Phoenix, a latent flow matching generative model, accurately predicts spatially resolved single-cell gene expression from routine histology with zero-shot generalization across unseen cohorts, tissues, and species, enabling population-scale spatial transcriptomics that reveals three conserved tumor ecosystems across 9,544 human cancers with distinct clinical outcomes and identifies transferable spatial biomarkers that predict treatment response across multiple cancer types and therapeutic regimens.

Spatial transcriptomics links gene expression to tissue architecture, providing a mechanistic view of cellular organization. Yet existing datasets cover few donors and miss the complexity of human disease. Experimental costs remain prohibitive, and large-scale profiling is impractically slow for population-level studies. Accurate computational methods are urgently needed. Predicting gene expression from standard histology, however, remains an open problem, as current approaches transfer poorly to unseen cohorts and diseases. Here, we present Phoenix, a latent flow matching generative model that infers pan-cancer spatially resolved single-cell gene expression with high accuracy. Phoenix analyzes treatment response in silico: Applied to 763 head and neck cancer patients, it identified three new spatial biomarkers that we validated across two cancers (breast cancer, n = 84; ovarian cancer, n = 157) and treatment regimens (platinum, trastuzumab). Phoenix generalizes beyond carcinomas: In a large sarcoma cohort (802 tissue microarray cores), it accurately predicted cell-type-specific signatures in held-out samples and captured chemotherapy-induced immune remodeling. Phoenix also extends across species: In a mouse model, it accurately predicted the expression of pancreatic cancer lineage markers and the mutant mKras^G12D allele in silico. Together, Phoenix establishes virtual spatial transcriptomics from routine histology as a scalable framework for studying tissue organization, therapeutic response, and disease mechanisms.