display_name":"Trust-Aware Sequence-to-Function Modelling in Regulatory Genomics","publication_year":2026,"publication_date":"2026-08-24","ids":{"openalex":"https://openalex.org/W7204118510","doi":"https://doi.org/10.64898/2026.08.20.745945"},"language":"en","primary_location":{"id":"doi:10.64898/2026.08.20.745945","doi":"https://doi.org/10.64898/2026.08.20.745945","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.08.20.745945","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/08/24/2026.08.20.745945.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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"parent_works":[],"lineage":["https://openalex.org/W7204118510"],"child_works_count":0,"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/2026/08/24/2026.08.20.745945.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000533004","display_name":"Abdulmujeeb T. Onawole","orcid":"https://orcid.org/0000-0002-4967-7245","observed_orcids":["https://orcid.org/0000-0002-4967-7245"]},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]},{"id":"https://openalex.org/I4405277047","display_name":"Institute for Molecular Bioscience","ror":"https://ror.org/018kjjj71","country_code":"AU","type":"facility","lineage":["https://openalex.org/I165143802","https://openalex.org/I4405277047"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Abdulmujeeb T. Onawole","raw_affiliation_strings":["Institute for Molecular Bioscience, The University of Queensland, Brisbane, QLD 4072, Australia"],"raw_orcid":"https://orcid.org/0000-0002-4967-7245","affiliations":[{"raw_affiliation_string":"Institute for Molecular Bioscience, The University of Queensland, Brisbane, QLD 4072, Australia","institution_ids":["https://openalex.org/I165143802","https://openalex.org/I4405277047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004287076","display_name":"Sulaimon Basiru","orcid":"https://orcid.org/0000-0001-9896-9343","observed_orcids":["https://orcid.org/0000-0001-9896-9343"]},"institutions":[{"id":"https://openalex.org/I4210131560","display_name":"Universit\u00e9 Mohammed VI Polytechnique","ror":"https://ror.org/03xc55g68","country_code":"MA","type":"education","lineage":["https://openalex.org/I4210131560"]}],"countries":["MA"],"is_corresponding":false,"raw_author_name":"Sulaimon Basiru","raw_affiliation_strings":["African Genome Center, University Mohammed VI Polytechnic (UM6P), Ben Guerir, Morocco"],"raw_orcid":"https://orcid.org/0000-0001-9896-9343","affiliations":[{"raw_affiliation_string":"African Genome Center, University Mohammed VI Polytechnic (UM6P), Ben Guerir, Morocco","institution_ids":["https://openalex.org/I4210131560"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059992342","display_name":"Musafau Oloyede Sanni","orcid":"https://orcid.org/0000-0002-3389-4851","observed_orcids":["https://orcid.org/0000-0002-3389-4851"]},"institutions":[{"id":"https://openalex.org/I28022161","display_name":"King Saud University","ror":"https://ror.org/02f81g417","country_code":"SA","type":"education","lineage":["https://openalex.org/I28022161"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Musafau Oloyede Sanni","raw_affiliation_strings":["Fetal Disease Programming Research Laboratory, Department of Zoology, King Saud University, Riyadh, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0002-3389-4851","affiliations":[{"raw_affiliation_string":"Fetal Disease Programming Research Laboratory, Department of Zoology, King Saud University, Riyadh, Saudi Arabia","institution_ids":["https://openalex.org/I28022161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147977032","display_name":"Monsuru Aiyedun","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Monsuru Aiyedun","raw_affiliation_strings":["Center for the Advanced Study of Drug Action, Department of Chemistry, Stony Brook University, Stony Brook, NY, 11794, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for the Advanced Study of Drug Action, Department of Chemistry, Stony Brook University, Stony Brook, NY, 11794, USA","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5116250598","display_name":"Ridwan Sulaimon","orcid":"https://orcid.org/0009-0002-4244-661X","observed_orcids":["https://orcid.org/0009-0002-4244-661X"]},"institutions":[{"id":"https://openalex.org/I60158472","display_name":"Concordia University","ror":"https://ror.org/0420zvk78","country_code":"CA","type":"education","lineage":["https://openalex.org/I60158472"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ridwan Sulaimon","raw_affiliation_strings":["Centre for Research in Molecular Modeling (CERMM) and Department of Chemistry and Biochemistry, Concordia University, Montreal, QC H4B 1R6, Canada"],"raw_orcid":"https://orcid.org/0009-0002-4244-661X","affiliations":[{"raw_affiliation_string":"Centre for Research in Molecular Modeling (CERMM) and Department of Chemistry and Biochemistry, Concordia University, Montreal, QC H4B 1R6, Canada","institution_ids":["https://openalex.org/I60158472"]}]}],"institutions":[],"countries_distinct_count":5,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5000533004"],"corresponding_institution_ids":["https://openalex.org/I165143802","https://openalex.org/I4405277047"],"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/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.8895999789237976,"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/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.8895999789237976,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.021299999207258224,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.007600000128149986,"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/chromatin-accessibility-prediction","display_name":"chromatin