User#
Import scvi-tools as:
import scvi
Model#
Automatic identification of ZI genes [Clivio et al., 2019]. |
|
Conditional version of single-cell Variational Inference, used for multi-resolution deconvolution of spatial transcriptomics data [Lopez et al., 2021]. |
|
Multi-resolution deconvolution of Spatial Transcriptomics data (DestVI) [Lopez et al., 2021]. |
|
Linearly-decoded VAE [Svensson et al., 2020]. |
|
Peak Variational Inference [Ashuach et al., 2022]. |
|
Single-cell annotation using variational inference [Xu et al., 2021]. |
|
single-cell Variational Inference [Lopez et al., 2018]. |
|
total Variational Inference [Gayoso et al., 2021]. |
|
Integration of multi-modal and single-modality data [Ashuach et al., 2021]. |
|
Amortized Latent Dirichlet Allocation [Blei et al., 2003]. |
|
EXPERIMENTAL single-cell Variational Inference [Lopez et al., 2018], but with a Jax backend. |
External models#
Reimplementation of CellAssign for reference-based annotation [Zhang et al., 2019]. |
|
Joint VAE for imputing missing genes in spatial data [Lopez et al., 2019]. |
|
Reimplementation of Stereoscope [Andersson et al., 2020] for deconvolution of spatial transcriptomics from single-cell transcriptomics. |
|
Reimplementation of Stereoscope [Andersson et al., 2020] for deconvolution of spatial transcriptomics from single-cell transcriptomics. |
|
Doublet detection in scRNA-seq [Bernstein et al., 2020]. |
|
Ambient RNA removal in scRNA-seq data [Sheng et al., 2022]. |
|
Reimplementation of Tangram [Biancalani et al., 2021] for mapping single-cell RNA-seq data to spatial data. |
Data loading#
scvi-tools
relies entirely on the AnnData format. For convenience, we have included data loaders from the AnnData API. Scanpy also has utilities to load data that are outputted by 10x’s Cell Ranger software.
Read .h5ad-formatted hdf5 file. |
|
Read .csv file. |
|
Read .loom-formatted hdf5 file. |
|
Read .txt, .tab, .data (text) file. |
|
Read scATAC-seq data outputted by 10x Genomics software. |
|
Read Multiome (scRNA + scATAC) data outputted by 10x Genomics software. |
Basic preprocessing#
For general single-cell preprocessing, we defer to our friends at Scanpy, and specifically their preprocessing module (scanpy.pp
).
All scvi-tools
models require raw UMI count data. The count data can be safely stored in an AnnData layer as one of the first steps of a Scanpy single-cell workflow:
adata.layers["counts"] = adata.X.copy()
Here we maintain a few package specific utilities for feature selection, etc.
Rank and select genes based on the enrichment of zero counts. |
|
Organize anndata object loaded from 10x for scvi models. |
|
Concatenate multiome and single-modality input anndata objects. |
Utilities#
Here we maintain miscellaneous general methods.
Util to run |
Configuration#
An instance of the ScviConfig
is available as scvi.settings
and allows configuring scvi-tools.
Config manager for scvi-tools. |