{"id":"https://openalex.org/W4389331567","doi":"https://doi.org/10.1109/tcbb.2023.3339597","title":"promSEMBLE: Hard Pattern Mining and Ensemble Learning for Detecting DNA Promoter Sequences","display_name":"promSEMBLE: Hard Pattern Mining and Ensemble Learning for Detecting DNA Promoter Sequences","publication_year":2023,"publication_date":"2023-12-05","ids":{"openalex":"https://openalex.org/W4389331567","doi":"https://doi.org/10.1109/tcbb.2023.3339597","pmid":"https://pubmed.ncbi.nlm.nih.gov/38051616"},"language":"en","primary_location":{"id":"doi:10.1109/tcbb.2023.3339597","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcbb.2023.3339597","pdf_url":null,"source":{"id":"https://openalex.org/S36029991","display_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","issn_l":"1545-5963","issn":["1545-5963","1557-9964","2374-0043"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5068521179","display_name":"Bindi M. Nagda","orcid":"https://orcid.org/0000-0003-3507-5494"},"institutions":[{"id":"https://openalex.org/I106959904","display_name":"Florida Institute of Technology","ror":"https://ror.org/04atsbb87","country_code":"US","type":"education","lineage":["https://openalex.org/I106959904"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Bindi M. Nagda","raw_affiliation_strings":["Dept. of Mathematical Sciences, Florida Institute of Technology, Melbourne, FL, USA"],"raw_orcid":"https://orcid.org/0000-0003-3507-5494","affiliations":[{"raw_affiliation_string":"Dept. of Mathematical Sciences, Florida Institute of Technology, Melbourne, FL, USA","institution_ids":["https://openalex.org/I106959904"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100777908","display_name":"V\u0103n Minh Nguy\u1ec5n","orcid":"https://orcid.org/0000-0002-2479-2503"},"institutions":[{"id":"https://openalex.org/I106959904","display_name":"Florida Institute of Technology","ror":"https://ror.org/04atsbb87","country_code":"US","type":"education","lineage":["https://openalex.org/I106959904"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Van Minh Nguyen","raw_affiliation_strings":["Dept. of Mathematical Sciences, Florida Institute of Technology, Melbourne, FL, USA"],"raw_orcid":"https://orcid.org/0000-0002-2479-2503","affiliations":[{"raw_affiliation_string":"Dept. of Mathematical Sciences, Florida Institute of Technology, Melbourne, FL, USA","institution_ids":["https://openalex.org/I106959904"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053279009","display_name":"Ryan T. White","orcid":"https://orcid.org/0000-0002-5524-629X"},"institutions":[{"id":"https://openalex.org/I106959904","display_name":"Florida Institute of Technology","ror":"https://ror.org/04atsbb87","country_code":"US","type":"education","lineage":["https://openalex.org/I106959904"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ryan T. White","raw_affiliation_strings":["Dept. of Mathematical Sciences, Florida Institute of Technology, Melbourne, FL, USA"],"raw_orcid":"https://orcid.org/0000-0002-5524-629X","affiliations":[{"raw_affiliation_string":"Dept. of Mathematical Sciences, Florida Institute of Technology, Melbourne, FL, USA","institution_ids":["https://openalex.org/I106959904"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5068521179"],"corresponding_institution_ids":["https://openalex.org/I106959904"],"apc_list":null,"apc_paid":null,"fwci":0.7497,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.7355533,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"21","issue":"1","first_page":"208","last_page":"214"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9988999962806702,"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":0.9988999962806702,"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/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.9977999925613403,"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":0.9959999918937683,"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":0.7551994323730469},{"id":"https://openalex.org/keywords/tata-box","display_name":"TATA box","score":0.7420215606689453},{"id":"https://openalex.org/keywords/dna-binding-site","display_name":"DNA binding site","score":0.647546648979187},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5868669152259827},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.5496415495872498},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.5365446209907532},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.5342926383018494},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.507495105266571},{"id":"https://openalex.org/keywords/transcription-factor","display_name":"Transcription factor","score":0.461870938539505},{"id":"https://openalex.org/keywords/dna","display_name":"DNA","score":0.46026521921157837},{"id":"https://openalex.org/keywords/regulatory-sequence","display_name":"Regulatory sequence","score":0.4558689296245575},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.44304805994033813},{"id":"https://openalex.org/keywords/consensus-sequence","display_name":"Consensus sequence","score":0.4114549160003662},{"id":"https://openalex.org/keywords/gene-expression","display_name":"Gene expression","score":0.14338013529777527},{"id":"https://openalex.org/keywords/base-sequence","display_name":"Base sequence","score":0.11936303973197937}],"concepts":[{"id":"https://openalex.org/C101762097","wikidata":"https://www.wikidata.org/wiki/Q224093","display_name":"Promoter","level":4,"score":0.7551994323730469},{"id":"https://openalex.org/C65888428","wikidata":"https://www.wikidata.org/wiki/Q1413955","display_name":"TATA box","level":5,"score":0.7420215606689453},{"id":"https://openalex.org/C3662595","wikidata":"https://www.wikidata.org/wiki/Q5205743","display_name":"DNA binding