{"id":13958635,"url":"https://github.com/zetayue/MXMNet","last_synced_at":"2025-07-21T00:31:32.670Z","repository":{"id":111968180,"uuid":"314647827","full_name":"zetayue/MXMNet","owner":"zetayue","description":"Source code for \"Molecular Mechanics-Driven Graph Neural Network with Multiplex Graph for Molecular Structures\"","archived":false,"fork":false,"pushed_at":"2023-11-15T02:53:59.000Z","size":50538,"stargazers_count":69,"open_issues_count":0,"forks_count":16,"subscribers_count":2,"default_branch":"master","last_synced_at":"2024-11-28T02:34:56.858Z","etag":null,"topics":["computational-biology","deep-learning","drug-discovery","geometric-deep-learning","graph-neural-networks","machine-learning"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/zetayue.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":"2020-11-20T19:15:31.000Z","updated_at":"2024-11-08T14:53:30.000Z","dependencies_parsed_at":"2024-11-28T02:32:29.699Z","dependency_job_id":"d5167c0d-fc78-4cfe-a4f1-811a8cc3c438","html_url":"https://github.com/zetayue/MXMNet","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/zetayue/MXMNet","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zetayue%2FMXMNet","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zetayue%2FMXMNet/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zetayue%2FMXMNet/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zetayue%2FMXMNet/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/zetayue","download_url":"https://codeload.github.com/zetayue/MXMNet/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zetayue%2FMXMNet/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":266221269,"owners_count":23894966,"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":["computational-biology","deep-learning","drug-discovery","geometric-deep-learning","graph-neural-networks","machine-learning"],"created_at":"2024-08-08T13:01:47.084Z","updated_at":"2025-07-21T00:31:27.660Z","avatar_url":"https://github.com/zetayue.png","language":"Python","funding_links":[],"categories":["分子"],"sub_categories":["网络服务_其他"],"readme":"# Molecular Mechanics-Driven Graph Neural Network with Multiplex Graph for Molecular Structures\n\nCode for **MXMNet** proposed in our paper: **[Molecular Mechanics-Driven Graph Neural Network with Multiplex Graph for Molecular Structures](https://arxiv.org/abs/2011.07457)**, which has been accepted by the *Machine Learning for Structural Biology Workshop* ([MLSB 2020](https://www.mlsb.io/)) and the *Machine Learning for Molecules Workshop* ([ML4Molecules 2020](https://ml4molecules.github.io/)) at the *34th Conference on Neural Information Processing Systems* (NeurIPS 2020).\n\n### Important Update about Improved Model (2023/11)\nWe have released the **[code](https://github.com/XieResearchGroup/Physics-aware-Multiplex-GNN)** for **PAMNet** in our *Nature Scientific Reports* paper \"**[A universal framework for accurate and efficient geometric deep learning of molecular systems](https://www.nature.com/articles/s41598-023-46382-8)**\", which is an improved version of MXMNet with **higher accuracy and efficiency**. **We highly recommend anyone interested in MXMNet try our PAMNet**.\n\n## Overall Architecture\n\n\u003cp align=\"center\"\u003e\n\u003cimg src=\"https://github.com/zetayue/MXMNet/blob/master/MXMNet.png?raw=true\"\u003e\n\u003c/p\u003e\n\n## Requirements\nCUDA : 10.1\nPython : 3.7.10\n\nThe other dependencies can be installed with:\n```\npip install -r requirements.txt\n```\n## How to Run\nYou can directly download, preprocess the QM9 dataset and train the model with \n```\npython main.py\n```\nOptional arguments:\n```\n  --gpu             GPU number\n  --seed            random seed\n  --epochs          number of epochs to train\n  --lr              initial learning rate\n  --wd              weight decay value\n  --n_layer         number of hidden layers\n  --dim             size of input hidden units\n  --batch_size      batch size\n  --target          index of target (0~11) for prediction on QM9\n  --cutoff          distance cutoff used in the global layer\n```\nThe default model to be trained is the MXMNet (BS=128, d_g=5) by using '--batch_size=128 --cutoff=5.0'.\n\n## Cite\nIf you find this model and code are useful in your work, please cite our paper:\n```\n@article{zhang2020molecular,\n  title={Molecular mechanics-driven graph neural network with multiplex graph for molecular structures},\n  author={Zhang, Shuo and Liu, Yang and Xie, Lei},\n  journal={arXiv preprint arXiv:2011.07457},\n  year={2020}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzetayue%2FMXMNet","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fzetayue%2FMXMNet","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzetayue%2FMXMNet/lists"}