accessibility prediction","score":0.7760000228881836},{"id":"https://openalex.org/keywords/regulatory-genomics","display_name":"regulatory genomics","score":0.6039999723434448},{"id":"https://openalex.org/keywords/explainable-ai","display_name":"explainable AI","score":0.7120000123977661},{"id":"https://openalex.org/keywords/model-credibility","display_name":"model credibility","score":0.671999990940094},{"id":"https://openalex.org/keywords/non-coding-variants","display_name":"non-coding variants","score":0.8069999814033508},{"id":"https://openalex.org/keywords/saturation-mutagenesis","display_name":"saturation mutagenesis","score":0.9580000042915344},{"id":"https://openalex.org/keywords/k562-cells","display_name":"K562 cells","score":0.7789999842643738},{"id":"https://openalex.org/keywords/atac-seq","display_name":"ATAC-seq","score":0.7149999737739563}],"concepts":[{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4440000057220459},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.43860000371932983},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.41440001130104065},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4124000072479248},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4007999897003174},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38269999623298645},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3815999925136566},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3750999867916107},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3652999997138977},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3546000123023987},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.34700000286102295},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.3393999934196472},{"id":"https://openalex.org/C40696583","wikidata":"https://www.wikidata.org/wiki/Q989120","display_name":"Type I and type II errors","level":2,"score":0.3361000120639801},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.32199999690055847},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.3188000023365021},{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.3061000108718872},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.30160000920295715},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.2971000075340271},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2939999997615814},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.28700000047683716},{"id":"https://openalex.org/C42747912","wikidata":"https://www.wikidata.org/wiki/Q1048447","display_name":"Multiplicative function","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27459999918937683},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2727000117301941},{"id":"https://openalex.org/C30481170","wikidata":"https://www.wikidata.org/wiki/Q37748","display_name":"Chromosome","level":3,"score":0.26649999618530273},{"id":"https://openalex.org/C36382193","wikidata":"https://www.wikidata.org/wiki/Q7068966","display_name":"Null model","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C143299363","wikidata":"https://www.wikidata.org/wiki/Q900584","display_name":"Attribution","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C197947376","wikidata":"https://www.wikidata.org/wiki/Q5155608","display_name":"Comparability","level":2,"score":0.2565999925136566},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.25440001487731934},{"id":"https://openalex.org/C183905921","wikidata":"https://www.wikidata.org/wiki/Q1038757","display_name":"Multiple comparisons problem","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.08.20.745945","doi":"https://doi.org/10.64898/2026.08.20.745945","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.08.20.745945","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/08/24/2026.08.20.745945.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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.08.20.745945","doi":"https://doi.org/10.64898/2026.08.20.745945","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.08.20.745945","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/08/24/2026.08.20.745945.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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320984","display_name":"University of Queensland","ror":"https://ror.org/00rqy9422"},{"id":"https://openalex.org/F4320336771","display_name":"Research Computing Centre, University of Queensland","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204118510.pdf","grobid_xml":"https://content.openalex.org/works/W7204118510.