{"id":"https://openalex.org/W7225009835","doi":"https://doi.org/10.64898/2026.10.29.762938","title":"ChAI-Net learns a regulatory code for chromatin co-accessibility","display_name":"ChAI-Net learns a regulatory code for chromatin co-accessibility","publication_year":2026,"publication_date":"2026-10-31","ids":{"openalex":"https://openalex.org/W7225009835","doi":"https://doi.org/10.64898/2026.10.29.762938"},"language":"en","primary_location":{"id":"doi:10.64898/2026.10.29.762938","doi":"https://doi.org/10.64898/2026.10.29.762938","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.29.762938","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/31/2026.10.29.762938.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":"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/2026/10/31/2026.10.29.762938.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5127893427","display_name":"Jodi Lee","orcid":null,"observed_orcids":[]},"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":"Jodi Lee","raw_affiliation_strings":["Gladstone Institute of Data Science and Biotechnology, San Francisco, CA 94158","Tetrad Graduate Program, University of California, San Francisco, San Francisco, CA 94158"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gladstone Institute of Data Science and Biotechnology, San Francisco, CA 94158","institution_ids":["https://openalex.org/I1321430492"]},{"raw_affiliation_string":"Tetrad Graduate Program, University of California, San Francisco, San Francisco, CA 94158","institution_ids":["https://openalex.org/I180670191"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024881367","display_name":"Kaite Zhang","orcid":"https://orcid.org/0000-0003-0050-2791","observed_orcids":["https://orcid.org/0000-0003-0050-2791"]},"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":"Kaite Zhang","raw_affiliation_strings":["Gladstone Institute of Data Science and Biotechnology, San Francisco, CA 94158","Tetrad Graduate Program, University of California, San Francisco, San Francisco, CA 94158"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gladstone Institute of Data Science and Biotechnology, San Francisco, CA 94158","institution_ids":["https://openalex.org/I1321430492"]},{"raw_affiliation_string":"Tetrad Graduate Program, University of California, San Francisco, San Francisco, CA 94158","institution_ids":["https://openalex.org/I180670191"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160278098","display_name":"Ethan Shurberg","orcid":null,"observed_orcids":[]},"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":"Ethan Shurberg","raw_affiliation_strings":["Biological and Medical Informatics Graduate Program, University of California, San Francisco, San Francisco, CA 94158","Gladstone Institute of Data Science and Biotechnology, San Francisco, CA 94158"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Biological and Medical Informatics Graduate Program, University of California, San Francisco, San Francisco, CA 94158","institution_ids":["https://openalex.org/I180670191"]},{"raw_affiliation_string":"Gladstone Institute of Data Science and Biotechnology, San Francisco, CA 94158","institution_ids":["https://openalex.org/I1321430492"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160279367","display_name":"Vijay S. Ramani","orcid":null,"observed_orcids":[]},"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":"Vijay Ramani","raw_affiliation_strings":["Department of Biochemistry & Biophysics, University of California, San Francisco, San Francisco, CA 94158","Gladstone Institute of Data Science and Biotechnology, San Francisco, CA 94158"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biochemistry & Biophysics, University of California, San Francisco, San Francisco, CA 94158","institution_ids":["https://openalex.org/I180670191"]},{"raw_affiliation_string":"Gladstone Institute of Data Science and Biotechnology, San Francisco, CA 94158","institution_ids":["https://openalex.org/I1321430492"]}]},{"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"]},{"id":"https://openalex.org/I4210100286","display_name":"Chan Zuckerberg Biohub San Francisco","ror":"https://ror.org/00knt4f32","country_code":"US","type":"facility","lineage":["https://openalex.org/I180670191","https://openalex.org/I4210100286","https://openalex.org/I4210121800","https://openalex.org/I95457486","https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Katherine S. Pollard","raw_affiliation_strings":["Biohub, San Francisco, CA 94158","Department of Epidemiology & Biostatistics, University of California, San Francisco, San Francisco, CA 94158","Gladstone Institute of Data Science and Biotechnology, San Francisco, CA 94158"],"raw_orcid":"https://orcid.org/0000-0002-9870-6196","affiliations":[{"raw_affiliation_string":"Biohub, San Francisco, CA 94158","institution_ids":["https://openalex.org/I4210100286"]},{"raw_affiliation_string":"Department of Epidemiology & Biostatistics, University of California, San Francisco, San Francisco, CA 94158","institution_ids":["https://openalex.org/I180670191"]},{"raw_affiliation_string":"Gladstone Institute