武汉大学Tian Tian等研究人员开发出用于空间组学数据多任务分析的依赖感知深度生成模型。相关论文于2024年5月23日在线发表在《自然—方法学》杂志上。

研究人员提出了spaVAE，这是一种依赖感知的深度生成空间变异自动编码器模型，它能从概率上描述计数数据，同时捕捉空间相关性。然后，它优化深度神经网络的参数，以近似空间分辨的转录组学（SRT）数据的基础分布。有了近似分布，spaVAE就能完成SRT数据分析中必不可少的几项分析任务，包括降维、可视化、聚类、批量整合、去噪、差异表达、空间插值、分辨率增强和空间可变基因的识别。

此外，研究人员还将spaVAE扩展为spaPeakVAE和spaMultiVAE，以分别表征空间ATAC-seq（利用测序分析转座酶可及性染色质）数据和空间多组学数据。

据了解，SRT技术极大地推动了生物医学研究的发展，但由于数据的离散性和高水平的噪声，再加上复杂的空间依赖性，其数据分析仍然具有挑战性。

附：英文原文

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

Author: Tian, Tian, Zhang, Jie, Lin, Xiang, Wei, Zhi, Hakonarson, Hakon

Issue&Volume: 2024-05-23

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.

DOI: 10.1038/s41592-024-02257-y

Source: https://www.nature.com/articles/s41592-024-02257-y