Transcriptome measurements of individual cells reflect unexplored biological diversity, but are also affected by technical noise and bias. This raises the need to model and account for the resulting uncertainty in any downstream analysis. Here, we introduce Single-cell Variational Inference (scVI), a scalable framework for probabilistic representation and analysis of gene expression in single cells. scVI uses stochastic optimization and deep neural networks to aggregate information across similar cells and genes and approximate the distributions that underlie the observed expression values, while accounting for batch effects and limited sensitivity. We utilize scVI for a range of fundamental analysis tasks – including batch correction, visualization, clustering and differential expression – and demonstrate its accuracy and scalability in comparison to the state-of-the-art in each task. scVI is publicly available and can be readily used as a principled and inclusive solution for analyzing single-cell transcriptomes.

The paired measurement of RNA and surface proteins in single cells with CITE-seq is a promising approach to connect transcriptional variation with cell phenotypes and functions. However, combining these paired views into a unified representation of cell state is made challenging by the unique technical characteristics of each measurement. Here we present Total Variational Inference (totalVI; https://scvi-tools.org ), a framework for end-to-end joint analysis of CITE-seq data that probabilistically represents the data as a composite of biological and technical factors including protein background and batch effects. To evaluate totalVI’s performance, we profiled immune cells from murine spleen and lymph nodes with CITE-seq, measuring over 100 surface proteins. We demonstrate that totalVI provides a cohesive solution for common analysis tasks like dimensionality reduction, the integration of datasets with different measured proteins, estimation of correlations between molecules, and differential expression testing.

As the number of single-cell transcriptomics datasets grows, the natural next step is to integrate the accumulating data to achieve a common ontology of cell types and states. However, it is not straightforward to compare gene expression levels across datasets and to automatically assign cell type labels in a new dataset based on existing annotations. In this manuscript, we demonstrate that our previously developed method, scVI, provides an effective and fully probabilistic approach for joint representation and analysis of scRNA-seq data, while accounting for uncertainty caused by biological and measurement noise. We also introduce single-cell ANnotation using Variational Inference (scANVI), a semi-supervised variant of scVI designed to leverage existing cell state annotations. We demonstrate that scVI and scANVI compare favorably to state-of-the-art methods for data integration and cell state annotation in terms of accuracy, scalability, and adaptability to challenging settings. In contrast to existing methods, scVI and scANVI integrate multiple datasets with a single generative model that can be directly used for downstream tasks, such as differential expression. Both methods are easily accessible through scvi-tools.

To the Editor -Methods for analyzing single-cell data 1-4 perform a core set of computational tasks. These tasks include dimensionality reduction, cell clustering, cell-state annotation, removal of unwanted variation, analysis of differential expression, identification of spatial patterns of gene expression, and joint analysis of multi-modal omics data. Many of these methods rely on likelihood-based models to represent variation in the data; we refer to these as 'probabilistic

Transcriptome profiles of individual cells reflect true and often unexplored biological diversity, but are also affected by noise of biological and technical nature. This raises the need to explicitly model the resulting uncertainty and take it into account in any downstream analysis, such as dimensionality reduction, clustering, and differential expression. Here, we introduce Single-cell Variational Inference (scVI), a scalable framework for probabilistic representation and analysis of gene expression in single cells. Our model uses variational inference, stochastic optimization and deep neural networks to approximate the parameters that govern the distribution of expression values of each gene in every cell, using a non-linear mapping between the observations and a low-dimensional latent space.By doing so, scVI pools information between similar cells or genes while taking nuisance factors of variation such as batch effects and limited sensitivity into account. To evaluate scVI, we conducted a comprehensive comparative analysis to existing methods for distributional modeling and dimensionality reduction, all of which rely on generalized linear models. We first show that scVI scales to over one million cells, whereas competing algorithms can process at most tens of thousands of cells. Next, we show that scVI fits unseen data more closely and can impute missing data more accurately, both indicative of a better generalization capacity. We then utilize scVI to conduct a set of fundamental analysis tasks -including batch correction, visualization, clustering and differential expressionand demonstrate its accuracy in comparison to the state-of-the-art tools in each task. scVI is publicly available, and can be readily used as a principled and inclusive solution for multiple tasks of single-cell RNA sequencing data analysis.

