Deep Generative Models for Single-cell Transcriptomics

Single-cell Variational Inference (scVI) is a set of tools for probabilistic analysis of single-cell RNA-sequencing data. We propose to solve quantitative biological questions with tailored and scalable Bayesian machinery. Examples of biological questions include cell-type discovery, data integration, transfer of annotations and differential expression analysis. Examples of statistical tools include deep generative models, stochastic variational inference, Bayesian decision theory and domain adaptation.
All the models in our codebase may fit millions of transcriptomic measurements in a few hours. In addition to the original publication, we recommend the following ressources to get more familiar with scVI:
- our codebase and documentation which includes user-friendly notebooks
- the podcast recorded on the bioinformatics chat
- the YosefLab blog usually includes discussions about special topics
- the News & View in Nature Methods
- our post on the Berkeley AI Research blog
Posts
Bayesian Nets: from white-boarding to laser cutting
Immortilizing Graphical Models with Laser Cutters
Publications
An empirical Bayes method for differential expression analysis of single cells with deep generative models
Detecting differentially expressed genes is important for characterizing subpopulations of cells. In scRNA-seq data, however, nuisance …
DestVI identifies continuums of cell types in spatial transcriptomics data
The function of mammalian cells is largely influenced by their tissue microenvironment. Advances in spatial transcriptomics open the …
A Python library for probabilistic analysis of single-cell omics data
Probabilistic models have provided the underpinnings for state-of-the-art performance in many single-cell omics data analysis tasks, …
Reconstructing unobserved cellular states from paired single-cell lineage tracing and transcriptomics data
Novel experimental assays now simultaneously measure lineage relationships and transcriptomic states from single cells, thanks to …
Joint probabilistic modeling of single-cell multi-omic data with totalVI
The paired measurement of RNA and surface protein abundance in single cells with CITE-seq is a promising approach to connect …
Probabilistic harmonization and annotation of single-cell transcriptomics data with deep generative models
As single-cell transcriptomics becomes a mainstream technology, the natural next step is to integrate the accumulating data in order to …
A joint model of RNA expression and surface protein abundance in single cells
Cellular indexing of transcriptomes and epitopes by sequencing (CITE-seq) combines unbiased single-cell transcriptome measurements with …
A joint model of unpaired data from scRNA-seq and spatial transcriptomics for imputing missing gene expression measurements
Spatial studies of transcriptome provide biologists with gene expression maps of heterogeneous and complex tissues. However, most …
Deep generative models for detecting differential expression in single cells
Detecting differentially expressed genes is important for characterizing subpopulations of cells. However, in scRNA-seq data, nuisance …
Detecting zero-inflated genes in single-cell transcriptomics data
In single-cell RNA sequencing data, biological processes or technical factors may induce an overabundance of zero measurements. …
Deep generative modeling for single-cell transcriptomics
Single-cell transcriptome measurements can reveal unexplored biological diversity, but they suffer from technical noise and bias that …
A deep generative model for gene expression profiles from single-cell RNA sequencing with application to differential expression
We propose a probabilistic model for interpreting gene expression levels that are observed through single-cell RNA sequencing. In the …
A deep generative model for gene expression profiles from single-cell RNA sequencing
We propose a probabilistic model for interpreting gene expression levels that are observed through single-cell RNA sequencing. In the …