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W130020229","https://openalex.org/W1901451661","https://openalex.org/W1972978214","https://openalex.org/W2051271918","https://openalex.org/W2198606573","https://openalex.org/W2259938310","https://openalex.org/W2345512687","https://openalex.org/W2553600202","https://openalex.org/W2944831967","https://openalex.org/W2949676527","https://openalex.org/W2967059818","https://openalex.org/W3046238651","https://openalex.org/W3163257742","https://openalex.org/W3203588026","https://openalex.org/W4213140257","https://openalex.org/W4252684946","https://openalex.org/W4280563114","https://openalex.org/W4300862723","https://openalex.org/W4376132682","https://openalex.org/W4392026531","https://openalex.org/W4401224836","https://openalex.org/W4402581506","https://openalex.org/W4403338304","https://openalex.org/W4405829527","https://openalex.org/W4406178430","https://openalex.org/W4406385639","https://openalex.org/W4411747924","https://openalex.org/W4415208966","https://openalex.org/W4416575616","https://openalex.org/W7125967877","https://openalex.org/W7151931292","https://openalex.org/W7163911915","https://openalex.org/W7171362730","https://openalex.org/W7171771040","https://openalex.org/W7196933469","https://openalex.org/W7196936241","https://openalex.org/W7201884562"],"related_works":["https://openalex.org/W7168205287","https://openalex.org/W7171362730","https://openalex.org/W7170865318","https://openalex.org/W4390139716","https://openalex.org/W4285012429","https://openalex.org/W7162571144","https://openalex.org/W7125425781","https://openalex.org/W4406123215","https://openalex.org/W4411701336"],"abstract_inverted_index":{"Abstract":[0],"Objective":[1],"Sequence-to-function":[2],"models":[3],"increasingly":[4],"predict":[5],"regulatory":[6,265],"activity,":[7],"such":[8],"as":[9],"chromatin":[10],"accessibility,":[11],"directly":[12],"from":[13,49],"DNA":[14],"sequence,":[15],"and":[16,66,84,99,113,126,134,174,213,220,232,234,251,258,287],"are":[17,223,290],"used":[18],"to":[19,228,310],"interpret":[20],"non-coding":[21],"genetic":[22],"variation.":[23],"Standard":[24],"accuracy":[25,316],"metrics,":[26],"computed":[27],"over":[28,154],"a":[29,54,69,102,155,196,296,303,313],"held-out":[30,103],"set":[31,106],"of":[32,152,274,295],"genomic":[33],"regions,":[34],"do":[35],"not":[36,224],"establish":[37],"whether":[38,53],"an":[39,129],"individual":[40],"prediction":[41,120,314],"remains":[42],"reliable":[43],"once":[44],"the":[45,139,181,244],"input":[46],"sequence":[47,288],"departs":[48],"that":[50,264],"set,":[51],"nor":[52],"model\u2019s":[55],"attribution-based":[56],"explanation":[57,285],"is":[58],"biologically":[59],"grounded":[60],"rather":[61],"than":[62,169,272,315],"coincidental.":[63],"We":[64],"develop":[65],"evaluate":[67],"RegTrust-XAI,":[68],"trust-aware":[70],"framework":[71],"separating":[72],"these":[73],"questions":[74],"using":[75],"three":[76],"inference-time":[77],"signals:":[78],"ensemble":[79,91,144],"consensus,":[80],"motif-grounded":[81],"attribution":[82,175],"coherence,":[83,112],"applicability-domain":[85,114,216],"distance.":[86],"Methods":[87],"A":[88,204],"five-model":[89],"convolutional":[90],"was":[92,208,230],"trained":[93],"on":[94,101,312],"517,790":[95],"K562":[96],"ATAC-seq":[97],"windows":[98],"evaluated":[100],"chromosome":[104],"test":[105],"(chr8/chr9,":[107],"n":[108],"=":[109,148,191,256],"42,844).":[110],"Consensus,":[111],"distance":[115,194,202],"were":[116,163,267],"each":[117,300],"tested":[118],"against":[119,128],"error,":[121],"alongside":[122],"complementary":[123],"sequence-novelty":[124],"analyses":[125],"validation":[127],"independent":[130],"lentiMPRA":[131,229],"reporter":[132],"assay":[133],"saturation-mutagenesis":[135,241],"MPRA":[136],"data":[137],"at":[138,243,247],"PKLR":[140,245],"promoter.":[141],"Results":[142],"The":[143],"reached":[145],"Spearman":[146],"\u03c1":[147,255],"0.782,":[149],"with":[150,211,215,239,270],"skill":[151],"0.328":[153],"constant-value":[156],"null":[157],"predictor.":[158],"High-consensus":[159],"predictions":[160,171],"(Scenarios":[161,172],"A+B)":[162],"consistently":[164],"enriched":[165],"for":[166,307],"lower":[167],"error":[168,179,186,198,212],"low-consensus":[170],"C+D),":[173],"coherence":[176],"further":[177,262],"separated":[178],"within":[180],"high-consensus":[182],"population":[183],"(mean":[184],"absolute":[185],"0.396":[187],"versus":[188],"0.435,":[189],"p":[190],"9.6e-10).":[192],"Applicability-domain":[193],"showed":[195,263],"monotonic":[197],"gradient":[199],"across":[200],"six":[201],"bands.":[203],"4-mer":[205],"composition-divergence":[206],"metric":[207],"negatively":[209],"associated":[210],"anti-correlated":[214],"distance,":[217],"so":[218],"composition-based":[219],"model-relevant":[221],"novelty":[222,289],"equivalent.":[225],"Attribution":[226],"transfer":[227],"assay-":[231],"subgroup-dependent,":[233],"predicted":[235],"allele-substitution":[236],"effects":[237,242],"correlated":[238],"measured":[240],"promoter":[246],"both":[248],"24":[249],"h":[250,253],"48":[252],"(":[254],"0.227":[257],"0.235).":[259],"Motif-specific":[260],"perturbation":[261],"attributions":[266],"strongly":[268],"context-dependent,":[269],"more":[271,304],"90%":[273],"multi-instance":[275],"motif":[276],"modules":[277],"exhibiting":[278],"superadditive":[279],"joint":[280],"effects.":[281],"Conclusions":[282],"Prediction":[283],"reliability,":[284],"validity,":[286],"related":[291],"but":[292],"distinct":[293],"properties":[294],"sequence-to-function":[297],"model.":[298],"Evaluating":[299],"explicitly":[301],"gives":[302],"complete":[305],"basis":[306],"deciding":[308],"when":[309],"act":[311],"alone.":[317]},"counts_by_year":[],"updated_date":"2026-11-14T11:04:58.165337","created_date":"2026-08-25T00:00:00"}