MAEF-GO

Multi-Stage Attention-Based Extraction and Fusion of Protein Sequence and Structural Features for Protein Function Prediction.

Clone the Repository

git clone https://github.com/nebstudio/MAEF-GO
cd MAEF-GO

Set Up the Environment

conda env create -f environment.yml
conda activate MAEF-GO
conda install pytorch==1.7.0 cudatoolkit=10.2 -c pytorch

Install PyTorch Geometric and Dependencies

wget https://data.pyg.org/whl/torch-1.7.0%2Bcu102/torch_cluster-1.5.9-cp37-cp37m-linux_x86_64.whl
wget https://data.pyg.org/whl/torch-1.7.0%2Bcu102/torch_scatter-2.0.7-cp37-cp37m-linux_x86_64.whl
wget https://data.pyg.org/whl/torch-1.7.0%2Bcu102/torch_sparse-0.6.9-cp37-cp37m-linux_x86_64.whl
wget https://data.pyg.org/whl/torch-1.7.0%2Bcu102/torch_spline_conv-1.2.1-cp37-cp37m-linux_x86_64.whl
pip install *.whl
pip install torch_geometric==1.6.3

Download and Prepare Data

cd data

Data set can be downloaded from here.

tar -zxvf processed.tar.gz

Run the testing script

python test.py --device 0 
               --task bp 
               --batch_size 64