{"id":"https://openalex.org/W3048084381","doi":"https://doi.org/10.1101/2020.08.07.241901","title":"Detecting regulatory elements in high-throughput reporter assays","display_name":"Detecting regulatory elements in high-throughput reporter assays","publication_year":2020,"publication_date":"2020-08-07","ids":{"openalex":"https://openalex.org/W3048084381","doi":"https://doi.org/10.1101/2020.08.07.241901","mag":"3048084381"},"language":"en","primary_location":{"id":"mag:3048084381","doi":"https://doi.org/10.1101/2020.08.07.241901","is_oa":false,"landing_page_url":"https://biorxiv.org/content/10.1101/2020.08.07.241901v1.full.pdf","pdf_url":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv (Cold Spring Harbor Laboratory)","raw_type":null},"volume":null,"type":"preprint","indexed_in":[],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101967040","display_name":"Young\u2010Sook Kim","orcid":"https://orcid.org/0000-0001-9619-7423","observed_orcids":["https://orcid.org/0000-0001-9619-7423"]},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Young\u2010Sook Kim","raw_affiliation_strings":["Program in Computational Biology & Bioinformatics, Duke University"],"raw_orcid":"https://orcid.org/0000-0001-9619-7423","affiliations":[{"raw_affiliation_string":"Program in Computational Biology & Bioinformatics, Duke University","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077555866","display_name":"Graham D. Johnson","orcid":"https://orcid.org/0000-0003-0723-4697","observed_orcids":["https://orcid.org/0000-0003-0723-4697"]},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]},{"id":"https://openalex.org/I4210126298","display_name":"Duke Medical Center","ror":"https://ror.org/03njmea73","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210126298","https://openalex.org/I4210144876"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Graham D. Johnson","raw_affiliation_strings":["Center for Genomic and Computational Biology, Duke University Medical School"],"raw_orcid":"https://orcid.org/0000-0003-0723-4697","affiliations":[{"raw_affiliation_string":"Center for Genomic and Computational Biology, Duke University Medical School","institution_ids":["https://openalex.org/I170897317","https://openalex.org/I4210126298"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064290525","display_name":"Jungkyun Seo","orcid":"https://orcid.org/0000-0001-5514-4421","observed_orcids":["https://orcid.org/0000-0001-5514-4421"]},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jungkyun Seo","raw_affiliation_strings":["Program in Computational Biology & Bioinformatics, Duke University"],"raw_orcid":"https://orcid.org/0000-0001-5514-4421","affiliations":[{"raw_affiliation_string":"Program in Computational Biology & Bioinformatics, Duke University","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057113487","display_name":"Alejandro Barrera","orcid":"https://orcid.org/0000-0001-9244-9822","observed_orcids":["https://orcid.org/0000-0001-9244-9822"]},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]},{"id":"https://openalex.org/I4210126298","display_name":"Duke Medical Center","ror":"https://ror.org/03njmea73","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210126298","https://openalex.org/I4210144876"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alejandro Barrera","raw_affiliation_strings":["Center for Genomic and Computational Biology, Duke University Medical School"],"raw_orcid":"https://orcid.org/0000-0001-9244-9822","affiliations":[{"raw_affiliation_string":"Center for Genomic and Computational Biology, Duke University Medical School","institution_ids":["https://openalex.org/I170897317","https://openalex.org/I4210126298"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087212280","display_name":"William H. Majoros","orcid":"https://orcid.org/0000-0001-7284-9335","observed_orcids":["https://orcid.org/0000-0001-7284-9335"]},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William H. Majoros","raw_affiliation_strings":["Duke Center for Statistical Genetics and Genomics, Duke University"],"raw_orcid":"https://orcid.org/0000-0001-7284-9335","affiliations":[{"raw_affiliation_string":"Duke Center for Statistical Genetics and Genomics, Duke University","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078947409","display_name":"Alejandro Ochoa","orcid":"https://orcid.org/0000-0003-4928-3403","observed_orcids":["https://orcid.org/0000-0003-4928-3403"]},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alejandro Ochoa","raw_affiliation_strings":["Program in Computational Biology & Bioinformatics, Duke University"],"raw_orcid":"https://orcid.org/0000-0003-4928-3403","affiliations":[{"raw_affiliation_string":"Program in Computational Biology & Bioinformatics, Duke University","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026198048","display_name":"Andrew S. Allen","orcid":"https://orcid.org/0000-0002-7232-2143","observed_orcids":["https://orcid.org/0000-0002-7232-2143"]},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew S. Allen","raw_affiliation_strings":["Duke Center for Statistical Genetics and Genomics, Duke University"],"raw_orcid":"https://orcid.org/0000-0002-7232-2143","affiliations":[{"raw_affiliation_string":"Duke Center for Statistical Genetics and Genomics, Duke University","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018030255","display_name":"Timothy E. Reddy","orcid":"https://orcid.org/0000-0002-7629-061X","observed_orcids":["https://orcid.org/0000-0002-7629-061X"]},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Timothy E. Reddy","raw_affiliation_strings":["Duke Center for Statistical Genetics and Genomics, Duke University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke