For more information on how to use BINARY, please visit the official documentation.
Follow these instructions to install BINARY, PySODB, and SOView in your Conda environment.
unzip BINARY.zip
cd BINARY/conda create -n binary python=3.8
conda activate binaryReplace <torch_version> and <cuda_version> with the desired version.
pip install torch==<torch_version>+<cuda_version> -f https://download.pytorch.org/whl/<cuda_version>/torch_stable.htmlExample:
pip install torch==1.13.0+cu117 -f https://download.pytorch.org/whl/cu117/torch_stable.htmlVisit the PyTorch Geometric Installation page(https://pytorch-geometric.readthedocs.io/en/latest/notes/installation.html) and then execute the copied command.
Example:
pip install pyg_lib torch_scatter torch_sparse torch_cluster torch_spline_conv torch_geometric -f https://data.pyg.org/whl/torch-1.13.0+cu117.htmlpip install -r requirements.txtconda install -c r rpy2Then, set the R environment variables. Replace <user_name> and <environment_name> with appropriate values:
export R_HOME=/home/<user_name>/anaconda3/envs/<environment_name>/lib/R
export R_LIBS_USER=/home/<user_name>/anaconda3/envs/<environment_name>/lib/R/libraryWhen configuring the installation paths for R_HOME and R_LIBS_USER, the standard Linux and Conda environment paths (such as .conda) may not be applicable. In such cases, users need to locate the R path and library path within the Conda virtual environment's Python packages and replace them accordingly.
Now, install the mclust library using Python:
python -c "import rpy2.robjects.packages as r; utils = r.importr('utils'); package_name = 'mclust'; utils.install_packages(package_name)"Keep the binary conda environment active and execute:
git clone https://github.com/TencentAILabHealthcare/pysodb.git
cd pysodb/
python setup.py installgit clone https://github.com/yuanzhiyuan/SOView.git
cd SOView/
pip install .