Reconstructing Spatial Transcriptomics at the Single-cell Resolution with BayesDeep.

ABSTRACT: Spatially resolved transcriptomics (SRT) techniques have revolutionized the characterization of molecular profiles while preserving spatial and morphological context. However, most next-generation sequencing-based SRT techniques are limited to measuring gene expression in a confined array of spots, capturing only a fraction of the spatial domain. Typically, these spots encompass gene expression from a few to hundreds of cells, underscoring a critical need for more detailed, single-cell resolution SRT data to enhance our understanding of biological functions within the tissue context. Addressing this challenge, we introduce BayesDeep, a novel Bayesian hierarchical model that leverages cellular morphological data from histology images, commonly paired with SRT data, to reconstruct SRT data a

SUBMITTER: Jiang X 

PROVIDER: S-EPMC10723442 | biostudies-literature | 2023 Dec

REPOSITORIES: biostudies-literature