{"id":"https://openalex.org/W3096508121","doi":"https://doi.org/10.1109/tcbb.2020.3035021","title":"Novel Transformer Networks for Improved Sequence Labeling in genomics","display_name":"Novel Transformer Networks for Improved Sequence Labeling in genomics","publication_year":2020,"publication_date":"2020-10-30","ids":{"openalex":"https://openalex.org/W3096508121","doi":"https://doi.org/10.1109/tcbb.2020.3035021","mag":"3096508121","pmid":"https://pubmed.ncbi.nlm.nih.gov/33125335"},"language":"en","primary_location":{"id":"doi:10.1109/tcbb.2020.3035021","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tcbb.2020.3035021","pdf_url":"https://ieeexplore.ieee.org/ielx7/8857/9702518/09246292.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/8857/9702518/09246292.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039596012","display_name":"Jim Clauwaert","orcid":"https://orcid.org/0000-0002-5876-1406"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Jim Clauwaert","raw_affiliation_strings":["KERMIT, Ghent University, Gent, Belgium"],"affiliations":[{"raw_affiliation_string":"KERMIT, Ghent University, Gent, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028945060","display_name":"Willem Waegeman","orcid":"https://orcid.org/0000-0002-5950-3003"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Willem Waegeman","raw_affiliation_strings":["KERMIT, Ghent University, Gent, Belgium"],"affiliations":[{"raw_affiliation_string":"KERMIT, Ghent University, Gent, Belgium","institution_ids":["https://openalex.org/I32597200"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5039596012"],"corresponding_institution_ids":["https://openalex.org/I32597200"],"apc_list":null,"apc_paid":null,"fwci":1.4913,"has_fulltext":true,"cited_by_count":42,"citation_normalized_percentile":{"value":0.82529925,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"19","issue":"1","first_page":"97","last_page":"106"},"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":0.9994999766349792,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9986000061035156,"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":0.5994406938552856},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5373984575271606},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5044289827346802},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5009889602661133},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.48392540216445923},{"id":"https://openalex.org/keywords/genomics","display_name":"Genomics","score":0.4807029366493225},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.4560842216014862},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4452192783355713},{"id":"https://openalex.org/keywords/sequence-motif","display_name":"Sequence motif","score":0.41275230050086975},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39639168977737427},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.35762888193130493},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.30555325746536255},{"id":"https://openalex.org/keywords/dna","display_name":"DNA","score":0.21710434556007385},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.2024330198764801},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.12053632736206055},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10108301043510437}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5994406938552856},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5373984575271606},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5044289827346802},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5009889602661133},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.48392540216445923},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.4807029366493225},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4560842216014862},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4452192783355713},{"id":"https://openalex.org/C117745874","wikidata":"https://www.wikidata.org/wiki/Q901612","display_name":"Sequence motif","level":3,"score":0.41275230050086975},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39639168977737427},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.35762888193130493},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.30555325746536255},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.21710434556007385},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.2024330198764801},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.12053632736206055},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10108301043510437},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"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":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","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":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004926","descriptor_name":"Escherichia coli","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D004926","descriptor_name":"Escherichia coli","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D004926","descriptor_name":"Escherichia coli","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1109/tcbb.2020.3035021","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tcbb.2020.3035021","pdf_url":"https://ieeexplore.ieee.org/ielx7/8857/9702518/09246292.