MERGE: Multi-faceted Hierarchical Graph-based GNN for Gene Expression Prediction from Whole Slide Histopathology Images

TL;DR

This paper introduces MERGE, a hierarchical graph-based GNN that leverages spatial and morphological clustering of tissue patches to improve gene expression prediction from whole slide histopathology images, outperforming existing methods.

Contribution

The paper proposes a novel multi-faceted hierarchical graph construction and GNN approach that captures interactions between distant tissue locations for better gene expression prediction.

Findings

MERGE outperforms state-of-the-art methods on gene expression prediction metrics.

Incorporating intra- and inter-cluster edges enhances model performance.

Gene-aware smoothing techniques improve data quality and prediction accuracy.

Abstract

Recent advances in Spatial Transcriptomics (ST) pair histology images with spatially resolved gene expression profiles, enabling predictions of gene expression across different tissue locations based on image patches. This opens up new possibilities for enhancing whole slide image (WSI) prediction tasks with localized gene expression. However, existing methods fail to fully leverage the interactions between different tissue locations, which are crucial for accurate joint prediction. To address this, we introduce MERGE (Multi-faceted hiErarchical gRaph for Gene Expressions), which combines a multi-faceted hierarchical graph construction strategy with graph neural networks (GNN) to improve gene expression predictions from WSIs. By clustering tissue image patches based on both spatial and morphological features, and incorporating intra- and inter-cluster edges, our approach fosters interactions between distant tissue locations during GNN learning. As an additional contribution, we evaluate different data smoothing techniques that are necessary to mitigate artifacts in ST data, often caused by technical imperfections. We advocate for adopting gene-aware smoothing methods that are more biologically justified. Experimental results on gene expression prediction show that our GNN method outperforms state-of-the-art techniques across multiple metrics.