{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T08:04:16Z","timestamp":1781078656019,"version":"3.54.1"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T00:00:00Z","timestamp":1781049600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T00:00:00Z","timestamp":1781049600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100002345","name":"Eberhard Karls Universit\u00e4t T\u00fcbingen","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100002345","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Bioinformatics"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>We study the prediction of T-cell response for specific given peptides, which could, among other applications, be a crucial step towards the development of personalized cancer vaccines. It is a challenging task due to limited, heterogeneous training data featuring a multi-domain structure; such data entail the danger of shortcut learning, where models learn general characteristics of peptide sources, such as the source organism, rather than specific peptide characteristics associated with T-cell response. Using a transformer model for T-cell response prediction, we show that the danger of inflated predictive performance is not merely theoretical but occurs in practice. Consequently, we propose a domain-aware evaluation scheme. We then study different transfer learning techniques to deal with the multi-domain structure and shortcut learning. We demonstrate a per-source fine tuning approach to be effective across a wide range of peptide sources and further show that our final model is competitive with existing state-of-the-art approaches for predicting T-cell responses for human peptides.<\/jats:p>","DOI":"10.1186\/s12859-026-06492-2","type":"journal-article","created":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T07:18:43Z","timestamp":1781075923000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Transfer learning for T-cell response prediction"],"prefix":"10.1186","volume":"27","author":[{"given":"Josua","family":"Stadelmaier","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Brandon","family":"Malone","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ralf","family":"Eggeling","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,10]]},"reference":[{"key":"6492_CR1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-56004-4","volume-title":"Janeway Immunologie","author":"K Murphy","year":"2018","unstructured":"Murphy K, Weaver C. Janeway Immunologie. 9th ed. Wiesbaden: Springer; 2018.","edition":"9"},{"issue":"6382","key":"6492_CR2","doi-asserted-by":"publisher","first-page":"1355","DOI":"10.1126\/science.aar7112","volume":"359","author":"U Sahin","year":"2018","unstructured":"Sahin U, T\u00fcreci \u00d6. Personalized vaccines for cancer immunotherapy. Science. 2018;359(6382):1355\u201360.","journal-title":"Science"},{"issue":"7894","key":"6492_CR3","doi-asserted-by":"publisher","first-page":"617","DOI":"10.1038\/s41586-021-04232-5","volume":"601","author":"JS Heitmann","year":"2022","unstructured":"Heitmann JS, Bilich T, Tandler C, Nelde A, Maringer Y, Marconato M, et al. A COVID-19 peptide vaccine for the induction of SARS-CoV-2 T cell immunity. Nature. 