SpaFactor: Lightweight Spatial Context-Aware Gene Program Modeling for Histology-to-Transcriptomics Inference

2026-09-23

AI Summary

This study addresses the high cost of spatial transcriptomics and the limitations of conventional methods that neglect gene synergy and remain susceptible to high-dimensional noise. We propose a lightweight framework based on low-rank morphology–program–gene decomposition. By integrating multiscale tissue context features and mapping them to latent gene programs via a residual MLP, the method jointly decodes coordinated multi-gene expression through shared gene loadings. This enables efficient inference of spatial transcriptomic profiles directly from H&E images without complex graph networks or auxiliary supervision. Evaluated across five public cohorts, the proposed approach achieves state-of-the-art overall performance, substantially improving prediction accuracy for spatially variable genes and enhancing the fidelity of biological pattern recovery.

Abstract

Spatial transcriptomics (ST) profiles gene expression within tissue architecture, but its cost and experimental complexity limit routine use. Predicting spatial expression from routinely available hematoxylin and eosin (HE) images therefore offers a scalable alternative. However, conventional methods often fit high-dimensional gene outputs as independent targets, overlooking the biological coordination among genes while remaining vulnerable to high-dimensional noise and overfitting. Existing attempts to address this limitation often rely on computationally heavy graph networks or complex auxiliary supervision. We therefore introduce SpaFactor, a lightweight and efficient low-rank morphology-program-gene factorization framework. At the input, SpaFactor efficiently fuses the visual representation of the central spot with multiscale local and regional neighborhood context, yielding a histologic representation that captures cellular morphology and microenvironmental heterogeneity. For modeling, a residual MLP stably learns a nonlinear mapping from the tissue microenvironment to low-dimensional latent gene programs. These activities are decoded through shared gene loadings into coordinated multi-gene expression predictions. Across five public cohorts, SpaFactor achieves the best aggregate performance, with particularly clear improvements for spatially variable genes, and more faithfully recovers biologically organized spatial patterns. These results demonstrate that lightweight joint modeling of tissue context and gene programs can improve both predictive accuracy and biological fidelity.

Problem

• spatial transcriptomics
• histology-to-transcriptomics
• gene program modeling
• spatial gene expression prediction
• high-dimensional noise

Innovation

• Spatial Transcriptomics
• Low-Rank Factorization
• Gene Programs
• Histology-to-Transcriptomics
• Lightweight Modeling