Sovereign 8s.is mirror of standardgalactic/celcomen
  • Jupyter Notebook 99.4%
  • Python 0.6%
Find a file
Repository files (latest commit first)
Filename Latest commit message Latest commit date
Hesam Asadollahzadeh c5cf6f3af1
Update README.md
2026-02-25 21:18:45 +11:00
celcomen fix typo 2025-03-20 20:24:39 +00:00
docs fix typo 2025-03-20 20:24:39 +00:00
images image 2024-09-02 17:39:37 +01:00
analysis.spatial_KO.xenium_human_glioblastoma_gpu.ipynb demo for gene KO counterfactuals 2025-01-09 17:55:15 +00:00
LICENSE Create LICENSE 2025-10-29 11:16:30 +00:00
pyproject.toml fix distance and n_neigh based edge_index 2025-02-04 15:13:37 +00:00
README.md Update README.md 2026-02-25 21:18:45 +11:00
readthedocs.yaml sphinx quick start and change theme in conf.py 2025-01-09 18:50:12 +00:00

Cell Communication Energy (celcomen)

GitHub stars GitHub forks Documentation Status Python 3.9+ PyPI - Downloads

GitHub

Causal generative model designed to disentangle intercellular and intracellular gene regulation with theoretical identifiability guarantees. Celcomen can generate counterfactual spatial transcriptomic samples by simulating the effect of local perturbations, such as gene activations/inhibitations or cell insertions/deletions.

You can find out more by reading our ICLR publication or manuscript.

Installation

Conda Environment

We recommend using Anaconda/Miniconda to create a conda environment for using celcomen. You can create a python environment using the following command:

conda create -n celcomen_env python=3.9

Then, you can activate the environment using:

conda activate celcomen_env

Install celcomen

Then install

pip install git+https://github.com/stathismegas/celcomen

Causal Disentanglement and Spatial Counterfactuals

To learn intracellular and extra-cellular gene regulation and then use it to simulate inflammation conuterfactuals in specific locaitons of the tissue, follow the tutorial analysis.spatial_KO.xenium_human_glioblastoma_gpu.ipynb.

As explained in the tutorial, the adata object should have count data, without any prior normalization or log-transformation.

More details about the documentation can be found on Read the Docs.

To reproduce our results from our paper and manuscript refer to our reproducibility repo.