Probabilistic models have provided the underpinnings for state-of-the-art performance in many single-cell omics data analysis tasks, including dimensionality reduction, clustering, differential expression, annotation, removal of unwanted variation, and integration across modalities. Many of the models being deployed are amenable to scalable stochastic inference techniques, and accordingly they are able to process single-cell datasets of realistic and growing sizes. However, the community-wide adoption of probabilistic approaches is hindered by a fractured software ecosystem resulting in an array of packages with distinct, and often complex interfaces. To address this issue, we developed scvi-tools (https://scvi-tools.org), a Python package that implements a variety of leading probabilistic methods. These methods, which cover many fundamental analysis tasks, are accessible through a standardized, easy-to-use interface with direct links to Scanpy, Seurat, and Bioconductor workflows. By standardizing the implementations, we were able to develop and reuse novel functionalities across different models, such as support for complex study designs through nonlinear removal of unwanted variation due to multiple covariates and reference-query integration via scArches. The extensible software building blocks that underlie scvi-tools also enable a developer environment in which new probabilistic models for single cell omics can be efficiently developed, benchmarked, and deployed. We demonstrate this through a code-efficient reimplementation of Stereoscope for deconvolution of spatial transcriptomics profiles. By catering to both the end user and developer audiences, we expect scvi-tools to become an essential software dependency and serve to formulate a community standard for probabilistic modeling of single cell omics.

As single-cell transcriptomics becomes a mainstream technology, the natural next step is to integrate the accumulating data in order to achieve a common ontology of cell types and states. However, owing to various nuisance factors of variation, it is not straightforward how to compare gene expression levels across data sets and how to automatically assign cell type labels in a new data set based on existing annotations. In this manuscript, we demonstrate that our previously developed method, scVI, provides an effective and fully probabilistic approach for joint representation and analysis of cohorts of single-cell RNA-seq data sets, while accounting for uncertainty caused by biological and measurement noise. We also introduce single-cell ANnotation using Variational Inference (scANVI), a semi-supervised variant of scVI designed to leverage any available cell state annotations -for instance when only one data set in a cohort is annotated, or when only a few cells in a single data set can be labeled using marker genes. We demonstrate that scVI and scANVI compare favorably to the existing methods for data integration and cell state annotation in terms of accuracy, scalability, and adaptability to challenging settings such as a hierarchical structure of cell state labels. We further show that different from existing methods, scVI and scANVI represent the integrated datasets with a single generative model that can be directly used for any probabilistic decision making task, using differential expression as our case study. scVI and scANVI are available as open source software and can be readily used to facilitate cell state annotation and help ensure consistency and reproducibility across studies.

Detecting differentially expressed genes is important for characterizing subpopulations of cells. In scRNA-seq data, however, nuisance variation due to technical factors like sequencing depth and RNA capture efficiency obscures the underlying biological signal. Deep generative models have been extensively applied to scRNA-seq data, with a special focus on embedding cells into a low-dimensional latent space and correcting for batch effects. However, little attention has been given to the problem of utilizing the uncertainty from the deep generative model for differential expression. Furthermore, the existing approaches do not allow controlling for the effect size or the false discovery rate. Here, we present lvm-DE, a generic Bayesian approach for performing differential expression from using a fitted deep generative model, while controlling the false discovery rate. We apply the lvm-DE framework to scVI and scSphere, two deep generative models. The resulting approaches outperform the state-of-the-art methods at estimating the log fold change in gene expression levels, as well as detecting differentially expressed genes between subpopulations of cells.