Journal Article

Deciphering spatial domains from spatially resolved transcriptomics through spatially regularized deep graph networks

Sun, Xue, Qiao, Xu, Zhang, Wei, Yu, Na, Gao, Rui, Zhang, Daoliang, Zhang, Wenjing, Li, Haoyang

2024

Overview

Background Recent advancements in spatially resolved transcriptomics (SRT) have opened up unprecedented opportunities to explore gene expression patterns within spatial contexts. Deciphering spatial domains is a critical task in spatial transcriptomic data analysis, aiding in the elucidation of tissue structural heterogeneity and biological functions. However, existing spatial domain detection methods ignore the consistency of expression patterns and spatial arrangements between spots, as well as the severe gene dropout phenomenon present in SRT data, resulting in suboptimal performance in identifying tissue spatial heterogeneity. Results In this paper, we introduce a novel framework, spatially regularized deep graph networks (SR-DGN), which integrates gene expression profiles with spatial information to learn spatially-consistent and informative spot representations. Specifically, SR-DGN employs graph attention networks (GAT) to adaptively aggregate gene expression information from neighboring spots, considering local expression patterns between spots. In addition, the spatial regularization constraint ensures the consistency of neighborhood relationships between physical and embedded spaces in an end-to-end manner. SR-DGN also employs cross-entropy (CE) loss to model gene expression states, effectively mitigating the impact of noisy gene dropouts. Conclusions Experimental results demonstrate that SR-DGN outperforms state-of-the-art methods in spatial domain identification across SRT data from different sequencing platforms. Moreover, SR-DGN is capable of recovering known microanatomical structures, yielding clearer low-dimensional visualizations and more accurate spatial trajectory inferences.

• Publisher: BioMed Central,BioMed Central Ltd,Springer Nature B.V,BMC
• Subject: Algorithms / Animal Genetics and Genomics / Biomedical and Life Sciences / Clustering / Computational Biology - methods / Cross-entropy loss / Data analysis / Gene expression / Gene Expression Profiling - methods / Genetic research / Graph attention network / Graphic methods / Graphical representations / Heterogeneity / Humans / Identification / Life Sciences / Methods / Microarrays / Microbial Genetics and Genomics / Networks / Neural networks / Plant Genetics and Genomics / Proteomics / Regularization / RNA sequencing / Spatial analysis / Spatial data / Spatial domains / Spatial heterogeneity / Spatial regularization constraint / Spatial resolved transcriptomics / Transcriptome / Transcriptomics