{"id":"https://openalex.org/W4387346412","doi":"https://doi.org/10.1145/3584371.3613013","title":"CodonBERT: Using BERT for Sentiment Analysis to Better Predict Genes with Low Expression","display_name":"CodonBERT: Using BERT for Sentiment Analysis to Better Predict Genes with Low Expression","publication_year":2023,"publication_date":"2023-09-03","ids":{"openalex":"https://openalex.org/W4387346412","doi":"https://doi.org/10.1145/3584371.3613013"},"language":"en","primary_location":{"id":"doi:10.1145/3584371.3613013","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3584371.3613013","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3584371.3613013","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3584371.3613013","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045156137","display_name":"Ashley Babjac","orcid":"https://orcid.org/0000-0002-0991-7726"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ashley Nicole Babjac","raw_affiliation_strings":["Department of Computer Science, University of Tennessee, Knoxville, Tennessee, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Tennessee, Knoxville, Tennessee, USA","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000606753","display_name":"Zhixiu Lu","orcid":"https://orcid.org/0009-0000-9904-9741"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhixiu Lu","raw_affiliation_strings":["Department of Computer Science, University of Tennessee, Knoxville, Tennessee, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Tennessee, Knoxville, Tennessee, USA","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019857186","display_name":"Scott Emrich","orcid":"https://orcid.org/0000-0002-5741-4517"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Scott J Emrich","raw_affiliation_strings":["Department of Computer Science, University of Tennessee, Knoxville, Tennessee, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Tennessee, Knoxville, Tennessee, USA","institution_ids":["https://openalex.org/I75027704"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5045156137"],"corresponding_institution_ids":["https://openalex.org/I75027704"],"apc_list":null,"apc_paid":null,"fwci":1.4117,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.81807732,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10521","display_name":"RNA and protein synthesis mechanisms","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/T10521","display_name":"RNA and protein synthesis mechanisms","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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9965999722480774,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9952999949455261,"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/encode","display_name":"ENCODE","score":0.8578833937644958},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7249364852905273},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6592794060707092},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.6248798370361328},{"id":"https://openalex.org/keywords/codon-usage-bias","display_name":"Codon usage bias","score":0.6002784967422485},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.5736060738563538},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.5159986019134521},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5044690370559692},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4970434010028839},{"id":"https://openalex.org/keywords/sentiment-analysis","display_name":"Sentiment analysis","score":0.4670948386192322},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4299430549144745},{"id":"https://openalex.org/keywords/coding-region","display_name":"Coding region","score":0.42951372265815735},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3257402181625366},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.26847127079963684},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.25514209270477295},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.21774283051490784},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07581016421318054},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0696556568145752}],"concepts":[{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.8578833937644958},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7249364852905273},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6592794060707092},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.6248798370361328},{"id":"https://openalex.org/C87253356","wikidata":"https://www.wikidata.org/wiki/Q1106472","display_name":"Codon usage bias","level":4,"score":0.6002784967422485},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5736060738563538},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.5159986019134521},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5044690370559692},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4970434010028839},{"id":"https://openalex.org/C66402592","wikidata":"https://www.wikidata.org/wiki/Q2271421","display_name":"Sentiment analysis","level":2,"score":0.4670948386192322},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4299430549144745},{"id":"https://openalex.org/C91779695","wikidata":"https://www.wikidata.org/wiki/Q3780824","display_name":"Coding region","level":3,"score":0.42951372265815735},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3257402181625366},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.26847127079963684},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.25514209270477295},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.21774283051490784},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07581016421318054},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0696556568145752},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3584371.3613013","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3584371.3613013","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3584371.3613013","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3584371.3613013","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3584371.3613013","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3584371.3613013","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.75,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387346412.pdf","grobid_xml":"https://content.openalex.org/works/W4387346412.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W2018590530","https://openalex.org/W2127303081","https://openalex.org/W2611528178","https://openalex.org/W2766995832","https://openalex.org/W2783989023","https://openalex.org/W2904542630","https://openalex.org/W2949205269","https://openalex.org/W2962101943","https://openalex.org/W3021283815","https://openalex.org/W3090005828","https://openalex.org/W3127238141","https://openalex.org/W3134359595","https://openalex.org/W3184133963","https://openalex.org/W4312054452","https://openalex.org/W4327550249"],"related_works":["https://openalex.org/W2275988210","https://openalex.org/W2359640100","https://openalex.org/W2017840720","https://openalex.org/W3192794374","https://openalex.org/W4362613237","https://openalex.org/W2038779464","https://openalex.org/W2982389646","https://openalex.org/W1994940553","https://openalex.org/W2102511336","https://openalex.org/W2167481233"],"abstract_inverted_index":{"Synonymous":[0],"codons,":[1],"which":[2],"encode":[3],"the":[4,107],"same":[5],"amino":[6],"acid":[7],"in":[8,17,32,62,68],"a":[9,80,94,126,127,155],"protein,":[10],"are":[11,29],"known":[12],"to":[13,24,92,118],"be":[14,175],"used":[15],"unequally":[16],"organisms.":[18,160],"Prior":[19],"research":[20],"has":[21,38],"been":[22],"able":[23],"uncover":[25],"\"preferred\"":[26],"codons":[27],"that":[28,43,130,144,164,173],"often":[30,55],"found":[31],"more":[33,58,133],"highly":[34],"expressed":[35],"genes.":[36],"This":[37],"enabled":[39],"different":[40],"computational":[41],"models":[42],"can":[44,174],"predict":[45],"gene":[46,60,99],"expression":[47,61,67],"of":[48,109,149,158,170],"protein-coding":[49,119],"genes;":[50],"however,":[51],"their":[52,139],"performance":[53],"is":[54,125,147],"affected":[56],"by":[57],"diverse":[59,156],"higher":[63],"organisms,":[64],"i.e.,":[65,112],"high":[66],"only":[69],"specific":[70],"tissues":[71],"or":[72],"cell":[73],"types.":[74],"In":[75],"this":[76],"paper,":[77],"we":[78,142,162],"use":[79],"Natural":[81],"Language":[82],"Processing":[83],"(NLP)":[84],"algorithm,":[85],"Bidirectional":[86],"Encoder":[87],"Representations":[88],"from":[89],"Transformers":[90],"(BERT),":[91],"develop":[93],"new":[95,122],"framework":[96],"for":[97,154],"predicting":[98],"expression.":[100],"Notably,":[101],"our":[102,145,165],"model":[103,129,146,159,166],"architecture":[104],"relies":[105],"on":[106],"idea":[108],"sentiment":[110],"analysis,":[111],"assigning":[113],"an":[114],"overall":[115],"\"emotion\"":[116],"(sentiment)":[117],"sequences.":[120],"Our":[121],"framework,":[123],"CodonBERT,":[124],"pre-trained":[128],"better":[131,152],"captures":[132],"intrinsic":[134],"relationships":[135],"between":[136],"sequences":[137],"and":[138,141],"expression,":[140],"show":[143,163],"capable":[148],"making":[150],"substantially":[151],"predictions":[153],"collection":[157],"Additionally,":[161],"learns":[167],"inherent":[168],"patterns":[169],"codon":[171],"usage":[172],"traced":[176],"using":[177],"explainable":[178],"AI":[179],"(XAI)":[180],"algorithms.":[181]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6}],"updated_date":"2026-03-15T09:29:46.208133","created_date":"2025-10-10T00:00:00"}