patpy – sample-level analysis framework for single-cell data

patpy is a toolbox for single-cell data analysis on sample level.

It provides:

• 👨‍⚕️ Interface to sample representation methods (otherwise known as patient representation)
• 📈 Analysis functions to get the most of your data
• 📊 Metrics for sample representation evaluation

⚠️ Warning: Development in Progress ⚠️

This repository is currently under active development Features and functionalities may change unexpectedly, and some aspects of the project are not yet complete.

Please proceed with caution and feel free to contribute, but be aware that:

• The codebase is still evolving.
• Documentation may be incomplete.
• Some features may be unstable or subject to change.

If you have any questions or face bugs, feel free to open an issue.

Thank you for your patience and interest. Stay tuned for updates!

Getting started

Please refer to the documentation. In particular, the

• API documentation.

Installation

You need to have Python 3.9 or newer installed on your system. If you don't have Python installed, we recommend installing Mambaforge.

There are several alternative options to install patpy:

1. Install the latest release of patpy from PyPI:

pip install patpy

2. Install the latest development version:

pip install git+https://github.com/lueckenlab/patpy.git@main

To install specific dependencies for some sample representation tools, use the following command:

pip install patpy[pilot]

All the available dependency groups: diffusionemd, mrvi, pilot, scpoli, wassersteintsne.

Some sample representation tools depend on packages not published on PyPI. To use them, install the extra and the upstream package from git:

# pascient
pip install patpy[pascient]
pip install git+https://github.com/genentech/pascient.git@main

# pulsar
pip install git+https://github.com/snap-stanford/PULSAR.git@main

Release notes

See the changelog.

Contact

For questions and help requests, you can reach out in the scverse discourse. If you found a bug, please use the issue tracker.

Building docs

1. Install sphinx

You may need add path to sphinx-doc to the $PATH

2. Install other doc section dependencies from the pyproject.toml

3. Build the documentation pages:

cd docs
make html

4. Open docs/_build/html/index.html

Citation

Preprint is coming soon. So far, you can refer to this repository as following:

APA

Shitov, V. (2024). patpy – sample-level analysis framework for single-cell data (Version 0.10.0) [Computer software]. https://github.com/lueckenlab/patpy/

BibTeX

@misc{shitov_patpy_2024,
  author = {Shitov, Vladimir},
  title = {patpy – sample-level analysis framework for single-cell data},
  year = {2024},
  url = {https://github.com/lueckenlab/patpy/},
  note = {Version 0.15.2}
}