Epitope-anchored contrastive transfer learning for paired CD8+ T cell receptor–antigen recognition

Zhang, N. & Bevan, M. J. CD8+ T cells: foot soldiers of the immune system. Immunity 35, 161–168 (2011).Article 

Google Scholar 
Petrelli, A. & van Wijk, F. CD8+ T cells in human autoimmune arthritis: the unusual suspects. Nat. Rev. Rheumatol. 12, 421–428 (2016).Article 

Google Scholar 
Reina-Campos, M., Scharping, N. E. & Goldrath, A. W. CD8+ T cell metabolism in infection and cancer. Nat. Rev. Immunol. 21, 718–738 (2021).Article 

Google Scholar 
Raskov, H., Orhan, A., Christensen, J. P. & Gögenur, I. Cytotoxic CD8+ T cells in cancer and cancer immunotherapy. Br. J. Cancer 124, 359–367 (2021).Article 

Google Scholar 
Philip, M. & Schietinger, A. CD8+ T cell differentiation and dysfunction in cancer. Nat. Rev. Immunol. 22, 209–223 (2022).Article 

Google Scholar 
Tian, S., Maile, R., Collins, E. J. & Frelinger, J. A. CD8+ T cell activation is governed by TCR-Peptide/MHC affinity, not dissociation rate. J. Immun. 179, 2952–2960 (2007).Article 

Google Scholar 
Rossjohn, J. et al. T cell antigen receptor recognition of antigen-presenting molecules. Annu. Rev. Immunol. 33, 169–200 (2015).Article 

Google Scholar 
Chandran, S. S. & Klebanoff, C. A. T cell receptor-based cancer immunotherapy: emerging efficacy and pathways of resistance. Immunol. Rev. 290, 127–147 (2019).Article 

Google Scholar 
Cowell, L. G. The diagnostic, prognostic, and therapeutic potential of adaptive immune receptor repertoire profiling in cancer. Cancer Res. 80, 643–654 (2020).Article 

Google Scholar 
Kidman, J. et al. Characteristics of TCR repertoire associated with successful immune checkpoint therapy responses. Front. Immunol. 11, 587014 (2020).Article 

Google Scholar 
Valpione, S. et al. The T cell receptor repertoire of tumor infiltrating T cells is predictive and prognostic for cancer survival. Nat. Commun. 12, 4098 (2021).Article 

Google Scholar 
Pai, J. A. & Satpathy, A. T. High-throughput and single-cell T cell receptor sequencing technologies. Nat. Methods 18, 881–892 (2021).Article 

Google Scholar 
Zhang, S.-Q. et al. High-throughput determination of the antigen specificities of T cell receptors in single cells. Nat. Biotechnol. 36, 1156–1159 (2018).Article 

Google Scholar 
Ng, A. H. C. et al. MATE-Seq: microfluidic antigen-TCR engagement sequencing. Lab Chip 19, 3011–3021 (2019).Article 

Google Scholar 
Sewell, A. K. Why must T cells be cross-reactive? Nat. Rev. Immunol. 12, 669–677 (2012).Article 

Google Scholar 
Spear, T. T., Evavold, B. D., Baker, B. M. & Nishimura, M. I. Understanding TCR affinity, antigen specificity, and cross-reactivity to improve TCR gene-modified T cells for cancer immunotherapy. Cancer Immunol. Immunother. 68, 1881–1889 (2019).Article 

Google Scholar 
Cole, D. K. et al. Hotspot autoimmune T cell receptor binding underlies pathogen and insulin peptide cross-reactivity. J. Clin. Invest. 126, 2191–2204 (2016).Article 

Google Scholar 
Cusick, M. F., Libbey, J. E. & Fujinami, R. S. Molecular mimicry as a mechanism of autoimmune disease. Clin. Rev. Allergy Immunol. 42, 102–111 (2012).Article 

