PGST: A prototype-guided parameter-efficient network for spatial transcriptomics prediction

Spatial transcriptomics (ST) aims to decode spatially resolved gene expression patterns while preserving tissue morphology. Current methods tend to use lower-cost deep learning approaches for gene expression prediction, yet face severe challenges. First, existing methods fail to give sufficient consideration to the spatial specificity of positional encoding inherent in ST; second, they neglect to leverage spatially coherent co-expression patterns across different domains; third, their reliance on linearly weighted aggregation induces vulnerability to noise and distribution shifts; and finally, these architectures exhibit limited parameter efficiency. To address these issues, we introduce prototype-guided network for spatial transcriptomics (PGST), which includes four parts: (1) oriented signal propagation through polar embedding strategy for spatial transcriptomics (PEST); (2) prototype-guided aggregation for global co-feature preservation; (3) global consistency enforcement via shared decoder with reconstruction loss; and (4) lightweight architectural design. Our framework integrates contrastive learning with graph neural networks to balance local-global spatial dependencies and cross-modal consistency. Experimental results on multiple datasets from ST demonstrate the superior performance of our PGST model than existing methods. Our source code is available at: https://github.com/RanSuLab/PGST https://github.com/RanSuLab/PGST.

Authors

• Yuan He
• Kaimiao Hu
• Changming Sun
• Leyi Wei Centre for Artificial Intelligence driven Drug Discovery, Faculty of Applied Science, Macao Polytechnic University
• Ran Su

Keywords

• Gene expression
• Transcriptomics
• Pipelines
• Prototypes
• Contrastive learning
• Computer architecture
• Decoding
• Vectors
• Bioinformatics
• Training
• Spatial Prediction
• Spatial Transcriptomics
• Graph Neural Networks
• Self-supervised Learning
• Predicted Gene Expression
• Positional Encoding
• Global Consistency
• Pearson Correlation
• Breast Cancer
• Higher Gene Expression
• Mutual Information
• Spatial Domain
• Y Chromosome
• Spatial Task
• Graph Convolutional Network
• Aggregation Method
• Pearson Correlation Coefficient Values
• Superior Capability
• Adjusted Rand Index
• L2 Loss
• Highly Variable Genes
• Spatial Recognition
• True Cluster
• deep learning
• histopathological images
• graph neural network