Deep learning-based prediction of the T cell receptor–antigen binding specificity
Open accessAbstract
Neoantigens play a key role in the recognition of tumor cells by T cells. However, only a small proportion of neoantigens truly elicit T cell responses, and fewer clues exist as to which neoantigens are recognized by which T cell receptors (TCRs). We built a transfer learning-based model, named pMHC-TCR binding prediction network (pMTnet), to predict TCR-binding specificities of neoantigens, and T cell antigens in general, presented by class I major histocompatibility complexes (pMHCs). pMTnet was comprehensively validated by a series of analyses, and showed advance over previous work by a large margin. By applying pMTnet in human tumor genomics data, we discovered that neoantigens were generally more immunogenic than self-antigens, but HERV-E, a special type of self-antigen that is re-activated in kidney cancer, is more immunogenic than neoantigens. We further discovered that patients with more clonally expanded T cells exhibiting better affinity against truncal, rather than subclonal, neoantigens, had more favorable prognosis and treatment response to immunotherapy, in melanoma and lung cancer but not in kidney cancer. Predicting TCR-neoantigen/antigen pairs is one of the most daunting challenges in modern immunology. However, we achieved an accurate prediction of the pairing only using the TCR sequence (CDR3β), antigen sequence, and class I MHC allele, and our work revealed unique insights into the interactions of TCRs and pMHCs in human tumors using pMTnet as a discovery tool.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
STAR: ultrafast universal RNA-seq aligner
Dobin, A., Davis, C. A., Schlesinger, F., Drenkow, J., Zaleski, C., Jha, S., Batut, P., Chaisson, M., & Gingeras, T. R. (2013) · Bioinformatics · doi:10.1093/bioinformatics/bts635 · Cited by 51,709 · see citing works
Mutational landscape determines sensitivity to PD-1 blockade in non–small cell lung cancer
Rizvi, N. A., Hellmann, M. D., Snyder, A., Kvistborg, P., Makarov, V., Havel, J. J., Lee, W., Yuan, J., Wong, P., Ho, T. S., et al. (2015) · Science · doi:10.1126/science.aaa1348 · Cited by 7,802 · see citing works
Van der Auwera, G. A., Carneiro, M. O., Hartl, C., Poplin, R., del Angel, G., Levy‐Moonshine, A., Jordan, T., Shakir, K., Roazen, D., Thibault, J., et al. (2013) · Current Protocols in Bioinformatics · doi:10.1002/0471250953.bi1110s43 · Cited by 6,687 · see citing works
Comprehensive molecular profiling of lung adenocarcinoma
The Cancer Genome Atlas Research Network (2014) · Nature · doi:10.1038/nature13385 · Cited by 5,732 · see citing works
Neoantigens in cancer immunotherapy
Schumacher, T. N., & Schreiber, R. D. (2015) · Science · doi:10.1126/science.aaa4971 · Cited by 4,783 · see citing works
Comprehensive genomic characterization of squamous cell lung cancers
The Cancer Genome Atlas Research Network (2012) · Nature · doi:10.1038/nature11404 · Cited by 3,994 · see citing works
Phenotypic Analysis of Antigen-Specific T Lymphocytes
Altman, J. D., Moss, P. A. H., Goulder, P. J. R., Barouch, D. H., McHeyzer-Williams, M. G., Bell, J. I., McMichael, A. J., & Davis, M. M. (1996) · Science · doi:10.1126/science.274.5284.94 · Cited by 3,544 · cited 1× · see citing works
“Accordingly, a number of experimental approaches—such as tetramer analysis 9 , tetramer-associated T-cell receptor sequencing 10 and T-scan 11 —have been developed to detect pairing between TCRs and pMHCs; however, these methods are time-consuming, technically challenging and costly.”
