用自编码器和稳定性分析，从肾癌数据中发现一个稳定且罕见的基因亚型。
Rare Genomic Subtype Discovery from RNA-seq via Autoencoder Embeddings and Stability-Aware Clustering
- 先用自编码器降维，再通过稳定性筛选确定最优聚类数
- 找到占6.85%的稀有亚型，跨20次随机种子保持高一致性
- 适合关注罕见癌症亚型或想提升聚类可靠性的研究者
在高维RNA-seq数据上进行无监督学习可揭示超出标准标签的分子亚型。我们结合自编码器表征与聚类稳定性分析，探索罕见但可复现的基因亚型。在包含801个样本、20,531个基因的UCI 'Gene Expression Cancer RNA-Seq'数据集（涵盖BRCA、COAD、KIRC、LUAD、PRAD）上，泛癌分析显示聚类几乎完全对应组织来源（Cramer's V = 0.887），作为负向对照。因此，我们将问题聚焦于KIRC（n = 146）：选取前2,000个高度可变基因，标准化后训练前馈自编码器（128维隐空间），并对k = 2–10运行k-means聚类。尽管全局指标偏好小k，但在预设发现规则（稀有性<10%且经匈牙利匹配后Jaccard ≥ 0.60，跨20次种子）下，k = 5为最优解（轮廓系数 = 0.129，DBI = 2.045），其中稀有簇C0占6.85%患者，稳定性极高（Jaccard = 0.787）。簇间差异表达分析（Welch's t检验，Benjamini-Hochberg FDR校正）识别出一致标记物。总体而言，泛癌聚类受组织来源主导，而基于稳定性的单癌方法揭示了一个罕见且可复现的KIRC亚型。
原文摘要 · Abstract (English)
Unsupervised learning on high-dimensional RNA-seq data can reveal molecular subtypes beyond standard labels. We combine an autoencoder-based representation with clustering and stability analysis to search for rare but reproducible genomic subtypes. On the UCI "Gene Expression Cancer RNA-Seq" dataset (801 samples, 20,531 genes; BRCA, COAD, KIRC, LUAD, PRAD), a pan-cancer analysis shows clusters aligning almost perfectly with tissue of origin (Cramer's V = 0.887), serving as a negative control. We therefore reframe the problem within KIRC (n = 146): we select the top 2,000 highly variable genes, standardize them, train a feed-forward autoencoder (128-dimensional latent space), and run k-means for k = 2-10. While global indices favor small k, scanning k with a pre-specified discovery rule (rare < 10 percent and stable with Jaccard >= 0.60 across 20 seeds after Hungarian alignment) yields a simple solution at k = 5 (silhouette = 0.129, DBI = 2.045) with a rare cluster C0 (6.85 percent of patients) that is highly stable (Jaccard = 0.787). Cluster-vs-rest differential expression (Welch's t-test, Benjamini-Hochberg FDR) identifies coherent markers. Overall, pan-cancer clustering is dominated by tissue of origin, whereas a stability-aware within-cancer approach reveals a rare, reproducible KIRC subtype.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。