Wang Hongzhi, Zhang Yu, Zhang Dandan, Luo Min
The Third Affiliated Hospital of Guangxi Medical University, Nanning, Guangxi Zhuang Autonomous Region, China.
Sci Rep. 2025 Jul 21;15(1):26444. doi: 10.1038/s41598-025-07813-w.
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.
肿瘤发生是一个微观进化过程，在此过程中，异质性肿瘤细胞在复杂的微环境中适应。当前的肿瘤组学分析通常仅专注于肿瘤样本，而忽略了正常组织所能提供的宝贵见解。为了弥补这一差距，我们引入了VaDTN（变分自编码器衍生的肿瘤到正常模型），这是一个泛癌框架，它将来自肿瘤和正常样本的转录组数据整合到一个统一的潜在空间中。通过在这个潜在空间中测量每个肿瘤与正常参考的“距离”，VaDTN揭示了与肿瘤进化和异质性相关的细微分子变化。我们将VaDTN应用于六种代表性癌症（皮肤黑色素瘤、乳腺癌、肝癌、肺鳞状细胞癌、胃癌和胰腺癌），识别出以独特转录谱为特征的不同亚型。值得注意的是，四种癌症类型（皮肤黑色素瘤、乳腺癌、肝癌和胃癌）基于这些亚型分组显示出显著的生存分层，强调了基于距离方法的临床相关性。因此，这种以参考为中心的观点为剖析肿瘤内多样性和指导潜在的精准肿瘤学策略提供了一个更精细的视角。
