用程序空间扩散模型，从组织切片预测基因表达谱。
Program-space Diffusion for Morphology-to-Transcriptomics Prediction
- 将基因表达预测转为程序空间的条件生成，利用协同变化模式
- 通过共识非负矩阵分解提取低维转录程序，降低生成维度
- 适合生物医学图像分析与多组学融合研究者使用
空间转录组学（ST）可在保留组织结构的前提下进行全基因组基因表达分析，但其成本高且扩展性差仍是主要瓶颈。这推动了直接从常规病理切片预测空间表达的研究。尽管已有成果令人鼓舞，但大多数方法在基因层面独立预测，未采用成熟的转录组建模方法，且依赖异构的基因选择策略，导致不同方法间难以公平比较。本文提出将形态学至转录组预测重构为转录程序空间中的条件生成任务，从而利用协调的转录变异，而非独立预测各基因。通过共识非负矩阵分解（cNMF）从训练数据中提取一组低维转录程序，以捕捉协调表达变化，并训练一个条件扩散模型，根据组织切片生成程序激活值。该框架充分利用了转录变异的协同性，显著降低了条件生成任务的维度。
原文摘要 · Abstract (English)
Spatial transcriptomics (ST) enables genome-wide gene expression profiling while preserving tissue architecture, but its cost and limited scalability remain major bottlenecks. This has motivated models that predict spatial expression directly from routine histology. Despite promising results, most existing approaches operate at the gene level without leveraging established transcriptomic modeling practices and rely on heterogeneous gene selection strategies, which complicates fair comparison across methods. We propose to reformulate morphology-to-transcriptomics prediction as conditional generation in transcriptional program space, thereby exploiting coordinated transcriptional variation instead of predicting genes independently. Using consensus non-negative matrix factorization (cNMF), we extract a low-dimensional set of transcriptional programs capturing coordinated expression variation in the training data, and train a conditional diffusion model to generate program activations from histology. This formulation exploits coordinated transcriptional variation and substantially lowers the dimensionality of the conditional generative task.
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。