scvi-tools (single-cell variational inference tools) is a package for end-to-end analysis of single-cell omics data. The package is primarily developed and maintained by the Yosef Lab at UC Berkeley and is composed of several deep generative models for omics data analysis:
scVI for analysis of single-cell RNA-seq data [Lopez18]
scANVI for cell annotation of scRNA-seq data using semi-labeled examples [Xu19]
totalVI for analysis of CITE-seq data [GayosoSteier20]
gimVI for imputation of missing genes in spatial transcriptomics from scRNA-seq data [Lopez19]
AutoZI for assessing gene-specific levels of zero-inflation in scRNA-seq data [Clivio19]
LDVAE for an interpretable linear factor model version of scVI [Svensson20]
These models are able to simultaneously perform many downstream tasks such as learning low-dimensional cell representations, harmonizing datasets from different experiments, and identifying differential expressed features [Boyeau19]. By levaraging advances in stochastic optimization, these models scale to millions of cells.
If you find a model useful for your research, please consider citing the corresponding publication.
scvi is now scvi-tools.
If you’d like to view documentation for scvi, please change the documentation version using the menu at the bottom right (versions <= 0.6.8).
New to scvi-tools? Check out the installation guide.
To the installation guide
The tutorials provide in-depth information on running scvi-tools models.
To the user guide
The API reference contains a detailed description of
the scvi-tools API.
To the API reference
Want to improve scvi-tools? The contributing guidelines
will guide you through the process.
To the development guide