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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:33125335","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33125335","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},{"id":"pmh:oai:archive.ugent.be:8721761","is_oa":true,"landing_page_url":"http://hdl.handle.net/1854/LU-8721761","pdf_url":null,"source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISSN: 1557-9964","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1109/tcbb.2020.3035021","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tcbb.2020.3035021","pdf_url":"https://ieeexplore.ieee.org/ielx7/8857/9702518/09246292.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4300000071525574,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G8829696140","display_name":null,"funder_award_id":"BOF24j2016001002","funder_id":"https://openalex.org/F4320335227","funder_display_name":"Bijzonder Onderzoeksfonds UGent"}],"funders":[{"id":"https://openalex.org/F4320322603","display_name":"Universiteit Gent","ror":"https://ror.org/00cv9y106"},{"id":"https://openalex.org/F4320327336","display_name":"Vlaamse regering","ror":null},{"id":"https://openalex.org/F4320335227","display_name":"Bijzonder Onderzoeksfonds UGent","ror":"https://ror.org/00cv9y106"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3096508121.pdf","grobid_xml":"https://content.openalex.org/works/W3096508121.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W1019830208","https://openalex.org/W1975924111","https://openalex.org/W1996475592","https://openalex.org/W2048869777","https://openalex.org/W2052024190","https://openalex.org/W2151181684","https://openalex.org/W2333207005","https://openalex.org/W2343039591","https://openalex.org/W2587688848","https://openalex.org/W2889772740","https://openalex.org/W2912984848","https://openalex.org/W2964110616","https://openalex.org/W2991019646","https://openalex.org/W4294170691","https://openalex.org/W4385245566","https://openalex.org/W6637573405","https://openalex.org/W6638583595","https://openalex.org/W6642556909","https://openalex.org/W6646363707","https://openalex.org/W6651112702","https://openalex.org/W6654988515","https://openalex.org/W6655685001","https://openalex.org/W6677222045","https://openalex.org/W6682301761","https://openalex.org/W6682691769","https://openalex.org/W6728895442","https://openalex.org/W6739901393","https://openalex.org/W6741119803","https://openalex.org/W6744294035","https://openalex.org/W6748890919","https://openalex.org/W6749192820","https://openalex.org/W6757069749","https://openalex.org/W6759074601","https://openalex.org/W6763187818","https://openalex.org/W6764680637","https://openalex.org/W6765947112","https://openalex.org/W6768800271","https://openalex.org/W6780226713","https://openalex.org/W6805081885"],"related_works":["https://openalex.org/W3176018525","https://openalex.org/W2903533908","https://openalex.org/W2903810591","https://openalex.org/W2963499882","https://openalex.org/W3026554633","https://openalex.org/W2888520903","https://openalex.org/W2890256614","https://openalex.org/W3098873988","https://openalex.org/W2949454572","https://openalex.org/W3066373881"],"abstract_inverted_index":{"In":[0,36],"genomics,":[1],"a":[2,54],"wide":[3],"range":[4],"of":[5,18,56,73,124,157],"machine":[6],"learning":[7],"methodologies":[8],"have":[9],"been":[10,42],"investigated":[11],"to":[12,144,151],"annotate":[13],"biological":[14],"sequences":[15],"for":[16,59,69,85,98,105,121,154],"positions":[17],"interest":[19],"such":[20],"as":[21,53],"transcription":[22,158],"start":[23,34,159],"sites,":[24,27,29,160],"translation":[25,161],"initiation":[26,162],"methylation":[28,166],"splice":[30],"sites":[31,163],"and":[32,107,116,141,164],"promoter":[33],"sites.":[35],"recent":[37],"years,":[38],"this":[39],"area":[40],"has":[41],"dominated":[43],"by":[44],"convolutional":[45],"neural":[46],"networks,":[47],"which":[48],"typically":[49],"outperform":[50],"previously-designed":[51],"methods":[52],"result":[55],"automated":[57],"scanning":[58],"influential":[60],"sequence":[61,88,138],"motifs.":[62],"However,":[63],"those":[64],"architectures":[65,84],"do":[66],"not":[67],"allow":[68],"the":[70,74,122,155],"efficient":[71],"processing":[72,106],"full":[75],"genomic":[76],"sequence.":[77],"As":[78],"an":[79,118],"improvement,":[80],"we":[81,132],"introduce":[82,117],"transformer":[83],"whole":[86],"genome":[87],"labeling":[89,139],"tasks.":[90],"We":[91,112],"show":[92],"that":[93],"these":[94],"architectures,":[95],"recently":[96],"introduced":[97],"natural":[99],"language":[100],"processing,":[101],"are":[102],"better":[103],"suited":[104],"annotating":[108],"long":[109],"DNA":[110],"sequences.":[111],"apply":[113],"existing":[114],"networks":[115],"optimized":[119],"method":[120],"calculation":[123],"attention":[125],"from":[126],"input":[127],"nucleotides.":[128],"To":[129],"demonstrate":[130],"this,":[131],"evaluate":[133],"our":[134],"architecture":[135],"on":[136],"several":[137],"tasks,":[140],"find":[142],"it":[143,150],"achieve":[145],"state-of-the-art":[146],"performances":[147],"when":[148],"comparing":[149],"specialized":[152],"models":[153],"annotation":[156],"4mC":[165],"in":[167],"E.":[168],"coli.":[169]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":10}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}