{"version":1,"type":"story","url":"https://digestai.news/story/researchers-release-hi-tph-dataset-and-hi-tph-plms-for-t-cell-receptor","json":"https://digestai.news/story/researchers-release-hi-tph-dataset-and-hi-tph-plms-for-t-cell-receptor.json","markdown":"https://digestai.news/story/researchers-release-hi-tph-dataset-and-hi-tph-plms-for-t-cell-receptor.md","slug":"researchers-release-hi-tph-dataset-and-hi-tph-plms-for-t-cell-receptor","headline":"Researchers release Hi-TPH dataset and Hi-TPH-PLMs for T cell receptor–pHLA binding prediction","summary":"A team led by Zhu, Lu, and colleagues published a new hierarchical dataset called Hi-TPH and a suite of fine-tuned protein language models named Hi-TPH-PLMs in Nature Computational Science. The dataset uses an on-the-fly selection method to generate nonbinding examples, addressing a key limitation in existing tools. On an external wet-lab test set, the models achieve a 19.2% performance gain over state-of-the-art methods. The authors analyze how different molecular components contribute to binding prediction, finding that HLA prediction depends on the presence of full T cell receptor chains. Both the dataset and models are publicly available on GitHub and Zenodo under a CC BY-NC 4.0 license. Funding came from the Key Science & Technology Project of Anhui Province and Zhongguancun Academy.","keyPoints":["Hi-TPH dataset and Hi-TPH-PLMs released for TCR–pHLA binding prediction","Models show 19.2% gain over state-of-the-art on external wet-lab test set","Data and models publicly available under CC BY-NC 4.0 license"],"whyItMatters":"Improves computational prediction of immune interactions, supporting personalized immunotherapy and vaccine design with more reliable tools.","category":{"slug":"research","name":"Research","url":"https://digestai.news/category/research"},"entities":{"companies":["Zhongguancun Academy"],"models":["Hi-TPH-PLMs"],"people":["X. Zhu","J. Lu","Y. Lu","Y. Zhang","F. Feng"]},"firstPublishedAt":"2026-10-26T00:00:00Z","updatedAt":"2026-10-26T00:00:00Z","sourceCount":1,"hasPrimarySource":true,"sources":[{"outlet":"Nature Machine Learning","title":"Machine learning dataset and benchmark for accurate T cell receptor–pHLA binding prediction","url":"https://nature.com/articles/s43588-026-01073-y","publishedAt":"2026-10-26T00:00:00Z","type":"primary","primary":true,"lead":true}],"sourceNotes":null,"discussions":[],"thread":null,"cite":{"text":"Digest AI, \"Researchers release Hi-TPH dataset and Hi-TPH-PLMs for T cell receptor–pHLA binding prediction\", 26 October 2026, https://digestai.news/story/researchers-release-hi-tph-dataset-and-hi-tph-plms-for-t-cell-receptor","publisher":"Digest AI","title":"Researchers release Hi-TPH dataset and Hi-TPH-PLMs for T cell receptor–pHLA binding prediction","datePublished":"2026-10-26T00:00:00Z","url":"https://digestai.news/story/researchers-release-hi-tph-dataset-and-hi-tph-plms-for-t-cell-receptor"},"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"}