{"id":"https://openalex.org/W3129125493","doi":"https://doi.org/10.1093/bib/bbab005","title":"A transformer architecture based on BERT and 2D convolutional neural network to identify DNA enhancers from sequence information","display_name":"A transformer architecture based on BERT and 2D convolutional neural network to identify DNA enhancers from sequence information","publication_year":2021,"publication_date":"2021-01-04","ids":{"openalex":"https://openalex.org/W3129125493","doi":"https://doi.org/10.1093/bib/bbab005","mag":"3129125493","pmid":"https://pubmed.ncbi.nlm.nih.gov/33539511"},"language":"en","primary_location":{"id":"doi:10.1093/bib/bbab005","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bib/bbab005","pdf_url":null,"source":{"id":"https://openalex.org/S91767247","display_name":"Briefings in Bioinformatics","issn_l":"1467-5463","issn":["1467-5463","1477-4054"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Briefings in Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","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/A5066420667","display_name":"Nguyen Quoc Khanh Le","orcid":"https://orcid.org/0000-0003-4896-7926"},"institutions":[{"id":"https://openalex.org/I47519274","display_name":"Taipei Medical University","ror":"https://ror.org/05031qk94","country_code":"TW","type":"education","lineage":["https://openalex.org/I47519274"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Nguyen Quoc Khanh Le","raw_affiliation_strings":["Professional Master Program in Artificial Intelligence in Medicine, Taipei Medical University, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Professional Master Program in Artificial Intelligence in Medicine, Taipei Medical University, Taipei, Taiwan","institution_ids":["https://openalex.org/I47519274"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026899391","display_name":"Quang\u2010Thai Ho","orcid":"https://orcid.org/0000-0002-0227-3032"},"institutions":[{"id":"https://openalex.org/I177733328","display_name":"Can Tho University","ror":"https://ror.org/0071qz696","country_code":"VN","type":"education","lineage":["https://openalex.org/I177733328"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Quang-Thai Ho","raw_affiliation_strings":["College of Information and Communication Technology, Can Tho University, Vietnam"],"affiliations":[{"raw_affiliation_string":"College of Information and Communication Technology, Can Tho University, Vietnam","institution_ids":["https://openalex.org/I177733328"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017977962","display_name":"Trinh\u2010Trung\u2010Duong Nguyen","orcid":"https://orcid.org/0000-0001-5793-649X"},"institutions":[{"id":"https://openalex.org/I99908691","display_name":"Yuan Ze University","ror":"https://ror.org/01fv1ds98","country_code":"TW","type":"education","lineage":["https://openalex.org/I99908691"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Trinh-Trung-Duong Nguyen","raw_affiliation_strings":["Department of Computer Science and Engineering, Yuan Ze University, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Yuan Ze University, Taiwan","institution_ids":["https://openalex.org/I99908691"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008287088","display_name":"Yu\u2010Yen Ou","orcid":"https://orcid.org/0000-0002-9894-926X"},"institutions":[{"id":"https://openalex.org/I99908691","display_name":"Yuan Ze University","ror":"https://ror.org/01fv1ds98","country_code":"TW","type":"education","lineage":["https://openalex.org/I99908691"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Yu-Yen Ou","raw_affiliation_strings":["Department of Computer Science and Engineering, Yuan Ze University, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Yuan Ze University, Taiwan","institution_ids":["https://openalex.org/I99908691"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5008287088","https://openalex.org/A5066420667"],"corresponding_institution_ids":["https://openalex.org/I47519274","https://openalex.org/I99908691"],"apc_list":{"value":4011,"currency":"USD","value_usd":4011},"apc_paid":null,"fwci":12.1184,"has_fulltext":false,"cited_by_count":188,"citation_normalized_percentile":{"value":0.9929801,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"22","issue":"5","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9983000159263611,"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":0.9979000091552734,"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/computer-science","display_name":"Computer science","score":0.7799234986305237},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7036922574043274},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6282448172569275},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6126759052276611},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5848591923713684},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5473783016204834},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5472079515457153},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4892387390136719},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4594666659832001},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.44458407163619995},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4249740242958069},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4112604856491089},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34320393204689026}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7799234986305237},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7036922574043274},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6282448172569275},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6126759052276611},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5848591923713684},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5473783016204834},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5472079515457153},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4892387390136719},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4594666659832001},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.44458407163619995},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4249740242958069},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4112604856491089},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34320393204689026},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000068598","descriptor_name":"Data