{"id":13958627,"url":"https://github.com/binghong-ml/retro_star","last_synced_at":"2025-07-21T00:31:31.764Z","repository":{"id":41274214,"uuid":"275294903","full_name":"binghong-ml/retro_star","owner":"binghong-ml","description":"Retro*: Learning Retrosynthetic Planning with Neural Guided A* Search","archived":false,"fork":false,"pushed_at":"2022-07-09T01:26:08.000Z","size":2980,"stargazers_count":134,"open_issues_count":16,"forks_count":32,"subscribers_count":5,"default_branch":"master","last_synced_at":"2024-11-28T02:34:55.075Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","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/binghong-ml.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}},"created_at":"2020-06-27T03:50:40.000Z","updated_at":"2024-11-26T03:53:07.000Z","dependencies_parsed_at":"2022-07-13T15:59:46.992Z","dependency_job_id":null,"html_url":"https://github.com/binghong-ml/retro_star","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/binghong-ml/retro_star","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/binghong-ml%2Fretro_star","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/binghong-ml%2Fretro_star/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/binghong-ml%2Fretro_star/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/binghong-ml%2Fretro_star/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/binghong-ml","download_url":"https://codeload.github.com/binghong-ml/retro_star/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/binghong-ml%2Fretro_star/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":[],"created_at":"2024-08-08T13:01:46.831Z","updated_at":"2025-07-21T00:31:26.756Z","avatar_url":"https://github.com/binghong-ml.png","language":"Jupyter Notebook","funding_links":[],"categories":["分子"],"sub_categories":["网络服务_其他"],"readme":"# Retrosynthetic Planning with Retro*\n\nRetro*: Learning Retrosynthetic Planning with Neural Guided A* Search\n\n```bibtex\n@inproceedings{chen2020retro,\n  title={Retro*: Learning Retrosynthetic Planning with Neural Guided A* Search},\n  author={Chen, Binghong and Li, Chengtao and Dai, Hanjun and Song, Le},\n  booktitle={The 37th International Conference on Machine Learning (ICML 2020)},\n  year={2020}\n}\n```\n\n#### 1. Setup the environment\n\n##### 1) Download the repository\n    \n    git clone git@github.com:binghong-ml/retro_star.git\n    cd retro_star\n    \n##### 2) Create a conda environment\n    \n    conda env create -f environment.yml\n    conda activate retro_star_env\n\n#### 2. Download the data\n\n##### 1) Download the building block molecules, pretrained models, and (optional) test data \n\nDownload and unzip the files from this [link](https://www.dropbox.com/s/ar9cupb18hv96gj/retro_data.zip?dl=0), \nand put all the folders (```dataset/```, ```one_step_model/``` and ```saved_models/```) under the ```retro_star``` directory.\n\n#### 3. Install Retro* lib\n\nInstall the retrosynthetic planning library with the following commands.\n\n    pip install -e retro_star/packages/mlp_retrosyn\n    pip install -e retro_star/packages/rdchiral\n    pip install -e .\n\n#### 4. Reproduce experiment results\n\nTo plan with Retro*, run the following command,\n\n    cd retro_star\n    python retro_plan.py --use_value_fn\n    \nIgnore the ```--use_value_fn``` option to plan without the learned value function.\n\nYou can also train your own value function via,\n\n    python train.py\n    \n\n#### 5. Example usage\n\nSee ```example.py``` for an example usage.\n\n```python\nfrom retro_star.api import RSPlanner\n\nplanner = RSPlanner(\n    gpu=-1,\n    use_value_fn=True,\n    iterations=100,\n    expansion_topk=50\n)\n\nresult = planner.plan('CCCC[C@@H](C(=O)N1CCC[C@H]1C(=O)O)[C@@H](F)C(=O)OC')\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbinghong-ml%2Fretro_star","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbinghong-ml%2Fretro_star","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbinghong-ml%2Fretro_star/lists"}