GraphSTAR: Proximal Operator-Based Graph Neural Network Enhanced by Dynamic Graph Aggregation for Spatial Transcriptomics

Spatial transcriptomics technologies carry out advanced sequencing analysis of molecular profiles with a spatial context, providing multi-source information essential for elucidating biological regulatory mechanisms. Nonetheless, it poses challenges in the integration of raw spatial coordinates with high-dimensional gene expression profiles in their native feature space. While spatial-aware methods effectively aggregate molecular information from local spatial neighborhoods, they fail to explore the long-range relationships associated with gene expression data. To address this issue, this paper introduces a novel approach termed GraphSTAR that encodes both spatial and gene expression data into undirected graphs, characterizing the local spatial proximity and global transcriptional similarity, respectively. Through a graph aggregation process, GraphSTAR integrates these diverse data sources within a joint graph structure, effectively modeling both local neighborhood relationships and long-range functional associations. Subsequently, a reassembled graph neural network is established by incorporating the graph aggregation into the feed-forward propagation using proximal operators, progressively refining spatial-informed latent representation to decipher spatial expression patterns of genes. Extensive experiments on benchmark datasets demonstrate that GraphSTAR outperforms state-of-the-art methods in both spatial domain identification and cell-type annotation tasks.

Authors

• Junyu Li
• Jingquan Yan University of Texas at Arlington
• Yi Liao
• Wenxiong Liao
• Ye Liu
• Hongmin Cai

Keywords

• Transcriptomics
• Gene expression
• Graph neural networks
• Spatial resolution
• Feature extraction
• Bioinformatics
• Annotations
• Spatial databases
• Computational modeling
• Transformers
• Aggregation Kinetics
• Dynamic Graph
• Spatial Transcriptomics
• Graph Aggregation
• Spatial Patterns
• Gene Expression Data
• Undirected
• Spatial Domain
• Spatial Coordinates
• Graph Structure
• Spatial Proximity
• Spatial Expression
• Latent Representation
• Spatial Expression Patterns
• Spatial Neighborhood
• Spatial Design
• Cell Type Annotation
• Proximal Operator
• Spatial Information
• Highly Variable Genes
• Graph Features
• Simulated Datasets
• Molecular Layer
• Metric Learning
• Forward Propagation
• Reconstruction Loss
• Original Features
• Formation Of Traces
• graph neural network
• cell-type annotation
• spatial domain identification