{"id":13481093,"url":"https://github.com/1128bian/C-SGEN","last_synced_at":"2025-03-27T11:31:48.005Z","repository":{"id":218341193,"uuid":"197864454","full_name":"1128bian/C-SGEN","owner":"1128bian","description":"Molecule Property Prediction based on Spatial Graph Embedding","archived":false,"fork":false,"pushed_at":"2019-07-18T05:48:44.000Z","size":1262,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2024-10-30T14:43:28.235Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":false,"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/1128bian.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":"2019-07-20T01:36:51.000Z","updated_at":"2022-03-02T12:35:16.000Z","dependencies_parsed_at":null,"dependency_job_id":"10740376-e317-400d-bf22-87ad137504f1","html_url":"https://github.com/1128bian/C-SGEN","commit_stats":null,"previous_names":["1128bian/c-sgen"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/1128bian%2FC-SGEN","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/1128bian%2FC-SGEN/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/1128bian%2FC-SGEN/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/1128bian%2FC-SGEN/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/1128bian","download_url":"https://codeload.github.com/1128bian/C-SGEN/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245836223,"owners_count":20680335,"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":"2024-07-31T17:00:48.628Z","updated_at":"2025-03-27T11:31:48.000Z","avatar_url":"https://github.com/1128bian.png","language":"Python","funding_links":[],"categories":["Deep Learning"],"sub_categories":[],"readme":"# C-SGEN\nA PyTorch implementation of \"Molecule Property Prediction based on Spatial Graph Embedding\"\n\u003cp align=\"center\"\u003e\n  \u003cimg width=\"800\" height=250 src=\"Model-C-SGEN.jpg\"\u003e\n\u003c/p\u003e\n\u003cp align=\"justify\"\u003e\n\n\n### Requirements\nThe codebase is implemented in Python 3.6.7. package versions used for development are just below.\n```\nTheano            1.0.3\nnumpy             1.16.4\nscipy             1.3.0\ntorch             1.1.0\ntimeit            1.1.0\nsklearn           0.0\ndeepchem          2.1.1\ntorch-scatter     1.2.0\ntorch-sparse      0.4.0\ntorch-cluster     1.4.2\ntorch-geometric   1.2.1\ntorch-spline-conv 1.1.0\ntorchvision       0.3.0\nrdkit             2019.03.3.0\nChemoPy           1.0.0\npickle            0.7.5\n```\n\n\n### Datasets\nFeature.npy, Normed_adj.npy, fingerprint_stand.npy and Interactions.npy are molecular features, adjacency matrices, molecular fingerprints and corresponding target values in the data, respectively.Input for C-SGEN Model\n\nfull_feature, edge and Interactions.npy are molecular features, adjacency matrices and corresponding target values of pytorch_geometric specific data format in the data, respectively.\n\n\n#### Model Hyper-Parameters\n```\n  --epochs                      INT     Number of epochs.                              Default is 33.\n  --batch-size                  INT     Number fo molecules per batch.                 Default is 8.\n  --C-SGEL-layers               INT     Number of C-SGELs.                             Default is 2.\n  --ch_num                      INT     Number of neurons in Graph embedding layer.    Default is 16.\n  --k                           INT     Number of filters in conv1d.                   Default is 4.\n  --lr_decay                    FLOAT   Weight decay / 10 epochs.                      Defatuls is 0.5.\n  --learning-rate               FLOAT   Adam learning rate.                            Default is 5e-4.\n```\n\n\n### Examples\n\nThe following commands learn a model and save the predictions. Training C-SGEN model on the default dataset,the data is ready to be saved in a folder. You can execute the above model directly.\n```\npython C-SGEN_trian.py\n```\n\nTraining a PyG model directly.\n```\npython pyg_trian.py\n```\n\nLoad data from DeepChem.\n```\npython load_FreeSolv.py\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2F1128bian%2FC-SGEN","html_url":"https://awesome.ecosyste.ms/projects/github.com%2F1128bian%2FC-SGEN","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2F1128bian%2FC-SGEN/lists"}