Search papers, labs, and topics across Lattice.
To overcome the noise and biological disconnect of fitting tens of thousands of genes independently, the authors design SpaFactor, a lightweight framework that maps multiscale histological visual context into low-rank latent gene programs before decoding into coordinated expression profiles. By substituting computationally heavy graph networks with structured morphology-program-gene factorization, the approach models biologically co-regulated modules while regularizing against microenvironmental image noise. Across five public benchmark cohorts, SpaFactor establishes state-of-the-art prediction accuracy, with pronounced gains in recovering biologically organized patterns of spatially variable genes.
Complex graph networks are overkill for histology-to-gene inference: factorizing tissue microenvironments into low-rank latent gene programs beats heavy architectures across five cohorts while slashing computational overhead.
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.
