{"id":"https://openalex.org/W3205986286","doi":"https://doi.org/10.1109/cibcb49929.2021.9562938","title":"Genome-scale prediction of bacterial promoters","display_name":"Genome-scale prediction of bacterial promoters","publication_year":2021,"publication_date":"2021-10-13","ids":{"openalex":"https://openalex.org/W3205986286","doi":"https://doi.org/10.1109/cibcb49929.2021.9562938","mag":"3205986286"},"language":"en","primary_location":{"id":"doi:10.1109/cibcb49929.2021.9562938","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cibcb49929.2021.9562938","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5043768967","display_name":"Miria Bernardino","orcid":"https://orcid.org/0000-0001-6775-9757"},"institutions":[{"id":"https://openalex.org/I129902397","display_name":"Dalhousie University","ror":"https://ror.org/01e6qks80","country_code":"CA","type":"education","lineage":["https://openalex.org/I129902397"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Miria Bernardino","raw_affiliation_strings":["Faculty of Computer Science Dalhousie University,Halifax,Canada","Faculty of Computer Science Dalhousie University, Halifax, Canada"],"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science Dalhousie University,Halifax,Canada","institution_ids":["https://openalex.org/I129902397"]},{"raw_affiliation_string":"Faculty of Computer Science Dalhousie University, Halifax, Canada","institution_ids":["https://openalex.org/I129902397"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063083987","display_name":"Robert G. Beiko","orcid":"https://orcid.org/0000-0002-5065-4980"},"institutions":[{"id":"https://openalex.org/I129902397","display_name":"Dalhousie University","ror":"https://ror.org/01e6qks80","country_code":"CA","type":"education","lineage":["https://openalex.org/I129902397"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Robert Beiko","raw_affiliation_strings":["Faculty of Computer Science Dalhousie University,Halifax,Canada","Faculty of Computer Science Dalhousie University, Halifax, Canada"],"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science Dalhousie University,Halifax,Canada","institution_ids":["https://openalex.org/I129902397"]},{"raw_affiliation_string":"Faculty of Computer Science Dalhousie University, Halifax, Canada","institution_ids":["https://openalex.org/I129902397"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5043768967"],"corresponding_institution_ids":["https://openalex.org/I129902397"],"apc_list":null,"apc_paid":null,"fwci":0.0804,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.44321146,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"2017","issue":null,"first_page":"01","last_page":"08"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9998999834060669,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9998999834060669,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9995999932289124,"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":0.9994999766349792,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/promoter","display_name":"Promoter","score":0.8996076583862305},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.6306422352790833},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.6000009179115295},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.5881447792053223},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.5877374410629272},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.5121381282806396},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5070855617523193},{"id":"https://openalex.org/keywords/false-positive-paradox","display_name":"False positive paradox","score":0.48529189825057983},{"id":"https://openalex.org/keywords/dna","display_name":"DNA","score":0.47573256492614746},{"id":"https://openalex.org/keywords/rna-polymerase-ii","display_name":"RNA polymerase II","score":0.4344601333141327},{"id":"https://openalex.org/keywords/consensus-sequence","display_name":"Consensus sequence","score":0.41369202733039856},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.273206889629364},{"id":"https://openalex.org/keywords/gene-expression","display_name":"Gene expression","score":0.21698197722434998},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.164271742105484},{"id":"https://openalex.org/keywords/base-sequence","display_name":"Base sequence","score":0.11048907041549683}],"concepts":[{"id":"https://openalex.org/C101762097","wikidata":"https://www.wikidata.org/wiki/Q224093","display_name":"Promoter","level":4,"score":0.8996076583862305},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.6306422352790833},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.6000009179115295},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.5881447792053223},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.5877374410629272},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.5121381282806396},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5070855617523193},{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.48529189825057983},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.47573256492614746},{"id":"https://openalex.org/C64350747","wikidata":"https://www.wikidata.org/wiki/Q15334993","display_name":"RNA polymerase II","level":5,"score":0.4344601333141327},{"id":"https://openalex.org/C54985914","wikidata":"https://www.wikidata.org/wiki/Q1295754","display_name":"Consensus