Google Scholar 
Linette, G. P. et al. Cardiovascular toxicity and titin cross-reactivity of affinity-enhanced T cells in myeloma and melanoma. Blood 122, 863–871 (2013).Article 

Google Scholar 
Hudson, D., Fernandes, R. A., Basham, M., Ogg, G. & Koohy, H. Can we predict T cell specificity with digital biology and machine learning? Nat. Rev. Immunol. 23, 511–521 (2023).Article 

Google Scholar 
Huang, H., Wang, C., Rubelt, F., Scriba, T. J. & Davis, M. M. Analyzing the Mycobacterium tuberculosis immune response by T-cell receptor clustering with GLIPH2 and genome-wide antigen screening. Nat. Biotechnol. 38, 1194–1202 (2020).Article 

Google Scholar 
Sidhom, J.-W., Larman, H. B., Pardoll, D. M. & Baras, A. S. DeepTCR is a deep learning framework for revealing sequence concepts within T-cell repertoires. Nat. Commun. 12, 1605 (2021).Article 

Google Scholar 
Mayer-Blackwell, K. et al. TCR meta-clonotypes for biomarker discovery with tcrdist3 enabled identification of public, HLA-restricted clusters of SARS-CoV-2 TCRs. eLife 10, e68605 (2021).Article 

Google Scholar 
Kevin, W. et al. TCR-BERT: learning the grammar of T-cell receptors for flexible antigen-xbinding analyses. Preprint at bioRxiv https://doi.org/10.1101/2021.11.18.469186 (2021).Gielis, S. et al. Detection of enriched T cell epitope specificity in full T cell receptor sequence repertoires. Front. Immunol. 10, 2820 (2019).Article 

Google Scholar 
Jokinen, E., Huuhtanen, J., Mustjoki, S., Heinonen, M. & Lähdesmäki, H. Predicting recognition between T cell receptors and epitopes with TCRGP. PLoS Comput. Biol. 17, e1008814 (2021).Article 

Google Scholar 
Montemurro, A. et al. NetTCR-2.0 enables accurate prediction of TCR-peptide binding by using paired TCRα and β sequence data. Commun. Biol. 4, 1060 (2021).Article 

Google Scholar 
Zhang, W. et al. A framework for highly multiplexed dextramer mapping and prediction of T cell receptor sequences to antigen specificity. Sci. Adv. 7, eabf5835 (2021).Article 
MathSciNet 

Google Scholar 
Croce, G. et al. Deep learning predictions of TCR-epitope interactions reveal epitope-specific chains in dual alpha T cells. Nat. Commun. 15, 3211 (2024).Article 

Google Scholar 
Springer, I., Tickotsky, N. & Louzoun, Y. Contribution of T cell receptor alpha and beta CDR3, MHC typing, V and J genes to peptide binding prediction. Front. Immunol. 12, 664514 (2021).Article 

Google Scholar 
Weber, A., Born, J. & Rodriguez Martínez, M. TITAN: T-cell receptor specificity prediction with bimodal attention networks. Bioinformatics 37, i237–i244 (2021).Article 

Google Scholar 
Lu, T. et al. Deep learning-based prediction of the T cell receptor–antigen binding specificity. Nat. Mach. Intell. 3, 864–875 (2021).Article 

Google Scholar 
Peng, X. et al. Characterizing the interaction conformation between T-cell receptors and epitopes with deep learning. Nat. Mach. Intell. 5, 395–407 (2023).Article 

Google Scholar 
Gao, Y. et al. Pan-peptide meta learning for T-cell receptor–antigen binding recognition. Nat. Mach. Intell. 5, 236–249 (2023).Article 

