{"id":"https://openalex.org/W4403093485","doi":"https://doi.org/10.21203/rs.3.rs-5104308/v1","title":"Dissection of core promoter syntax through single nucleotide resolution modeling of transcription initiation","display_name":"Dissection of core promoter syntax through single nucleotide resolution modeling of transcription initiation","publication_year":2024,"publication_date":"2024-10-04","ids":{"openalex":"https://openalex.org/W4403093485","doi":"https://doi.org/10.21203/rs.3.rs-5104308/v1"},"language":"en","primary_location":{"id":"doi:10.21203/rs.3.rs-5104308/v1","doi":"https://doi.org/10.21203/rs.3.rs-5104308/v1","is_oa":true,"landing_page_url":"https://www.researchsquare.com/article/rs-5104308/latest.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Research Square","raw_type":"posted-content"},"volume":null,"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.researchsquare.com/article/rs-5104308/latest.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024923108","display_name":"Charles G. Danko","orcid":"https://orcid.org/0000-0002-1999-7125","observed_orcids":["https://orcid.org/0000-0002-1999-7125"]},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Charles Danko","raw_affiliation_strings":["Cornell University"],"raw_orcid":"https://orcid.org/0000-0002-1999-7125","affiliations":[{"raw_affiliation_string":"Cornell University","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"last","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/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adam He","raw_affiliation_strings":["Cornell University"],"raw_orcid":"https://orcid.org/0000-0003-2084-6970","affiliations":[{"raw_affiliation_string":"Cornell University","institution_ids":["https://openalex.org/I205783295"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I205783295"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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":0.9994999766349792,"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":0.9994999766349792,"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":0.0,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.0,"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":0.8050000071525574},{"id":"https://openalex.org/keywords/core-promoter","display_name":"core promoter","score":0.9769999980926514},{"id":"https://openalex.org/keywords/cis-regulatory-elements","display_name":"cis-regulatory elements","score":0.8960000276565552},{"id":"https://openalex.org/keywords/deep-learning-prediction","display_name":"deep learning prediction","score":0.6899999976158142},{"id":"https://openalex.org/keywords/protein-dna-interactions","display_name":"protein-DNA interactions","score":0.8230000138282776},{"id":"https://openalex.org/keywords/transcriptional-activator","display_name":"transcriptional activator","score":0.8939999938011169},{"id":"https://openalex.org/keywords/tata-less-promoter","display_name":"TATA-less promoter","score":0.949999988079071},{"id":"https://openalex.org/keywords/tata-binding-protein","display_name":"TATA-binding protein","score":0.7269999980926514},{"id":"https://openalex.org/keywords/enhancers","display_name":"enhancers","score":0.8320000171661377},{"id":"https://openalex.org/keywords/pro-seq","display_name":"PRO-seq","score":0.5709999799728394}],"concepts":[{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.58099365234375},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.48963218927383423},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.48507705330848694},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.44947099685668945},{"id":"https://openalex.org/C512185932","wikidata":"https://www.wikidata.org/wiki/Q28745","display_name":"Nucleotide","level":3,"score":0.4316880702972412},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.42282789945602417},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.37823209166526794},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3737840950489044},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.2320418655872345},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.14167478680610657},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11202073097229004},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.09817653894424438},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0822199285030365}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21203/rs.3.rs-5104308/v1","doi":"https://doi.org/10.21203/rs.3.rs-5104308/v1","is_oa":true,"landing_page_url":"https://www.researchsquare.com/article/rs-5104308/latest.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Research Square","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.21203/rs.3.rs-5104308/v1","doi":"https://doi.org/10.21203/rs.3.rs-5104308/v1","is_oa":true,"landing_page_url":"https://www.researchsquare.com/article/rs-5104308/latest.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Research Square","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4399256283","https://openalex.org/W2064390432","https://openalex.org/W4414387490","https://openalex.org/W4395447528","https://openalex.org/W4395447546","https://openalex.org/W7168292298","https://openalex.org/W7160384206","https://openalex.org/W2105089812","https://openalex.org/W1989471545","https://openalex.org/W3084020252"],"abstract_inverted_index":{"Abstract":[0],"How":[1],"the":[2,30,72,101,107,121,143],"DNA":[3,42],"sequence":[4,43,144],"of":[5,34,50,58,98,123],"cis-regulatory":[6],"elements":[7],"encode":[8,95],"transcription":[9,35,73,147],"initiation":[10,36,104,109,118],"patterns":[11,119],"remains":[12],"poorly":[13],"understood.":[14],"Here":[15],"we":[16],"introduce":[17],"CLIPNET,":[18],"a":[19,53],"deep":[20],"learning":[21],"model":[22],"trained":[23],"on":[24],"population-scale":[25],"PRO-cap":[26],"data":[27],"that":[28,116],"predicts":[29],"position":[31],"and":[32,67,88,106,125,130],"quantity":[33,105],"with":[37,100],"single":[38],"nucleotide":[39],"resolution":[40],"from":[41],"more":[44,79],"accurately":[45],"than":[46],"existing":[47],"approaches.":[48],"Interpretation":[49],"CLIPNET":[51],"revealed":[52],"complex":[54],"regulatory":[55],"syntax":[56],"consisting":[57],"DNA-protein":[59],"interactions":[60],"in":[61,120,135],"five":[62],"major":[63],"positions":[64],"between":[65],"-200":[66],"+50":[68],"bp":[69],"relative":[70],"to":[71,94],"start":[74],"site,":[75],"as":[76,78],"well":[77],"subtle":[80],"positional":[81],"preferences":[82],"among":[83],"transcriptional":[84],"activators.":[85],"Transcriptional":[86],"activator":[87],"core":[89,113],"promoter":[90,114],"motifs":[91,115,129],"work":[92],"non-additively":[93],"distinct":[96],"aspects":[97],"initiation,":[99],"former":[102],"driving":[103],"latter":[108],"position.":[110],"We":[111],"identified":[112],"explain":[117],"majority":[122],"promoters":[124],"enhancers,":[126],"including":[127],"DPR":[128],"AT-rich":[131],"TBP":[132],"binding":[133],"sequences":[134],"TATA-less":[136],"promoters.":[137],"Our":[138],"results":[139],"provide":[140],"insights":[141],"into":[142],"architecture":[145],"governing":[146],"initiation.":[148]},"counts_by_year":[],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2024-10-04T00:00:00"}
