{"id":"https://openalex.org/W7160538132","doi":"https://doi.org/10.1021/acs.jcim.5c02744","title":"BERT-T6: Toward High-Accuracy T6SS Bacterial Toxin Identification Using a Protein Language Model","display_name":"BERT-T6: Toward High-Accuracy T6SS Bacterial Toxin Identification Using a Protein Language Model","publication_year":2026,"publication_date":"2026-05-07","ids":{"openalex":"https://openalex.org/W7160538132","doi":"https://doi.org/10.1021/acs.jcim.5c02744","pmid":"https://pubmed.ncbi.nlm.nih.gov/42095236"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.5c02744","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.5c02744","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","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/A5135588262","display_name":"Xianwei Mo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210101936","display_name":"Central People's Hospital of Zhanjiang","ror":"https://ror.org/00zzrkp92","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210101936"]},{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]},{"id":"https://openalex.org/I49835588","display_name":"Macao Polytechnic University","ror":"https://ror.org/02sf5td35","country_code":"MO","type":"education","lineage":["https://openalex.org/I49835588"]}],"countries":["CA","CN","MO"],"is_corresponding":false,"raw_author_name":"Xianwei Mo","raw_affiliation_strings":["Centre for Artificial Intelligence Driven Drug Discovery, Faculty of Applied Sciences","Macao Polytechnic University, Rua de Lu\u00eds Gonzaga Gomes","Zhanjiang Institute of Clinical Medicine, Central People\u2019s Hospital of Zhanjiang, No.236 Yuanzhu Road, Zhanjiang, Guangdong 524045 China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Artificial Intelligence Driven Drug Discovery, Faculty of Applied Sciences","institution_ids":["https://openalex.org/I4210164862"]},{"raw_affiliation_string":"Macao Polytechnic University, Rua de Lu\u00eds Gonzaga Gomes","institution_ids":["https://openalex.org/I49835588"]},{"raw_affiliation_string":"Zhanjiang Institute of Clinical Medicine, Central People\u2019s Hospital of Zhanjiang, No.236 Yuanzhu Road, Zhanjiang, Guangdong 524045 China","institution_ids":["https://openalex.org/I4210101936"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135603935","display_name":"Jianxiu Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I4210093057","display_name":"Faculty (United Kingdom)","ror":"https://ror.org/00qpxe165","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210093057"]},{"id":"https://openalex.org/I49835588","display_name":"Macao Polytechnic University","ror":"https://ror.org/02sf5td35","country_code":"MO","type":"education","lineage":["https://openalex.org/I49835588"]}],"countries":["GB","MO"],"is_corresponding":false,"raw_author_name":"Jianxiu Cai","raw_affiliation_strings":["Faculty of Applied Sciences","Macao Polytechnic University, Rua de Lu\u00eds Gonzaga Gomes"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Applied Sciences","institution_ids":["https://openalex.org/I4210093057"]},{"raw_affiliation_string":"Macao Polytechnic University, Rua de Lu\u00eds Gonzaga Gomes","institution_ids":["https://openalex.org/I49835588"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135586170","display_name":"Shirley W. I. Siu","orcid":"https://orcid.org/0000-0002-3695-7758"},"institutions":[{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]},{"id":"https://openalex.org/I49835588","display_name":"Macao Polytechnic University","ror":"https://ror.org/02sf5td35","country_code":"MO","type":"education","lineage":["https://openalex.org/I49835588"]}],"countries":["CA","MO"],"is_corresponding":true,"raw_author_name":"Shirley W. I. Siu","raw_affiliation_strings":["Centre for Artificial Intelligence Driven Drug Discovery, Faculty of Applied Sciences","Macao Polytechnic University, Rua de Lu\u00eds Gonzaga Gomes"],"raw_orcid":"https://orcid.org/0000-0002-3695-7758","affiliations":[{"raw_affiliation_string":"Centre for Artificial Intelligence Driven Drug Discovery, Faculty of Applied Sciences","institution_ids":["https://openalex.org/I4210164862"]},{"raw_affiliation_string":"Macao Polytechnic University, Rua de Lu\u00eds Gonzaga Gomes","institution_ids":["https://openalex.org/I49835588"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5135586170"],"corresponding_institution_ids":["https://openalex.org/I4210164862","https://openalex.org/I49835588"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.4992314,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"66","issue":"10","first_page":"5609","last_page":"5624"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.39480000734329224,"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":0.39480000734329224,"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/T11684","display_name":"Vibrio