A Multi-scale Fused Graph Neural Network with Inter-view Contrastive Learning for Spatial Transcriptomics Data Clustering

TL;DR

This paper introduces stMFG, a multi-scale graph neural network with layer-wise cross-view attention and contrastive learning, significantly improving spatial domain clustering in transcriptomics data.

Contribution

The paper proposes a novel multi-scale interactive fusion graph neural network with layer-wise attention and contrastive learning for better spatial transcriptomics clustering.

Findings

Outperforms state-of-the-art methods on DLPFC and breast cancer datasets.

Achieves up to 14% ARI improvement in clustering accuracy.

Effectively captures multi-scale semantic information and cross-view interactions.

Abstract

Spatial transcriptomics enables genome-wide expression analysis within native tissue context, yet identifying spatial domains remains challenging due to complex gene-spatial interactions. Existing methods typically process spatial and feature views separately, fusing only at output level - an "encode-separately, fuse-late" paradigm that limits multi-scale semantic capture and cross-view interaction. Accordingly, stMFG is proposed, a multi-scale interactive fusion graph network that introduces layer-wise cross-view attention to dynamically integrate spatial and gene features after each convolution. The model combines cross-view contrastive learning with spatial constraints to enhance discriminability while maintaining spatial continuity. On DLPFC and breast cancer datasets, stMFG outperforms state-of-the-art methods, achieving up to 14% ARI improvement on certain slices.