DestVI identifies continuums of cell types in spatial transcriptomics data

Abstract

The function of mammalian cells is largely influenced by their tissue microenvironment. Advances in spatial transcriptomics open the way for studying these important determinants of cellular function by enabling a transcriptome-wide evaluation of gene expression in situ. A critical limitation of the current technologies, however, is that their resolution is limited to niches (spots) of sizes well beyond that of a single cell, thus providing measurements for cell aggregates which may mask critical interactions between neighboring cells of different types. While joint analysis with single-cell RNA-sequencing (scRNA-seq) can be leveraged to alleviate this problem, current analyses are limited to a discrete view of cell type proportion inside every spot. This limitation becomes critical in the common case where, even within a cell type, there is a continuum of cell states that cannot be clearly demarcated but reflects important differences in the way cells function and interact with their surroundings. To address this, we developed Deconvolution of Spatial Transcriptomics profiles using Variational Inference (DestVI), a probabilistic method for multi-resolution analysis for spatial transcriptomics that explicitly models continuous variation within cell types. Using simulations, we demonstrate that DestVI is capable of providing higher resolution compared to the existing methods and that it can estimate gene expression by every cell type inside every spot. We then introduce an automated pipeline that uses DestVI for analysis of single tissue slices and comparison between tissues. We apply this pipeline to study the immune crosstalk within lymph nodes to infection and explore the spatial organization of a mouse tumor model. In both cases, we demonstrate that DestVI can provide a high resolution and accurate spatial characterization of the cellular organization of these tissues, and that it is capable of identifying important cell-type-specific changes in gene expression -between different tissue regions or between conditions. DestVI is available as an open-source software package in the scvi-tools codebase (https://scvi-tools.org). 2.

BayesTME: A unified statistical framework for spatial transcriptomics

“…We benchmarked BayesTME against other methods: BayesSpace 11 , cell2location 16 , DestVI 15 , CARD 29 , RCTD 30 , STdeconvolve 14 , stLearn 12 , and Giotto 13 on simulated data based on real single-cell RNA sequencing (scRNA) data. We randomly sampled K * cell types from a previously-clustered scRNA dataset 16 ; we conducted experiments for K * from 3 to 8.…”

“…Spatial clustering methods 11,12,13 fuse spots together to effectively capture regions of constant cell type proportion with varying cell counts. Spot deconvolution methods 14,15,16 separate the aggregate signals into independent component signals with each attributable to a different cell type. Spatial differential expression methods 17,18 assess the aggregate spot signal to detect regions where individual genes or gene sets follow a spatial pattern.…”

Emerging artificial intelligence applications in Spatial Transcriptomics analysis

“…In addition, since cell type distribution is correlated with their spatial locations, computing cell-type proportions in each spot utilizing both spatial and genomic information is of great interest. Many deep learning methods have been developed for such purposes, either in combination with high-resolution H&E images [59] or by integrating scRNA-Seq data [60] , [61] . The methods utilize diverse methodologies, including neural networks ( Fig.…”

“…Furthermore, Tangram could visualize the chromatin accessibility information in space by analyzing SHARE-seq [63] data containing matched RNA and chromatin accessibility information from single cells. External benchmark study [64] showed Tangram had decent deconvolution performance across diverse real and synthetic datasets and top performance in predicting spatial distribution of gene expression compared to Seurat [65] , Cell2location [66] , SpatialDWLS [67] , RCTD [68] , Stereoscope [69] , DestVI [60] , STRIDE [70] , SPOTLight [71] , and DSTG [72] .…”

“…DestVI [60] is a Bayesian deep generative model for deconvolution and continuous estimation of cell states of ST data. DestVI consists of two latent variable models (LVMs): one for the reference scRNA-Seq data (scLVM), and the other for the ST data (stLVM).…”