Center for Statistical Genetics and Genomics, Duke University","institution_ids":["https://openalex.org/I170897317"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":0.9868000149726868,"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":0.9868000149726868,"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":0.0017000000225380063,"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/T10261","display_name":"Genetic Associations and Epidemiology","score":0.0010999999940395355,"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/starr-seq","display_name":"STARR-seq","score":0.9929999709129333},{"id":"https://openalex.org/keywords/statistical-models","display_name":"statistical models","score":0.6700000166893005},{"id":"https://openalex.org/keywords/false-discovery-rate-control","display_name":"false discovery rate control","score":0.656000018119812},{"id":"https://openalex.org/keywords/signal-correlation","display_name":"signal correlation","score":0.640999972820282}],"concepts":[{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.6050164699554443},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.5545894503593445},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.5422978401184082},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.5086715817451477},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.47406214475631714},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.45715516805648804},{"id":"https://openalex.org/C21592294","wikidata":"https://www.wikidata.org/wiki/Q3238407","display_name":"Regulatory sequence","level":4,"score":0.42669668793678284},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.34356820583343506},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30896222591400146},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.2798302173614502},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.2658522129058838},{"id":"https://openalex.org/C165864922","wikidata":"https://www.wikidata.org/wiki/Q411391","display_name":"Regulation of gene expression","level":3,"score":0.22037160396575928},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08266398310661316},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3048084381","doi":"https://doi.org/10.1101/2020.08.07.241901","is_oa":false,"landing_page_url":"https://biorxiv.org/content/10.1101/2020.08.07.241901v1.full.pdf","pdf_url":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv (Cold Spring Harbor Laboratory)","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1450574606","https://openalex.org/W1844405070","https://openalex.org/W1897931464","https://openalex.org/W1914649288","https://openalex.org/W1967824604","https://openalex.org/W1988650678","https://openalex.org/W2002234191","https://openalex.org/W2014677321","https://openalex.org/W2018742603","https://openalex.org/W2029181455","https://openalex.org/W2053742705","https://openalex.org/W2058358568","https://openalex.org/W2062989416","https://openalex.org/W2069520341","https://openalex.org/W2077874719","https://openalex.org/W2079407198","https://openalex.org/W2091811407","https://openalex.org/W2099107563","https://openalex.org/W2099320873","https://openalex.org/W2110065044","https://openalex.org/W2114104545","https://openalex.org/W2118258530","https://openalex.org/W2119969731","https://openalex.org/W2135995702","https://openalex.org/W2137465688","https://openalex.org/W2158226173","https://openalex.org/W2169964199","https://openalex.org/W2170219300","https://openalex.org/W2170551349","https://openalex.org/W2171808845","https://openalex.org/W2179438025","https://openalex.org/W2259938310","https://openalex.org/W2341539131","https://openalex.org/W2764274744","https://openalex.org/W2767826728","https://openalex.org/W2768013244","https://openalex.org/W2772841828","https://openalex.org/W2887625843","https://openalex.org/W2904690440","https://openalex.org/W2915985519","https://openalex.org/W2953622121","https://openalex.org/W2956088786","https://openalex.org/W3008828407"],"related_works":["https://openalex.org/W3136845791","https://openalex.org/W4391969096","https://openalex.org/W4411716354","https://openalex.org/W3185496276","https://openalex.org/W2953611656","https://openalex.org/W4385497084","https://openalex.org/W4386947744","https://openalex.org/W4401595798","https://openalex.org/W7131360231","https://openalex.org/W2887294008"],"abstract_inverted_index":{"Abstract":[0],"High-throughput":[2],"reporter":[3],"assays":[4],"such":[5],"as":[6],"self-transcribing":[7],"active":[8],"regulatory":[9,20,64,83],"region":[10],"sequencing":[11],"(STARR-seq)":[12],"have":[13],"made":[14],"it":[15],"possible":[16],"to":[17,55,60],"measure":[18],"genome-wide":[19],"element":[21],"activity":[22],"across":[23],"the":[24,44],"human":[25],"genome.":[26],"The":[27],"assays,":[28],"however,":[29],"also":[30],"present":[31],"substantial":[32],"analytical":[33],"challenges.":[34],"Here,":[35],"we":[36],"identify":[37],"technical":[38],"biases":[39,58],"that":[40],"explain":[41],"most":[42],"of":[43,63,78],"variance":[45],"in":[46],"STARR-seq":[47],"signals.":[48],"We":[49],"then":[50],"develop":[51],"a":[52],"statistical":[53],"model":[54],"correct":[56],"those":[57],"and":[59,71,81,85],"improve":[61],"detection":[62,77],"elements.":[65],"This":[66],"approach":[67],"substantially":[68],"improves":[69,76],"precision":[70],"recall":[72],"over":[73],"current":[74],"methods,":[75],"both":[79],"activating":[80],"repressive":[82],"elements,":[84],"controls":[86],"for":[87],"false":[88],"discoveries":[89],"despite":[90],"strong":[91],"local":[92],"signal":[93],"correlations.":[94]},"counts_by_year":[],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2020-08-13T00:00:00"}
