{"id":29194688,"url":"https://github.com/psi-cmd/synprepy","last_synced_at":"2025-07-02T04:31:27.172Z","repository":{"id":302012484,"uuid":"1008984768","full_name":"psi-cmd/synprepy","owner":"psi-cmd","description":"Single step retrosynthesis prediction","archived":false,"fork":false,"pushed_at":"2025-06-30T04:32:38.000Z","size":81,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-06-30T05:28:21.918Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Jupyter Notebook","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/psi-cmd.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,"zenodo":null}},"created_at":"2025-06-26T11:52:46.000Z","updated_at":"2025-06-30T04:32:41.000Z","dependencies_parsed_at":"2025-06-30T05:38:38.216Z","dependency_job_id":null,"html_url":"https://github.com/psi-cmd/synprepy","commit_stats":null,"previous_names":["psi-cmd/synprepy"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/psi-cmd/synprepy","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/psi-cmd%2Fsynprepy","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/psi-cmd%2Fsynprepy/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/psi-cmd%2Fsynprepy/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/psi-cmd%2Fsynprepy/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/psi-cmd","download_url":"https://codeload.github.com/psi-cmd/synprepy/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/psi-cmd%2Fsynprepy/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":263074275,"owners_count":23409731,"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":"2025-07-02T04:30:47.717Z","updated_at":"2025-07-02T04:31:27.157Z","avatar_url":"https://github.com/psi-cmd.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"\r\n# 化学反应逆向预测\r\n\r\n## Python 版本\r\n\r\npython3.6\r\n\r\n## 安装依赖\r\n* RDKit\r\n```bash\r\n# 安装rdkit\r\nconda install -c conda-forge rdkit\r\n# 安装pytorch\r\n请按照官网安装: https://pytorch.org/\r\n# 安装pyg\r\n请按照官网安装: https://pytorch-geometric.readthedocs.io/en/latest/notes/installation.html\r\n# 安装其他依赖\r\ncd synprepy # 进入项目文件夹\r\npip install -r requirements.txt\r\n\r\n```\r\n\r\n## 准备数据\r\n\r\n1. 准备具有如下反应数据的tsv文件\r\n\r\n| rid | rxn_smi |\r\n| --- | ------- |\r\n| 0 | [OH:2][N:3]1[N:4]=[N:5][C:6]2=[C:7]1[CH:8]=[CH:9][CH:10]=[CH:11]2\u003e\u003e[OH:2][N:3]1[N:4]=[N:5][C:6]2=[C:7]1[CH:8]=[CH:9][CH:10]=[CH:11]2 |\r\n| 1 | [O:13]1[CH2:14][CH2:15][CH2:16][CH2:17]1\u003e\u003e[O:13]([CH2:14][C@@H:15]1[O:13][C@H:17]2[C@@H:15]([CH2:14][CH2:16]1)[CH2:16]2)[CH3:17] |\r\n\r\n\r\n## 填写配置文件（config.json）\r\n\r\n```json\r\n{\r\n    \"root\": \"存储反应数据和反应模板数据的文件夹路径\",\r\n    \"rxn_data_tsv_file_name\": \"反应数据文件名（该文件必须处于上个设置的root文件夹内）\",\r\n    \"rid_with_rxn_template_tsv_file_name\": \"保持默认即可\",\r\n    \"rxn_centralized_template_tsv_file_name\": \"保持默认即可\",\r\n    \"rxn_extended_template_tsv_file_name\": \"保持默认即可\",\r\n    \"rid_with_tid_tsv_file_name\": \"保持默认即可\",\r\n    \"rxn_centralized_template_selector_config\": {\r\n        \"root\": \"存储中心反应模板选择器的相关文件的文件夹\",\r\n        \"train_rids_file_name\": \"保持默认即可\",\r\n        \"test_rids_file_name\": \"保持默认即可\",\r\n        \"train_temp_dir_name\": \"保持默认即可\",\r\n        \"test_temp_dir_name\": \"保持默认即可\",\r\n        \"min_num_covered_rxns_by_rxn_centralized_template\": \"过滤模板时要求模板的最少覆盖反应数\",\r\n        \"filter_tids_file_name\": \"保持默认即可\",\r\n        \"device\": \"cpu或者cuda\",\r\n        \"batch_size\": 1000,\r\n        \"epoch_num\": 200,\r\n        \"lr_start\": 0.0005,\r\n        \"lr_end\": 1e-7\r\n    },\r\n\r\n  \"min_num_covered_rxns_by_rxn_extended_template\": 50\r\n}\r\n```\r\n\r\n## 单步反应预测\r\n\r\n1. 抽取反应模板：\r\n\r\n运行 rxn_template_prepare.py\r\n\r\n2. 训练单步反应模板选择器：\r\n\r\n运行 rxn_template_selector/rct_train_test.py\r\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpsi-cmd%2Fsynprepy","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fpsi-cmd%2Fsynprepy","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpsi-cmd%2Fsynprepy/lists"}