{"id":"https://openalex.org/W7224997852","doi":"https://doi.org/10.64898/2026.10.29.762743","title":"A comprehensive map of the sequence basis of transcription initiation in humans","display_name":"A comprehensive map of the sequence basis of transcription initiation in humans","publication_year":2026,"publication_date":"2026-10-30","ids":{"openalex":"https://openalex.org/W7224997852","doi":"https://doi.org/10.64898/2026.10.29.762743"},"language":"en","primary_location":{"id":"doi:10.64898/2026.10.29.762743","doi":"https://doi.org/10.64898/2026.10.29.762743","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.29.762743","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/30/2026.10.29.762743.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","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/30/2026.10.29.762743.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126496422","display_name":"Adam Youlin He","orcid":"https://orcid.org/0000-0003-2084-6970","observed_orcids":["https://orcid.org/0000-0003-2084-6970"]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adam Y. He","raw_affiliation_strings":["Departments of Genetics Stanford University"],"raw_orcid":"https://orcid.org/0000-0003-2084-6970","affiliations":[{"raw_affiliation_string":"Departments of Genetics Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144717735","display_name":"Claire Tian","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Claire Tian","raw_affiliation_strings":["Departments of Genetics Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Departments of Genetics Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083952534","display_name":"Anshul Bharat Kundaje","orcid":"https://orcid.org/0000-0003-3084-2287","observed_orcids":["https://orcid.org/0000-0003-3084-2287"]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Anshul Kundaje","raw_affiliation_strings":["Departments of Genetics Computer Science Stanford University","Departments of Genetics Stanford University"],"raw_orcid":"https://orcid.org/0000-0003-3084-2287","affiliations":[{"raw_affiliation_string":"Departments of Genetics Computer Science Stanford University","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Departments of Genetics Stanford University","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5083952534"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"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":0.9990000128746033,"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":0.9990000128746033,"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":0.00019999999494757503,"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":0.00019999999494757503,"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-initiation","display_name":"transcription initiation","score":0.9980000257492065},{"id":"https://openalex.org/keywords/enhancers","display_name":"enhancers","score":0.6690000295639038},{"id":"https://openalex.org/keywords/promoter","display_name":"promoter","score":0.9929999709129333},{"id":"https://openalex.org/keywords/deep-learning-models","display_name":"deep learning models","score":0.7360000014305115},{"id":"https://openalex.org/keywords/sequence-determinants","display_name":"sequence determinants","score":0.7599999904632568},{"id":"https://openalex.org/keywords/human-organs","display_name":"human organs","score":0.4690000116825104},{"id":"https://openalex.org/keywords/cancer-types","display_name":"cancer types","score":0.7289999723434448},{"id":"https://openalex.org/keywords/chromatin-accessibility","display_name":"chromatin accessibility","score":0.4429999887943268},{"id":"https://openalex.org/keywords/transcriptional-regulation","display_name":"transcriptional regulation","score":0.35899999737739563}],"concepts":[{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.6898999810218811},{"id":"https://openalex.org/C111936080","wikidata":"https://www.wikidata.org/wiki/Q913367","display_name":"Enhancer","level":4,"score":0.6815999746322632},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.6377999782562256},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5788000226020813},{"id":"https://openalex.org/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"score":0.47769999504089355},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.44690001010894775},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.40709999203681946},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.3601999878883362},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.36010000109672546},{"id":"https://openalex.org/C117745874","wikidata":"https://www.wikidata.org/wiki/Q901612","display_name":"Sequence motif","level":3,"score":0.33820000290870667},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.30809998512268066},{"id":"https://openalex.org/C197077220","wikidata":"https://www.wikidata.org/wiki/Q720988","display_name":"Human genome","level":4,"score":0.28949999809265137},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.28349998593330383},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.27379998564720154},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C146027311","wikidata":"https://www.wikidata.org/wiki/Q18031820","display_name":"TAF2","level":5,"score":0.2703999876976013},{"id":"https://openalex.org/C61053724","wikidata":"https://www.wikidata.org/wiki/Q1154615","display_name":"Sequence analysis","level":3,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.10.29.762743","doi":"https://doi.org/10.64898/2026.10.29.762743","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.29.762743","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/30/2026.10.29.762743.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:10.64898/2026.10.29.762743","doi":"https://doi.org/10.64898/2026.10.29.762743","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.29.762743","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/30/2026.10.29.762743.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":[{"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being","score":0.428600013256073}],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320334432","display_name":"Stanford Research Computing Center, Stanford University","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224997852.pdf","grobid_xml":"https://content.openalex.org/works/W7224997852.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W1686333409","https://openalex.org/W1988398836","https://openalex.org/W2007844697","https://openalex.org/W2014787267","https://openalex.org/W2076154138","https://openalex.org/W2092390808","https://openalex.org/W2119037385","https://openalex.org/W2247766769","https://openalex.org/W2327703312","https://openalex.org/W2898981235","https://openalex.org/W2982028528","https://openalex.org/W3087265072","https://openalex.org/W4392763126","https://openalex.org/W4404535307","https://openalex.org/W7081654526","https://openalex.org/W7118833036"],"related_works":["https://openalex.org/W4395447546","https://openalex.org/W4395447528","https://openalex.org/W4399256283","https://openalex.org/W2711348","https://openalex.org/W7100671370","https://openalex.org/W4403093485","https://openalex.org/W4414387490","https://openalex.org/W2950890882","https://openalex.org/W6910807856","https://openalex.org/W2064390432"],"abstract_inverted_index":{"Abstract":[0],"Transcription":[1],"initiation":[2,29,48],"is":[3],"a":[4],"key":[5],"marker":[6],"of":[7,17],"active":[8],"enhancers":[9],"and":[10,19,37,54],"promoters.":[11],"Here":[12],"we":[13],"describe":[14],"an":[15],"atlas":[16],"efficient":[18],"interpretable":[20],"deep":[21],"learning":[22],"models":[23,45],"trained":[24],"on":[25],"over":[26],"200":[27],"transcription":[28],"profiling":[30],"experiments":[31],"representing":[32],"all":[33],"major":[34],"human":[35],"organs":[36],"many":[38],"cancer":[39],"types.":[40],"We":[41],"show":[42],"that":[43],"our":[44],"accurately":[46],"predict":[47],"patterns":[49],"from":[50],"local":[51],"DNA":[52],"sequence":[53,57],"decode":[55],"their":[56],"determinants":[58],"across":[59],"diverse":[60],"cellular":[61],"contexts.":[62]},"counts_by_year":[],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2026-11-01T00:00:00"}
