{"id":19603911,"url":"https://github.com/divelab/graphbp","last_synced_at":"2025-04-27T19:32:32.756Z","repository":{"id":39713158,"uuid":"482969628","full_name":"divelab/GraphBP","owner":"divelab","description":"Official implementation of \"Generating 3D Molecules for Target Protein Binding\" [ICML2022 Long Presentation]","archived":false,"fork":false,"pushed_at":"2023-07-20T16:35:44.000Z","size":9257,"stargazers_count":107,"open_issues_count":0,"forks_count":24,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-04-05T02:21:46.867Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/divelab.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2022-04-18T19:22:25.000Z","updated_at":"2025-03-24T16:10:11.000Z","dependencies_parsed_at":"2024-11-11T09:34:16.466Z","dependency_job_id":"fabff871-6611-4e4e-a217-a125ae98f2b6","html_url":"https://github.com/divelab/GraphBP","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/divelab%2FGraphBP","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/divelab%2FGraphBP/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/divelab%2FGraphBP/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/divelab%2FGraphBP/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/divelab","download_url":"https://codeload.github.com/divelab/GraphBP/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":251195923,"owners_count":21550870,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-11-11T09:33:39.174Z","updated_at":"2025-04-27T19:32:27.745Z","avatar_url":"https://github.com/divelab.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Update: Our code has been moved into [AIRS](https://github.com/divelab/AIRS/tree/main/OpenMI/GraphBP). Please refer to AIRS for any future updates. This repo is no longer maintained.\n\n\n# Generating 3D Molecules for Target Protein Binding\nThis is the official implementation of the **GraphBP** method proposed in the following paper.\n\nMeng Liu, Youzhi Luo, Kanji Uchino, Koji Maruhashi, and Shuiwang Ji. \"[Generating 3D Molecules for Target Protein Binding](https://arxiv.org/abs/2204.09410)\". [ICML 2022 **Long Presentation**]\n\n![](https://github.com/divelab/GraphBP/blob/main/assets/GraphBP.png)\n\n\n## Requirements\nWe include key dependencies below. The versions we used are in the parentheses. Our detailed environmental setup is available in [environment.yml](https://github.com/divelab/GraphBP/blob/main/GraphBP/environment.yml).\n* PyTorch (1.9.0)\n* PyTorch Geometric (1.7.2)\n* rdkit-pypi (2021.9.3)\n* biopython (1.79)\n* openbabel (3.3.1)\n\n\n## Preparing Data\n* Download and extract the CrossDocked2020 dataset:\n```linux\nwget https://bits.csb.pitt.edu/files/crossdock2020/v1.1/CrossDocked2020_v1.1.tgz -P data/crossdock2020/\ntar -C data/crossdock2020/ -xzf data/crossdock2020/CrossDocked2020_v1.1.tgz\nwget https://bits.csb.pitt.edu/files/it2_tt_0_lowrmsd_mols_train0_fixed.types -P data/crossdock2020/\nwget https://bits.csb.pitt.edu/files/it2_tt_0_lowrmsd_mols_test0_fixed.types -P data/crossdock2020/\n```\n**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` \nfile with a new one, where these samples are deleted. The new one is available [here](https://github.com/divelab/GraphBP/blob/main/GraphBP/data/crossdock2020/it2_tt_0_lowrmsd_mols_train0_fixed.types).\n\n* Split data files:\n```linux\npython scripts/split_sdf.py data/crossdock2020/it2_tt_0_lowrmsd_mols_train0_fixed.types data/crossdock2020\npython scripts/split_sdf.py data/crossdock2020/it2_tt_0_lowrmsd_mols_test0_fixed.types data/crossdock2020\n```\n\n## Run\n* Train GraphBP from scratch:\n```linux\nCUDA_VISIBLE_DEVICES=${you_gpu_id} python main.py\n```\n**Note**: GraphBP can be trained on a `48GB GPU` with `batchsize=16`. Our trained model is available [here](https://github.com/divelab/GraphBP/blob/main/GraphBP/trained_model/model_33.pth).\n\n* Generate atoms in the 3D space with the trained model:\n```linux\nCUDA_VISIBLE_DEVICES=${you_gpu_id} python main_gen.py\n```\n\n* Postprocess and then save the generated molecules:\n```linux\nCUDA_VISIBLE_DEVICES=${you_gpu_id} python main_eval.py\n```\n\n\n\n## Reference\n```\n@inproceedings{liu2022graphbp,\n  title={Generating 3D Molecules for Target Protein Binding},\n  author={Meng Liu and Youzhi Luo and Kanji Uchino and Koji Maruhashi and Shuiwang Ji},\n  booktitle={International Conference on Machine Learning},\n  year={2022}\n}\n```\n\n## Acknowledgments\nThis work was supported in part by National Science Foundation grants IIS-2006861 and IIS-1908220.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdivelab%2Fgraphbp","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdivelab%2Fgraphbp","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdivelab%2Fgraphbp/lists"}