Learning Identifiable Factorized Causal Representations of Cellular Responses

OpenReview | arXiv | BibTeX

Official code for the NeurIPS 2024 paper Learning Identifiable Factorized Causal Representations of Cellular Responses. This work was performed by Haiyi Mao, Romain Lopez, Kai Liu, Jan-Christian H"{u}tter, David Richmond, Panayiotis (Takis) Benos, Lin Qiu, Please cite us when making use of our code or ideas.

Installation

cd $PROJECT_DIR
conda config --append channels conda-forge
conda create -n fcr-env --file requirements.txt
conda activate fcr-env

Data Availability

sciPlex: https://www.science.org/doi/10.1126/science.aax6234

multiPlex: https://www.nature.com/articles/s41467-020-17440-w

Run

# train
./main.sh &
test_sciPlex.ipynb contains the steps to perform the analysis

BibTex

@inproceedings{
mao2024learning,
title={Learning Identifiable Factorized Causal Representations of Cellular Responses},
author={Haiyi Mao and Romain Lopez and Kai Liu and Jan-Christian Huetter and David Richmond and Panayiotis V. Benos and Lin Qiu},
booktitle={Advances in Neural Information Processing Systems},
year={2024},
note={\url{https://github.com/Genentech/fcr}
}