{"id":"https://openalex.org/W7225203115","doi":"https://doi.org/10.64898/2026.10.29.762447","title":"Unsupervised prioritization of gene-regulatory variants with isolation forests","display_name":"Unsupervised prioritization of gene-regulatory variants with isolation forests","publication_year":2026,"publication_date":"2026-11-03","ids":{"openalex":"https://openalex.org/W7225203115","doi":"https://doi.org/10.64898/2026.10.29.762447"},"language":"en","primary_location":{"id":"doi:10.64898/2026.10.29.762447","doi":"https://doi.org/10.64898/2026.10.29.762447","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.29.762447","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/11/03/2026.10.29.762447.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","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/11/03/2026.10.29.762447.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065118104","display_name":"Andreas W. Schmidt","orcid":"https://orcid.org/0000-0001-5609-290X","observed_orcids":["https://orcid.org/0000-0001-5609-290X"]},"institutions":[{"id":"https://openalex.org/I8087733","display_name":"University of T\u00fcbingen","ror":"https://ror.org/03a1kwz48","country_code":"DE","type":"education","lineage":["https://openalex.org/I8087733"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Andreas W. Schmidt","raw_affiliation_strings":["Institute of Medical Genetics and Applied Genomics, University of Tuebingen, Tuebingen, Germany.;"],"raw_orcid":"https://orcid.org/0000-0001-5609-290X","affiliations":[{"raw_affiliation_string":"Institute of Medical Genetics and Applied Genomics, University of Tuebingen, Tuebingen, Germany.;","institution_ids":["https://openalex.org/I8087733"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056862255","display_name":"Jonas Rosendahl","orcid":"https://orcid.org/0000-0003-4513-0506","observed_orcids":["https://orcid.org/0000-0003-4513-0506"]},"institutions":[{"id":"https://openalex.org/I68956291","display_name":"Martin Luther University Halle-Wittenberg","ror":"https://ror.org/05gqaka33","country_code":"DE","type":"education","lineage":["https://openalex.org/I68956291"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jonas Rosendahl","raw_affiliation_strings":["Department of Internal Medicine I, University Medicine Halle (UMH), Martin Luther University Halle-Wittenberg (MLU), Halle (Saale), Germany"],"raw_orcid":"https://orcid.org/0000-0003-4513-0506","affiliations":[{"raw_affiliation_string":"Department of Internal Medicine I, University Medicine Halle (UMH), Martin Luther University Halle-Wittenberg (MLU), Halle (Saale), Germany","institution_ids":["https://openalex.org/I68956291"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009696834","display_name":"Helmut Laumen","orcid":"https://orcid.org/0000-0002-5885-5242","observed_orcids":["https://orcid.org/0000-0002-5885-5242"]},"institutions":[{"id":"https://openalex.org/I68956291","display_name":"Martin Luther University Halle-Wittenberg","ror":"https://ror.org/05gqaka33","country_code":"DE","type":"education","lineage":["https://openalex.org/I68956291"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Helmut Laumen","raw_affiliation_strings":["Department of Internal Medicine I, University Medicine Halle (UMH), Martin Luther University Halle-Wittenberg (MLU), Halle (Saale), Germany"],"raw_orcid":"https://orcid.org/0000-0002-5885-5242","affiliations":[{"raw_affiliation_string":"Department of Internal Medicine I, University Medicine Halle (UMH), Martin Luther University Halle-Wittenberg (MLU), Halle (Saale), Germany","institution_ids":["https://openalex.org/I68956291"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088012592","display_name":"Stephan Ossowski","orcid":"https://orcid.org/0000-0002-7416-9568","observed_orcids":["https://orcid.org/0000-0002-7416-9568","https://orcid.org/0000-0002-2094-5592"]},"institutions":[{"id":"https://openalex.org/I8087733","display_name":"University of T\u00fcbingen","ror":"https://ror.org/03a1kwz48","country_code":"DE","type":"education","lineage":["https://openalex.org/I8087733"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Stephan Ossowski","raw_affiliation_strings":["Institute of Medical Genetics and Applied Genomics, University