{"id":13481245,"url":"https://github.com/Luckick/EAGCN","last_synced_at":"2025-03-27T11:32:04.787Z","repository":{"id":101471191,"uuid":"121056751","full_name":"Luckick/EAGCN","owner":"Luckick","description":"Multi-View Spectral Graph Convolution with Consistent Edge Attention for Molecular Modeling","archived":false,"fork":false,"pushed_at":"2021-10-01T02:38:08.000Z","size":2366,"stargazers_count":202,"open_issues_count":0,"forks_count":44,"subscribers_count":8,"default_branch":"master","last_synced_at":"2024-10-30T14:43:45.559Z","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":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Luckick.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}},"created_at":"2018-02-10T21:40:33.000Z","updated_at":"2024-10-19T12:48:15.000Z","dependencies_parsed_at":null,"dependency_job_id":"30c46f91-6add-4ca9-ba7d-a98c5988a88e","html_url":"https://github.com/Luckick/EAGCN","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/Luckick%2FEAGCN","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Luckick%2FEAGCN/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Luckick%2FEAGCN/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Luckick%2FEAGCN/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Luckick","download_url":"https://codeload.github.com/Luckick/EAGCN/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245836296,"owners_count":20680349,"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":"2024-07-31T17:00:50.051Z","updated_at":"2025-03-27T11:32:04.120Z","avatar_url":"https://github.com/Luckick.png","language":"Python","funding_links":[],"categories":["Deep Learning","Implement:"],"sub_categories":[],"readme":"\n\n# EAGCN\n\nThis is a PyTorch implementation of paper \"[Multi-View Spectral Graph Convolution with Consistent Edge Attention for Molecular Modeling](https://www.sciencedirect.com/science/article/abs/pii/S092523122100271X)\" published at Neurocomputing. \n\u003c!--\nWe also released a previous [arXiv version](https://arxiv.org/abs/1802.04944v1).\n--\u003e\n\n## Installation\n\nInstall pytorch and torchvision. \n\n## Train EAGCN model\n\n### Dataset\n\nFour benchmark datasets ([Tox21, HIV, Freesolv and Lipophilicity](http://moleculenet.ai/datasets-1)) are utilized in this study to evaluate the predictive performance of built graph convolutional networks.  They are all downloaded from the [MoleculeNet](http://moleculenet.ai/) that hold various benchmark datasets for molecular machine learning.\n\nDatasets are also provided in folder \"Data\".\n\n### Train the model\nOpen the folder \"eagcn_pytorch\".\n\nWhen you train the model, you can use:\n\n    python train.py\n\nsupport files:    \nEAGCN_dataset.py: pre-processing data      \nneural_fp.py: from smiles to graph     \nlayers.py: define layers     \nmodels.py: define models     \nutils.py: other tools     \n\n\n### Visualization Tools\ncheck_model.py: check parameters (edge attention for each layer).     \nmol_to_vec.py: visualize the molecule in 2D space, compare with other molecules which have similiar SMILEs.      \nplot.py: show model training process.      \ntsnes.py: tsne visualization about atom subtype, also provide umap option.     \nkmeans_atomrep.py: kmeans clustering for atom subtype.     \nplot_molecule.py: plot single molecule.    \n\n## Citation\n\nIf you use this repository, e.g., the code and the datasets, in your research, please cite the following paper:\n```\n@article{shang2021multi,\n  title={Multi-view spectral graph convolution with consistent edge attention for molecular modeling},\n  author={Shang, Chao and Liu, Qinqing and Tong, Qianqian and Sun, Jiangwen and Song, Minghu and Bi, Jinbo},\n  journal={Neurocomputing},\n  volume={445},\n  pages={12--25},\n  year={2021},\n  publisher={Elsevier}\n}\n```\n\n## Acknowledgments\nCode is inspired by [GCN](https://github.com/tkipf/gcn) and [conv_qsar_fast](https://github.com/connorcoley/conv_qsar_fast)\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FLuckick%2FEAGCN","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FLuckick%2FEAGCN","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FLuckick%2FEAGCN/lists"}