Scholarlink

Cell-free DNA (cfDNA) analysis is crucial for noninvasive diagnostics, but computational deconvolution faces data complexity and interpretability challenges. We present cfDecon, a deep-learning framework that uses multichannel autoencoder and iterative refinement to generate condition-aware methylation profiles. Through comprehensive simulations and clinical validations, cfDecon consistently outperforms existing methods and demonstrates superior disease detection capability, offering a promising framework for personalized medicine applications.

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

cfDecon: Accurate and Interpretable Methylation-Based Cell Type Deconvolution for Cell-Free DNA

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Yixuan Wang,
  • Jiayi Li,
  • Jingqi Li,
  • Shen Yang,
  • Yuhan Huang,
  • Xinyuan Liu,
  • Yimin Fan,
  • Irwin King,
  • Yumei Li,
  • Yu Li

摘要

Cell-free DNA (cfDNA) analysis is crucial for noninvasive diagnostics, but computational deconvolution faces data complexity and interpretability challenges. We present cfDecon, a deep-learning framework that uses multichannel autoencoder and iterative refinement to generate condition-aware methylation profiles. Through comprehensive simulations and clinical validations, cfDecon consistently outperforms existing methods and demonstrates superior disease detection capability, offering a promising framework for personalized medicine applications.