Google Scholar 
Bjørn, P. Y. K. et al. STAPLER: efficient learning of TCR-peptide specificity prediction from full-length TCR-peptide data. Preprint at bioRxiv https://doi.org/10.1101/2023.04.25.538237 (2023).Ethan, F., Manjima, D. & Binbin, C. TAPIR: a T-cell receptor language model for predicting rare and novel targets. Preprint at bioRxiv https://doi.org/10.1101/2023.09.12.557285 (2023).Meynard-Piganeau, B., Feinauer, C., Weigt, M., Walczak, A. M. & 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. USA 121, e2316401121 (2024).Jensen, M. F. & Nielsen, M. NetTCR 2.2 – Improved TCR specificity predictions by combining pan- and peptide-specific training strategies, loss-scaling and integration of sequence similarity. eLife 12, RP93934 (2023).Article 

Google Scholar 
Yi, H. et al. pan-MHC and cross-species prediction of T cell receptor-antigen binding. Preprint at bioRxiv https://doi.org/10.1101/2023.12.01.569599 (2023).Spindler, M. J. et al. Massively parallel interrogation and mining of natively paired human TCRαβ repertoires. Nat. Biotechnol. 38, 609–619 (2020).Article 

Google Scholar 
Dens, C., Laukens, K., Bittremieux, W. & Meysman, P. The pitfalls of negative data bias for the T-cell epitope specificity challenge. Nat. Mach. Intell. 5, 1060–1062 (2023).Article 

Google Scholar 
La Gruta, N. L., Gras, S., Daley, S. R., Thomas, P. G. & Rossjohn, J. Understanding the drivers of MHC restriction of T cell receptors. Nat. Rev. Immunol. 18, 467–478 (2018).Article 

Google Scholar 
Song, I. et al. Broad TCR repertoire and diverse structural solutions for recognition of an immunodominant CD8+ T cell epitope. Nat. Struct. Mol. Biol. 24, 395–406 (2017).Article 

Google Scholar 
Singh, R., Sledzieski, S., Bryson, B., Cowen, L. & Berger, B. Contrastive learning in protein language space predicts interactions between drugs and protein targets. Proc. Natl Acad. Sci. USA 120, e2220778120 (2023).Article 

Google Scholar 
Minervina, A. A. et al. SARS-CoV-2 antigen exposure history shapes phenotypes and specificity of memory CD8+ T cells. Nat. Immunol. 23, 781–790 (2022).Article 

Google Scholar 
Yang, X. et al. Autoimmunity-associated T cell receptors recognize HLA-B*27-bound peptides. Nature 612, 771–777 (2022).Article 

Google Scholar 
Dolton, G. et al. Targeting of multiple tumor-associated antigens by individual T cell receptors during successful cancer immunotherapy. Cell 186, 3333–3349.e3327 (2023).Article 

Google Scholar 
Bepler, T. & Berger, B. Learning the protein language: evolution, structure, and function. Cell Syst. 12, 654–669.e653 (2021).Article 

Google Scholar 
Atchley, W. R., Zhao, J., Fernandes, A. D. & Drüke, T. Solving the protein sequence metric problem. Proc. Natl Acad. Sci. USA 102, 6395–6400 (2005).Article 

Google Scholar 
He, K., Zhang, X., Ren, S. & Sun, J. Deep residual learning for image recognition. In Proc. IEEE Conference on Computer Vision and Pattern Recognition 770–778 (IEEE, 2016).Neefjes, J., Jongsma, M. L. M., Paul, P. & Bakke, O. Towards a systems understanding of MHC class I and MHC class II antigen presentation. Nat. Rev. Immunol. 11, 823–836 (2011).Article 

Google Scholar 
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. 48, W449–W454 (2020).Article 

Google Scholar 
Albert, B. A. et al. Deep neural networks predict class I major histocompatibility complex epitope presentation and transfer learn neoepitope immunogenicity. Nat. Mach. Intell. 5, 861–872 (2023).Article 

Google Scholar 
Khosla, P. et al. Supervised contrastive learning. In Proc. Advances in Neural Information Processing Systems (eds Larochelle, H. et al.) 18661–18673 (Curran Associates, 2020).Goncharov, M. et al. VDJdb in the pandemic era: a compendium of T cell receptors specific for SARS-CoV-2. Nat. Methods 19, 1017–1019 (2022).Article 