of Data Science and Biotechnology, San Francisco, CA 94158","institution_ids":["https://openalex.org/I1321430492"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5005062415"],"corresponding_institution_ids":["https://openalex.org/I1321430492","https://openalex.org/I180670191","https://openalex.org/I4210100286"],"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":0.9980000257492065,"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":0.9980000257492065,"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/T12820","display_name":"Chromatin Remodeling and Cancer","score":0.0005000000237487257,"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/T10269","display_name":"Epigenetics and DNA Methylation","score":9.999999747378752e-05,"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/transcription-factor-cooperativity","display_name":"transcription factor cooperativity","score":0.7409999966621399},{"id":"https://openalex.org/keywords/cis-regulatory-elements","display_name":"cis-regulatory elements","score":0.8309999704360962},{"id":"https://openalex.org/keywords/enhancers","display_name":"enhancers","score":0.8029999732971191},{"id":"https://openalex.org/keywords/promoter","display_name":"promoter","score":0.9850000143051147},{"id":"https://openalex.org/keywords/sequence-motifs","display_name":"sequence motifs","score":0.6480000019073486},{"id":"https://openalex.org/keywords/nucleosome-positioning","display_name":"nucleosome positioning","score":0.6959999799728394},{"id":"https://openalex.org/keywords/mouse-embryonic-stem-cells","display_name":"mouse embryonic stem cells","score":0.8930000066757202},{"id":"https://openalex.org/keywords/protein-dna-interactions","display_name":"protein-DNA interactions","score":0.7149999737739563}],"concepts":[{"id":"https://openalex.org/C83640560","wikidata":"https://www.wikidata.org/wiki/Q180951","display_name":"Chromatin","level":3,"score":0.8481000065803528},{"id":"https://openalex.org/C2778021871","wikidata":"https://www.wikidata.org/wiki/Q648006","display_name":"Footprinting","level":4,"score":0.781499981880188},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.6848999857902527},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5238000154495239},{"id":"https://openalex.org/C84772758","wikidata":"https://www.wikidata.org/wiki/Q271794","display_name":"Nucleosome","level":4,"score":0.5174999833106995},{"id":"https://openalex.org/C2775905019","wikidata":"https://www.wikidata.org/wiki/Q192572","display_name":"In silico","level":3,"score":0.5023000240325928},{"id":"https://openalex.org/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"score":0.4977000057697296},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.4763000011444092},{"id":"https://openalex.org/C190796033","wikidata":"https://www.wikidata.org/wiki/Q1093165","display_name":"Cis-regulatory module","level":5,"score":0.4706999957561493},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.45159998536109924},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4259999990463257},{"id":"https://openalex.org/C67258246","wikidata":"https://www.wikidata.org/wiki/Q5065897","display_name":"ChIA-PET","level":5,"score":0.4250999987125397},{"id":"https://openalex.org/C21592294","wikidata":"https://www.wikidata.org/wiki/Q3238407","display_name":"Regulatory sequence","level":4,"score":0.37049999833106995},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.3695000112056732},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.36320000886917114},{"id":"https://openalex.org/C64927066","wikidata":"https://www.wikidata.org/wiki/Q36293","display_name":"Histone","level":3,"score":0.35600000619888306},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.35409998893737793},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.34790000319480896},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.34119999408721924},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3384000062942505},{"id":"https://openalex.org/C161078062","wikidata":"https://www.wikidata.org/wiki/Q1068690","display_name":"Functional genomics","level":5,"score":0.3246999979019165},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.30820000171661377},{"id":"https://openalex.org/C165864922","wikidata":"https://www.wikidata.org/wiki/Q411391","display_name":"Regulation of gene expression","level":3,"score":0.3059000074863434},{"id":"https://openalex.org/C67339327","wikidata":"https://www.wikidata.org/wiki/Q1502576","display_name":"Gene regulatory network","level":4,"score":0.30160000920295715},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2937000095844269},{"id":"https://openalex.org/C22427896","wikidata":"https://www.wikidata.org/wiki/Q4493748","display_name":"DNA footprinting","level":5,"score":0.28220000863075256},{"id":"https://openalex.org/C3662595","wikidata":"https://www.wikidata.org/wiki/Q5205743","display_name":"DNA binding site","level":5,"score":0.2750000059604645},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C117745874","wikidata":"https://www.wikidata.org/wiki/Q901612","display_name":"Sequence motif","level":3,"score":0.26820001006126404},{"id":"https://openalex.org/C176619506","wikidata":"https://www.wikidata.org/wiki/Q5065899","display_name":"ChIP-sequencing","level":5,"score":0.2630000114440918},{"id":"https://openalex.org/C32276052","wikidata":"https://www.wikidata.org/wiki/Q908349","display_name":"Motif (music)","level":2,"score":0.25119999051094055},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.10.29.762938","doi":"https://doi.org/10.64898/2026.10.29.762938","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.29.762938","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/31/2026.10.29.762938.