Scholarlink

<p>Tumorigenesis is a microevolutionary process in which heterogeneous tumor cells adapt within a complex microenvironment. Current tumor omics analyses often focus exclusively on tumor samples, overlooking the valuable insights that normal tissues can provide. To address this gap, we introduce VaDTN (Variational Autoencoder–Derived Tumor-to-Normal), a pan-cancer framework that integrates transcriptomic data from both tumor and normal samples into a unified latent space. By measuring each tumor’s “distance” from a normal reference within this latent space, VaDTN reveals subtle molecular shifts linked to tumor evolution and heterogeneity. We applied VaDTN to six representative cancers <b>(</b>SKCM<b>,</b> BRCA<b>,</b> LIHC<b>,</b> LUSC<b>,</b> STAD<b>,</b> and PAAD<b>)</b>, identifying distinct subtypes characterized by unique transcriptional profiles. Notably, four cancer types (SKCM, BRCA, LIHC, and STAD) displayed significant survival stratification based on these subtype groupings, underscoring the clinical relevance of the distance-based approach. This reference-centered perspective thus provides a refined lens for dissecting intra-tumor diversity and guiding potential precision oncology strategies.</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

Novel cancer subtyping method guided by tumor-normal sample in latent space of transcriptomic variational autoencoder

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年7月21日

查看全文
  • Hongzhi Wang,
  • Yu Zhang,
  • Dandan Zhang,
  • Min Luo

摘要

Tumorigenesis is a microevolutionary process in which heterogeneous tumor cells adapt within a complex microenvironment. Current tumor omics analyses often focus exclusively on tumor samples, overlooking the valuable insights that normal tissues can provide. To address this gap, we introduce VaDTN (Variational Autoencoder–Derived Tumor-to-Normal), a pan-cancer framework that integrates transcriptomic data from both tumor and normal samples into a unified latent space. By measuring each tumor’s “distance” from a normal reference within this latent space, VaDTN reveals subtle molecular shifts linked to tumor evolution and heterogeneity. We applied VaDTN to six representative cancers (SKCM, BRCA, LIHC, LUSC, STAD, and PAAD), identifying distinct subtypes characterized by unique transcriptional profiles. Notably, four cancer types (SKCM, BRCA, LIHC, and STAD) displayed significant survival stratification based on these subtype groupings, underscoring the clinical relevance of the distance-based approach. This reference-centered perspective thus provides a refined lens for dissecting intra-tumor diversity and guiding potential precision oncology strategies.