单细胞论文记录(part13)--SpaGCN: Integrating gene expression, spatial location and histology to ...

学习笔记，仅供参考，有错必纠
Authors：Jian Hu，Xiangjie Li，Mingyao Li
Journal：Nature Methods
Year：2021

---

---

SpaGCN: Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network

abstract

Recent advances in spatially resolved transcriptomics (SRT) technologies have enabled comprehensive characterization of gene expression patterns in the context of tissue microenvironment. 为了阐明基因表达的空间变化，我们提出了SpaGCN，这是一种图卷积网络方法，在SRT数据分析中整合了基因表达、空间位置和组织学. Through graph convolution, SpaGCN aggregates gene expression of each spot from its neighboring spots, which enables the identification of spatial domains(空间域) with coherent expression and histology (一致表达和组织学). The subsequent domain guided differential expression (DE) analysis then detects genes with enriched expression patterns in the identified domains (检测出在识别的领域中具有丰富表达模式的基因). Analyzing seven SRT datasets using SpaGCN, we show it can detect genes with much more enriched spatial expression patterns than competing methods. Furthermore, genes detected by SpaGCN are transferrable and can be utilized to study spatial variation of gene expression in other datasets(SpaGCN检测到的基因是可转移的，可以用来研究其他数据集中基因表达的空间变化). SpaGCN is computationally fast, platform independent, making it a desirable tool for diverse SRT studies.

Overview of SpaGCN and evaluation.

We explain the workflow of SpaGCN using in situ capturing-based SRT data as an example, but the method can be easily modified to analyze other types of SRT data. As shown in Fig. 1a, SpaGCN first builds a graph to represent the relationship of all spots considering both spatial location and histology information. Next, SpaGCN utilizes a graph convolutional layer to aggregate gene expression information from neighboring spots. Then, SpaGCN uses the aggregated expression matrix to cluster spots using an unsupervised iterative clustering algorithm. Each cluster is considered as a spatial domain from which SpaGCN then detects SVGs that are enriched in a domain by DE analysis (Fig. 1b). When a single gene cannot mark the expression pattern of a domain, SpaGCN will construct a meta gene, formed by the combination of multiple genes, to represent the expression pattern of the domain.

To showcase the strength of SpaGCN, we applied it to seven publicly available datasets (Supplementary Table 1). The spatial domains identified by SpaGCN agree better with known tissue structures than Louvain, stLearn, and BayesSpace. We also compared SVGs detected by SpaGCN with those detected by SpatialDE and SPARK, and found that the SpaGCN-detected SVGs have more coherent expression patterns and better biological interpretability than the other two methods. The specificity of spatial expression patterns revealed by SpaGCN-detected SVGs were further confirmed by Moran’s I and Geary’s C statistics, two commonly used metrics for quantifying spatial autocorrelation of gene expression.

Fig. 1 | Workflow of SpaGCN. a, SpaGCN首先使用图卷积网络(GCN)整合基因表达、空间位置和组织学信息，然后使用无监督的迭代聚类将spot分成不同的空间域. GCN是基于一个无定向的加权图，其中每两个spot之间的边缘权重由两个spot之间的欧氏距离决定，spot由空间坐标（x,y）和第三维坐标z定义(z从组织学图像的RGB值获得). b, 对于每个检测到的空间域，SpaGCN通过domain引导的DE分析识别SVG或meta genes.

Methods

The network parameters and cluster centroids are simultaneously optimized by minimizing L using stochastic gradient descent with momentum. This unsupervised iterative clustering algorithm has previously been utilized for scRNA-seq analysis and showed superior performance over Louvain’s method.
After clustering, SpaGCN also provides an optional refinement step for the clustering result. In this step, SpaGCN examines the domain assignment of each spot and its surrounding spots. For a given spot, if more than half of its surrounding spots are assigned to a different domain, this spot will be relabeled to the same domain as the major label of its surrounding spots. As this refinement step only relabels a few spots, it has little impact on the downstream SVG detection. We performed cluster refinement only for the human dorsolateral prefrontal cortex 10x Visium data and the STARmap data when comparing to their manual annotations with clear domain boundaries.