2022;601(7894):617\u201322.","journal-title":"Nature"},{"issue":"W1","key":"6492_CR4","doi-asserted-by":"publisher","first-page":"449","DOI":"10.1093\/nar\/gkaa379","volume":"48","author":"B Reynisson","year":"2020","unstructured":"Reynisson B, Alvarez B, Paul S, Peters B, Nielsen M. NetMHCpan-4.1 and NetMHCIIpan-4.0: improved predictions of MHC antigen presentation by concurrent motif deconvolution and integration of MS MHC eluted ligand data. Nucleic Acids Res. 2020;48(W1):449\u201354.","journal-title":"Nucleic Acids Res"},{"issue":"1","key":"6492_CR5","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1016\/j.cels.2020.06.010","volume":"11","author":"TJ O\u2019Donnell","year":"2020","unstructured":"O\u2019Donnell TJ, Rubinsteyn A, Laserson U. MHCflurry 2.0: improved pan-allele prediction of MHC class I-presented peptides by incorporating antigen processing. Cell Syst. 2020;11(1):42\u2013487.","journal-title":"Cell Syst"},{"key":"6492_CR6","doi-asserted-by":"publisher","first-page":"4172","DOI":"10.1093\/bioinformatics\/btab422","volume":"37","author":"J Cheng","year":"2021","unstructured":"Cheng J, Bendjama K, Rittner K, Malone B. BERTMHC: improved MHC-peptide class II interaction prediction with transformer and multiple instance learning. Bioinformatics. 2021;37:4172\u20139.","journal-title":"Bioinformatics"},{"issue":"1","key":"6492_CR7","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1016\/j.cels.2022.12.002","volume":"14","author":"D Gfeller","year":"2023","unstructured":"Gfeller D, Schmidt J, Croce G, Guillaume P, Bobisse S, Genolet R, et al. Improved predictions of antigen presentation and TCR recognition with MixMHCpred2.2 and PRIME2.0 reveal potent SARS-CoV-2 CD8+ T-cell epitopes. Cell Syst. 2023;14(1):72\u2013835.","journal-title":"Cell Syst"},{"key":"6492_CR8","doi-asserted-by":"publisher","first-page":"1369","DOI":"10.3389\/fimmu.2018.01369","volume":"9","author":"SK Dhanda","year":"2018","unstructured":"Dhanda SK, Karosiene E, Edwards L, Grifoni A, Paul S, Andreatta M, et al. Predicting HLA CD4 immunogenicity in human populations. Front Immunol. 2018;9:1369.","journal-title":"Front Immunol"},{"issue":"D1","key":"6492_CR9","doi-asserted-by":"publisher","first-page":"339","DOI":"10.1093\/nar\/gky1006","volume":"47","author":"R Vita","year":"2018","unstructured":"Vita R, Mahajan S, Overton JA, Dhanda SK, Martini S, Cantrell JR, et al. The immune epitope database (IEDB): 2018 update. Nucleic Acids Res. 2018;47(D1):339\u201343.","journal-title":"Nucleic Acids Res"},{"issue":"4","key":"6492_CR10","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1007\/BF00172063","volume":"41","author":"H-G Rammensee","year":"1995","unstructured":"Rammensee H-G, Friede T, Stevanovi\u0107 S. MHC ligands and peptide motifs: first listing. Immunogenetics. 1995;41(4):178\u2013228.","journal-title":"Immunogenetics"},{"key":"6492_CR11","doi-asserted-by":"publisher","first-page":"827","DOI":"10.3389\/fimmu.2019.00827","volume":"10","author":"M Ogishi","year":"2019","unstructured":"Ogishi M, Yotsuyanagi H. Quantitative prediction of the landscape of T cell epitope immunogenicity in sequence space. Front Immunol. 2019;10:827.","journal-title":"Front Immunol"},{"issue":"1","key":"6492_CR12","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1186\/s13073-023-01225-z","volume":"15","author":"CH Lee","year":"2023","unstructured":"Lee CH, Huh J, Buckley PR, Jang M, Pinho MP, Fernandes RA, et al. A robust deep learning workflow to predict cd8+ t-cell epitopes. Genome Medicine. 