SAGE-FM: A lightweight and interpretable spatial transcriptomics foundation model

TL;DR

SAGE-FM is a lightweight, interpretable graph convolutional network-based model that captures spatial gene expression relationships, outperforming existing methods in clustering, biological heterogeneity, and downstream tasks in spatial transcriptomics.

Contribution

Introduces SAGE-FM, a novel spatial transcriptomics foundation model based on GCNs that is lightweight, interpretable, and effective across multiple biological and computational tasks.

Findings

Achieves 91% correlation for masked gene recovery.

Outperforms MOFA in clustering and heterogeneity preservation.

Enables accurate downstream tasks like tumor subtype prediction.

Abstract

Spatial transcriptomics enables spatial gene expression profiling, motivating computational models that capture spatially conditioned regulatory relationships. We introduce SAGE-FM, a lightweight spatial transcriptomics foundation model based on graph convolutional networks (GCNs) trained with a masked central spot prediction objective. Trained on 416 human Visium samples spanning 15 organs, SAGE-FM learns spatially coherent embeddings that robustly recover masked genes, with 91% of masked genes showing significant correlations (p < 0.05). The embeddings generated by SAGE-FM outperform MOFA and existing spatial transcriptomics methods in unsupervised clustering and preservation of biological heterogeneity. SAGE-FM generalizes to downstream tasks, enabling 81% accuracy in pathologist-defined spot annotation in oropharyngeal squamous cell carcinoma and improving glioblastoma subtype prediction relative to MOFA. In silico perturbation experiments further demonstrate that the model captures directional ligand-receptor and upstream-downstream regulatory effects consistent with ground truth. These results demonstrate that simple, parameter-efficient GCNs can serve as biologically interpretable and spatially aware foundation models for large-scale spatial transcriptomics.