Scholarlink

<p>Cell-free RNA (cfRNA) profiling has emerged as a powerful tool for non-invasive disease detection, but its application is limited by data sparsity and complexity, especially in settings with constrained sample availability. We introduce Exai-1, a multimodal, transformer-based generative foundation model that integrates RNA sequence embeddings with cfRNA abundance data to capture biologically meaningful representations of circulating RNAs. By leveraging both sequence and expression modalities, Exai-1 captures a biologically meaningful latent structure of cfRNA profiles. Pretrained on over 306 billion tokens from 8,339 samples, Exai-1 enhances signal fidelity, reduces technical noise and improves disease detection by generating synthetic cfRNA profiles. We show that self-attention and variational inference are particularly important for the preservation of biological signals and contextual relationships. Additionally, Exai-1 facilitates cross-biofluid translation and assay compatibility through disentangling biological signals from confounders. By uniting sequence-informed embeddings with cfRNA expression patterns, Exai-1 establishes a transfer learning foundation for liquid biopsy, offering a scalable and adaptable framework for next-generation cfRNA-based diagnostics.</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

A multimodal cell-free RNA language model for liquid biopsy applications

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年12月10日

查看全文
  • Mehran Karimzadeh,
  • Aiden M. Sababi,
  • Amir Momen-Roknabadi,
  • Nae-Chyun Chen,
  • Taylor B. Cavazos,
  • Sukh Sekhon,
  • Jieyang Wang,
  • Rose Hanna,
  • Alice Huang,
  • Dang Nguyen,
  • Selina Chen,
  • Ti Lam,
  • Kimberly H. Chau,
  • Anna Hartwig,
  • Lisa Fish,
  • Helen Li,
  • Babak Behsaz,
  • Fereydoun Hormozdiari,
  • Babak Alipanahi,
  • Hani Goodarzi

摘要

Cell-free RNA (cfRNA) profiling has emerged as a powerful tool for non-invasive disease detection, but its application is limited by data sparsity and complexity, especially in settings with constrained sample availability. We introduce Exai-1, a multimodal, transformer-based generative foundation model that integrates RNA sequence embeddings with cfRNA abundance data to capture biologically meaningful representations of circulating RNAs. By leveraging both sequence and expression modalities, Exai-1 captures a biologically meaningful latent structure of cfRNA profiles. Pretrained on over 306 billion tokens from 8,339 samples, Exai-1 enhances signal fidelity, reduces technical noise and improves disease detection by generating synthetic cfRNA profiles. We show that self-attention and variational inference are particularly important for the preservation of biological signals and contextual relationships. Additionally, Exai-1 facilitates cross-biofluid translation and assay compatibility through disentangling biological signals from confounders. By uniting sequence-informed embeddings with cfRNA expression patterns, Exai-1 establishes a transfer learning foundation for liquid biopsy, offering a scalable and adaptable framework for next-generation cfRNA-based diagnostics.