2023;15(1):70.","journal-title":"Genome Medicine"},{"issue":"10","key":"6492_CR13","doi-asserted-by":"publisher","first-page":"e1003266","DOI":"10.1371\/journal.pcbi.1003266","volume":"9","author":"JJ Calis","year":"2013","unstructured":"Calis JJ, Maybeno M, Greenbaum JA. Properties of MHC class I presented peptides that enhance immunogenicity. PLoS Comput Biol. 2013;9(10):e1003266.","journal-title":"PLoS Comput Biol"},{"key":"6492_CR14","first-page":"5998","volume":"30","author":"A Vaswani","year":"2017","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, et al. Attention is all you need. Adv Neural Inf Process Syst. 2017;30:5998\u20136008.","journal-title":"Adv Neural Inf Process Syst"},{"issue":"10","key":"6492_CR15","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","volume":"22","author":"SJ Pan","year":"2009","unstructured":"Pan SJ, Yang Q. A survey on transfer learning. IEEE Trans Knowl Data Eng. 2009;22(10):1345\u201359.","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"6492_CR16","unstructured":"Rosenstein MT. To transfer or not to transfer. In: NIPS 2005. 2005."},{"issue":"6","key":"6492_CR17","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1093\/bib\/bbab160","volume":"22","author":"G Li","year":"2021","unstructured":"Li G, Iyer B, Prasath VS, Ni Y, Salomonis N. Deepimmuno: deep learning-empowered prediction and generation of immunogenic peptides for t-cell immunity. Brief Bioinform. 2021;22(6):160.","journal-title":"Brief Bioinform"},{"issue":"1","key":"6492_CR18","doi-asserted-by":"publisher","first-page":"4314","DOI":"10.1038\/s41467-023-39902-7","volume":"14","author":"A Brown","year":"2023","unstructured":"Brown A, Tomasev N, Freyberg J, Liu Y, Karthikesalingam A, Schrouff J. Detecting shortcut learning for fair medical ai using shortcut testing. Nat Commun. 2023;14(1):4314.","journal-title":"Nat Commun"},{"issue":"11","key":"6492_CR19","doi-asserted-by":"publisher","first-page":"665","DOI":"10.1038\/s42256-020-00257-z","volume":"2","author":"R Geirhos","year":"2020","unstructured":"Geirhos R, Jacobsen J-H, Michaelis C, Zemel R, Brendel W, Bethge M, et al. Shortcut learning in deep neural networks. Nat Mach Intell. 2020;2(11):665\u201373.","journal-title":"Nat Mach Intell"},{"issue":"1","key":"6492_CR20","doi-asserted-by":"publisher","first-page":"238","DOI":"10.1186\/1471-2105-8-238","volume":"8","author":"M Nielsen","year":"2007","unstructured":"Nielsen M, Lundegaard C, Lund O. Prediction of MHC class II binding affinity using SMM-align, a novel stabilization matrix alignment method. BMC Bioinform. 2007;8(1):238.","journal-title":"BMC Bioinform"},{"issue":"1","key":"6492_CR21","doi-asserted-by":"publisher","first-page":"387","DOI":"10.1186\/s12859-015-0767-x","volume":"16","author":"M Nettling","year":"2015","unstructured":"Nettling M, Treutler H, Grau J, Keilwagen J, Posch S, Grosse I. Difflogo: a comparative visualization of sequence motifs. BMC Bioinform. 2015;16(1):387.","journal-title":"BMC Bioinform"},{"issue":"1","key":"6492_CR22","doi-asserted-by":"publisher","first-page":"375","DOI":"10.1186\/s12859-015-0797-4","volume":"16","author":"R Eggeling","year":"2015","unstructured":"Eggeling R, Roos T, Myllym\u00e4ki P, Grosse I. Inferring intra-motif dependencies of DNA binding sites from ChIP-seq data. BMC Bioinform. 2015;16(1):375.","journal-title":"BMC Bioinform"},{"key":"6492_CR23","doi-asserted-by":"crossref","unstructured":"Rao R, Bhattacharya N, Thomas N, Duan Y, Chen P, Canny J, et al. Evaluating protein transfer learning with TAPE. Adv Neural Inf Process Syst. 2019;32:9689\u20139701.","DOI":"10.1101\/676825"},{"key":"6492_CR24","doi-asserted-by":"crossref","unstructured":"Tzeng E, Hoffman J, Saenko K, Darrell T. Adversarial discriminative domain adaptation. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2017. pp. 7167\u201376.","DOI":"10.1109\/CVPR.2017.316"},{"key":"6492_CR25","unstructured":"Schoenauer Sebag A, Heinrich L, Schoenauer M, Sebag M, Wu L, Altschuler S. Multi-domain adversarial learning. In: ICLR 2019 - Seventh annual international conference on learning representations. New Orleans, United States; 2019."