The easiest way to get familiar with scvi-tools is to follow along with our tutorials.
Many are also designed to work seamlessly in Google Colab, a free cloud computing platform. These tutorials have a Colab badge in their introduction. In general, these tutorials are designed to work with the latest installable version of scvi-tools.
To download the tutorials:
Click the Colab within the tutorial (if available).
Download it with the option in the file menu.
Rapidly learn the basics to run any of the scvi-tools models.
How do I get my data prepared for scvi-tools?
Straight to tutorial…
This is a walkthrough of a totalVI-based analysis pipeline, from dimension reduction to differential expression.
To the tutorial
Here we describe how to use scVI and scANVI for integrating data from Tabula Muris.
It’s scVI, but with PCA-like interpretability.
totalVI can be used to integrate datasets from CITE-seq (RNA + protein) and datasets with only RNA (scRNA-seq). Integration enables imputation of missing proteins in the cells measured with scRNA-seq.
scvi-tools can be used interfaced directly from R. Learn the basics here.
gimVI can be used to integrate spatial and sequencing data. Integration enables imputation of missing genes in the cells measured with a spatial technology.
AutoZI can be used to determine which genes are zero-inflated. This can be extended to finding cell-type specific zero-inflation.
This tutorial was contributed by Eduardo Beltrame.