sequence","level":4,"score":0.41369202733039856},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.273206889629364},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.21698197722434998},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.164271742105484},{"id":"https://openalex.org/C3017666073","wikidata":"https://www.wikidata.org/wiki/Q1764062","display_name":"Base sequence","level":3,"score":0.11048907041549683},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cibcb49929.2021.9562938","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cibcb49929.2021.9562938","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1019830208","https://openalex.org/W1570993795","https://openalex.org/W1966716734","https://openalex.org/W2004132756","https://openalex.org/W2037728701","https://openalex.org/W2055043387","https://openalex.org/W2115378879","https://openalex.org/W2124022856","https://openalex.org/W2124266758","https://openalex.org/W2130172777","https://openalex.org/W2132247880","https://openalex.org/W2142678478","https://openalex.org/W2168597324","https://openalex.org/W2170647386","https://openalex.org/W2232370058","https://openalex.org/W2551087326","https://openalex.org/W2587688848","https://openalex.org/W2675954008","https://openalex.org/W2754289562","https://openalex.org/W2889772740","https://openalex.org/W2896262061","https://openalex.org/W2905321002","https://openalex.org/W2949453554","https://openalex.org/W2952170484","https://openalex.org/W2963250244","https://openalex.org/W2963403868","https://openalex.org/W2963739921","https://openalex.org/W2966917770","https://openalex.org/W2969662046","https://openalex.org/W2982501585","https://openalex.org/W3021134454","https://openalex.org/W4236236547","https://openalex.org/W4385245566","https://openalex.org/W6739901393"],"related_works":["https://openalex.org/W1967514004","https://openalex.org/W2039269859","https://openalex.org/W3183610476","https://openalex.org/W4205601555","https://openalex.org/W2127848647","https://openalex.org/W2134800947","https://openalex.org/W2577304556","https://openalex.org/W2021252085","https://openalex.org/W1528506138","https://openalex.org/W1708105888"],"abstract_inverted_index":{"Proteins":[0],"are":[1,16,93,106,136],"responsible":[2],"for":[3,20,273],"many":[4],"tasks":[5],"including":[6],"cell":[7,40],"growth":[8],"and":[9,83,110,146,193,196,249,266,269,275],"metabolism.":[10],"Transcription,":[11],"the":[12,21,30,39,42,56,74,147,200,215,221,230,239,258,270],"process":[13],"where":[14,165],"genes":[15,75,92],"used":[17,28,272],"as":[18,65],"templates":[19],"production":[22],"of":[23,32,58,61,73,81,102,143,159,171,190,202,211,224,233,241,247],"a":[24,59,99,120,183],"messenger":[25],"RNA":[26,66],"intermediate":[27],"in":[29,53,132,163,243],"synthesis":[31],"proteins,":[33,62],"is":[34,55,173],"regulated":[35],"to":[36,46,68,76,89,95,112,129,175,177,209],"ensure":[37],"that":[38,114,186,210,251],"has":[41],"appropriate":[43],"response":[44],"according":[45],"its":[47],"current":[48],"needs.":[49],"An":[50],"essential":[51],"step":[52],"transcription":[54],"binding":[57],"group":[60],"collectively":[63],"known":[64],"polymerase,":[67],"short":[69],"promoter":[70],"sequences":[71,86],"upstream":[72],"be":[77,96,278],"transcribed.":[78],"Automated":[79],"identification":[80],"promoters":[82,105,131,225],"nearby":[84],"regulatory":[85],"can":[87,277],"help":[88],"predict":[90],"which":[91],"likely":[94],"active":[97],"under":[98],"given":[100],"set":[101],"conditions.":[103],"However,":[104],"short,":[107],"highly":[108],"variable,":[109],"belong":[111],"subclasses":[113],"sometimes":[115],"overlap,":[116],"making":[117],"their":[118,152],"recognition":[119],"very":[121],"difficult":[122],"problem.":[123],"Several":[124],"tools":[125],"have":[126],"been":[127],"developed":[128],"identify":[130],"DNA,":[133],"but":[134],"methods":[135],"generally":[137],"tested":[138],"on":[139,155,204],"small,":[140],"balanced":[141,205],"subsets":[142],"genomic":[144],"sequence,":[145],"results":[148],"may":[149],"not":[150],"reflect":[151],"expected":[153,174],"performance":[154,201],"genomes":[156],"with":[157,229,257],"millions":[158],"DNA":[160,191],"base":[161],"pairs":[162],"length":[164],"only":[166],"<tex":[167],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[168],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\sim$</tex>":[169],"1%":[170],"sequence":[172],"correspond":[176],"promoters.":[178,262],"Here":[179],"we":[180],"introduce":[181],"Expositor,":[182],"neural-network-based":[184],"method":[185],"uses":[187],"different":[188,245],"types":[189],"encodings":[192],"tunable":[194],"sensitivity":[195],"specificity":[197],"parameters.":[198],"Although":[199],"Expositor":[203,242,263],"datasets":[206,271],"was":[207,255],"comparable":[208],"other":[212],"approaches,":[213],"at":[214,280],"genome":[216],"scale":[217],"our":[218],"approach":[219],"finds":[220],"highest":[222],"number":[223,232],"(70%":[226],"against":[227],"46%)":[228],"smallest":[231],"false":[234],"positives.":[235],"We":[236],"also":[237],"examined":[238],"accuracy":[240],"distinguishing":[244],"classes":[246,254],"promoters,":[248],"found":[250],"misclassification":[252],"between":[253,261],"consistent":[256],"biological":[259],"similarity":[260],"source":[264],"code":[265],"pretrained":[267],"model,":[268],"training":[274],"testing":[276],"accessed":[279],"https://github.com/beiko-lab/Expositor.":[281]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
