{"id":"https://openalex.org/W3131121088","doi":"https://doi.org/10.1093/bioinformatics/btab133","title":"BERT4Bitter: a bidirectional encoder representations from transformers (BERT)-based model for improving the prediction of bitter peptides","display_name":"BERT4Bitter: a bidirectional encoder representations from transformers (BERT)-based model for improving the prediction of bitter peptides","publication_year":2021,"publication_date":"2021-02-24","ids":{"openalex":"https://openalex.org/W3131121088","doi":"https://doi.org/10.1093/bioinformatics/btab133","mag":"3131121088","pmid":"https://pubmed.ncbi.nlm.nih.gov/33638635"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btab133","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btab133","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"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":"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/A5037914988","display_name":"Phasit Charoenkwan","orcid":"https://orcid.org/0000-0002-8161-6856"},"institutions":[{"id":"https://openalex.org/I48076826","display_name":"Chiang Mai University","ror":"https://ror.org/05m2fqn25","country_code":"TH","type":"education","lineage":["https://openalex.org/I48076826"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Phasit Charoenkwan","raw_affiliation_strings":["Modern Management and Information Technology, College of Arts, Media and Technology, Chiang Mai University , Chiang Mai 50200, Thailand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Modern Management and Information Technology, College of Arts, Media and Technology, Chiang Mai University , Chiang Mai 50200, Thailand","institution_ids":["https://openalex.org/I48076826"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043577834","display_name":"Chanin Nantasenamat","orcid":"https://orcid.org/0000-0003-1040-663X"},"institutions":[{"id":"https://openalex.org/I25399158","display_name":"Mahidol University","ror":"https://ror.org/01znkr924","country_code":"TH","type":"education","lineage":["https://openalex.org/I25399158"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Chanin Nantasenamat","raw_affiliation_strings":["Center of Data Mining and Biomedical Informatics, Faculty of Medical Technology, Mahidol University , Bangkok 10700, Thailand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center of Data Mining and Biomedical Informatics, Faculty of Medical Technology, Mahidol University , Bangkok 10700, Thailand","institution_ids":["https://openalex.org/I25399158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061480012","display_name":"Md Mehedi Hasan","orcid":"https://orcid.org/0000-0003-4952-0739"},"institutions":[{"id":"https://openalex.org/I114832834","display_name":"Tulane University","ror":"https://ror.org/04vmvtb21","country_code":"US","type":"education","lineage":["https://openalex.org/I114832834"]},{"id":"https://openalex.org/I207014233","display_name":"Kyushu Institute of Technology","ror":"https://ror.org/02278tr80","country_code":"JP","type":"education","lineage":["https://openalex.org/I207014233"]}],"countries":["JP","US"],"is_corresponding":false,"raw_author_name":"Md Mehedi Hasan","raw_affiliation_strings":["Department of Bioscience and Bioinformatics, Kyushu Institute of Technology , Iizuka, Fukuoka 820-8502, Japan","Tulane Center for Biomedical Informatics and Genomics, Division of Biomedical Informatics and Genomics, John W. Deming Department of Medicine, School of Medicine, Tulane University , New Orleans, LA 70112, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Bioscience and Bioinformatics, Kyushu Institute of Technology , Iizuka, Fukuoka 820-8502, Japan","institution_ids":["https://openalex.org/I207014233"]},{"raw_affiliation_string":"Tulane Center for Biomedical Informatics and Genomics, Division of Biomedical Informatics and Genomics, John W. Deming Department of Medicine, School of Medicine, Tulane University , New Orleans, LA 70112, USA","institution_ids":["https://openalex.org/I114832834"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040180866","display_name":"Balachandran Manavalan","orcid":"https://orcid.org/0000-0003-0697-9419"},"institutions":[{"id":"https://openalex.org/I57664883","display_name":"Ajou University","ror":"https://ror.org/03tzb2h73","country_code":"KR","type":"education","lineage":["https://openalex.org/I57664883"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Balachandran Manavalan","raw_affiliation_strings":["Department of Physiology, Ajou University School of Medicine , Suwon 443380, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Physiology, Ajou University School of Medicine , Suwon 443380, Republic of Korea","institution_ids":["https://openalex.org/I57664883"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084444175","display_name":"Watshara