FEAST: Fully Connected Expressive Attention for Spatial Transcriptomics

TL;DR

FEAST is an attention-based framework that models all pairwise tissue interactions in spatial transcriptomics, incorporating negative interactions and richer context to improve gene expression prediction.

Contribution

It introduces a fully connected attention model with negative-aware attention and off-grid sampling, addressing limitations of previous graph-based methods.

Findings

Outperforms state-of-the-art gene expression prediction methods.

Provides biologically plausible attention maps showing positive and negative interactions.

Enhances morphological context capture with off-grid sampling.

Abstract

Spatial Transcriptomics (ST) provides spatially-resolved gene expression, offering crucial insights into tissue architecture and complex diseases. However, its prohibitive cost limits widespread adoption, leading to significant attention on inferring spatial gene expression from readily available whole slide images. While graph neural networks have been proposed to model interactions between tissue regions, their reliance on pre-defined sparse graphs prevents them from considering potentially interacting spot pairs, resulting in a structural limitation in capturing complex biological relationships. To address this, we propose FEAST (Fully connected Expressive Attention for Spatial Transcriptomics), an attention-based framework that models the tissue as a fully connected graph, enabling the consideration of all pairwise interactions. To better reflect biological interactions, we introduce negative-aware attention, which models both excitatory and inhibitory interactions, capturing essential negative relationships that standard attention often overlooks. Furthermore, to mitigate the information loss from truncated or ignored context in standard spot image extraction, we introduce an off-grid sampling strategy that gathers additional images from intermediate regions, allowing the model to capture a richer morphological context. Experiments on public ST datasets show that FEAST surpasses state-of-the-art methods in gene expression prediction while providing biologically plausible attention maps that clarify positive and negative interactions. Our code is available at https://github.com/starforTJ/ FEAST.