FLAG: Foundation model representation with Latent diffusion Alignment via Graph for spatial gene expression prediction

TL;DR

FLAG is a diffusion-based framework that models spatial gene expression as structured distributions, effectively capturing gene and spatial relationships while addressing high-dimensional challenges.

Contribution

Introduces FLAG, a novel diffusion-based method with a spatial graph encoder and GFM alignment to improve structural fidelity in spatial gene expression prediction.

Findings

FLAG outperforms traditional models in structural fidelity metrics.

FLAG achieves competitive accuracy in PCC and MSE.

The code is publicly available at https://github.com/darkflash03/FLAG.

Abstract

Predicting spatial gene expression from routine H\&E enables large-scale molecular profiling, yet current models treat this as isolated pointwise tasks, thereby overlooking essential biological structures like gene coordination and spatial distribution. To preserve these relationships, we introduce \textbf{FLAG}, a diffusion-based framework that redefines this task as structured distribution modeling. At the same time, we identify the critical \textbf{Gene Dimension Curse}, where joint modeling gene expression and their spatial interactions fail in high-dimensional spaces, and FLAG solves this challenge by integrating a spatial graph encoder for topological consistency and utilizing Gene Foundation Model (GFM) alignment for gene-gene fidelity in the generation process. To rigorously assess model performance, we propose a set of novel structural evaluation metrics, including Gene Structural Correlation (\textbf{GSC}) and Spatial Structural Correlation (\textbf{SSC}). Our experiments demonstrate that FLAG is highly competitive in traditional accuracy (PCC/MSE) while achieving significantly enhanced structural fidelity in capturing both gene-gene and gene-spatial relationships. The code is available at https://github.com/darkflash03/FLAG.