{"id":"https://openalex.org/W7155611897","doi":"https://doi.org/10.1093/bioinformatics/btag200","title":"Supervised fine-tuning enhances unsupervised learning from 45 million amino acids in TCR and peptide sequences","display_name":"Supervised fine-tuning enhances unsupervised learning from 45 million amino acids in TCR and peptide sequences","publication_year":2026,"publication_date":"2026-04-21","ids":{"openalex":"https://openalex.org/W7155611897","doi":"https://doi.org/10.1093/bioinformatics/btag200","pmid":"https://pubmed.ncbi.nlm.nih.gov/42032806"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btag200","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btag200","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":true,"oa_status":"gold","oa_url":"https://doi.org/10.1093/bioinformatics/btag200","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020000974","display_name":"Kewei Zhou","orcid":null},"institutions":[{"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":["MO"],"is_corresponding":false,"raw_author_name":"Kewei Zhou","raw_affiliation_strings":["Faculty of Applied Sciences, Macao Polytechnic University Centre for Artificial Intelligence Driven Drug Discovery, , Rua de Lu\u00eds Gonzaga Gomes , Macao, 999078,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Applied Sciences, Macao Polytechnic University Centre for Artificial Intelligence Driven Drug Discovery, , Rua de Lu\u00eds Gonzaga Gomes , Macao, 999078,","institution_ids":["https://openalex.org/I49835588"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134614468","display_name":"Kai Xu","orcid":null},"institutions":[{"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":["MO"],"is_corresponding":false,"raw_author_name":"Kai Xu","raw_affiliation_strings":["Faculty of Applied Sciences, Macao Polytechnic University Centre for Artificial Intelligence Driven Drug Discovery, , Rua de Lu\u00eds Gonzaga Gomes , Macao, 999078,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Applied Sciences, Macao Polytechnic University Centre for Artificial Intelligence Driven Drug Discovery, , Rua de Lu\u00eds Gonzaga Gomes , Macao, 999078,","institution_ids":["https://openalex.org/I49835588"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101326352","display_name":"Shaolong Lin","orcid":null},"institutions":[{"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":["MO"],"is_corresponding":false,"raw_author_name":"Shaolong Lin","raw_affiliation_strings":["Faculty of Applied Sciences, Macao Polytechnic University Centre for Artificial Intelligence Driven Drug Discovery, , Rua de Lu\u00eds Gonzaga Gomes , Macao, 999078,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Applied Sciences, Macao Polytechnic University Centre for Artificial Intelligence Driven Drug Discovery, , Rua de Lu\u00eds Gonzaga Gomes , Macao, 999078,","institution_ids":["https://openalex.org/I49835588"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134594212","display_name":"Silong Zhai","orcid":null},"institutions":[{"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":["MO"],"is_corresponding":false,"raw_author_name":"Silong Zhai","raw_affiliation_strings":["Faculty of Applied Sciences, Macao Polytechnic University Centre for Artificial Intelligence Driven Drug Discovery, , Rua de Lu\u00eds Gonzaga Gomes , Macao, 999078,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Applied Sciences, Macao Polytechnic University Centre for Artificial Intelligence Driven Drug Discovery, , Rua de Lu\u00eds Gonzaga Gomes , Macao, 999078,","institution_ids":["https://openalex.org/I49835588"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054987508","display_name":"Huanxiang Liu","orcid":"https://orcid.org/0000-0002-9284-3667"},"institutions":[{"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":["MO"],"is_corresponding":false,"raw_author_name":"Huanxiang Liu","raw_affiliation_strings":["Faculty of Applied Sciences, Macao Polytechnic University Centre for Artificial Intelligence Driven Drug Discovery, , Rua de Lu\u00eds Gonzaga Gomes , Macao, 999078,"],"raw_orcid":"https://orcid.org/0000-0002-9284-3667","affiliations":[{"raw_affiliation_string":"Faculty of Applied Sciences, Macao Polytechnic University Centre for Artificial Intelligence Driven Drug Discovery, , Rua de Lu\u00eds Gonzaga Gomes , Macao, 999078,","institution_ids":["https://openalex.org/I49835588"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5134589520","display_name":"Xiaojun Yao","orcid":null},"institutions":[{"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":["MO"],"is_corresponding":true,"raw_author_name":"Xiaojun Yao","raw_affiliation_strings":["Faculty of Applied Sciences, Macao Polytechnic University Centre for Artificial Intelligence Driven Drug