{"id":"https://openalex.org/W7203932464","doi":"https://doi.org/10.64898/2026.08.17.744355","title":"RegFM: an interpretable context-aware foundation model for human transcriptional regulation","display_name":"RegFM: an interpretable context-aware foundation model for human transcriptional regulation","publication_year":2026,"publication_date":"2026-08-21","ids":{"openalex":"https://openalex.org/W7203932464","doi":"https://doi.org/10.64898/2026.08.17.744355"},"language":"en","primary_location":{"id":"doi:10.64898/2026.08.17.744355","doi":"https://doi.org/10.64898/2026.08.17.744355","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.08.17.744355","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/08/21/2026.08.17.744355.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-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"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/2026/08/21/2026.08.17.744355.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080423090","display_name":"Zijing Gao","orcid":"https://orcid.org/0009-0005-7269-0244","observed_orcids":["https://orcid.org/0009-0005-7269-0244"]},"institutions":[{"id":"https://openalex.org/I4405271667","display_name":"Beijing National Research Center for Information Science and Technology","ror":"https://ror.org/02tcm9e24","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4405271667"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zijing Gao","raw_affiliation_strings":["Ministry of Education Key Laboratory of Bioinformatics, Bioinformatics Division at the Beijing National Research Center for Information Science and Technology, Center for Synthetic and Systems Biology, Department of Automation, Tsinghua University, Beijing 100084, China;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ministry of Education Key Laboratory of Bioinformatics, Bioinformatics Division at the Beijing National Research Center for Information Science and Technology, Center for Synthetic and Systems Biology, Department of Automation, Tsinghua University, Beijing 100084, China;","institution_ids":["https://openalex.org/I4405271667","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100984452","display_name":"Yining Sun","orcid":"https://orcid.org/0009-0004-7806-4992","observed_orcids":["https://orcid.org/0009-0004-7806-4992"]},"institutions":[{"id":"https://openalex.org/I4405271667","display_name":"Beijing National Research Center for Information Science and Technology","ror":"https://ror.org/02tcm9e24","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4405271667"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yining Sun","raw_affiliation_strings":["Ministry of Education Key Laboratory of Bioinformatics, Bioinformatics Division at the Beijing National Research Center for Information Science and Technology, Center for Synthetic and Systems Biology, Department of Automation, Tsinghua University, Beijing 100084, China;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ministry of Education Key Laboratory of Bioinformatics, Bioinformatics Division at the Beijing National Research Center for Information Science and Technology, Center for Synthetic and Systems Biology, Department of Automation, Tsinghua University, Beijing 100084, China;","institution_ids":["https://openalex.org/I4405271667","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138078070","display_name":"Haochen Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haochen Wang","raw_affiliation_strings":["Department of Biostatistics, Yale University, New Haven, CT 06510, USA;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biostatistics, Yale University, New Haven, CT 06510, USA;","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135075802","display_name":"Rui Jiang","orcid":"https://orcid.org/0000-0002-3989-318X","observed_orcids":["https://orcid.org/0000-0002-3989-318X","https://orcid.org/0000-0002-7533-3753","https://orcid.org/0009-0004-4568-5565","https://orcid.org/0009-0006-1721-3952"]},"institutions":[{"id":"https://openalex.org/I4405271667","display_name":"Beijing National Research Center for Information Science and Technology","ror":"https://ror.org/02tcm9e24","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4405271667"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Jiang","raw_affiliation_strings":["Ministry of Education Key Laboratory of Bioinformatics, Bioinformatics Division at the Beijing National Research Center for Information Science and Technology, Center for Synthetic and Systems Biology, Department of Automation, Tsinghua University, Beijing 100084, China;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ministry of Education Key Laboratory of Bioinformatics, Bioinformatics Division at the Beijing National Research Center for Information Science and Technology, Center for Synthetic and Systems Biology, Department of Automation, Tsinghua University, Beijing 100084, China;","institution_ids":["https://openalex.org/I4405271667","https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100393711","display_name":"Qiao