Dependency-aware deep generative models for multitasking analysis of spatial omics data

doi:10.1038/s41592-024-02257-y

Dependency-aware deep generative models for multitasking analysis of spatial omics data

2024-05-23

2

PRE

AI

DOI：10.1038/s41592-024-02257-y

Original

Original request for help

Save

Abstract

En 中文

Spatially resolved transcriptomics (SRT) technologies have significantly advanced biomedical research, but their data analysis remains challenging due to the discrete nature of the data and the high levels of noise, compounded by complex spatial dependencies. Here, we propose spaVAE, a dependency-aware, deep generative spatial variational autoencoder model that probabilistically characterizes count data while capturing spatial correlations. spaVAE introduces a hybrid embedding combining a Gaussian process prior with a Gaussian prior to explicitly capture spatial correlations among spots. It then optimizes the parameters of deep neural networks to approximate the distributions underlying the SRT data. With the approximated distributions, spaVAE can contribute to several analytical tasks that are essential for SRT data analysis, including dimensionality reduction, visualization, clustering, batch integration, denoising, differential expression, spatial interpolation, resolution enhancement and identification of spatially variable genes. Moreover, we have extended spaVAE to spaPeakVAE and spaMultiVAE to characterize spatial ATAC-seq (assay for transposase-accessible chromatin using sequencing) data and spatial multi-omics data, respectively. Using a dependency-aware deep generative framework, spaVAE efficiently models spatially resolved transcriptomics data and advances diverse analysis tasks. Following similar strategies, spaPeakVAE and spaMultiVAE enable spatial ATAC-seq data and spatial multi-omics data modeling and analysis, respectively.

Keywords:

CELL

EXPRESSION

Dependency-aware deep generative models for multitasking analysis of spatial omics data

Abstract

Journal

Organization