Scholarlink

<p>Plasma proteomics can provide a dynamic molecular readout of human health, but models that learn generalizable protein-expression patterns in population cohorts remain limited. Here we show that ProLM, a BERT-based plasma proteomics model pretrained on 15,499 relatively healthy UK Biobank participants, captures baseline protein-expression relationships and supports prediction of 16 common chronic diseases. After disease-specific fine-tuning, the ProLM-derived proteomic risk score outperformed the Age+Sex model for all 16 diseases, the cardiovascular disease (ASCVD) risk equation for 14 diseases and a 35-variable clinical PANEL score for 11 diseases. Model interpretation highlighted proteins including GDF15 whose expression changed more than 15 years before clinical diagnosis, and key findings were externally evaluated in the China Kadoorie Biobank. These results support plasma proteomics pretrained models as tools for early chronic-disease risk stratification, while prospective validation is needed before clinical implementation.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

ProLM: a plasma proteomics pretrained model for the general population

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月13日

查看全文
  • Shizheng Qiu,
  • Ming Zhao,
  • Xin Chen,
  • Zhishuai Zhang,
  • Huanyu You,
  • Xu Sun,
  • Jirui Guo,
  • Haozheng Liang,
  • Yu Guo,
  • Lu Chen,
  • Jun Lv,
  • Dianjianyi Sun,
  • Ling Yang,
  • Yiping Chen,
  • Huaidong Du,
  • Zhengming Chen,
  • Liming Li,
  • Yang Hu,
  • Guiyou Liu,
  • Canqing Yu,
  • Yadong Wang

摘要

Plasma proteomics can provide a dynamic molecular readout of human health, but models that learn generalizable protein-expression patterns in population cohorts remain limited. Here we show that ProLM, a BERT-based plasma proteomics model pretrained on 15,499 relatively healthy UK Biobank participants, captures baseline protein-expression relationships and supports prediction of 16 common chronic diseases. After disease-specific fine-tuning, the ProLM-derived proteomic risk score outperformed the Age+Sex model for all 16 diseases, the cardiovascular disease (ASCVD) risk equation for 14 diseases and a 35-variable clinical PANEL score for 11 diseases. Model interpretation highlighted proteins including GDF15 whose expression changed more than 15 years before clinical diagnosis, and key findings were externally evaluated in the China Kadoorie Biobank. These results support plasma proteomics pretrained models as tools for early chronic-disease risk stratification, while prospective validation is needed before clinical implementation.