bacteria research studies","score":0.14949999749660492,"subfield":{"id":"https://openalex.org/subfields/1310","display_name":"Endocrinology"},"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/T13326","display_name":"Biochemical and Structural Characterization","score":0.08079999685287476,"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/generalizability-theory","display_name":"Generalizability theory","score":0.6585999727249146},{"id":"https://openalex.org/keywords/virulence","display_name":"Virulence","score":0.6347000002861023},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.612500011920929},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5692999958992004},{"id":"https://openalex.org/keywords/effector","display_name":"Effector","score":0.5573999881744385},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.37560001015663147},{"id":"https://openalex.org/keywords/bacterial-protein","display_name":"Bacterial protein","score":0.3479999899864197},{"id":"https://openalex.org/keywords/protein\u2013protein-interaction","display_name":"Protein\u2013protein interaction","score":0.3434999883174896}],"concepts":[{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.6585999727249146},{"id":"https://openalex.org/C60987743","wikidata":"https://www.wikidata.org/wiki/Q1460232","display_name":"Virulence","level":3,"score":0.6347000002861023},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.612500011920929},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5746999979019165},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5692999958992004},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5637999773025513},{"id":"https://openalex.org/C51785407","wikidata":"https://www.wikidata.org/wiki/Q2627568","display_name":"Effector","level":2,"score":0.5573999881744385},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5350000262260437},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5275999903678894},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.37560001015663147},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3571000099182129},{"id":"https://openalex.org/C2993175405","wikidata":"https://www.wikidata.org/wiki/Q8054","display_name":"Bacterial protein","level":3,"score":0.3479999899864197},{"id":"https://openalex.org/C11804247","wikidata":"https://www.wikidata.org/wiki/Q896177","display_name":"Protein\u2013protein interaction","level":2,"score":0.3434999883174896},{"id":"https://openalex.org/C2781090273","wikidata":"https://www.wikidata.org/wiki/Q1623405","display_name":"Virulence factor","level":4,"score":0.3215999901294708},{"id":"https://openalex.org/C126831891","wikidata":"https://www.wikidata.org/wiki/Q221673","display_name":"Host (biology)","level":2,"score":0.3116999864578247},{"id":"https://openalex.org/C49039625","wikidata":"https://www.wikidata.org/wiki/Q84230","display_name":"Secretion","level":2,"score":0.29750001430511475},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2897999882698059},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.27869999408721924},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C179185449","wikidata":"https://www.wikidata.org/wiki/Q219699","display_name":"Suppressor","level":3,"score":0.2623000144958496},{"id":"https://openalex.org/C8891405","wikidata":"https://www.wikidata.org/wiki/Q1059","display_name":"Immune system","level":2,"score":0.26089999079704285},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.2540999948978424}],"mesh":[{"descriptor_ui":"D000098410","descriptor_name":"Transfer Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098410","descriptor_name":"Transfer Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001427","descriptor_name":"Bacterial Toxins","qualifier_ui":"Q000032","qualifier_name":"analysis","is_major_topic":true},{"descriptor_ui":"D001427","descriptor_name":"Bacterial Toxins","qualifier_ui":"Q000032","qualifier_name":"analysis","is_major_topic":true},{"descriptor_ui":"D001427","descriptor_name":"Bacterial Toxins","qualifier_ui":"Q000032","qualifier_name":"analysis","is_major_topic":true},{"descriptor_ui":"D001427","descriptor_name":"Bacterial Toxins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D001427","descriptor_name":"Bacterial Toxins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D001427","descriptor_name":"Bacterial Toxins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D058947","descriptor_name":"Bacterial Secretion Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D058947","descriptor_name":"Bacterial Secretion Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D058947","descriptor_name":"Bacterial