conda env create -f environment.yml
conda activate cbgbench

conda install pytorch==2.0.1 torchvision==0.15.2 torchaudio==2.0.2 pytorch-cuda=11.8 -c pytorch -c nvidia
conda install pyg pytorch-scatter pytorch-cluster -c pyg

# install rdkit, efgs, obabel, etc.
pip install --use-pep517 EFGs
pip install biopython
pip install lxml
conda install rdkit openbabel tensorboard tqdm pyyaml easydict python-lmdb -c conda-forge

# install plip
mkdir tools
cd tools
git clone https://github.com/pharmai/plip.git
cd plip
python setup.py install
alias plip='python plip/plip/plipcmd.py'
cd ..

### Note that if there is an error in setup.py, it can be ignored as long as openbabel is installed.

# install docking tools
conda install -c conda-forge numpy swig boost-cpp sphinx sphinx_rtd_theme
python -m pip install git+https://github.com/Valdes-Tresanco-MS/AutoDockTools_py3
pip install meeko==0.1.dev3 scipy pdb2pqr vina

# If you are unable to install vina, you can try: conda install vina
# If you encounter the following error:
# ImportError: libtiff.so.5: cannot open shared object file: No such file or directory
# Please try the following steps to resolve it:
pip uninstall pillow
pip install pillow

- CGBBench
    - data
        - pl
            - crossdocked_name2id.pt
            - crossdocked_v1.1_rmsd1.0_pocket10_processed_fullatom.lmdb
            - crossdocked_v1.1_rmsd1.0_pocket10_processed_linker.lmdb
        - pl_arfg
            - crossdocked_name2id_arfuncgroup.pt
            - crossdocked_v1.1_rmsd1.0_pocket10_processed_arfuncgroup.lmdb
        - pl_decomp
            - crossdocked_name2id_frag.pt
            - crossdocked_name2id_linker.pt
            - crossdocked_name2id_scaffold.pt
            - crossdocked_name2id_sidechain.pt
            - crossdocked_v1.1_rmsd1.0_pocket10_processed_frag.lmdb
            - crossdocked_v1.1_rmsd1.0_pocket10_processed_linker.lmdb
            - crossdocked_v1.1_rmsd1.0_pocket10_processed_scaffold.lmdb
            - crossdocked_v1.1_rmsd1.0_pocket10_processed_sidechain.lmdb
        - pl_fg
            - crossdocked_name2id_funcgroup.pt
            - crossdocked_v1.1_rmsd1.0_pocket10_processed_funcgroup.lmdb

mkdir raw_data
tar -xzvf crossdocked_v1.1_rmsd1.0.tar.gz ./raw_data

python ./scripts/extract_pockets.py --source raw_data/crossdocked_v1.1_rmsd1.0 --dest raw_data/crossdocked_v1.1_rmsd1.0_pocket10

- CGBBench
    - data
        - case_study
            - processed
                - case_study_processed_fullatom.lmdb
                - case_study_processed_funcgroup.lmdb
                - case_study_name2id.pt
                ...

python train.py --config ./configs/{task}/train/{method}.yml --logdir ./logs/{task}/{method}

python train.py --config ./configs/denovo/train/d3fg_fg.yml --logdir ./logs/denovo/d3fg_fg
python train.py --config ./configs/denovo/train/d3fg_linker.yml --logdir ./logs/denovo/d3fg_linker

# TODO
- CBGBench
    - logs
        - denovo
            - d3fg_fg
                - pretrain
                    - checkpoints
                        - 951000.pt
            - d3fg_linker
                - pretrain
                    - checkpoints
                        - 4840000.pt
            - diffbp
                - pretrain
                    - checkpoints
                        - 4848000.pt
            ...
        - frag
            - diffbp
                - pretrain
                    - checkpoints
                        - 476000.pt
            ...
        ...

bash generate.sh --method {method} --task {task} --tag {tag} --checkpoint {ckpt_number}

bash generate.sh --method targetdiff --task denovo --tag selftrain --checkpoint

bash generate.sh --method targetdiff --task denovo --tag selftrain --checkpoint 100000

bash generate.sh --method d3fg_fg --task denovo --tag {tag} --checkpoint  # generate the functional groups
bash generate.sh --method d3fg_linker --task denovo --tag {tag} --checkpoint # generate the linkers

cd evaluate_scripts
bash evaluate.sh --method {method} --task {task} --tag {tag}

bash evaluate.sh --method targetdiff --task denovo --tag selftrain
bash evaluate.sh --method targetdiff --task frag --tag selftrain
bash evaluate.sh --method targetdiff --task linker --tag selftrain
bash evaluate.sh --method targetdiff --task scaffold --tag selftrain
bash evaluate.sh --method targetdiff --task sidechain --tag selftrain

cd evaluate_scripts
bash bash evaluate.sh --method {method} --task {task} --tag pretrained

@misc{lin2024cbgbench,
      title={CBGBench: Fill in the Blank of Protein-Molecule Complex Binding Graph},
      author={Haitao Lin and Guojiang Zhao and Odin Zhang and Yufei Huang and Lirong Wu and Zicheng Liu and Siyuan Li and Cheng Tan and Zhifeng Gao and Stan Z. Li},
      year={2024},
      eprint={2406.10840},
      archivePrefix={arXiv},
}

@misc{lin2024diffbpgenerativediffusion3d,
      title={DiffBP: Generative Diffusion of 3D Molecules for Target Protein Binding}, 
      author={Haitao Lin and Yufei Huang and Odin Zhang and Siqi Ma and Meng Liu and Xuanjing Li and Lirong Wu and Jishui Wang and Tingjun Hou and Stan Z. Li},
      year={2024},
      eprint={2211.11214},
      archivePrefix={arXiv},
      primaryClass={q-bio.BM},
      url={https://arxiv.org/abs/2211.11214}, 
}
@inproceedings{
    lin2023functionalgroupbased,
    title={Functional-Group-Based Diffusion for Pocket-Specific Molecule Generation and Elaboration},
    author={Haitao Lin and Yufei Huang and Odin Zhang and Yunfan Liu and Lirong Wu and Siyuan Li and Zhiyuan Chen and Stan Z. Li},
    booktitle={Thirty-seventh Conference on Neural Information Processing Systems},
    year={2023},
    url={https://openreview.net/forum?id=lRG11M91dx}
}