of Tuebingen, Tuebingen, Germany.;"],"raw_orcid":"https://orcid.org/0000-0002-7416-9568","affiliations":[{"raw_affiliation_string":"Institute of Medical Genetics and Applied Genomics, University of Tuebingen, Tuebingen, Germany.;","institution_ids":["https://openalex.org/I8087733"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5088012592"],"corresponding_institution_ids":["https://openalex.org/I8087733"],"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/T10261","display_name":"Genetic Associations and Epidemiology","score":0.8999000191688538,"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":0.8999000191688538,"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":0.06400000303983688,"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":0.006000000052154064,"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":0.890999972820282},{"id":"https://openalex.org/keywords/isolation-forest","display_name":"Isolation Forest","score":0.9070000052452087},{"id":"https://openalex.org/keywords/enformer","display_name":"Enformer","score":0.8970000147819519},{"id":"https://openalex.org/keywords/transcription-factor-binding-sites","display_name":"transcription factor binding sites","score":0.7760000228881836},{"id":"https://openalex.org/keywords/non-coding-variants","display_name":"non-coding variants","score":0.75},{"id":"https://openalex.org/keywords/transcription-factor-binding-motifs","display_name":"transcription factor binding motifs","score":0.5490000247955322},{"id":"https://openalex.org/keywords/linkage-disequilibrium","display_name":"linkage disequilibrium","score":0.7099999785423279},{"id":"https://openalex.org/keywords/causal-variant-identification","display_name":"causal variant identification","score":0.5849999785423279}],"concepts":[{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.6944000124931335},{"id":"https://openalex.org/C168393362","wikidata":"https://www.wikidata.org/wiki/Q5421706","display_name":"Expression quantitative trait loci","level":5,"score":0.625},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.5702000260353088},{"id":"https://openalex.org/C35605836","wikidata":"https://www.wikidata.org/wiki/Q2064311","display_name":"Linkage disequilibrium","level":5,"score":0.5461000204086304},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4878000020980835},{"id":"https://openalex.org/C2777615720","wikidata":"https://www.wikidata.org/wiki/Q11888847","display_name":"Prioritization","level":2,"score":0.4341999888420105},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.4174000024795532},{"id":"https://openalex.org/C3662595","wikidata":"https://www.wikidata.org/wiki/Q5205743","display_name":"DNA binding site","level":5,"score":0.4108999967575073},{"id":"https://openalex.org/C106208931","wikidata":"https://www.wikidata.org/wiki/Q1098876","display_name":"Genome-wide association study","level":5,"score":0.4065000116825104},{"id":"https://openalex.org/C81941488","wikidata":"https://www.wikidata.org/wiki/Q853421","display_name":"Quantitative trait locus","level":3,"score":0.4032999873161316},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39070001244544983},{"id":"https://openalex.org/C186413461","wikidata":"https://www.wikidata.org/wiki/Q744727","display_name":"Genetic association","level":5,"score":0.3885999917984009},{"id":"https://openalex.org/C106934330","wikidata":"https://www.wikidata.org/wiki/Q1971873","display_name":"Trait","level":2,"score":0.38839998841285706},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.38019999861717224},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.37619999051094055},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.36820000410079956},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36169999837875366},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.35530000925064087},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.31360000371932983},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.31139999628067017},{"id":"https://openalex.org/C2775941552","wikidata":"https://www.wikidata.org/wiki/Q25212305","display_name":"Isolation (microbiology)","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C199216141","wikidata":"https://www.wikidata.org/wiki/Q4995178","display_name":"Conserved sequence","level":4,"score":0.25519999861717224},{"id":"https://openalex.org/C67339327","wikidata":"https://www.wikidata.org/wiki/Q1502576","display_name":"Gene regulatory network","level":4,"score":0.2533999979496002}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.10.29.762447","doi":"https://doi.org/10.64898/2026.10.29.762447","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.29.762447","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/11/03/2026.10.29.762447.