发表机构
University of Liverpool; Zhejiang Normal University（利物浦大学; 浙江师范大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
Path2ST是一种基于细胞-组织层级的跨模态转换框架，通过融合层级条件机制、尺度自适应生成与全谱损失函数，实现从H&E图像精准预测空间转录组，在三个数据集上达到最优性能。
AI 中文摘要
从苏木精-伊红（H&E）染色图像预测空间基因表达是空间转录组学（ST）的一种高性价比替代方案。然而，现有方法将H&E图像视为通用视觉输入，忽略了其内在的生物学层级——空间组织的细胞类型共同构成调控局部基因表达程序的功能性组织微环境。为填补这一空白，我们将H&E到ST的预测建模为跨模态语义转换任务，并提出Path2ST，这是一个基于层级的自回归框架，包含三个关键组件：（i）层级细胞-组织条件机制，融合显式和隐式细胞特征与组织层级语义表示，构建层级条件信号；（ii）基于层级语义词汇的尺度自适应自回归生成过程，实现从粗到细、符合生物学规律的表达合成；（iii）SpectraLoss，一种全谱目标函数，联合约束序数保真度、建模转录爆发并使语义结构与细胞类型对齐。在三个数据集上的大量实验表明，Path2ST达到了最先进的性能，验证其可生成高度准确且空间连贯的转录组图谱。相关代码已在该httpsURL发布。
英文摘要
Predicting spatial gene expression from hematoxylin and eosin (H\&E)-stained images offers a cost-effective alternative to spatial transcriptomics (ST). However, existing methods treat H\&E images as generic visual inputs and ignore their intrinsic biological hierarchy, where spatially organized cell types collectively form functional tissue microenvironments that govern local gene expression programs. To bridge this gap, we formulate H\&E-to-ST prediction as a cross-modal semantic translation task and propose Path2ST, a hierarchically grounded autoregressive framework featuring three key components: (i) a Hierarchical Cell-Tissue Conditioning mechanism that fuses explicit and implicit cellular features with tissue-level semantic representations to construct hierarchical conditioning signals; (ii) a Scale-Adaptive Autoregressive Generation process over a hierarchical semantic vocabulary, enabling coarse-to-fine, biologically consistent expression synthesis; and (iii) SpectraLoss, a full-spectrum objective that jointly enforces ordinal fidelity, models transcriptional bursts, and aligns semantic structures with cell types. Extensive experiments on three datasets demonstrate state-of-the-art performance, validating that Path2ST generates highly accurate and spatially coherent transcriptomic profiles. The related code is released at https://github.com/RuochenLiu23/Path2ST.