Discovery, , Rua de Lu\u00eds Gonzaga Gomes , Macao, 999078,"],"raw_orcid":"https://orcid.org/0000-0002-8974-0173","affiliations":[{"raw_affiliation_string":"Faculty of Applied Sciences, Macao Polytechnic University Centre for Artificial Intelligence Driven Drug Discovery, , Rua de Lu\u00eds Gonzaga Gomes , Macao, 999078,","institution_ids":["https://openalex.org/I49835588"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5134589520"],"corresponding_institution_ids":["https://openalex.org/I49835588"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.54136765,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"42","issue":"5","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.32330000400543213,"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":0.32330000400543213,"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":0.20600000023841858,"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/T10519","display_name":"Advanced Proteomics Techniques and Applications","score":0.0738999992609024,"subfield":{"id":"https://openalex.org/subfields/1607","display_name":"Spectroscopy"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.6474999785423279},{"id":"https://openalex.org/keywords/peptide","display_name":"Peptide","score":0.5551999807357788},{"id":"https://openalex.org/keywords/amino-acid","display_name":"Amino acid","score":0.5220999717712402},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.4982999861240387},{"id":"https://openalex.org/keywords/amino-acid-substitution","display_name":"Amino acid substitution","score":0.39070001244544983},{"id":"https://openalex.org/keywords/t-cell-receptor","display_name":"T-cell receptor","score":0.3723999857902527},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.34950000047683716}],"concepts":[{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.6474999785423279},{"id":"https://openalex.org/C2779281246","wikidata":"https://www.wikidata.org/wiki/Q172847","display_name":"Peptide","level":2,"score":0.5551999807357788},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5285000205039978},{"id":"https://openalex.org/C515207424","wikidata":"https://www.wikidata.org/wiki/Q8066","display_name":"Amino acid","level":2,"score":0.5220999717712402},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5174000263214111},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.4982999861240387},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.49079999327659607},{"id":"https://openalex.org/C2993683473","wikidata":"https://www.wikidata.org/wiki/Q30693176","display_name":"Amino acid substitution","level":4,"score":0.39070001244544983},{"id":"https://openalex.org/C19317047","wikidata":"https://www.wikidata.org/wiki/Q412037","display_name":"T-cell receptor","level":4,"score":0.3723999857902527},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.34950000047683716},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.32820001244544983},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3075999915599823},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3003000020980835},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29429998993873596},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.29170000553131104},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2867000102996826},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.2563000023365021},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.25429999828338623},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.2531000077724457}],"mesh":[{"descriptor_ui":"D000069553","descriptor_name":"Supervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069558","descriptor_name":"Unsupervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069558","descriptor_name":"Unsupervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069558","descriptor_name":"Unsupervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010455","descriptor_name":"Peptides","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D010455","descriptor_name":"Peptides","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D010455","descriptor_name":"Peptides","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D010455","descriptor_name":"Peptides","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D010455","descriptor_name":"Peptides","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D010455","descriptor_name":"Peptides","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D011948","descriptor_name":"Receptors, Antigen, T-Cell","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D011948","descriptor_name":"Receptors, Antigen, T-Cell","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D011948","descriptor_name":"Receptors, Antigen, T-Cell","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D011