SpatialDG: a novel spatial domain identification method for spatially resolved transcriptomics data based on dual-graph neural network
Open Access
- 1 March 2026
- journal article
- research article
- Published by Oxford University Press (OUP) in Briefings in Bioinformatics
- Vol. 27 (2)
Abstract
Spatially resolved transcriptomic (ST) technologies offer transformative opportunities to chart gene expression landscapes within intact tissue architecture. Uncovering spatially discrete domains of biological function is essential for deciphering tissue heterogeneity, developmental processes, and disease mechanisms. Yet, the inherent noise, high dimensionality, and spatial sparsity of ST data present substantial challenges to the unsupervised delineation of these domains. We present SpatialDG, a dual-graph self-supervised contrastive learning framework for ST. SpatialDG combines graph neural networks with self-supervised contrastive learning to learn informative and discriminative spot representations by maximizing the agreement between local (node) and global (graph) embeddings and leveraging spatial adjacency to enhance representation learning. Specifically, SpatialDG constructs both a gene expression similarity graph and a spatial adjacency graph, integrating them via a dual-view contrastive architecture that aligns molecular and spatial information, while a zero-inflated negative binomial reconstruction loss accounts for the count-based and sparse nature of gene expression data. SpatialDG achieves significant gains over state-of-the-art algorithms in both healthy and cancer datasets, demonstrating robust generalization across diverse ST landscapes. In conclusion, SpatialDG efficiently unravels biologically meaningful domains from spatial and genetic signals, providing a powerful and generalizable tool to mine tissue architecture in ST datasets.Keywords
Funding Information
- iCANDOC—Doctoral education pilot in precision cancer medicine—program of the iCAN Digital Precision Cancer Medicine Flagship
- GeneCellNano Flagship
- European Union CARES
This publication has 66 references indexed in Scilit:
- Large-Scale Cellular-Resolution Gene Profiling in Human Neocortex Reveals Species-Specific Molecular SignaturesCell, 2012
- IGFBP-5 induces cell adhesion, increases cell survival and inhibits cell migration in MCF-7 human breast cancer cells.Journal of Cell Science, 2012
- IGFBP7 reduces breast tumor growth by induction of senescence and apoptosis pathwaysBreast Cancer Research and Treatment, 2011
- Deficiency in trefoil factor 1 (TFF1) increases tumorigenicity of human breast cancer cells and mammary tumor development in TFF1-knockout miceOncogene, 2011
- S100A6 – New facts and featuresBiochemical and Biophysical Research Communications, 2009
- TIMP-1 as a tumor marker in breast cancer – An updateActa Oncologica, 2008
- Nomenclature of the Human Immunoglobulin Heavy (IGH) GenesExperimental and Clinical Immunogenetics, 2001
- Segmentation of brain MR images through a hidden Markov random field model and the expectation-maximization algorithmIEEE Transactions on Medical Imaging, 2001
- Control of Shh activity and signaling in the neural tubeDevelopmental Dynamics, 2000
- CD79a: a novel marker for B-cell neoplasms in routinely processed tissue samplesBlood, 1995