},{"key":"6492_CR26","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, et al. Scikit-learn: machine learning in Python. J Mach Learn Res. 2011;12:2825\u201330.","journal-title":"J Mach Learn Res"},{"issue":"11","key":"6492_CR27","first-page":"2579","volume":"9","author":"L Maaten","year":"2008","unstructured":"Maaten L, Hinton G. Visualizing data using t-SNE. J Mach Learn Res. 2008;9(11):2579\u2013605.","journal-title":"J Mach Learn Res"},{"issue":"4","key":"6492_CR28","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1038\/s41573-021-00387-y","volume":"21","author":"F Lang","year":"2022","unstructured":"Lang F, Schr\u00f6rs B, L\u00f6wer M, T\u00fcreci \u00d6, Sahin U. Identification of neoantigens for individualized therapeutic cancer vaccines. Nat Rev Drug Discov. 2022;21(4):261\u201382.","journal-title":"Nat Rev Drug Discov"},{"key":"6492_CR29","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1016\/j.jim.2015.03.022","volume":"422","author":"S Paul","year":"2015","unstructured":"Paul S, Arlehamn CSL, Scriba TJ, Dillon MB, Oseroff C, Hinz D, et al. Development and validation of a broad scheme for prediction of HLA class II restricted T cell epitopes. J Immunol Methods. 2015;422:28\u201334.","journal-title":"J Immunol Methods"},{"key":"6492_CR30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41577-023-00835-3","volume":"23","author":"D Hudson","year":"2023","unstructured":"Hudson D, Fernandes RA, Basham M, Ogg G, Koohy H. Can we predict T cell specificity with digital biology and machine learning? Nat Rev Immunol. 2023;23:1\u201311.","journal-title":"Nat Rev Immunol"},{"issue":"8","key":"6492_CR31","doi-asserted-by":"publisher","first-page":"e4379","DOI":"10.1002\/pro.4379","volume":"31","author":"R Yin","year":"2022","unstructured":"Yin R, Feng BY, Varshney A, Pierce BG. Benchmarking AlphaFold for protein complex modeling reveals accuracy determinants. Protein Sci. 2022;31(8):e4379.","journal-title":"Protein Sci"},{"issue":"8","key":"6492_CR32","doi-asserted-by":"publisher","first-page":"9416","DOI":"10.15252\/msb.20199416","volume":"16","author":"DS Fischer","year":"2020","unstructured":"Fischer DS, Wu Y, Schubert B, Theis FJ. Predicting antigen specificity of single T cells based on TCR CDR 3 regions. Mol Syst Biol. 2020;16(8):9416.","journal-title":"Mol Syst Biol"},{"issue":"3","key":"6492_CR33","doi-asserted-by":"publisher","first-page":"818","DOI":"10.1016\/j.cell.2020.09.015","volume":"183","author":"DK Wells","year":"2020","unstructured":"Wells DK, Buuren MM, Dang KK, Hubbard-Lucey VM, Sheehan KC, Campbell KM, et al. Key parameters of tumor epitope immunogenicity revealed through a consortium approach improve neoantigen prediction. Cell. 2020;183(3):818\u201334.","journal-title":"Cell"},{"issue":"3","key":"6492_CR34","doi-asserted-by":"publisher","first-page":"569","DOI":"10.1016\/j.celrep.2017.03.072","volume":"19","author":"G Chen","year":"2017","unstructured":"Chen G, Yang X, Ko A, Sun X, Gao M, Zhang Y, et al. Sequence and structural analyses reveal distinct and highly diverse human CD8+ TCR repertoires to immunodominant viral antigens. Cell Rep. 2017;19(3):569\u201383.","journal-title":"Cell Rep"},{"key":"6492_CR35","doi-asserted-by":"publisher","DOI":"10.1016\/j.immuno.2024.100045","volume":"16","author":"M Nielsen","year":"2024","unstructured":"Nielsen M, Eugster A, Jensen MF, Goel M, Tiffeau-Mayer A, Pelissier A, et al. Lessons learned from the immrep23 tcr-epitope prediction challenge. ImmunoInformatics. 