conda create -n naepro python=3.8 -y
conda activate naepro
conda install pytorch=1.10.2 cudatoolkit=11.3 -c pytorch -y
bash setup.sh We provide the checkpoints used in the paper in Google Drive
Please download the checkpoints and put them in the models folder.
If you want to train your own model, please follow the training guidance below
Taking myoglobin as an example, we can train the model via the following scripts:bash train.shbash design.shThere are five items in the output directory:
- protein.txt refers to the designed protein sequence
- src.seq.txt refers to the ground truth sequences
- pdb.txt refers to the target PDB ID and the corresponding chains
- pred_pdbs refers to the directory of designed pdbs
- tgt_pdbs refers to the directory of target pdbs