BackgroundGenomic and Transcriptomic Features of Response to Anti-PD-1 Therapy in Metastatic Melanoma
Hugo, W., Zaretsky, J. M., Sun, L., Song, C., Moreno, B. H., Hu-Lieskovan, S., Berent-Maoz, B., Pang, J., Chmielowski, B., Cherry, G., et al. (2016) · Cell · doi:10.1016/j.cell.2016.02.065 · Cited by 3,448 · see citing works
Genomic correlates of response to CTLA-4 blockade in metastatic melanoma
Van Allen, E. M., Miao, D., Schilling, B., Shukla, S. A., Blank, C., Zimmer, L., Sucker, A., Hillen, U., Geukes Foppen, M. H., Goldinger, S. M., et al. (2015) · Science · doi:10.1126/science.aad0095 · Cited by 2,839 · see citing works
Genomic correlates of response to immune checkpoint therapies in clear cell renal cell carcinoma
Miao, D., Margolis, C. A., Gao, W., Voss, M. H., Li, W., Martini, D. J., Norton, C., Bossé, D., Wankowicz, S. M., Cullen, D., et al. (2018) · Science · doi:10.1126/science.aan5951 · Cited by 1,249 · see citing works
Liu, D., Schilling, B., Liu, D., Sucker, A., Livingstone, E., Jerby-Arnon, L., Zimmer, L., Gutzmer, R., Satzger, I., Loquai, C., et al. (2019) · Nature Medicine · doi:10.1038/s41591-019-0654-5 · Cited by 1,039 · see citing works
High-throughput determination of the antigen specificities of T cell receptors in single cells
Zhang, S.-Q., Ma, K.-Y., Schonnesen, A. A., Zhang, M., He, C., Sun, E., Williams, C. M., Jia, W., & Jiang, N. (2018) · Nature Biotechnology · doi:10.1038/nbt.4282 · Cited by 200 · see citing works
PIRD: pan immune repertoire database
Zhang, W., Wang, L., Liu, K., Wei, X., Yang, K., Du, W., Wang, S., Guo, N., Ma, C., Luo, L., et al. (2020) · Bioinformatics · doi:10.1093/bioinformatics/btz614 · Cited by 166 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Artificial Intelligence in Oncology: Current Landscape, Challenges, and Future Directions
Lotter, W., Hassett, M. J., Schultz, N., Kehl, K. L., Van Allen, E. M., & Cerami, E. (2024) · Cancer Discovery · doi:10.1158/2159-8290.cd-23-1199 · Cited by 196 · see citing works
Pan-Peptide Meta Learning for T-cell receptor–antigen binding recognition
Gao, Y., Gao, Y., Fan, Y., Zhu, C., Wei, Z., Zhou, C., Chuai, G., Chen, Q., Zhang, H., & Liu, Q. (2023) · Nature Machine Intelligence · doi:10.1038/s42256-023-00619-3 · Cited by 155 · see citing works
- Authors
- Lu, T., Zhang, Z., Zhu, J., Wang, Y., Jiang, P., Xiao, X., Bernatchez, C., Heymach, J. V., Gibbons, D. L., Wang, J., Xu, L., Reuben, A., & Wang, T.
- Affiliations
- The University of Texas Southwestern Medical Center (US)
- The University of Texas MD Anderson Cancer Center (US)
- New York University (US)
- Corresponding author
- Reuben, Alexandre
- Wang, Tao
- ORCID
- Venue
- Nature Machine Intelligence
- Published
- 2021-09-23
- Volume
- 3
- Issue
- 10
- Pages
- 864-875
- ISSN
- 2522-5839 (ISSN-L)
- PMC
- PMC9396750
- OpenAlex
- W3198942356
- Cited by
- 295
- References
- 13
- Citations by year
- 2026: 66 · 2025: 80 · 2024: 74 · 2023: 58 · 2022: 15 · 2021: 1
- FWCI
- 11.61
- Type
- journal article
- Language
- en
- Open access
- green
- www.ncbi.nlm.nih.gov
- Licence
- Locations
- Nature Machine Intelligence (publishedVersion)
- PubMed (publishedVersion)
- PubMed Central (acceptedVersion)
- Funders
- UT | University of Texas MD Anderson Cancer Center (Lung Cancer Moon Shot, Institutional Research Grant)
- The Waun Ki Hong Lung Cancer Research Fund Exon 20 Group Rexanna’s Foundation for Fighting Lung Cancer
- Cancer Prevention and Research Institute of Texas (RP190208)
- U.S. Department of Health & Human Services | National Institutes of Health (5P30CA142543, R01CA258584)
- Topics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › vaccines and immunoinformatics approaches
- Health Sciences › Medicine › Oncology › Cancer Immunotherapy and Biomarkers
- Life Sciences › Immunology and Microbiology › Immunology › Immunotherapy and Immune Responses
- Keywords
- neoantigens, peptide-MHC class I complexes, transfer learning, tumor immunogenicity, T cell clones, melanoma, lung cancer, kidney cancer, immunotherapy response, cancer genomics
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
