{
  "abstract": "T-cell receptor (TCR) recognition of antigenic peptides presented by human leukocyte antigen (HLA) molecules underpins adaptive immunity and T cell-based immunotherapy. However, the scarcity of complete interaction data and TCR cross-reactivity challenge robust prediction. Here, we present UpTCR, a unified progressive knowledge-transfer foundation model that learns from incomplete data to predict TCR-antigen-HLA binding. UpTCR progressively transfers knowledge from dimeric and trimeric interactions to tetrameric complexes and uses soft contrastive learning to mitigate false negatives. It outperforms existing methods in predicting TCR binding specificity and antigen-HLA binding affinity, particularly for neoantigens, and reveals pairwise residue-level interactions across the tetramer. UpTCR also transfers effectively to breast cancer cohorts with limited data. Prospective validation against melanoma antigen variants identifies eight immunogenic peptides that elicit T cell responses and one variant associated with immune escape. These findings establish UpTCR as a generalizable and interpretable tool for studying antigen recognition and advancing TCR-based immunotherapies.",
  "abstract_shown": true,
  "affiliations": [
    "School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, 214122 China",
    "Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, 518071 China",
    "Cancer Centre and Institute of Translational Medicine, Faculty of Health Sciences, University of Macau, Macau, 999078 China",
    "AI for Life Sciences Lab, Tencent, Shenzhen, 518000 China",
    "Department of general surgery, Peking Union Medical College Hospital, Beijing, China",
    "Institute of Biomedical Engineering and Instrumentation, Hangzhou Dianzi University, Hangzhou, 310018 China",
    "The PRC Ministry of Education Engineering Research Center of Intelligent Technology for Healthcare, Wuxi, Jiangsu 214122 China"
  ],
  "article_type": "research article",
  "arxiv": null,
  "author_total": 25,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Tianxu Lv"
    },
    {
      "affs": [
        1
      ],
      "name": "Yang Xiao"
    },
    {
      "affs": [
        2
      ],
      "name": "Li Chen"
    },
    {
      "affs": [
        3
      ],
      "name": "Bing He",
      "orcid": "0000-0003-1719-9290"
    },
    {
      "affs": [
        1
      ],
      "name": "Maiyi Zhong"
    },
    {
      "affs": [
        2
      ],
      "name": "Zihan Feng"
    },
    {
      "affs": [
        1
      ],
      "name": "Zheyu Hu"
    },
    {
      "affs": [
        1
      ],
      "name": "Fei Ye"
    },
    {
      "affs": [
        4
      ],
      "name": "Jiashu Han"
    },
    {
      "affs": [
        3
      ],
      "name": "Shouzhi Chen"
    },
    {
      "affs": [
        3
      ],
      "name": "Zhenchao Tang",
      "orcid": "0000-0003-4258-1301"
    },
    {
      "affs": [
        3
      ],
      "name": "Jiale Zhou"
    },
    {
      "affs": [
        3
      ],
      "name": "Dawei Huang"
    },
    {
      "affs": [
        0
      ],
      "name": "Xiaoqing Lian"
    },
    {
      "affs": [
        0
      ],
      "name": "Jiansong Fan"
    },
    {
      "affs": [
        1
      ],
      "name": "Yixuan Huang"
    },
    {
      "affs": [
        1
      ],
      "name": "Chenyi Lei"
    },
    {
      "affs": [
        1
      ],
      "name": "Dandan Meng"
    },
    {
      "affs": [
        0
      ],
      "name": "Yuan Liu"
    },
    {
      "affs": [
        5
      ],
      "name": "Lihua Li",
      "orcid": "0000-0003-0435-6453"
    },
    {
      "affs": [
        0,
        6
      ],
      "name": "Pengjiang Qian"
    },
    {
      "affs": [
        3
      ],
      "name": "Jianhua Yao",
      "orcid": "0000-0001-9157-9596"
    },
    {
      "affs": [
        2
      ],
      "name": "Kai Miao",
      "orcid": "0000-0003-4832-3354"
    },
    {
      "affs": [
        1
      ],
      "name": "Xiao Liu",
      "orcid": "0000-0002-8073-0534"
    },
    {
      "affs": [
        0,
        6
      ],
      "name": "Xiang Pan",
      "orcid": "0000-0002-7671-518X"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/dby9ghz0mv6b8.bib",
  "cited_by": 0,
  "doi": "10.1038/s41467-026-78075-x",
  "fulltext_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC13696701/",
  "id": "dby9ghz0mv6b8",
  "issns": [
    "2041-1723"
  ],
  "landing_url": "https://doi.org/10.1038/s41467-026-78075-x",
  "language": "en",
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "heading",
      "Article"
    ],
    [
      "openalex",
      "1312|vaccines and immunoinformatics approaches"
    ]
  ],
  "openalex": "W7214168946",
  "pdf_url": "https://europepmc.org/articles/PMC13696701?pdf=render",
  "pmcid": "PMC13696701",
  "pmid": "42928063",
  "published": "2026-09-24",
  "publisher": "Nature Publishing Group",
  "ris": "https://research.draconitic.com/paper/dby9ghz0mv6b8.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:18:00Z",
      "native_id": "PMC13696701",
      "source": "pmc",
      "url": "https://doi.org/10.1038/s41467-026-78075-x"
    },
    {
      "first_seen": "2026-10-30T12:21:18Z",
      "native_id": "MED:42928063",
      "source": "europepmc",
      "url": "https://europepmc.org/article/MED/42928063"
    }
  ],
  "subjects": [
    {
      "field": "biochemistry",
      "origin": "openalex:1312|vaccines and immunoinformatics approaches",
      "subfield": "molecular-biology"
    }
  ],
  "title": "UpTCR: a unified progressive knowledge transfer foundation model for robust T-cell receptor-antigen binding recognition",
  "title_text": "UpTCR: a unified progressive knowledge transfer foundation model for robust T-cell receptor-antigen binding recognition",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T12:33:59Z",
  "url": "https://research.draconitic.com/paper/dby9ghz0mv6b8",
  "venue": "Nature Communications",
  "versions": []
}