Liu","orcid":"https://orcid.org/0000-0002-9781-3360","observed_orcids":["https://orcid.org/0000-0002-9781-3360"]},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Qiao Liu","raw_affiliation_strings":["Department of Biostatistics, Yale University, New Haven, CT 06510, USA;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biostatistics, Yale University, New Haven, CT 06510, USA;","institution_ids":["https://openalex.org/I32971472"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100393711"],"corresponding_institution_ids":["https://openalex.org/I32971472"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"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":0.9839000105857849,"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":0.9839000105857849,"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/T10621","display_name":"Gene Regulatory Network Analysis","score":0.010599999688565731,"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/T11289","display_name":"Single-cell and spatial transcriptomics","score":0.000699999975040555,"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/transcriptional-regulation","display_name":"transcriptional regulation","score":0.9940000176429749},{"id":"https://openalex.org/keywords/cis-regulatory-elements","display_name":"cis-regulatory elements","score":0.9380000233650208},{"id":"https://openalex.org/keywords/trans-acting-regulators","display_name":"trans-acting regulators","score":0.8989999890327454},{"id":"https://openalex.org/keywords/transcription-factors","display_name":"transcription factors","score":0.9599999785423279},{"id":"https://openalex.org/keywords/chromatin-regulators","display_name":"chromatin regulators","score":0.9980000257492065},{"id":"https://openalex.org/keywords/gene-expression-prediction","display_name":"gene expression prediction","score":0.7419999837875366},{"id":"https://openalex.org/keywords/bivalent-promoters","display_name":"bivalent promoters","score":0.9629999995231628},{"id":"https://openalex.org/keywords/dose-sensitivity","display_name":"dosage sensitivity","score":0.8629999756813049},{"id":"https://openalex.org/keywords/perturbation-response-prediction","display_name":"perturbation response prediction","score":0.8600000143051147},{"id":"https://openalex.org/keywords/model-interpretability","display_name":"model interpretability","score":0.671999990940094},{"id":"https://openalex.org/keywords/single-cell-transcriptomics","display_name":"single-cell transcriptomics","score":0.7480000257492065},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.6269999742507935}],"concepts":[{"id":"https://openalex.org/C27153228","wikidata":"https://www.wikidata.org/wiki/Q3787274","display_name":"Transcriptional regulation","level":4,"score":0.6704999804496765},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5907999873161316},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.5583000183105469},{"id":"https://openalex.org/C165864922","wikidata":"https://www.wikidata.org/wiki/Q411391","display_name":"Regulation of gene expression","level":3,"score":0.5540000200271606},{"id":"https://openalex.org/C21592294","wikidata":"https://www.wikidata.org/wiki/Q3238407","display_name":"Regulatory sequence","level":4,"score":0.5038999915122986},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5016000270843506},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.4975000023841858},{"id":"https://openalex.org/C83640560","wikidata":"https://www.wikidata.org/wiki/Q180951","display_name":"Chromatin","level":3,"score":0.48179998993873596},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.45579999685287476},{"id":"https://openalex.org/C67339327","wikidata":"https://www.wikidata.org/wiki/Q1502576","display_name":"Gene regulatory network","level":4,"score":0.4072999954223633},{"id":"https://openalex.org/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"score":0.4052000045776367},{"id":"https://openalex.org/C190796033","wikidata":"https://www.wikidata.org/wiki/Q1093165","display_name":"Cis-regulatory module","level":5,"score":0.385699987411499},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.3774999976158142},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.36250001192092896},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.3555999994277954},{"id":"https://openalex.org/C152662350","wikidata":"https://www.wikidata.org/wiki/Q815297","display_name":"Systems biology","level":2,"score":0.3467999994754791},{"id":"https://openalex.org/C101762097","wikidata":"https://www.wikidata.org/wiki/Q224093","display_name":"Promoter","level":4,"score":0.29980000853538513},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.29919999837875366},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.2948000133037567},{"id":"https://openalex.org/C2775930736","wikidata":"https://www.wikidata.org/wiki/Q7309708","display_name":"Regulatory