Google Scholar 
Feng, D., Bond, C. J., Ely, L. K., Maynard, J. & Garcia, K. C. Structural evidence for a germline-encoded T cell receptor–major histocompatibility complex interaction ‘codon’. Nat. Immunol. 8, 975–983 (2007).Article 

Google Scholar 
Meysman, P. et al. Benchmarking solutions to the T-cell receptor epitope prediction problem: IMMREP22 workshop report. Immunonformatics (Amst.) 9, 100024 (2023).
Google Scholar 
Lefranc, M.-P. et al. IMGT unique numbering for immunoglobulin and T cell receptor variable domains and Ig superfamily V-like domains. Dev. Comp. Immunol. 27, 55–77 (2003).Article 

Google Scholar 
Borràs, D. M. et al. Single cell dynamics of tumor specificity vs bystander activity in CD8+ T cells define the diverse immune landscapes in colorectal cancer. Cell Discov. 9, 114 (2023).Article 

Google Scholar 
Zhang, B. et al. Multimodal single-cell datasets characterize antigen-specific CD8+ T cells across SARS-CoV-2 vaccination and infection. Nat. Immunol. 24, 1725–1734 (2023).Article 

Google Scholar 
Huuhtanen, J. et al. Evolution and modulation of antigen-specific T cell responses in melanoma patients. Nat. Commun. 13, 5988 (2022).Article 

Google Scholar 
Reiser, J.-B. et al. CDR3 loop flexibility contributes to the degeneracy of TCR recognition. Nat. Immunol. 4, 241–247 (2003).Article 

Google Scholar 
McInnes, L., Healy, J. & Melville, J. Umap: uniform manifold approximation and projection for dimension reduction. Preprint at https://arxiv.org/abs/1802.03426 (2018).Francis, J. M. et al. Allelic variation in class I HLA determines CD8+ T cell repertoire shape and cross-reactive memory responses to SARS-CoV-2. Sci. Immunol. 7, eabk3070 (2022).
Google Scholar 
Shomuradova, A. S. et al. SARS-CoV-2 epitopes are recognized by a public and diverse repertoire of human T Cell receptors. Immunity 53, 1245–1257.e1245 (2020).Article 

Google Scholar 
van der Leun, A. M., Thommen, D. S. & Schumacher, T. N. CD8+ T cell states in human cancer: insights from single-cell analysis. Nat. Rev. Cancer 20, 218–232 (2020).Article 

Google Scholar 
Leem, J., de Oliveira, S. H. P., Krawczyk, K. & Deane, C. M. STCRDab: the structural T-cell receptor database. Nucleic Acids Res. 46, D406–D412 (2017).Article 

Google Scholar 
Andersen, R. et al. Long-asting complete responses in patients with metastatic melanoma after adoptive cell therapy with tumor-infiltrating lymphocytes and an attenuated IL2 regimen. Clin. Cancer Res. 22, 3734–3745 (2016).Article 

Google Scholar 
Vita, R. et al. The Immune Epitope Database (IEDB): 2018 update. Nucleic Acids Res. 47, D339–D343 (2018).Article 

Google Scholar 
Wooldridge, L. et al. A single autoimmune T cell receptor recognizes more than a million different peptides. J. Biol. Chem. 287, 1168–1177 (2012).Article 

Google Scholar 
Birnbaum, M. E. et al. Deconstructing the peptide-MHC specificity of T cell recognition. Cell 157, 1073–1087 (2014).Article 

Google Scholar 
Nagano, Y. et al. Contrastive learning of T cell receptor representations. Preprint at https://arxiv.org/abs/2406.06397 (2024).Sethna, Z. et al. Population variability in the generation and selection of T-cell repertoires. PLoS Comput. Biol. 16, e1008394 (2020).Article 

