{"id":"https://openalex.org/W4406259932","doi":"https://doi.org/10.1109/bibm62325.2024.10822735","title":"A large language model for predicting T cell receptor-antigen binding specificity","display_name":"A large language model for predicting T cell receptor-antigen binding specificity","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4406259932","doi":"https://doi.org/10.1109/bibm62325.2024.10822735"},"language":"en","primary_location":{"id":"doi:10.1109/bibm62325.2024.10822735","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm62325.2024.10822735","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"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/A5102871890","display_name":"Xing Fang","orcid":"https://orcid.org/0000-0002-1801-6831"},"institutions":[{"id":"https://openalex.org/I134687103","display_name":"Nanjing Tech University","ror":"https://ror.org/03sd35x91","country_code":"CN","type":"education","lineage":["https://openalex.org/I134687103"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xing Fang","raw_affiliation_strings":["Nanjing Tech University,College of Computer and Information Engineering,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing Tech University,College of Computer and Information Engineering,Nanjing,China","institution_ids":["https://openalex.org/I134687103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104298204","display_name":"Chenpeng Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I134687103","display_name":"Nanjing Tech University","ror":"https://ror.org/03sd35x91","country_code":"CN","type":"education","lineage":["https://openalex.org/I134687103"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenpeng Yu","raw_affiliation_strings":["Nanjing Tech University,College of Computer and Information Engineering,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing Tech University,College of Computer and Information Engineering,Nanjing,China","institution_ids":["https://openalex.org/I134687103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113266694","display_name":"Shiye Tian","orcid":null},"institutions":[{"id":"https://openalex.org/I134687103","display_name":"Nanjing Tech University","ror":"https://ror.org/03sd35x91","country_code":"CN","type":"education","lineage":["https://openalex.org/I134687103"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiye Tian","raw_affiliation_strings":["Nanjing Tech University,College of Computer and Information Engineering,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing Tech University,College of Computer and Information Engineering,Nanjing,China","institution_ids":["https://openalex.org/I134687103"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100387512","display_name":"Hui Liu","orcid":"https://orcid.org/0000-0001-7158-913X"},"institutions":[{"id":"https://openalex.org/I134687103","display_name":"Nanjing Tech University","ror":"https://ror.org/03sd35x91","country_code":"CN","type":"education","lineage":["https://openalex.org/I134687103"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Liu","raw_affiliation_strings":["Nanjing Tech University,College of Computer and Information Engineering,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing Tech University,College of Computer and Information Engineering,Nanjing,China","institution_ids":["https://openalex.org/I134687103"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I134687103"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1489","last_page":"1492"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12576","display_name":"vaccines and immunoinformatics approaches","score":0.986299991607666,"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/T12576","display_name":"vaccines and immunoinformatics approaches","score":0.986299991607666,"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/T11016","display_name":"Monoclonal and Polyclonal Antibodies Research","score":0.9616000056266785,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10911","display_name":"Chemical Synthesis and