Weakly supervised learning uncovers phenotypic signatures in single-cell data

Getting started

Please refer to the documentation. In particular, the

• API documentation

and the tutorials:

• Classification with MultiMIL
• Regression with MultiMIL

Please also check out our sample prediction pipeline, which contains MultiMIL and several other baselines.

Installation

You need to have Python 3.10 or newer installed on your system. We recommend installing Mambaforge.

To create and activate a new environment:

mamba create --name multimil python=3.10
mamba activate multimil

Next, there are several alternative options to install multimil:

1. Install the latest release of multimil from PyPI:

pip install multimil

2. Or install the latest development version:

pip install git+https://github.com/theislab/multimil.git@main

Release notes

See the changelog.

Contact

If you found a bug, please use the issue tracker.

Citation

Weakly supervised learning uncovers phenotypic signatures in single-cell data

Anastasia Litinetskaya, Soroor Hediyeh-zadeh, Amir Ali Moinfar, Mohammad Lotfollahi, Fabian J. Theis

bioRxiv 2024.07.29.605625; doi: https://doi.org/10.1101/2024.07.29.605625

Reproducibility

Code and notebooks to reproduce the results from the paper are available at theislab/multimil_reproducibility.