Shoombuatong","orcid":"https://orcid.org/0000-0002-3394-8709"},"institutions":[{"id":"https://openalex.org/I25399158","display_name":"Mahidol University","ror":"https://ror.org/01znkr924","country_code":"TH","type":"education","lineage":["https://openalex.org/I25399158"]}],"countries":["TH"],"is_corresponding":true,"raw_author_name":"Watshara Shoombuatong","raw_affiliation_strings":["Center of Data Mining and Biomedical Informatics, Faculty of Medical Technology, Mahidol University , Bangkok 10700, Thailand"],"raw_orcid":"https://orcid.org/0000-0002-3394-8709","affiliations":[{"raw_affiliation_string":"Center of Data Mining and Biomedical Informatics, Faculty of Medical Technology, Mahidol University , Bangkok 10700, Thailand","institution_ids":["https://openalex.org/I25399158"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5040180866","https://openalex.org/A5084444175"],"corresponding_institution_ids":["https://openalex.org/I25399158","https://openalex.org/I57664883"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":11.0718,"has_fulltext":false,"cited_by_count":176,"citation_normalized_percentile":{"value":0.99160916,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"37","issue":"17","first_page":"2556","last_page":"2562"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.6715999841690063,"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":0.6715999841690063,"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/T11561","display_name":"Protein Hydrolysis and Bioactive Peptides","score":0.0544000007212162,"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/T11667","display_name":"Advanced Chemical Sensor Technologies","score":0.03240000084042549,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.755073070526123},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.668323278427124},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6176561117172241},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6090307831764221},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5788155794143677},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5551763772964478},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5215528011322021},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.47342661023139954},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.42595499753952026},{"id":"https://openalex.org/keywords/web-server","display_name":"Web server","score":0.4230361878871918},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.4160754084587097},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.1364101767539978},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.12285548448562622},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.11671623587608337},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.10599935054779053},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08159211277961731}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.755073070526123},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.668323278427124},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6176561117172241},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6090307831764221},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5788155794143677},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5551763772964478},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5215528011322021},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.47342661023139954},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.42595499753952026},{"id":"https://openalex.org/C11392498","wikidata":"https://www.wikidata.org/wiki/Q11288","display_name":"Web server","level":3,"score":0.4230361878871918},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.4160754084587097},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.1364101767539978},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.12285548448562622},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.11671623587608337},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.10599935054779053},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08159211277961731},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/btab133","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btab133","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"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":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:33638635","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33638635","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":"Bioinformatics (Oxford, England)","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7300000190734863,"id":"https://metadata.un.org/sdg/2","display_name":"Zero