HEXST: Hexagonal Shifted-Window Transformer for Spatial Transcriptomics Gene Expression Prediction

TL;DR

HEXST introduces a hexagonal-aware Transformer model that improves spatial gene expression prediction from histology slides by aligning with the hexagonal sampling geometry and enhancing gene-wise spatial contrast.

Contribution

The paper presents HEXST, a novel geometry-aligned Transformer with shifted-window attention and contrast-sensitive objectives tailored for hexagonal spatial transcriptomics data.

Findings

HEXST outperforms existing models across seven datasets.

It accurately predicts spatial gene expression while preserving heterogeneity.

HEXST enhances gene-wise contrast in predictions.

Abstract

Spatial transcriptomics offers spatially resolved gene expression profiling within tissue sections, but its cost and limited throughput hinder large-scale deployment. To extend this capability to routine practice, recent computational methods aim to infer spatial gene expression directly from ubiquitous hematoxylin and eosin-stained histology slides. However, most existing models assume Cartesian or geometry-agnostic locality, despite the hexagonal sampling of widely used spot-array platforms, and point-wise regression objectives often yield over-smoothed gene expression profiles, obscuring gene-specific spatial heterogeneity. To address these, we propose HEXST, a geometry-aligned Transformer for spatial gene expression prediction from histology. HEXST operates directly on hexagonal spot coordinates to enable efficient local-to-global contextual modeling via tailored shifted-window attention mechanism and hexagonal rotary positional encoding. To enhance gene-wise spatial contrast, HEXST complements point-wise regression with a contrast-sensitive differential objective and transcriptomic priors from a pretrained single-cell foundation model during training. Across seven spatial transcriptomics datasets, HEXST consistently outperforms state-of-the-art models, providing accurate and robust spatial gene expression predictions while preserving gene-wise contrast and spatial heterogeneity.