{"version":1,"type":"story","url":"https://digestai.news/story/researchers-unveil-uptcr-model-for-tcr-antigen-binding-prediction","json":"https://digestai.news/story/researchers-unveil-uptcr-model-for-tcr-antigen-binding-prediction.json","markdown":"https://digestai.news/story/researchers-unveil-uptcr-model-for-tcr-antigen-binding-prediction.md","slug":"researchers-unveil-uptcr-model-for-tcr-antigen-binding-prediction","headline":"Researchers unveil UpTCR model for TCR-antigen binding prediction","summary":"A team of researchers has developed UpTCR, a foundation model designed to predict T-cell receptor (TCR) binding to antigenic peptides presented by HLA molecules. Published in Nature Communications, the model addresses data scarcity by progressively transferring knowledge from simpler dimeric and trimeric interactions to complex tetrameric structures. It employs soft contrastive learning to handle false negatives in training data.\n\nThe model outperforms existing methods in predicting binding specificity and affinity, particularly for neoantigens. In prospective validation using melanoma antigen variants, UpTCR identified eight immunogenic peptides that triggered T-cell responses and one variant linked to immune escape. The authors, including employees of Tencent AI for Life Sciences Lab, report the tool generalizes to breast cancer cohorts with limited data and reveals residue-level interaction maps. Funding came from multiple Chinese national and regional grants.","keyPoints":["UpTCR predicts TCR-antigen-HLA binding using progressive knowledge transfer from incomplete data","Model identifies 8 immunogenic melanoma peptides and 1 immune escape variant in validation","Researchers include Tencent AI for Life Sciences Lab employees; funded by Chinese grants"],"whyItMatters":"UpTCR offers a generalizable tool for immunotherapy design, enabling prediction of T-cell responses against cancer neoantigens with limited training data.","category":{"slug":"research","name":"Research","url":"https://digestai.news/category/research"},"entities":{"companies":["Tencent AI for Life Sciences Lab"],"models":["UpTCR"],"people":["Lv, T.","Xiao, Y.","Chen, L.","B.H.","S.C.","Z.T."]},"firstPublishedAt":"2026-09-24T00:00:00Z","updatedAt":"2026-09-24T00:00:00Z","sourceCount":1,"hasPrimarySource":true,"sources":[{"outlet":"Nature Machine Learning","title":"UpTCR: a unified progressive knowledge transfer foundation model for robust T-cell receptor-antigen binding recognition","url":"https://nature.com/articles/s41467-026-78075-x","publishedAt":"2026-09-24T00:00:00Z","type":"primary","primary":true,"lead":true}],"sourceNotes":null,"discussions":[],"thread":null,"cite":{"text":"Digest AI, \"Researchers unveil UpTCR model for TCR-antigen binding prediction\", 24 September 2026, https://digestai.news/story/researchers-unveil-uptcr-model-for-tcr-antigen-binding-prediction","publisher":"Digest AI","title":"Researchers unveil UpTCR model for TCR-antigen binding prediction","datePublished":"2026-09-24T00:00:00Z","url":"https://digestai.news/story/researchers-unveil-uptcr-model-for-tcr-antigen-binding-prediction"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}