Enhancing Super-Resolution Spatial Transcriptomics Data by Transfer Learning

High-definition spatial transcriptomics (ST) technologies such as Visium HD enable subcellular tissue characterization but remain constrained by their limited accessibility due to high costs and technical complexity. Existing super-resolution methods predominantly rely on an image-guided paradigm, premised on the assumption that gene expression strictly mirrors histological morphology. However, this assumption breaks down for genes with complex spatial distributions lacking distinct visual correlates, often leading to biological artifacts. To address this, we introduce SpotZoomer, a framework that formulates resolution enhancement as a knowledge transfer problem via generative domain adaptation. It leverages public high-definition ST data as a "teacher" to learn intrinsic spatial expression priors, which are then transferred to coarse spot data to reconstruct high-fidelity gene profiles that capture molecular details beyond the reach of morphological guidance alone. Extensive benchmarking across 19 datasets demonstrates the substantial value of the reference-based paradigm implemented by SpotZoomer over the reference-free image-only paradigm, achieving improved reconstruction accuracy and biological fidelity while complementing rather than displacing reference-free methods in settings where high-resolution priors are unavailable. SpotZoomer thus provides a scalable, data-driven strategy for upgrading standard ST resources to subcellular resolution.