Sun Xue, Zhang Wei, Li Wenrui, Yu Na, Zhang Daoliang, Zou Qi, Dong Qiongye, Zhang Xianglin, Liu Zhiping, Yuan Zhiyuan, Gao Rui
Center of Intelligent Medicine, School of Control Science and Engineering, Shandong University, Jinan, Shandong 250061, China.
MOE Key Lab of Bioinformatics and Bioinformatics Division of BNRIST, Department of Automation, Tsinghua University, Beijing 100084, China.
J Genet Genomics. 2025 Jan;52(1):93-104. doi: 10.1016/j.jgg.2024.09.015. Epub 2024 Oct 2.
Recent advances in spatially resolved transcriptomics (SRT) have provided new opportunities for characterizing spatial structures of various tissues. Graph-based geometric deep learning has gained widespread adoption for spatial domain identification tasks. Currently, most methods define adjacency relation between cells or spots by their spatial distance in SRT data, which overlooks key biological interactions like gene expression similarities, and leads to inaccuracies in spatial domain identification. To tackle this challenge, we propose a novel method, SpaGRA (https://github.com/sunxue-yy/SpaGRA), for automatic multi-relationship construction based on graph augmentation. SpaGRA uses spatial distance as prior knowledge and dynamically adjusts edge weights with multi-head graph attention networks (GATs). This helps SpaGRA to uncover diverse node relationships and enhance message passing in geometric contrastive learning. Additionally, SpaGRA uses these multi-view relationships to construct negative samples, addressing sampling bias posed by random selection. Experimental results show that SpaGRA presents superior domain identification performance on multiple datasets generated from different protocols. Using SpaGRA, we analyze the functional regions in the mouse hypothalamus, identify key genes related to heart development in mouse embryos, and observe cancer-associated fibroblasts enveloping cancer cells in the latest Visium HD data. Overall, SpaGRA can effectively characterize spatial structures across diverse SRT datasets.
空间分辨转录组学（SRT）的最新进展为表征各种组织的空间结构提供了新机遇。基于图的几何深度学习已在空间域识别任务中得到广泛应用。目前，大多数方法在SRT数据中通过细胞或斑点之间的空间距离来定义邻接关系，这忽略了诸如基因表达相似性等关键生物相互作用，并导致空间域识别不准确。为应对这一挑战，我们提出了一种新方法SpaGRA（https://github.com/sunxue-yy/SpaGRA），用于基于图增强的自动多关系构建。SpaGRA将空间距离用作先验知识，并通过多头图注意力网络（GAT）动态调整边权重。这有助于SpaGRA揭示多样的节点关系，并增强几何对比学习中的消息传递。此外，SpaGRA利用这些多视图关系构建负样本，解决随机选择带来的采样偏差问题。实验结果表明，SpaGRA在从不同协议生成的多个数据集上呈现出卓越的域识别性能。使用SpaGRA，我们分析了小鼠下丘脑的功能区域，鉴定了与小鼠胚胎心脏发育相关的关键基因，并在最新的Visium HD数据中观察到癌症相关成纤维细胞包裹癌细胞的现象。总体而言，SpaGRA能够有效地表征不同SRT数据集的空间结构。
