From features to slice: parameter-cloud modeling of spatial transcriptomics for simulation and 3D interpolatory augmentation.

ABSTRACT: Computational simulation and data augmentation of spatial transcriptomics (ST) are essential for quantitative benchmarking, reproducibility, and methodological innovation. Yet current models often lack flexibility in controlling spatial and transcriptional heterogeneity, fail to capture higher-order gene dependencies, and rarely extend to three-dimensional or alignment-aware contexts. Here we present FEAST, a computational infrastructure that models ST data within a parameter cloud - a latent manifold encoding gene-level mean, variance, and sparsity. By sampling and perturbing this manifold, FEAST generates high-fidelity synthetic slices with tunable spatial and transcriptional variation, enabling systematic evaluation of clustering, deconvolution, and spatial alignment algorithms. Beyond

SUBMITTER: Chen Y 

PROVIDER: S-EPMC12710759 | biostudies-literature | 2025 Dec

REPOSITORIES: biostudies-literature