Installation¶

scVelo requires Python 3.6 or later. We recommend to use Miniconda.

PyPI¶

Install scVelo from PyPI using:

pip install -U scvelo

-U is short for --upgrade. If you get a Permission denied error, use pip install -U scvelo --user instead.

Development Version¶

To work with the latest development version, install from GitHub using:

pip install git+https://github.com/theislab/scvelo@develop

or:

git clone https://github.com/theislab/scvelo && cd scvelo
git checkout --track origin/develop
pip install -e .

-e is short for --editable and links the package to the original cloned location such that pulled changes are also reflected in the environment.

To contribute to scVelo, cd into the cloned directory and install the latest packages required for development together with the pre-commit hooks:

pip install -e ".[dev]"
pre-commit install

Dependencies¶

anndata - annotated data object.
scanpy - toolkit for single-cell analysis.
numpy, scipy, pandas, scikit-learn, matplotlib.

Parts of scVelo (directed PAGA and Louvain modularity) require (optional):

pip install python-igraph louvain

Using fast neighbor search via hnswlib further requires (optional):

pip install pybind11 hnswlib

Jupyter Notebook¶

To run the tutorials in a notebook locally, please install:

conda install notebook

and run jupyter notebook in the terminal. If you get the error Not a directory: 'xdg-settings', use jupyter notebook --no-browser instead and open the url manually (or use this bugfix).

If you run into issues, do not hesitate to approach us or raise a GitHub issue.