Prophet is a transformer-based regression model that predicts cellular responses by decomposing experiments into cell state, treatment, and functional readout, leveraging extensive screening datasets and scalability to significantly reduce the number of required experiments and identify effective treatments.

git clone https://github.com/theislab/prophet.git
cd prophet
pip install -e .

Model checkpoints and input embeddings can be downloaded here and here. Examples for how to query the results of various experiments can be found at tutorial.ipynb.

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. If you have used our work in your research, please cite our preprint.