state","level":3,"score":0.289000004529953},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.2874000072479248},{"id":"https://openalex.org/C162317418","wikidata":"https://www.wikidata.org/wiki/Q252857","display_name":"Transcriptome","level":4,"score":0.28630000352859497},{"id":"https://openalex.org/C197077220","wikidata":"https://www.wikidata.org/wiki/Q720988","display_name":"Human genome","level":4,"score":0.2838999927043915},{"id":"https://openalex.org/C2992339755","wikidata":"https://www.wikidata.org/wiki/Q3817769","display_name":"Transcriptional activity","level":4,"score":0.2761000096797943},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C47042493","wikidata":"https://www.wikidata.org/wiki/Q265799","display_name":"Human genetics","level":3,"score":0.2703999876976013},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.25949999690055847},{"id":"https://openalex.org/C33498276","wikidata":"https://www.wikidata.org/wiki/Q2138797","display_name":"Regulator gene","level":4,"score":0.25540000200271606}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.08.17.744355","doi":"https://doi.org/10.64898/2026.08.17.744355","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.08.17.744355","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/08/21/2026.08.17.744355.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-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.08.17.744355","doi":"https://doi.org/10.64898/2026.08.17.744355","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.08.17.744355","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/08/21/2026.08.17.744355.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-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1135421935","display_name":null,"funder_award_id":"2025YFC3409300","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G1800556644","display_name":null,"funder_award_id":"2023YFF1204802","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G7432469636","display_name":null,"funder_award_id":"32550616","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8872129737","display_name":null,"funder_award_id":"62273194","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G908290377","display_name":null,"funder_award_id":"62\u2009273\u2009194","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7203932464.pdf","grobid_xml":"https://content.openalex.org/works/W7203932464.grobid-xml"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W2885185669","https://openalex.org/W2964121744","https://openalex.org/W3086105743","https://openalex.org/W4382490702","https://openalex.org/W4383473945"],"related_works":["https://openalex.org/W4409126223","https://openalex.org/W7125698885","https://openalex.org/W4406155921","https://openalex.org/W7165385383","https://openalex.org/W7128321117","https://openalex.org/W7160994374","https://openalex.org/W4403386923","https://openalex.org/W7163166160","https://openalex.org/W2990395719","https://openalex.org/W4400602351"],"abstract_inverted_index":{"Abstract":[0],"Transcriptional":[1],"regulation":[2,62,150],"is":[3],"governed":[4],"by":[5,82],"interactions":[6],"between":[7,66],"cis-regulatory":[8,67,121],"elements":[9],"(CREs)":[10],"and":[11,20,71,78,89,96,126,129,143,151],"trans-acting":[12,72],"regulators":[13,73,80],"in":[14],"a":[15,51,64,112,141],"context-specific":[16],"manner.":[17],"Although":[18],"DNA":[19],"single-cell":[21],"foundation":[22,53],"models":[23],"have":[24],"enabled":[25],"modeling":[26,147],"regulatory":[27,103,157],"biology":[28],"at":[29],"scale,":[30],"most":[31],"represent":[32],"either":[33],"sequence":[34],"or":[35],"cellular":[36,109],"state":[37],"alone,":[38],"limiting":[39],"their":[40],"ability":[41],"to":[42],"capture":[43],"context-dependent":[44,155],"gene":[45,118,156],"regulation.":[46,58],"Here":[47],"we":[48],"present":[49],"RegFM,":[50],"context-aware":[52],"model":[54],"for":[55,146],"human":[56,148],"transcriptional":[57,61,149],"RegFM":[59,100,132,138],"treats":[60],"as":[63,140],"dialogue":[65],"sequences":[68],"(e.g.,":[69,74],"CREs)":[70],"transcription":[75],"factors":[76],"(TFs)":[77],"chromatin":[79],"(CRs))":[81],"coupling":[83],"long-range":[84],"CRE":[85],"representations":[86,104],"with":[87],"TFs":[88],"CRs":[90],"activity.":[91],"Trained":[92],"on":[93],"large-scale":[94],"ENCODE":[95],"CELLxGENE":[97],"transcriptomic":[98],"profiles,":[99],"learns":[101],"gene-centered":[102],"that":[105],"generalize":[106],"across":[107],"unseen":[108],"contexts.":[110],"In":[111],"wide":[113],"range":[114],"of":[115],"tasks,":[116],"including":[117],"expression":[119],"prediction,":[120,131],"element":[122],"annotation,":[123],"bivalent":[124],"promoter":[125],"dosage-sensitivity":[127],"classification,":[128],"perturbation-response":[130],"consistently":[133],"improves":[134],"over":[135],"existing":[136],"methods.":[137],"emerges":[139],"scalable":[142],"interpretable":[144],"framework":[145],"provides":[152],"insights":[153],"into":[154],"programs.":[158]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-08-22T00:00:00"}
