相关性引导的流匹配与退火掩码用于空间转录组生成
Correlation-Guided Flow Matching with Annealed Masking for Spatial Transcriptomics Generation
- University of Cambridge（剑桥大学）
- The University of Edinburgh（爱丁堡大学）
- National University of Singapore（新加坡国立大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对空间转录组预测中忽略基因相互作用的局限，提出相关性引导的流匹配框架CorrFlow，通过退火掩码和基因图正则化显式建模基因依赖，在12个数据集上取得最优PCC和HPCC。
AI中文摘要：
空间转录组学（ST）提供空间分辨的基因表达谱，但成本高昂，这促使人们从组织学图像预测ST。生成模型已成为ST预测的主流范式，因为它们能够对基因表达的条件分布进行建模并捕捉其固有的随机性。然而，这些方法通常将基因视为独立的预测目标，忽略了生物系统中内在的基因-基因相互作用，这限制了它们保留具有生物学意义的共表达模式的能力。我们认为，反映共享通路和调控机制的基因-基因相互作用，对于生成数值准确且生物学连贯的ST图谱至关重要。在本文中，我们提出了CorrFlow，一种用于组织学到ST预测的相关性引导的流匹配框架，通过两种互补机制显式建模基因-基因依赖性。首先，我们引入了一种退火掩码流匹配策略，其中基因子集按照依赖于时间步的退火调度逐步被掩码，鼓励模型在剩余基因的条件下推断被掩码的基因，并促进超越逐基因边际估计的联合条件建模。其次，我们设计了一种基因图正则化优化方案，该方案整合了来自STRING数据库的先验知识和由WGCNA估计的数据驱动的共表达，以构建基因亲和力图，从而在预测的表达中强制执行局部一致性和全局平滑性。在12个数据集上的大量实验表明，CorrFlow在评估方法中取得了最佳的平均PCC和HPCC，从而产生更具生物学连贯性的ST预测。
英文摘要：
Spatial transcriptomics (ST) provides spatially resolved gene expression profiling but remains expensive, motivating the prediction of ST from histology images. Generative models have emerged as a mainstream paradigm for ST prediction due to their ability to model the conditional distribution of gene expression and capture its inherent stochasticity. However, these methods typically treat genes as independent prediction targets and overlook the intrinsic gene-gene interactions in biological systems, which limits their ability to preserve biologically meaningful co-expression patterns. We argue that gene-gene interactions, which reflect shared pathways and regulatory mechanisms, are essential for generating numerically accurate and biologically coherent ST profiles. In this paper, we propose CorrFlow, a correlation-guided flow matching framework for histology-to-ST prediction that explicitly models gene-gene dependencies through two complementary mechanisms. First, we introduce an annealed masked flow matching strategy, where subsets of genes are progressively masked following a timestep-dependent annealing schedule, encouraging the model to infer masked genes conditioned on the remaining genes and promoting joint conditional modeling beyond per-gene marginal estimation. Second, we devise a gene graph-regularized optimization scheme that integrates prior knowledge from the STRING database and data-driven co-expression estimated by WGCNA to construct a gene affinity graph, which enforces both local consistency and global smoothness in the predicted expression. Extensive experiments across 12 datasets show that CorrFlow achieves the best average PCC and HPCC among evaluated methods, leading to more biologically coherent ST predictions.
