biolord - biological representation disentanglement#

A deep generative framework for disentangling known and unknown attributes in single-cell data.

We assume partial supervision over known attributes (categorical or ordered) along with single-cell measurements. Given the partial supervision biolord finds a decomposed latent space, and provides a generative model to obtain single-cell measurements for different cell states.

For more details read our pubication in Nature Biotechnology.

The biolord pipeline

Getting started#

Please refer to the documentation.

Installation#

There are several alternative options to install biolord:

Install the latest release of biolord from PyPI:
```
pip install biolord
```

Install the latest development version:

pip install git+https://github.com/nitzanlab/biolord.git@main

Release notes#

See the changelog.

Contact#

Feel free to contact us by mail. If you found a bug, please use the issue tracker.

Citation#

@article{piran2024disentanglement,
  title={Disentanglement of single-cell data with biolord},
  author={Piran, Zoe and Cohen, Niv and Hoshen, Yedid and Nitzan, Mor},
  journal={Nature Biotechnology},
  pages={1--6},
  year={2024},
  publisher={Nature Publishing Group US New York}
}

biolord - biological representation disentanglement

Contents