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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.10.29.762938","doi":"https://doi.org/10.64898/2026.10.29.762938","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.29.762938","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/31/2026.10.29.762938.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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F3179574403","display_name":"Milken Institute","ror":"https://ror.org/03f5t6469"},{"id":"https://openalex.org/F4320306159","display_name":"W. M. Keck Foundation","ror":"https://ror.org/000dswa46"},{"id":"https://openalex.org/F4320310168","display_name":"Gladstone Institutes","ror":"https://ror.org/038321296"},{"id":"https://openalex.org/F4320337338","display_name":"National Heart, Lung, and Blood Institute","ror":"https://ror.org/012pb6c26"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7225009835.pdf","grobid_xml":"https://content.openalex.org/works/W7225009835.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W2605409611","https://openalex.org/W2898981235","https://openalex.org/W4362660267","https://openalex.org/W4386609944","https://openalex.org/W4404395545","https://openalex.org/W4405829527","https://openalex.org/W4414497183","https://openalex.org/W4416943542","https://openalex.org/W7152081240","https://openalex.org/W7158816791","https://openalex.org/W7163593787","https://openalex.org/W7212797718"],"related_works":["https://openalex.org/W4405829527","https://openalex.org/W4321478299","https://openalex.org/W4410730055","https://openalex.org/W7081654526","https://openalex.org/W3024754576","https://openalex.org/W2960370523","https://openalex.org/W7224129511","https://openalex.org/W4220889904","https://openalex.org/W2342138444","https://openalex.org/W7165081489"],"abstract_inverted_index":{"Abstract":[0],"The":[1],"regulation":[2],"of":[3,22,29,62,79,120,132,155,178],"chromatin":[4,23,98],"accessibility":[5],"is":[6,197],"critical":[7],"for":[8,169],"cell":[9],"function":[10],"and":[11,34,109,128,161],"identity.":[12],"Advances":[13],"in":[14,36,66,110,145,163],"single-molecule":[15,195],"long-read":[16],"footprinting":[17,174],"have":[18],"enabled":[19],"near-nucleotide-resolution":[20],"readout":[21],"fiber":[24],"organization,":[25],"capturing":[26],"both":[27],"coordination":[28],"transcription":[30],"factor":[31],"(TF)":[32],"binding":[33],"variation":[35],"nucleosome":[37],"positioning":[38],"previously":[39],"obscured":[40],"by":[41],"bulk":[42],"methods.":[43],"Here":[44],"we":[45,72,88,113],"combine":[46],"this":[47],"technique":[48],"with":[49,76],"deep":[50],"learning":[51],"to":[52,185],"study":[53],"how":[54,187],"protein-DNA":[55],"interactions":[56],"are":[57,81,135],"coordinated":[58,146],"within":[59,125],"different":[60],"types":[61],"cis":[63],"-regulatory":[64],"elements":[65],"mouse":[67],"embryonic":[68],"stem":[69],"cells.":[70],"First,":[71],"quantify":[73],"the":[74,102,153,183],"frequency":[75],"which":[77],"pairs":[78],"positions":[80],"simultaneously":[82],"accessible":[83],"on":[84],"individual":[85],"molecules.":[86],"Then,":[87],"train":[89],"ChAI-Net,":[90],"a":[91,142],"neural":[92],"network":[93],"that":[94,115],"predicts":[95],"these":[96,133,188],"locus-specific":[97],"co-accessibility":[99,124],"maps":[100],"from":[101,173],"underlying":[103,123],"DNA":[104],"sequence.":[105],"Through":[106],"model":[107],"interpretation":[108],"silico":[111],"experiments,":[112],"show":[114],"ChAI-Net":[116],"learns":[117],"unique":[118],"combinations":[119],"sequence":[121],"motifs":[122,134],"enhancers,":[126],"promoters,":[127],"CTCF-bound":[129],"sites.":[130],"Many":[131],"missed":[136],"when":[137],"modeling":[138],"average":[139],"accessibility,":[140],"suggesting":[141],"specific":[143],"role":[144],"binding.":[147],"ChAI-Net\u2019s":[148],"regulatory":[149,171],"grammar":[150],"also":[151],"highlights":[152],"importance":[154],"TF":[156,179],"motif":[157],"orientation,":[158],"spacing,":[159],"positioning,":[160],"co-occurrence":[162],"driving":[164],"co-accessibility.":[165],"Thus,":[166],"our":[167],"framework":[168],"extracting":[170],"rules":[172,189],"data":[175],"expands":[176],"understanding":[177],"cooperativity,":[180],"while":[181],"laying":[182],"groundwork":[184],"elucidate":[186],"vary":[190],"across":[191],"cellular":[192],"contexts":[193],"as":[194],"genomics":[196],"deployed":[198],"at":[199],"scale.":[200]},"counts_by_year":[],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2026-11-01T00:00:00"}
