Skip to content

Latest commit

 

History

History
65 lines (51 loc) · 2.79 KB

README.md

File metadata and controls

65 lines (51 loc) · 2.79 KB
Raw

Generating 3D Molecules for Target Protein Binding

This is the official implementation of the GraphBP method proposed in the following paper.

Meng Liu, Youzhi Luo, Kanji Uchino, Koji Maruhashi, and Shuiwang Ji. "Generating 3D Molecules for Target Protein Binding". [ICML 2022 Long Presentation]

Requirements

We include key dependencies below. The versions we used are in the parentheses. Our detailed environmental setup is available in environment.yml.

  • PyTorch (1.9.0)
  • PyTorch Geometric (1.7.2)
  • rdkit-pypi (2021.9.3)
  • biopython (1.79)
  • openbabel (3.3.1)

Preparing Data

  • Download and extract the CrossDocked2020 dataset:
wget https://bits.csb.pitt.edu/files/crossdock2020/v1.1/CrossDocked2020_v1.1.tgz -P data/crossdock2020/
tar -C data/crossdock2020/ -xzf data/crossdock2020/CrossDocked2020_v1.1.tgz
wget https://bits.csb.pitt.edu/files/it2_tt_0_lowrmsd_mols_train0_fixed.types -P data/crossdock2020/
wget https://bits.csb.pitt.edu/files/it2_tt_0_lowrmsd_mols_test0_fixed.types -P data/crossdock2020/

Note: (1) The unzipping process could take a lot of time. Unzipping on SSD is much faster!!! (2) Several samples in the training set cannot be processed by our code. Hence, we recommend replacing the it2_tt_0_lowrmsd_mols_train0_fixed.types file with a new one, where these samples are deleted. The new one is available here.

  • Split data files:
python scripts/split_sdf.py data/crossdock2020/it2_tt_0_lowrmsd_mols_train0_fixed.types data/crossdock2020
python scripts/split_sdf.py data/crossdock2020/it2_tt_0_lowrmsd_mols_test0_fixed.types data/crossdock2020

Run

  • Train GraphBP from scratch:
CUDA_VISIBLE_DEVICES=${you_gpu_id} python main.py

Note: GraphBP can be trained on a 48GB GPU with batchsize=16. Our trained model is available here.

  • Generate atoms in the 3D space with the trained model:
CUDA_VISIBLE_DEVICES=${you_gpu_id} python main_gen.py
  • Postprocess and then save the generated molecules:
CUDA_VISIBLE_DEVICES=${you_gpu_id} python main_eval.py

Citation

@inproceedings{liu2022graphbp,
  title={Generating 3D Molecules for Target Protein Binding},
  author={Meng Liu and Youzhi Luo and Kanji Uchino and Koji Maruhashi and Shuiwang Ji},
  booktitle={International Conference on Machine Learning},
  year={2022}
}

Acknowledgments

This work was supported in part by National Science Foundation grants IIS-2006861 and IIS-1908220.