948","descriptor_name":"Receptors, Antigen, T-Cell","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D011948","descriptor_name":"Receptors, Antigen, T-Cell","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D011948","descriptor_name":"Receptors, Antigen, T-Cell","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":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btag200","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btag200","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:42032806","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42032806","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},{"id":"pmh:oai:pubmedcentral.nih.gov:13175252","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13175252/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btag200","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btag200","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.4461129605770111,"id":"https://metadata.un.org/sdg/2","display_name":"Zero hunger"}],"awards":[{"id":"https://openalex.org/G6000416594","display_name":null,"funder_award_id":"0030/2024/RIA1","funder_id":"https://openalex.org/F4320323893","funder_display_name":"Fundo para o Desenvolvimento das Ci\u00eancias e da Tecnologia"}],"funders":[{"id":"https://openalex.org/F4320323893","display_name":"Fundo para o Desenvolvimento das Ci\u00eancias e da Tecnologia","ror":"https://ror.org/05vna4324"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W2156654829","https://openalex.org/W2170747616","https://openalex.org/W2884809460","https://openalex.org/W2945822699","https://openalex.org/W3043056436","https://openalex.org/W3080758869","https://openalex.org/W3113525558","https://openalex.org/W3146944767","https://openalex.org/W3177500196","https://openalex.org/W3196225703","https://openalex.org/W3196626346","https://openalex.org/W4200374506","https://openalex.org/W4206774638","https://openalex.org/W4207047906","https://openalex.org/W4210493562","https://openalex.org/W4220655797","https://openalex.org/W4224120598","https://openalex.org/W4291624945","https://openalex.org/W4320896665","https://openalex.org/W4366816229","https://openalex.org/W4387476832","https://openalex.org/W4391224757","https://openalex.org/W4392199651","https://openalex.org/W4408010982","https://openalex.org/W4408059607","https://openalex.org/W4409956822","https://openalex.org/W4410325217","https://openalex.org/W4411032083","https://openalex.org/W4413775728","https://openalex.org/W4414938342","https://openalex.org/W7117359016","https://openalex.org/W7118021296","https://openalex.org/W7125836389"],"related_works":[],"abstract_inverted_index":{"MOTIVATION:":[0],"T":[1,17],"cell":[2,18],"receptor":[3],"(TCR)":[4],"and":[5,26,49,60,92,102,154],"peptide":[6,50],"interactions":[7],"(TPI)":[8],"are":[9,141],"one":[10],"of":[11,16,22,76,126],"the":[12,105,142],"most":[13],"important":[14],"parts":[15],"immunity.":[19],"Experimental":[20],"identification":[21],"TPI":[23],"is":[24,30,149],"time-consuming":[25],"labor-intensive;":[27],"therefore,":[28],"it":[29],"necessary":[31],"to":[32,41,52,144],"develop":[33],"computational":[34],"prediction":[35,67],"method":[36],"that":[37,135],"exploit":[38],"existing":[39,96],"data":[40],"predict":[42],"TPI.":[43],"RESULTS:":[44],"We":[45],"use":[46],"huge":[47],"TCR":[48,138],"sequences":[51,120],"pre-train":[53],"two":[54],"language":[55,82,98],"models":[56,99],"(\u223c152M":[57],"parameters),":[58],"respectively,":[59],"integrate":[61],"them":[62],"into":[63],"a":[64],"sequence-based":[65],"only":[66],"framework":[68,130],"(i.e.":[69,100],"RoBERTcr)":[70],"with":[71],"supervised":[72],"fine-tuning":[73],"(SFT).":[74],"Visualization":[75],"amino":[77],"acids":[78],"embedding":[79],"from":[80,128],"pre-trained":[81],"model":[83],"(PLM)":[84],"shows":[85],"biochemical":[86],"clusters":[87],"based":[88,116],"on":[89,117],"different":[90],"properties,":[91],"our":[93,129],"PLMs":[94],"outperform":[95],"protein":[97],"ESM":[101],"ProtTrans)":[103],"under":[104],"same":[106],"condition.":[107],"RoBERTcr":[108,148],"achieved":[109],"higher":[110],"performance":[111],"than":[112],"other":[113],"state-of-the-art":[114],"methods":[115],"structures":[118],"or":[119],"without":[121],"dataset":[122],"bias.":[123],"The":[124],"visualization":[125],"attention":[127],"implies":[131],"valuable":[132],"spatial":[133],"information":[134],"residues":[136],"in":[137],"contacting":[139],"peptides":[140],"key":[143],"their":[145],"interaction.":[146],"AVAILABILITY:":[147],"free":[150],"available":[151],"at":[152],"https://fca_icdb.mpu.edu.mo/robertcr/":[153],"https://doi.org/10.5281/zenodo.18043054.":[155]},"counts_by_year":[],"updated_date":"2026-06-24T13:16:06.693445","created_date":"2026-04-26T00:00:00"}
