scHierarchy: Hierarchical logistic regression model for marker gene selection using hierachical cell annotations

Installation

Linux installation

conda create -y -n schierarchy-env python=3.9
conda activate schierarchy-env
pip install git+https://github.com/dissatisfaction-ai/scHierarchy.git

Mac installation

conda create -y -n schierarchy-env python=3.8
conda activate schierarchy-env
pip install git+https://github.com/pyro-ppl/pyro.git@dev
conda install -y -c anaconda hdf5 pytables netcdf4
pip install git+https://github.com/dissatisfaction-ai/scHierarchy.git

Usage example notebook

https://github.com/dissatisfaction-ai/scHierarchy/blob/main/docs/notebooks/marker_selection_example.ipynb

This will be updated using a publicly available dataset & Colab - however, it is challenging to find published dataset with several annotation levels yet sufficiently small to be used on Colab.