2024;16:100045.","journal-title":"ImmunoInformatics"},{"key":"6492_CR36","doi-asserted-by":"publisher","first-page":"100024","DOI":"10.1016\/j.immuno.2023.100024","volume":"9","author":"P Meysman","year":"2023","unstructured":"Meysman P, Barton J, Bravi B, Cohen-Lavi L, Karnaukhov V, Lilleskov E, et al. Benchmarking solutions to the t-cell receptor epitope prediction problem: Immrep22 workshop report. ImmunoInformatics. 2023;9:100024.","journal-title":"ImmunoInformatics"},{"issue":"3","key":"6492_CR37","doi-asserted-by":"publisher","first-page":"236","DOI":"10.1038\/s42256-023-00619-3","volume":"5","author":"Y Gao","year":"2023","unstructured":"Gao Y, Gao Y, Fan Y, Zhu C, Wei Z, Zhou C, et al. Pan-peptide meta learning for t-cell receptor-antigen binding recognition. Nat Mach Intell. 2023;5(3):236\u201349.","journal-title":"Nat Mach Intell"},{"issue":"1","key":"6492_CR38","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1093\/bib\/bbad436","volume":"25","author":"J Zhang","year":"2024","unstructured":"Zhang J, Ma W, Yao H. Accurate tcr-pmhc interaction prediction using a bert-based transfer learning method. Brief Bioinform. 2024;25(1):436.","journal-title":"Brief Bioinform"},{"issue":"24","key":"6492_CR39","doi-asserted-by":"publisher","first-page":"e2316401121","DOI":"10.1073\/pnas.2316401121","volume":"121","author":"B Meynard-Piganeau","year":"2024","unstructured":"Meynard-Piganeau B, Feinauer C, Weigt M, Walczak AM, Mora T. Tulip: A transformer-based unsupervised language model for interacting peptides and t cell receptors that generalizes to unseen epitopes. Proc Natl Acad Sci. 2024;121(24):e2316401121.","journal-title":"Proc Natl Acad Sci"},{"key":"6492_CR40","doi-asserted-by":"crossref","unstructured":"Culka M, Lounsbury NW, Thrift W, Nerli S, Wallace A, Nikolenyi G, Orlova D, Mukhyala K, AlQuraishi M. Predicting specificity of tcr-pmhc interactions using machine learning and biophysical models. bioRxiv, 2025\u201304 2025.","DOI":"10.1101\/2025.04.04.647165"},{"key":"6492_CR41","doi-asserted-by":"crossref","unstructured":"Li S, Zong C. Multi-domain sentiment classification. In: Moore JD, Teufel S, Allan J, Furui S, editors. Proceedings of ACL-08: HLT, Short Papers. Columbus, Ohio: Association for Computational Linguistics; 2008. p. 257\u201360.","DOI":"10.3115\/1557690.1557765"},{"key":"6492_CR42","unstructured":"Sagawa S, Koh PW, Lee T, Gao I, Xie SM, Shen K, et al. Extending the WILDS benchmark for unsupervised adaptation. In: International Conference on Learning Representations. 2022."},{"key":"6492_CR43","doi-asserted-by":"crossref","unstructured":"M\u00fcller M, Huber F, Arnaud M, Kraemer AI, Altimiras ER, Michaux J, Taillandier-Coindard M, Chiffelle J, Murgues B, Gehret T, et al. Machine learning methods and harmonized datasets improve immunogenic neoantigen prediction. Immunity 2023.","DOI":"10.1016\/j.immuni.2023.09.002"}],"container-title":["BMC Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12859-026-06492-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-026-06492-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-026-06492-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T07:38:17Z","timestamp":1781077097000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s12859-026-06492-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,10]]},"references-count":43,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["6492"],"URL":"https:\/\/doi.org\/10.1186\/s12859-026-06492-2","relation":{},"ISSN":["1471-2105"],"issn-type":[{"value":"1471-2105","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,10]]},"assertion":[{"value":"26 February 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 May 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 June 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"124"}}