Google Scholar 
Tanno, H. et al. Determinants governing T cell receptor α/β-chain pairing in repertoire formation of identical twins. Proc. Natl Acad. Sci. USA 117, 532–540 (2020).Article 

Google Scholar 
Zhang, Z., Xiong, D., Wang, X., Liu, H. & Wang, T. Mapping the functional landscape of T cell receptor repertoires by single-T cell transcriptomics. Nat. Methods 18, 92–99 (2021).Article 

Google Scholar 
Schattgen, S. A. et al. Integrating T cell receptor sequences and transcriptional profiles by clonotype neighbor graph analysis (CoNGA). Nat. Biotechnol. 40, 54–63 (2022).Article 

Google Scholar 
Gao, Y. et al. Unified cross-modality integration and analysis of T cell receptors and T cell transcriptomes by low-resource-aware representation learning. Cell Genomics 4, 100553 (2024).Article 

Google Scholar 
Drost, F. et al. Multi-modal generative modeling for joint analysis of single-cell T cell receptor and gene expression data. Nat. Commun. 15, 5577 (2024).Article 

Google Scholar 
Bradley, P. Structure-based prediction of T cell receptor:peptide-MHC interactions. eLife 12, e82813 (2023).Article 

Google Scholar 
Yost, K. E. et al. Clonal replacement of tumor-specific T cells following PD-1 blockade. Nat. Med. 25, 1251–1259 (2019).Article 

Google Scholar 
Kourtis, N. et al. A single-cell map of dynamic chromatin landscapes of immune cells in renal cell carcinoma. Nat. Cancer 3, 885–898 (2022).Article 

Google Scholar 
Liu, T. et al. Single cell profiling of primary and paired metastatic lymph node tumors in breast cancer patients. Nat. Commun. 13, 6823 (2022).Article 

Google Scholar 
Zheng, L. et al. Pan-cancer single-cell landscape of tumor-infiltrating T cells. Science 374, abe6474 (2021).Article 

Google Scholar 
Wu, T. D. et al. Peripheral T cell expansion predicts tumour infiltration and clinical response. Nature 579, 274–278 (2020).Article 

Google Scholar 
Tickotsky, N., Sagiv, T., Prilusky, J., Shifrut, E. & Friedman, N. McPAS-TCR: a manually curated catalogue of pathology-associated T cell receptor sequences. Bioinformatics 33, 2924–2929 (2017).Article 

Google Scholar 
Zhang, W. et al. PIRD: Pan Immune Repertoire Database. Bioinformatics 36, 897–903 (2019).Article 

Google Scholar 
A new way of exploring immunity–linking highly multiplexed antigen recognition to immune repertoire and phenotype. 10x Genomics https://www.10xgenomics.com/library/a14cde (2022).Smith, T. F. & Waterman, M. S. Identification of common molecular subsequences. J. Mol. Biol. 147, 195–197 (1981).Article 

Google Scholar 
Edgar, R. C. MUSCLE: multiple sequence alignment with high accuracy and high throughput. Nucleic Acids Res. 32, 1792–1797 (2004).Article 

Google Scholar 
Kirkpatrick, S., Gelatt, C. D. & Vecchi, M. P. Optimization by simulated annealing. Science 220, 671–680 (1983).Article 
MathSciNet 

Google Scholar 
Yin, R. et al. TCRmodel2: high-resolution modeling of T cell receptor recognition using deep learning. Nucleic Acids Res. 51, W569–W576 (2023).Article 

Google Scholar 
Tareen, A. & Kinney, J. B. Logomaker: beautiful sequence logos in Python. Bioinformatics 36, 2272–2274 (2019).Article 

Google Scholar 
Zhang, Y. zhangyumeng1sjtu/EPACT: EPACT v0.1.1 (v0.1.1-beta). Zenodo https://doi.org/10.5281/zenodo.10996144 (2024).