用语言模型解码癌症循环转录组特征
Decoding cancer circulating transcriptomic signatures with language models.
摘要(中文译文)
当前用于多癌种检测的液体活检方法通常基于血浆游离RNA（cfRNA，即循环于血液中、可反映疾病状态的短RNA片段），并依赖基因注释，这可能遗漏来自未注释或重复基因组区域的信号。我们提出GeneLLM，一种基于Transformer的模型，可直接处理人类比对cfRNA读段的核苷酸序列，以识别具有癌症指示意义的特征。通过绕过基因水平的定量分析，该模型保留了来自转录组“暗物质”的信号。模型学习潜在的伪生物标志物（由聚合的cfRNA读段嵌入得到的原型表征），这些表征作为癌症分类的判别特征，而非对应于明确的基因组序列。我们在此展示，在一个多中心队列中，GeneLLM在多种癌症中取得的ROC-AUC值为0.9250至0.9962，同时在典型测序深度的六分之一条件下仍保持相当的性能。这些结果表明，对血浆cfRNA进行序列水平建模能够捕获超越依赖注释方法的诊断相关信息，从而实现更具成本效益且可扩展的癌症筛查。
Abstract
Current liquid biopsy methods for multi-cancer detection using plasma cell-free RNA (cfRNA, short RNA fragments circulating in blood that can reflect disease states) typically rely on gene annotations, which can overlook signals from unannotated or repetitive genomic regions. We present GeneLLM, a Transformer-based model that directly processes the nucleotide sequences of human-mapped cfRNA reads to identify cancer-indicative signatures. By bypassing gene-level quantification, the model retains signals from transcriptomic dark matter. The model learns latent pseudo-biomarkers (prototype representations from aggregated cfRNA read embeddings) that serve as discriminative features for cancer classification, rather than corresponding to explicit genomic sequences. Here we show that, in a multi-centre cohort, GeneLLM achieves ROC-AUC values ranging from 0.9250 to 0.9962 across several cancers, while maintaining comparable performance at one-sixth of the typical sequencing depth. These results suggest that sequence-level modelling of plasma cfRNA can capture diagnostically relevant information beyond annotation-dependent approaches, enabling more cost-efficient and scalable cancer screening.
如何引用
AMA
Siwei Deng, Lei Sha, Yongcheng Jin, Tianyao Zhou, Chengen Wang, Qianpu Liu, et al. Decoding cancer circulating transcriptomic signatures with language models.. Nature communications. 2026; doi:10.1038/s41467-026-74411-3.
APA
Siwei Deng, Lei Sha, Yongcheng Jin, Tianyao Zhou, Chengen Wang, Qianpu Liu, et al (2026). Decoding cancer circulating transcriptomic signatures with language models.. Nature communications. https://doi.org/10.1038/s41467-026-74411-3
GB/T 7714
Siwei Deng, Lei Sha, Yongcheng Jin, Tianyao Zhou, Chengen Wang, Qianpu Liu, et al. Decoding cancer circulating transcriptomic signatures with language models.[J]. Nature communications, 2026 doi:10.1038/s41467-026-74411-3.
在 PubMed增强版 阅读全文
翻译全文 · AI 文献问答 · PDF 原文下载 · 引用导出