patpy

Contents

patpy#

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

overview

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

Installation

New to patpy? Check out the installation guide.

Installation
Tutorials

Follow tutorials for a quickstart and examples of patpy applications.

Tutorials
API reference

The API reference contains a detailed description of the patpy API.

API
Discussion

Need help? Found a bug? Interested in contributing to the code? Open an issue on GitHub!

https://github.com/lueckenlab/patpy/issues

Citation#

For now, patpy can be cited as a repository:

@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 0.9.2}
}

If you use it for benchmarking sample representation methods, check out our paper at LMRL workshop at ICLR:

@inproceedings{
    shitov2025benchmarking,
    title={Benchmarking Sample Representations from Single-Cell Data: Metrics for Biologically Meaningful Embeddings},
    author={Vladimir Shitov and Mohammad Moghareh Dehkordi and Malte D Luecken},
    booktitle={Learning Meaningful Representations of Life (LMRL) Workshop at ICLR 2025},
    year={2025},
    url={https://openreview.net/forum?id=IoRv5afWtb}
}
Contents