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

• Published in: Nature methods Vol. 18; no. 11; pp. 1342 - 1351
• Main Authors: Hu, Jian, Li, Xiangjie, Coleman, Kyle, Schroeder, Amelia, Ma, Nan, Irwin, David J., Lee, Edward B., Shinohara, Russell T., Li, Mingyao
• Format: Journal Article
• Language: English
• Published: New York Nature Publishing Group US 01.11.2021; Nature Publishing Group
• Subjects: 631/114/2401; 631/114/2415; 631/1647/794; 631/208/212/2019; 631/61/212/2019; Algorithms; Animals; Artificial neural networks; Bioinformatics; Biological Microscopy; Biological Techniques; Biomedical and Life Sciences; Biomedical Engineering/Biotechnology; Brain - metabolism; Cluster Analysis; Computational Biology; Data analysis; Datasets; Domains; Dorsolateral Prefrontal Cortex - metabolism; Gene expression; Gene Expression Regulation; Genes; Genetic diversity; Genetic research; Histology; Humans; Life Sciences; Mice; Microenvironments; Neural networks; Neural Networks, Computer; Pancreatic Neoplasms - genetics; Pancreatic Neoplasms - pathology; Proteomics; Software; Spatial Analysis; Spatial variations; Transcriptome; Visual Cortex - metabolism; United States
• ISSN: 1548-7091; 1548-7105; 1548-7105
• DOI: 10.1038/s41592-021-01255-8

Recent advances in spatially resolved transcriptomics (SRT) technologies have enabled comprehensive characterization of gene expression patterns in the context of tissue microenvironment. To elucidate spatial gene expression variation, we present SpaGCN, a graph convolutional network approach that integrates gene expression, spatial location and histology in SRT data analysis. Through graph convolution, SpaGCN aggregates gene expression of each spot from its neighboring spots, which enables the identification of spatial domains with coherent expression and histology. The subsequent domain guided differential expression (DE) analysis then detects genes with enriched expression patterns in the identified domains. 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 is computationally fast, platform independent, making it a desirable tool for diverse SRT studies. SpaGCN is a spatially resolved transcriptomics data analysis tool for identifying spatial domains and spatially variable genes using graph convolutional networks.