Secretion Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1021/acs.jcim.5c02744","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.5c02744","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},{"id":"pmid:42095236","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42095236","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":"Journal of chemical information and modeling","raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W1952228151","https://openalex.org/W1966260873","https://openalex.org/W2053574509","https://openalex.org/W2089333639","https://openalex.org/W2097154580","https://openalex.org/W2115486016","https://openalex.org/W2121297944","https://openalex.org/W2170747616","https://openalex.org/W2419295916","https://openalex.org/W2625731836","https://openalex.org/W2790865507","https://openalex.org/W2884767381","https://openalex.org/W2899841051","https://openalex.org/W2936496314","https://openalex.org/W2963351448","https://openalex.org/W3134163647","https://openalex.org/W3146944767","https://openalex.org/W3177500196","https://openalex.org/W4205773061","https://openalex.org/W4210987966","https://openalex.org/W4281665783","https://openalex.org/W4288066876","https://openalex.org/W4304114151","https://openalex.org/W4304957600","https://openalex.org/W4310641985","https://openalex.org/W4312213835","https://openalex.org/W4318071656","https://openalex.org/W4321376757","https://openalex.org/W4323653846","https://openalex.org/W4360603156","https://openalex.org/W4378515434","https://openalex.org/W4380421996","https://openalex.org/W4381597351","https://openalex.org/W4384120498","https://openalex.org/W4385950607","https://openalex.org/W4387653240","https://openalex.org/W4388288522","https://openalex.org/W4390705035","https://openalex.org/W4393445051","https://openalex.org/W4396912951","https://openalex.org/W4400878092","https://openalex.org/W4401021891","https://openalex.org/W4401966068","https://openalex.org/W4402626008","https://openalex.org/W4404729851","https://openalex.org/W4406289821","https://openalex.org/W4406928246","https://openalex.org/W4407086353","https://openalex.org/W4408412676","https://openalex.org/W4408617735","https://openalex.org/W4408977743","https://openalex.org/W4409011676","https://openalex.org/W4412110991"],"related_works":[],"abstract_inverted_index":{"Type":[0],"VI":[1],"secretion":[2],"system":[3],"effectors":[4],"(T6SEs)":[5],"are":[6],"key":[7],"virulence":[8,184],"factors":[9],"that":[10],"disrupt":[11],"critical":[12],"cellular":[13],"components":[14],"in":[15,113,147],"target":[16],"cells,":[17],"facilitating":[18],"bacterial":[19,34,183],"competition":[20],"or":[21],"host":[22],"immune":[23],"evasion.":[24],"Accurate":[25],"identification":[26],"of":[27,64,124,128,132,136,140,145,156,182],"T6SEs":[28],"is":[29],"therefore":[30],"crucial":[31],"for":[32,74,103,168,176],"understanding":[33],"pathogenesis.":[35],"Although":[36],"several":[37],"computational":[38],"predictors":[39],"based":[40],"on":[41,89],"traditional":[42],"machine":[43],"learning":[44,47,102,164],"and":[45,67,116,142,165],"deep":[46],"have":[48],"been":[49],"developed,":[50],"their":[51],"performance":[52],"still":[53],"requires":[54],"improvement.":[55],"In":[56],"this":[57,90],"study,":[58],"we":[59,92],"systematically":[60],"evaluated":[61],"a":[62,95,121,126,130,134,158,173],"range":[63],"sequence-based":[65],"features":[66],"embeddings":[68,80],"from":[69,98],"pretrained":[70],"protein":[71,159],"language":[72,160],"models":[73],"T6SE":[75,104,169],"prediction.":[76,170],"Among":[77],"these,":[78],"ProtBert":[79,99],"were":[81],"identified":[82],"as":[83],"the":[84,154],"most":[85],"effective":[86],"representation.":[87],"Building":[88],"finding,":[91],"present":[93],"BERT-T6,":[94],"predictor":[96],"fine-tuned":[97],"via":[100],"transfer":[101,163],"classification":[105],"with":[106,120,162],"imbalance":[107],"awareness.":[108],"It":[109],"demonstrated":[110],"good":[111],"generalizability":[112],"independent":[114],"test":[115],"achieved":[117],"state-of-the-art":[118],"performance,":[119],"mean":[122],"accuracy":[123],"0.959,":[125],"sensitivity":[127],"0.909,":[129],"specificity":[131],"0.973,":[133],"precision":[135],"0.905,":[137],"an":[138,143],"F1-score":[139],"0.907,":[141],"MCC":[144],"0.881":[146],"five":[148],"repeated":[149],"experiments.":[150],"This":[151],"work":[152],"highlights":[153],"effectiveness":[155],"using":[157],"model":[161],"imbalance-aware":[166],"training":[167],"BERT-T6":[171],"provides":[172],"valuable":[174],"tool":[175],"identifying":[177],"T6SEs,":[178],"supporting":[179],"further":[180],"investigation":[181],"mechanisms.":[185]},"counts_by_year":[],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2026-05-08T00:00:00"}
