scVI

Single-cell Variational Inference

• Free software: MIT license
• Documentation: https://scvi.readthedocs.io.

Quick Start

1. Install Python 3.7. We typically use the Miniconda Python distribution and Linux.
2. Install PyTorch. If you have an Nvidia GPU, be sure to install a version of PyTorch that supports it -- scVI runs much faster with a discrete GPU.

3. Install scVI in one of the following ways:

   1. Through conda conda install scvi -c bioconda -c conda-forge
   2. Through pip pip install scvi
   3. Through pip with packages to run notebooks pip install scvi[notebooks]
   4. Nightly version - clone this repo and run pip install .
   5. For development - clone this repo and run pip install -e .[test,notebooks]

4. If you wish to use multiple GPUs for hyperparameter tuning, install MongoDb.
5. Follow along with our Jupyter notebooks to quickly get familiar with scVI!

   1. Getting started:

      • data loading
      • basic usage (scVI)

   2. Analyzing several datasets:

      • harmonization (scVI)
      • annotation (scANVI)

   3. Advanced topics:

      • interaction with scanpy
      • linear decoder for gene interpretation (LDVAE)
      • imputation of unobserved gene expression (gimVI)
      • automated hyperparameter search
      • joint model for CITE-seq data (totalVI)
      • detection of zero-inflated genes (AutoZI)

References

Romain Lopez, Jeffrey Regier, Michael Cole, Michael I. Jordan, Nir Yosef. "Deep generative modeling for single-cell transcriptomics." Nature Methods, 2018. [pdf]

Chenling Xu∗, Romain Lopez∗, Edouard Mehlman∗, Jeffrey Regier, Michael I. Jordan, Nir Yosef. "Harmonization and Annotation of Single-cell Transcriptomics data with Deep Generative Models." Submitted, 2019. [pdf]

Romain Lopez∗, Achille Nazaret∗, Maxime Langevin*, Jules Samaran*, Jeffrey Regier*, Michael I. Jordan, Nir Yosef. "A joint model of unpaired data from scRNA-seq and spatial transcriptomics for imputing missing gene expression measurements." ICML Workshop on Computational Biology, 2019. [pdf]

Adam Gayoso, Romain Lopez, Zoë Steier, Jeffrey Regier, Aaron Streets, Nir Yosef. "A joint model of RNA expression and surface protein abundance in single cells." Machine Learning in Computational Biology (MLCB), 2019. [pdf]

Oscar Clivio, Romain Lopez, Jeffrey Regier, Adam Gayoso, Michael I. Jordan, Nir Yosef. "Detecting zero-inflated genes in single-cell transcriptomics data." Machine Learning in Computational Biology (MLCB), 2019. [pdf]

Pierre Boyeau, Romain Lopez, Jeffrey Regier, Adam Gayoso, Michael I. Jordan, Nir Yosef. "Deep generative models for detecting differential expression in single cells." Machine Learning in Computational Biology (MLCB), 2019. [pdf]

Valentine Svensson, Lior Pachter. "Interpretable factor models of single-cell RNA-seq via variational autoencoders." bioRxiv, 2019. [pdf]