用无监督对比学习挖掘癌症亚型与生存关联，无需标签也能精准分群。
OmicsCL: Unsupervised Contrastive Learning for Cancer Subtype Discovery and Survival Stratification
- 通过对比学习融合基因表达、甲基化等多组学数据，构建统一表征空间。
- 在乳腺癌数据上发现与生存期显著相关的临床有意义聚类，无监督一致性达0.62。
- 可灵活调节优先分亚型或预测生存，适合生物机制探索和精准医疗研究。
从多组学数据中进行疾病亚型的无监督学习，为推进个性化医疗提供了重要机遇。我们提出OmicsCL，一种模块化对比学习框架，能够将基因表达、DNA甲基化、miRNA表达等异构组学模态联合嵌入统一潜在空间。该方法引入生存感知的对比损失，促使模型学习与生存相关模式对齐，而无需依赖标注结果。在TCGA BRCA数据集上的评估显示，OmicsCL揭示了具有临床意义的聚类，并实现了与患者生存高度一致的无监督表现（concordance = 0.62）。框架在不同超参数设置下均表现出鲁棒性，且可调参以侧重亚型一致性或生存分层能力。消融实验表明，集成生存感知损失显著提升了表征的预测能力。这些结果凸显了对比目标在高维、异质组学数据中发现生物学洞见的巨大潜力。
原文摘要 · Abstract (English)
Unsupervised learning of disease subtypes from multi-omics data presents a significant opportunity for advancing personalized medicine. We introduce OmicsCL, a modular contrastive learning framework that jointly embeds heterogeneous omics modalities-such as gene expression, DNA methylation, and miRNA expression-into a unified latent space. Our method incorporates a survival-aware contrastive loss that encourages the model to learn representations aligned with survival-related patterns, without relying on labeled outcomes. Evaluated on the TCGA BRCA dataset, OmicsCL uncovers clinically meaningful clusters and achieves strong unsupervised concordance with patient survival. The framework demonstrates robustness across hyperparameter configurations and can be tuned to prioritize either subtype coherence or survival stratification. Ablation studies confirm that integrating survival-aware loss significantly enhances the predictive power of learned embeddings. These results highlight the promise of contrastive objectives for biological insight discovery in high-dimensional, heterogeneous omics data.
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。