{"id":21908638,"url":"https://github.com/chao1224/neuralmd","last_synced_at":"2025-04-16T01:53:18.968Z","repository":{"id":265096125,"uuid":"787420723","full_name":"chao1224/NeuralMD","owner":"chao1224","description":"NeuralMD for protein-ligand binding simulation","archived":false,"fork":false,"pushed_at":"2025-01-11T06:34:35.000Z","size":1210,"stargazers_count":11,"open_issues_count":1,"forks_count":1,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-03-29T03:42:37.224Z","etag":null,"topics":["binding","binding-affinity","ligand","md","molecular-dynamics","molecular-dynamics-simulation","protein","protein-ligand-binding"],"latest_commit_sha":null,"homepage":"https://chao1224.github.io/NeuralMD","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/chao1224.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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":"2024-04-16T13:44:19.000Z","updated_at":"2025-01-22T16:21:24.000Z","dependencies_parsed_at":"2024-11-27T16:43:39.545Z","dependency_job_id":"c7fb0736-fdd7-4684-932d-10622a5af781","html_url":"https://github.com/chao1224/NeuralMD","commit_stats":null,"previous_names":["chao1224/neuralmd"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/chao1224%2FNeuralMD","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/chao1224%2FNeuralMD/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/chao1224%2FNeuralMD/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/chao1224%2FNeuralMD/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/chao1224","download_url":"https://codeload.github.com/chao1224/NeuralMD/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":249183065,"owners_count":21226140,"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":["binding","binding-affinity","ligand","md","molecular-dynamics","molecular-dynamics-simulation","protein","protein-ligand-binding"],"created_at":"2024-11-28T17:13:06.522Z","updated_at":"2025-04-16T01:53:18.922Z","avatar_url":"https://github.com/chao1224.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# **NeuralMD:** A Multi-Grained Symmetric Differential Equation Model for Learning Protein-Ligand Binding Dynamics\n\nAuthors: Shengchao Liu*, Weitao Du*, Hannan Xu, Yanjing Li, Zhuoxinran Li, Vignesh Bhethanabotla, Divin Yan, Christian Borgs*, Anima Anandkumar*, Hongyu Guo*, Jennifer Chayes*\n\n[[Project Page](https://chao1224.github.io/NeuralMD)] [[ArXiv](https://arxiv.org/abs/2401.15122)]\n[[Datasets on HuggingFace](https://huggingface.co/datasets/chao1224/NeuralMD/tree/main)] [[Checkpoints on HuggingFace](https://huggingface.co/chao1224/NeuralMD/tree/main)]\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"figure/pipeline.png\" /\u003e \n\u003c/p\u003e\n\n\u003cp align=\"left\"\u003e\n  \u003cimg src=\"figure/final.gif\" width=\"100%\" /\u003e \n\u003c/p\u003e\n\n\n# 1. Environment\n\n## Conda\n\nSetup the anaconda\n ```bash\nwget https://repo.continuum.io/archive/Anaconda3-2019.10-Linux-x86_64.sh\nbash Anaconda3-2019.10-Linux-x86_64.sh -b\nexport PATH=$PWD/anaconda3/bin:$PATH\n ```\n\n## Packages\nStart with some basic packages.\n```bash\nconda create -n Geom3D python=3.9\nconda activate Geom3D\nconda install -y numpy networkx scikit-learn\nconda install -y -c conda-forge rdkit\nconda install -y pytorch==2.2 pytorch-cuda=12.1 -c pytorch -c nvidia\nconda install -y -c pyg -c conda-forge pyg=2.5\nconda install -y -c pyg pytorch-scatter\nconda install -y -c pyg pytorch-sparse\nconda install -y -c pyg pytorch-cluster\n\npip install ogb==1.2.1\n\npip install sympy\n\npip install ase\n\npip install lie_learn # for TFN and SE3-Trans\n\npip install packaging # for SEGNN\npip3 install e3nn # for SEGNN\n\npip install transformers # for smiles\npip install selfies # for selfies\n\npip install atom3d # for Atom3D\npip install cffi # for Atom3D\npip install biopython # for Atom3D\n\npip install cython # for pyximport \n\nconda install -y -c conda-forge py-xgboost-cpu # for XGB\n\npip install pymatgen  # for CIF loading\npip install h5py\n\npip install torch-ema\n\ngit clone git@github.com:chao1224/torchdiffeq.git\ncd torchdiffeq\n\npip install MDAnalysis\n\npip install -e .\n```\n\n# 2. Datasets Preparation\n\nWe provide two ways to generate the datasets for MISATO.\n1. We provide the script under `data/MISATO` to generate two sub-datasets, and you can check the `data/README.md` for more details.\n2. You can download the datasets from zenodo and HuggingFace directly.\n  2.1. You can download the MISATO `MD.hdf5` data from [zenodo link](https://zenodo.org/records/7711953), or use the following CMD:\n  ```\n  wget -O data/MD/h5_files/MD.hdf5 https://zenodo.org/record/7711953/files/MD.hdf5\n  ```\n  2.2. Then you can download the dataset from [HuggingFace link](https://huggingface.co/datasets/chao1224/NeuralMD/tree/main) provided by us.\n\nThe data folder structure looks like the following:\n```\n.\n`-- MISATO_1000\n|   `-- raw\n|   |   `-- train_MD.txt\n|   |   `-- test_MD.txt\n|   |   `-- MD.hdf5\n|   |   `-- val_MD.txt\n`-- MISATO\n|   `-- raw\n|   |   `-- train_MD.txt\n|   |   `-- test_MD.txt\n|   |   `-- MD.hdf5\n|   |   `-- val_MD.txt\n`-- README.md\n`-- MISATO_100\n|   `-- raw\n|   |   `-- train_MD.txt\n|   |   `-- test_MD.txt\n|   |   `-- MD.hdf5\n|   |   `-- val_MD.txt\n```\n\n# 3. Scripts\n\nPlease check `examples` for semi-flexible binding experiments.\n\nWe have two types of tasks\n- `multi_traj`\n- `single_traj`\nand four ML methods\n- `VerletMD`\n- `GNNMD`\n- `DenoisinLD`\n- `NeuralMD`\n  - `--NeuralMD_binding_model=NeuralMD_Binding01` for NeuralMD ODE\n  - `--NeuralMD_binding_model=NeuralMD_Binding02` or `--NeuralMD_binding_model=NeuralMD_Binding04` for NeuralMD SDE\n\n# 4. Checkpoints\n\nWe provide the optimal checkpoints and corresponding hyperparameters at [this HuggingFace link](https://huggingface.co/chao1224/NeuralMD/tree/main).\n\n# Cite Us\n\nFeel free to cite this work if you find it useful to you!\n\n```\n@inproceedings{\n    @article{liu2024NeuralMD,\n    title={A Multi-Grained Symmetric Differential Equation Model for Learning Protein-Ligand Binding Dynamics},\n    author={Liu, Shengchao* and Du, Weitao* and Xu, Hannan and Li, Yanjing and Li, Zhuoxinran and Bhethanabotla, Vignesh and Liang, Yan and Borgs, Christian* and Anandkumar, Anima* and Guo, Hongyu* and Chayes, Jennifer*},\n    journal={arXiv preprint arXiv:2401.15122},\n    year={2024}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fchao1224%2Fneuralmd","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fchao1224%2Fneuralmd","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fchao1224%2Fneuralmd/lists"}