site","level":5,"score":0.647546648979187},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5868669152259827},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.5496415495872498},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.5365446209907532},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.5342926383018494},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.507495105266571},{"id":"https://openalex.org/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"score":0.461870938539505},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.46026521921157837},{"id":"https://openalex.org/C21592294","wikidata":"https://www.wikidata.org/wiki/Q3238407","display_name":"Regulatory sequence","level":4,"score":0.4558689296245575},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.44304805994033813},{"id":"https://openalex.org/C54985914","wikidata":"https://www.wikidata.org/wiki/Q1295754","display_name":"Consensus sequence","level":4,"score":0.4114549160003662},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.14338013529777527},{"id":"https://openalex.org/C3017666073","wikidata":"https://www.wikidata.org/wiki/Q1764062","display_name":"Base sequence","level":3,"score":0.11936303973197937},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D011401","descriptor_name":"Promoter Regions, Genetic","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011401","descriptor_name":"Promoter Regions, Genetic","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011401","descriptor_name":"Promoter Regions, Genetic","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D014158","descriptor_name":"Transcription, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014158","descriptor_name":"Transcription, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014158","descriptor_name":"Transcription, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016385","descriptor_name":"TATA Box","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016385","descriptor_name":"TATA Box","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016385","descriptor_name":"TATA Box","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1109/tcbb.2023.3339597","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcbb.2023.3339597","pdf_url":null,"source":{"id":"https://openalex.org/S36029991","display_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","issn_l":"1545-5963","issn":["1545-5963","1557-9964","2374-0043"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","raw_type":"journal-article"},{"id":"pmid:38051616","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38051616","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM transactions on computational biology and bioinformatics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1534477342","https://openalex.org/W1963636903","https://openalex.org/W1979649334","https://openalex.org/W1991259976","https://openalex.org/W1998722587","https://openalex.org/W2040480653","https://openalex.org/W2067116931","https://openalex.org/W2075435641","https://openalex.org/W2087181226","https://openalex.org/W2096210973","https://openalex.org/W2104788940","https://openalex.org/W2107163098","https://openalex.org/W2121400095","https://openalex.org/W2147029237","https://openalex.org/W2167155713","https://openalex.org/W2543735465","https://openalex.org/W2558947257","https://openalex.org/W2809624722","https://openalex.org/W2896457183","https://openalex.org/W2896699990","https://openalex.org/W2908351833","https://openalex.org/W2932524182","https://openalex.org/W2963739921","https://openalex.org/W3109860017","https://openalex.org/W3127238141","https://openalex.org/W4200285930","https://openalex.org/W4246193833","https://openalex.org/W6739901393","https://openalex.org/W6743446608"],"related_works":["https://openalex.org/W2033386886","https://openalex.org/W1942920824","https://openalex.org/W2392370788","https://openalex.org/W2079238525","https://openalex.org/W2025776314","https://openalex.org/W4249725176","https://openalex.org/W2375898214","https://openalex.org/W2356348012","https://openalex.org/W2108407399","https://openalex.org/W1887844619"],"abstract_inverted_index":{"Accurate":[0],"identification":[1,58],"of":[2,7,20,38,59,88,104,125,140],"DNA":[3,35,102,150],"promoter":[4,30,39,89,92,147],"sequences":[5,93,103],"is":[6,22,41],"crucial":[8],"importance":[9],"in":[10,33,131],"unraveling":[11],"the":[12,34,95,99,138,146],"underlying":[13],"mechanisms":[14],"that":[15,118,143],"regulate":[16],"gene":[17],"transcription.":[18],"Initiation":[19],"transcription":[21,26],"controlled":[23],"through":[24],"regulatory":[25,49],"factors":[27],"binding":[28],"to":[29,46,84],"core":[31],"regions":[32,40],"sequence.":[36],"Detection":[37],"necessary":[42],"if":[43],"we":[44,116],"are":[45],"build":[47],"genetic":[48],"networks":[50,74],"for":[51,57,136,145],"biomedical":[52],"and":[53,56,79,97,112],"clinical":[54],"applications,":[55],"rarely":[60],"expressed":[61],"genes.":[62],"We":[63],"propose":[64],"a":[65,122],"novel":[66],"ensemble":[67],"learning":[68],"technique":[69],"using":[70],"deep":[71],"recurrent":[72],"neural":[73],"with":[75,94],"convolutional":[76],"feature":[77],"extraction":[78],"hard":[80],"negative":[81],"pattern":[82],"mining":[83],"detect":[85],"several":[86],"types":[87],"sequences,":[90],"including":[91],"TATA-box":[96],"without":[98],"TATA-box,":[100],"within":[101,149],"four":[105],"different":[106],"species.":[107],"Using":[108],"extensive":[109],"independent":[110],"tests":[111],"previously":[113],"published":[114],"results,":[115],"demonstrate":[117],"our":[119],"method":[120],"sets":[121],"new":[123],"state-of-the-art":[124],"over":[126],"98%":[127],"Matthews":[128],"correlation":[129],"coefficient":[130],"all":[132],"eight":[133],"organism":[134],"categories":[135],"recognizing":[137],"stretch":[139],"base":[141],"pairs":[142],"code":[144],"region":[148],"sequences.":[151]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