hunger"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W1501531009","https://openalex.org/W1607581237","https://openalex.org/W1977538566","https://openalex.org/W2004353783","https://openalex.org/W2015861736","https://openalex.org/W2023306209","https://openalex.org/W2057851162","https://openalex.org/W2064675550","https://openalex.org/W2089885047","https://openalex.org/W2101234009","https://openalex.org/W2101746535","https://openalex.org/W2124335086","https://openalex.org/W2139752415","https://openalex.org/W2150874198","https://openalex.org/W2284978990","https://openalex.org/W2340720529","https://openalex.org/W2520488855","https://openalex.org/W2589065420","https://openalex.org/W2604272474","https://openalex.org/W2624385633","https://openalex.org/W2709823493","https://openalex.org/W2734608416","https://openalex.org/W2756470092","https://openalex.org/W2791848964","https://openalex.org/W2883969623","https://openalex.org/W2888955024","https://openalex.org/W2911489562","https://openalex.org/W2946834045","https://openalex.org/W2951765074","https://openalex.org/W2952126842","https://openalex.org/W2963740900","https://openalex.org/W2971432438","https://openalex.org/W2971874382","https://openalex.org/W2977291005","https://openalex.org/W2999143619","https://openalex.org/W2999580270","https://openalex.org/W3009548091","https://openalex.org/W3009776949","https://openalex.org/W3009820544","https://openalex.org/W3013552211","https://openalex.org/W3015957975","https://openalex.org/W3033211610","https://openalex.org/W3037668068","https://openalex.org/W3039241573","https://openalex.org/W3046351677","https://openalex.org/W3084375074","https://openalex.org/W3090580446","https://openalex.org/W3093729849","https://openalex.org/W3096599651","https://openalex.org/W4206174637","https://openalex.org/W6675354045","https://openalex.org/W6779841872","https://openalex.org/W6780239951","https://openalex.org/W6784820139"],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2341842940","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W2291782699","https://openalex.org/W1993948687","https://openalex.org/W2059640416","https://openalex.org/W2329895846"],"abstract_inverted_index":{"MOTIVATION:":[0],"The":[1,184],"identification":[2,37],"of":[3,20,31,38,78,111,140,153,188],"bitter":[4,40,62,94,174],"peptides":[5,41,63,175],"through":[6],"experimental":[7],"approaches":[8],"is":[9,42,82,192],"an":[10,109],"expensive":[11],"and":[12,113,117,143,151,171,179],"time-consuming":[13],"endeavor.":[14],"Due":[15],"to":[16,92,97],"the":[17,26,29,36,76,83,105,127,135,149,158,189],"huge":[18],"number":[19],"newly":[21],"available":[22,202],"peptide":[23],"sequences":[24],"in":[25],"post-genomic":[27],"era,":[28],"development":[30,178],"automated":[32],"computational":[33],"models":[34],"for":[35,60,115,168,176],"novel":[39,173],"highly":[43],"desirable.":[44],"RESULTS:":[45],"In":[46],"this":[47,81],"work,":[48],"we":[49],"present":[50],"BERT4Bitter,":[51],"a":[52,86,165],"bidirectional":[53],"encoder":[54],"representation":[55],"from":[56,65],"transformers":[57],"(BERT)-based":[58],"model":[59,88],"predicting":[61],"directly":[64],"their":[66],"amino":[67],"acid":[68],"sequence":[69],"without":[70],"using":[71],"any":[72],"structural":[73],"information.":[74],"To":[75],"best":[77,106],"our":[79],"knowledge,":[80],"first":[84],"time":[85],"BERT-based":[87],"has":[89],"been":[90],"employed":[91],"identify":[93],"peptides.":[95],"Compared":[96],"widely":[98],"used":[99],"machine":[100],"learning":[101],"models,":[102],"BERT4Bitter":[103,132,159,191],"achieved":[104],"performance":[107],"with":[108,138],"accuracy":[110,142],"0.861":[112],"0.922":[114],"cross-validation":[116],"independent":[118,128],"tests,":[119],"respectively.":[120],"Furthermore,":[121],"extensive":[122],"empirical":[123],"benchmarking":[124],"experiments":[125],"on":[126],"dataset":[129],"demonstrated":[130],"that":[131,157],"clearly":[133],"outperformed":[134],"existing":[136],"method":[137,160],"improvements":[139],"8.0%":[141],"16.0%":[144],"Matthews":[145],"coefficient":[146],"correlation,":[147],"highlighting":[148],"effectiveness":[150],"robustness":[152],"BERT4Bitter.":[154],"We":[155],"believe":[156],"proposed":[161,190],"herein":[162],"will":[163],"be":[164],"useful":[166],"tool":[167],"rapidly":[169],"screening":[170],"identifying":[172],"drug":[177],"nutritional":[180],"research.":[181],"AVAILABILITYAND":[182],"IMPLEMENTATION:":[183],"user-friendly":[185],"web":[186],"server":[187],"freely":[193],"accessible":[194],"at":[195,203],"http://pmlab.pythonanywhere.com/BERT4Bitter.":[196],"SUPPLEMENTARY":[197],"INFORMATION:":[198],"Supplementary":[199],"data":[200],"are":[201],"Bioinformatics":[204],"online.":[205]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":37},{"year":2024,"cited_by_count":46},{"year":2023,"cited_by_count":30},{"year":2022,"cited_by_count":39},{"year":2021,"cited_by_count":21}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}