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:10.64898/2026.10.29.762447","doi":"https://doi.org/10.64898/2026.10.29.762447","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.29.762447","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/11/03/2026.10.29.762447.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":[{"score":0.46810001134872437,"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3"}],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7225203115.pdf","grobid_xml":"https://content.openalex.org/works/W7225203115.grobid-xml"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W2899638272","https://openalex.org/W4399649598","https://openalex.org/W7131430872","https://openalex.org/W7213745552"],"related_works":["https://openalex.org/W2949204199","https://openalex.org/W7170068868","https://openalex.org/W3168560461","https://openalex.org/W3019163011","https://openalex.org/W2897905267","https://openalex.org/W1905157184","https://openalex.org/W1973064777","https://openalex.org/W4407265021","https://openalex.org/W4399708950","https://openalex.org/W3096179303"],"abstract_inverted_index":{"Most":[0],"common":[1,134,195],"variants":[2,160,179,196],"occur":[3],"in":[4,148,163],"non-coding":[5],"genomic":[6],"regions.":[7],"Numerous":[8],"expression":[9],"quantitative":[10],"trait":[11],"loci":[12,29],"(eQTLs)":[13],"can":[14],"influence":[15],"nearby":[16],"gene":[17],"expression.":[18],"Across":[19],"diverse":[20,68],"traits":[21],"and":[22,74,84,151,172,197],"diseases,":[23],"many":[24],"genome-wide":[25],"association":[26],"study":[27],"(GWAS)":[28],"have":[30],"been":[31],"shown":[32],"to":[33,114],"colocalize":[34],"with":[35,141],"eQTLs,":[36],"supporting":[37],"gene-regulatory":[38,86,129,152],"causal":[39,50],"mechanisms.":[40],"However,":[41,90],"linkage":[42],"disequilibrium":[43],"(LD)":[44],"obscures":[45],"the":[46,49,64,91,116,119,174,185],"identification":[47],"of":[48,67,99,176],"variant(s),":[51],"necessitating":[52],"prioritization":[53,60],"by":[54],"functional":[55],"annotations.":[56],"Previously":[57],"published":[58],"variant":[59],"tools":[61,82],"relied":[62],"on":[63,111],"machine-learning-based":[65],"combination":[66],"feature":[69],"types":[70],"like":[71],"evolutionary":[72],"conservation":[73],"chromatin":[75],"information,":[76],"whereas":[77],"more":[78],"recent":[79],"deep":[80,123],"learning":[81,124],"learn":[83],"describe":[85],"DNA":[87],"sequence":[88],"grammar.":[89],"latter":[92],"approaches":[93],"often":[94],"generate":[95],"a":[96,105,127],"large":[97],"number":[98],"scores":[100],"per":[101],"variant.":[102,135],"We":[103,155],"designed":[104],"novel":[106,137],"unsupervised":[107],"machine-learning":[108],"approach":[109,138],"based":[110],"isolation":[112,142],"forests":[113,143],"integrate":[115],"predictions":[117,190],"from":[118],"broadly":[120],"used":[121],"Enformer":[122],"model":[125],"into":[126],"single":[128],"predictive":[130],"score":[131],"for":[132,193],"each":[133],"Our":[136],"eQTL":[139],"prediction":[140],"(eQIF)":[144],"demonstrates":[145],"strong":[146],"performance":[147],"predicting":[149],"eQTLs":[150],"GWAS":[153],"variants.":[154],"show":[156],"that":[157,173],"top":[158,177],"eQIF":[159,178,189],"are":[161,191],"located":[162],"evolutionarily":[164],"conserved":[165],"transcription":[166],"factor":[167],"binding":[168],"site":[169],"(TFBS)":[170],"footprints,":[171],"frequency":[175],"within":[180],"overrepresented":[181],"TFBS":[182],"motifs":[183],"recapitulates":[184],"motif":[186],"information":[187],"content.":[188],"precomputed":[192],"9,431,969":[194],"publicly":[198],"available.":[199]},"counts_by_year":[],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2026-11-04T00:00:00"}