Accuracy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000068598","descriptor_name":"Data Accuracy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000068598","descriptor_name":"Data Accuracy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","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":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004742","descriptor_name":"Enhancer Elements, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D004742","descriptor_name":"Enhancer Elements, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D004742","descriptor_name":"Enhancer Elements, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008954","descriptor_name":"Models, Biological","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008954","descriptor_name":"Models, Biological","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008954","descriptor_name":"Models, Biological","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012680","descriptor_name":"Sensitivity and Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012680","descriptor_name":"Sensitivity and Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012680","descriptor_name":"Sensitivity and Specificity","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":"D014158","descriptor_name":"Transcription, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019303","descriptor_name":"Multilingualism","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019303","descriptor_name":"Multilingualism","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019303","descriptor_name":"Multilingualism","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1093/bib/bbab005","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bib/bbab005","pdf_url":null,"source":{"id":"https://openalex.org/S91767247","display_name":"Briefings in Bioinformatics","issn_l":"1467-5463","issn":["1467-5463","1477-4054"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Briefings in Bioinformatics","raw_type":"journal-article"},{"id":"pmid:33539511","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33539511","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":"Briefings in bioinformatics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8299999833106995,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1501531009","https://openalex.org/W1541931954","https://openalex.org/W1807324513","https://openalex.org/W1969770714","https://openalex.org/W1977855308","https://openalex.org/W2170747616","https://openalex.org/W2493916176","https://openalex.org/W2565121836","https://openalex.org/W2623751800","https://openalex.org/W2793168264","https://openalex.org/W2799347953","https://openalex.org/W2799357357","https://openalex.org/W2807186140","https://openalex.org/W2915815599","https://openalex.org/W2946297791","https://openalex.org/W2976851955","https://openalex.org/W2984726926","https://openalex.org/W2987092090","https://openalex.org/W2995514860","https://openalex.org/W3005378260","https://openalex.org/W3007215678","https://openalex.org/W3009820544","https://openalex.org/W3036832155","https://openalex.org/W3039317077","https://openalex.org/W3090188079","https://openalex.org/W3093120804","https://openalex.org/W3109006384","https://openalex.org/W3136918052","https://openalex.org/W6719819555","https://openalex.org/W6755207826"],"related_works":["https://openalex.org/W3199871245","https://openalex.org/W2081900870","https://openalex.org/W2915436880","https://openalex.org/W3123942215","https://openalex.org/W4285819037","https://openalex.org/W3198729192","https://openalex.org/W1964783010","https://openalex.org/W3121292129","https://openalex.org/W4390516098","https://openalex.org/W4387517132"],"abstract_inverted_index":{"Recently,":[0],"language":[1,13,37],"representation":[2],"models":[3,98],"have":[4],"drawn":[5],"a":[6,33,70,107,120,196],"lot":[7],"of":[8,48,58,84,141],"attention":[9],"in":[10,61,78,125,139,155,174,199],"the":[11,46,54,59,82,151],"natural":[12,92],"processing":[14],"field":[15],"due":[16],"to":[17,31,52,80,99,114,150],"their":[18],"remarkable":[19],"results.":[20],"Among":[21],"them,":[22],"bidirectional":[23],"encoder":[24],"representations":[25],"from":[26],"transformers":[27],"(BERT)":[28],"has":[29],"proven":[30],"be":[32],"simple,":[34],"yet":[35],"powerful":[36],"model":[38,77],"that":[39,131,161,189],"achieved":[40],"novel":[41,71],"state-of-the-art":[42,153],"performance.":[43],"BERT":[44,97,176,190],"adopted":[45],"concept":[47],"contextualized":[49],"word":[50],"embedding":[51],"capture":[53],"semantics":[55],"and":[56,94,122,145,191],"context":[57],"words":[60],"which":[62,118],"they":[63],"appeared.":[64],"In":[65,185],"this":[66,126],"study,":[67,109],"we":[68,110,187],"present":[69],"technique":[72],"by":[73,166],"incorporating":[74],"BERT-based":[75,133],"multilingual":[76],"bioinformatics":[79],"represent":[81],"information":[83],"DNA":[85,89,115],"sequences.":[86],"We":[87,128],"treated":[88],"sequences":[90],"as":[91],"sentences":[93],"then":[95,129],"used":[96],"transform":[100],"them":[101],"into":[102],"fixed-length":[103],"numerical":[104],"matrices.":[105],"As":[106],"case":[108],"applied":[111],"our":[112,132],"method":[113],"enhancer":[116],"prediction,":[117],"is":[119],"well-known":[121],"challenging":[123],"problem":[124],"field.":[127],"observed":[130],"features":[134,154,177],"improved":[135],"more":[136],"than":[137,179],"5-10%":[138],"terms":[140],"sensitivity,":[142],"specificity,":[143],"accuracy":[144],"Matthews":[146],"correlation":[147],"coefficient":[148],"compared":[149],"current":[152],"bioinformatics.":[156],"Moreover,":[157],"advanced":[158],"experiments":[159],"show":[160],"deep":[162],"learning":[163,175,183],"(as":[164],"represented":[165],"2D":[167,192],"convolutional":[168],"neural":[169],"networks;":[170],"CNN)":[171],"holds":[172],"potential":[173],"better":[178],"other":[180],"traditional":[181],"machine":[182],"techniques.":[184],"conclusion,":[186],"suggest":[188],"CNNs":[193],"could":[194],"open":[195],"new":[197],"avenue":[198],"biological":[200],"modeling":[201],"using":[202],"sequence":[203],"information.":[204]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":32},{"year":2024,"cited_by_count":45},{"year":2023,"cited_by_count":33},{"year":2022,"cited_by_count":37},{"year":2021,"cited_by_count":34}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}