-
Create environment with pytorch installed. Use
cpuonly
version if you don't have an nvidia gpu locally:conda create -p env python=3.8.10 -y conda activate ./env
pip install pre-commit
pip install -r requirements.txt
pip install -r requirements-dev.txt
pip install torch_scatter torch_sparse torch_cluster torch_spline_conv -f https://data.pyg.org/whl/torch-2.1.0+cpu.html
pre-commit install
- Ensure docker is installed on your system
- Modify the required parameters in the .env file according to your preferences.
- Navigate to SUPREME_refactoring directory
- Run the following command to build the docker image with a specified tag name (e.g., "supreme")
sudo docker build . -t supreme
- Run docker container
docker run supreme
sudo docker container prune -f && sudo docker image prune -f && sudo docker system prune -a
Organize your multi-omics data by placing it in the data/sample_data/raw directory. Modify the prepare_data function within the pre_process_data.py module, specifically change lines 60 to 92. Then, execute main.py.