Analysis","score":0.954200029373169,"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":0.5497156977653503},{"id":"https://openalex.org/keywords/receptor","display_name":"Receptor","score":0.4219190776348114},{"id":"https://openalex.org/keywords/antigen","display_name":"Antigen","score":0.41986745595932007},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.41279780864715576},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.25217464566230774},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.22902223467826843},{"id":"https://openalex.org/keywords/immunology","display_name":"Immunology","score":0.14619076251983643},{"id":"https://openalex.org/keywords/biochemistry","display_name":"Biochemistry","score":0.12324920296669006}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5497156977653503},{"id":"https://openalex.org/C170493617","wikidata":"https://www.wikidata.org/wiki/Q208467","display_name":"Receptor","level":2,"score":0.4219190776348114},{"id":"https://openalex.org/C147483822","wikidata":"https://www.wikidata.org/wiki/Q103537","display_name":"Antigen","level":2,"score":0.41986745595932007},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.41279780864715576},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.25217464566230774},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.22902223467826843},{"id":"https://openalex.org/C203014093","wikidata":"https://www.wikidata.org/wiki/Q101929","display_name":"Immunology","level":1,"score":0.14619076251983643},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.12324920296669006}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm62325.2024.10822735","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm62325.2024.10822735","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2031011895","https://openalex.org/W2163660115","https://openalex.org/W2409761064","https://openalex.org/W3080758869","https://openalex.org/W3196225703","https://openalex.org/W3198942356","https://openalex.org/W4312982034","https://openalex.org/W4323320132","https://openalex.org/W4388979610","https://openalex.org/W6730161283","https://openalex.org/W6755207826","https://openalex.org/W6811456798"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"The":[0,28,215],"human":[1,31],"immune":[2],"response":[3,194],"depends":[4],"on":[5,51,126,143,198],"the":[6,17,42,52,88,107,112,171,180],"binding":[7,54,165],"of":[8,30,139,182],"T-cell":[9],"receptors":[10],"(TCRs)":[11],"to":[12,20,35,68,71,86,105,118],"antigens":[13],"(pTCR),":[14],"which":[15,152],"elicits":[16],"T":[18],"cells":[19],"eliminate":[21],"viruses,":[22],"tumor":[23],"cells,":[24],"and":[25,38,83,123,141,147,195,218],"other":[26],"pathogens.":[27],"ability":[29],"immunity":[32],"system":[33],"responding":[34],"unknown":[36],"viruses":[37],"bacteria":[39],"stems":[40],"from":[41,95],"TCR":[43,96,114],"diversity.":[44],"However,":[45],"this":[46,58,127,222],"vast":[47],"diversity":[48],"poses":[49],"challenges":[50],"TCR-antigen":[53],"prediction":[55,158],"methods.":[56,159],"In":[57],"study,":[59],"we":[60,78,99,186],"propose":[61],"a":[62,161,199],"Masked":[63],"Language":[64],"Model":[65],"(MLM),":[66],"referred":[67],"as":[69],"tcrLM,":[70],"overcome":[72],"limitations":[73],"in":[74,211,221],"model":[75],"generalization.":[76],"Specifically,":[77],"randomly":[79],"masked":[80,89],"sequence":[81,116],"segments":[82],"train":[84],"tcrLM":[85,125,135,207],"infer":[87],"segment,":[90],"thereby":[91],"extract":[92],"expressive":[93],"feature":[94],"sequences.":[97],"Meanwhile,":[98],"introduced":[100],"virtual":[101],"adversarial":[102],"training":[103],"techniques":[104],"enhance":[106],"model\u2019s":[108],"robustness.":[109],"We":[110],"built":[111],"largest":[113],"CDR3":[115],"dataset":[117],"date":[119],"(comprising":[120],"2,277,773,840":[121],"residuals),":[122],"pre-trained":[124],"dataset.":[128],"Our":[129],"extensive":[130],"experimental":[131],"results":[132],"demonstrate":[133],"that":[134,188,206],"achieved":[136],"AUC":[137],"values":[138],"0.937":[140],"0.933":[142],"independent":[144],"test":[145,166],"sets":[146],"external":[148],"validation":[149],"sets,":[150],"respectively,":[151],"remarkably":[153],"outperformed":[154],"four":[155],"previously":[156],"published":[157],"On":[160],"large-scale":[162],"COVID-19":[163],"pTCR":[164],"set,":[167],"our":[168,183,189],"method":[169,174],"outperforms":[170],"current":[172],"state-of-the-art":[173],"by":[175],"at":[176],"least":[177],"8%,":[178],"highlighting":[179],"generalizability":[181],"method.":[184],"Furthermore,":[185],"validated":[187],"approach":[190],"effectively":[191],"predicts":[192],"immunotherapy":[193],"clinical":[196,200],"outcomes":[197],"cohorts.":[201],"These":[202],"findings":[203],"clearly":[204],"indicate":[205],"exhibits":[208],"significant":[209],"potential":[210],"predicting":[212],"antigenic":[213],"immunogenicity.":[214],"source":[216],"code":[217],"datasets":[219],"used":[220],"study":[223],"are":[224],"available":[225],"at:":[226],"https://github.com/hliulab/tcrLM.":[227]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}