User guide#

scvi-tools is composed of models that can perform one or many analysis tasks. In the user guide, we provide an overview of each model with emphasis on the math behind the model, how it connects to the code, and how the code connects to analysis.

Overview of tasks

scRNA-seq analysis#

Model	Reference	Tasks
scVI	[Lopez et al., 2018]	Dimensionality reduction, removal of unwanted variation, integration across replicates, donors, and technologies, differential expression, imputation, normalization of other cell- and sample-level confounding factors
scANVI	[Xu et al., 2021]	scVI tasks with cell type transfer from reference, seed labeling
LDVAE	[Svensson et al., 2020]	scVI tasks with linear decoder
AUTOZI	[Clivio et al., 2019]	for assessing gene-specific levels of zero-inflation in scRNA-seq data
CellAssign	[Zhang et al., 2019]	Marker-based automated annotation
Solo	[Bernstein et al., 2020]	Doublet detection
scAR	[Sheng et al., 2022]	Ambient RNA removal

ATAC-seq analysis#

Model	Reference	Tasks
PeakVI	[Ashuach et al., 2022]	Dimensionality reduction, removal of unwanted variation, integration across replicates, donors, and technologies, differential expression, imputation, normalization of other cell- and sample-level confounding factors
ScBasset	[Yuan and Kelley, 2022]	Dimensionality reduction, removal of unwanted variation, integration across replicates, donors, and technologies, imputation

Multimodal analysis#

CITE-seq#

Model	Reference	Tasks
totalVI	[Gayoso et al., 2021]	Dimensionality reduction, removal of unwanted variation, integration across replicates, donors, and technologies, differential expression, protein imputation, imputation, normalization of other cell- and sample-level confounding factors

Multiome#

Model	Reference	Tasks
MultiVI	[Ashuach et al., 2021]	Integration of paired/unpaired multiome data, missing modality imputation, normalization of other cell- and sample-level confounding factors

Spatial transcriptomics analysis#

Model	Reference	Tasks
DestVI	[Lopez et al., 2021]	Multi-resolution deconvolution, cell-type-specific gene expression imputation, comparative analysis
Stereoscope	[Andersson et al., 2020]	Deconvolution
gimVI	[Lopez et al., 2019]	Imputation of missing spatial genes
Tangram	[Biancalani et al., 2021]	Deconvolution, single cell spatial mapping

General purpose analysis#

Model	Reference	Tasks
Amortized LDA	[Blei et al., 2003]	Topic modeling

Background#