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

Document Type

Article

Publication Date

8-1-2024

Abstract

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.

Identifier

85193988508 (Scopus)

Publication Title

Nature Methods

External Full Text Location

https://doi.org/10.1038/s41592-024-02257-y

e-ISSN

15487105

ISSN

15487091

PubMed ID

38783067

First Page

1501

Last Page

1513

Issue

8

Volume

21

Grant

BK20230781

Fund Ref

Natural Science Foundation of Jiangsu Province

This document is currently not available here.

Share

COinS