用120万份数据训练模型，让病理切片预测基因表达，助力癌症精准治疗
A Multimodal Foundation Model of Spatial Transcriptomics and Histology for Biological Discovery and Clinical Prediction
- 融合组织形态与基因表达，构建跨模态基础模型
- 在11种肿瘤中实现高精度基因表达预测，优于现有方法
- 可广泛适配不同设备，适合生物发现与临床预后研究
空间转录组学（ST）可在解剖背景下绘制基因表达图谱，但成本高、通量低。苏木精-伊红（H&E）染色提供丰富形态信息，却缺乏分子分辨率。我们提出STORM（Spatial Transcriptomics and Histology Representation Model），一个基于18个器官、120万份空间分辨转录组数据与匹配组织学图像的大型基础模型。该模型采用分层架构，整合形态特征、基因表达与空间上下文，通过鲁棒的分子-形态表征实现成像与组学间的桥梁。STORM显著提升空间域发现能力，生成生物学一致的组织图谱，并在11种肿瘤类型中，从H&E图像预测空间基因表达的表现优于现有方法。模型具备平台无关性，在Visium、Xenium、Visium HD和CosMx上均表现稳定。应用于23个独立队列共7,245名患者，其免疫治疗反应预测与预后评估显著优于现有生物标志物，为空间导向的发现与临床精准医学提供可扩展框架。
原文摘要 · Abstract (English)
Spatial transcriptomics (ST) enables gene expression mapping within anatomical context but remains costly and low-throughput. Hematoxylin and eosin (H\&E) staining offers rich morphology yet lacks molecular resolution. We present \textbf{\ours} (\textbf{S}patial \textbf{T}ranscriptomics and hist\textbf{O}logy \textbf{R}epresentation \textbf{M}odel), a foundation model trained on 1.2 million spatially resolved transcriptomic profiles with matched histology across 18 organs. Using a hierarchical architecture integrating morphological features, gene expression, and spatial context, STORM bridges imaging and omics through robust molecular--morphological representations. STORM enhances spatial domain discovery, producing biologically coherent tissue maps, and outperforms existing methods in predicting spatial gene expression from H\&E images across 11 tumor types. The model is platform-agnostic, performing consistently across Visium, Xenium, Visium HD, and CosMx. Applied to 23 independent cohorts comprising 7,245 patients, STORM significantly improves immunotherapy response prediction and prognostication over established biomarkers, providing a scalable framework for spatially informed discovery and clinical precision medicine.
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。