Multiscale confidence quantification for virtual spatial transcriptomics with UTOPIA

Abstract Virtual spatial transcriptomics (ST) methods predict gene expression or cell types from histology images, extending molecular readouts beyond the limited regions or samples directly measured by ST platforms. However, the statistical reliability of these predictions remains unclear. Here, we present UTOPIA, a model-agnostic framework for multiscale confidence quantification in virtual ST. UTOPIA assigns statistically calibrated confidence scores to predictions across spatial resolutions and biological granularities, ranging from single genes to metagenes and from specific cell types to broader cell classes. UTOPIA controls false discovery rates for detecting genes, metagenes, or cell types while accounting for local tissue context. We show that prediction confidence depends critically on both spatial resolution and biological granularity, with reliable inference often emerging only at coarser, biologically meaningful scales. Across multiple ST platforms and in both in-sample and out-of-sample settings, UTOPIA enhances interpretability, prevents false biological conclusions, and enables more trustworthy downstream analyses of virtual ST. Competing Interest Statement M.L. receives research funding from Biogen Inc. unrelated to the current manuscript. M.L. is a co-founder of OmicPath AI LLC. T.H.H. is a co-founder of Kure.ai therapeutics and has received consulting fees from IQVIA; these affiliations and financial compensations are unrelated to the current manuscript. L.W. serves as a member of the Scientific Advisory Board for SELLAS Life Sciences and receives compensation outside the scope of this submitted work. The other authors declare no competing financial interests.