{"id":15140783,"url":"https://github.com/aksub99/moldqn-pytorch","last_synced_at":"2025-10-23T17:31:43.520Z","repository":{"id":39729504,"uuid":"216264204","full_name":"aksub99/MolDQN-pytorch","owner":"aksub99","description":"A PyTorch Implementation of \"Optimization of Molecules via Deep Reinforcement Learning\".","archived":false,"fork":false,"pushed_at":"2023-03-24T23:37:44.000Z","size":3199,"stargazers_count":75,"open_issues_count":7,"forks_count":28,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-01-15T22:35:13.462Z","etag":null,"topics":["chemistry","deep-learning","dqn-pytorch","drug-discovery","inverse-design","machine-learning","materials-informatics","materials-science","molecule","python","pytorch","pytorch-implementation","pytorch-rl","reinforcement-learning"],"latest_commit_sha":null,"homepage":null,"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/aksub99.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}},"created_at":"2019-10-19T20:09:32.000Z","updated_at":"2024-12-02T03:05:54.000Z","dependencies_parsed_at":"2023-01-22T04:48:10.055Z","dependency_job_id":"c62454b4-9b58-499e-ab69-6fa88f4919de","html_url":"https://github.com/aksub99/MolDQN-pytorch","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/aksub99%2FMolDQN-pytorch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aksub99%2FMolDQN-pytorch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aksub99%2FMolDQN-pytorch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aksub99%2FMolDQN-pytorch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/aksub99","download_url":"https://codeload.github.com/aksub99/MolDQN-pytorch/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":237869064,"owners_count":19379259,"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":["chemistry","deep-learning","dqn-pytorch","drug-discovery","inverse-design","machine-learning","materials-informatics","materials-science","molecule","python","pytorch","pytorch-implementation","pytorch-rl","reinforcement-learning"],"created_at":"2024-09-26T08:41:17.147Z","updated_at":"2025-10-23T17:31:41.472Z","avatar_url":"https://github.com/aksub99.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# MolDQN-pytorch\n[![MIT\nlicense](https://img.shields.io/badge/License-MIT-blue.svg)](https://lbesson.mit-license.org/)\n[![made-with-python](https://img.shields.io/badge/Made%20with-Python-1f425f.svg)](https://www.python.org/)\n\nPyTorch implementation of MolDQN as described in [Optimization of Molecules via Deep Reinforcement Learning](https://www.nature.com/articles/s41598-019-47148-x)\nby Zhenpeng Zhou, Steven Kearnes, Li Li, Richard N. Zare and Patrick Riley.\n\n## Installation\n\n## \u003ca name=\"source\"\u003e\u003c/a\u003eFrom source:\n\n1) Install `rdkit`.  \n   `conda create -c rdkit -n my-rdkit-env rdkit`  \n   `conda activate my-rdkit-env`  \n   `conda install -c conda-forge rdkit`  \n   \n2) Clone this repository.  \n   `git clone https://github.com/aksub99/MolDQN-pytorch.git`  \n   `cd MolDQN-pytorch`\n   \n3) Install the requirements given in `requirements.txt`.  \n   `pip install -r requirements.txt`  \n   \n4) Install `baselines`.  \n   `pip install \"git+https://github.com/openai/baselines.git\"`  \n   \n## From Docker:\n\nUsing a docker image requires an NVIDIA GPU.  If you do not have a GPU please follow the directions for [installing from source](#source)\nIn order to get GPU support you will have to use the [nvidia-docker](https://github.com/NVIDIA/nvidia-docker) plugin.\n``` bash\n# Build the Dockerfile in Dockerfiles/Dockerfile to create a Docker image.\ncd Dockerfiles\ndocker build -t moldqn_pytorch:latest .\n\n# This will create a container from the image we just created.\nnvidia-docker run -[Options] moldqn_pytorch:latest python path/to/main.py\n```\nPlease remember to modify the `TB_LOG_PATH` variable in `main.py` depending on where you wish to store your tensorboard runs file.\n## Training the MolDQN:\n\n`python main.py`\n\nA simple example to train the model on a single property optimization task can be seen in `examples/MolDQN-pytorch.ipynb`.\n\n## Results:\n\nThe following was the reward curve obtained when the model was trained for 5000 episodes on a single property optimization task (QED in this case).\n\n\u003cimg src=\"https://github.com/aksub99/MolDQN-pytorch/blob/master/Results/plots/episode_reward.svg\" height=\"500\" width=\"500\"\u003e\n\n## References:\nThe original tensorflow implementation can be found at https://github.com/google-research/google-research/tree/master/mol_dqn\nThis repository re-uses some code from the original implementation.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faksub99%2Fmoldqn-pytorch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Faksub99%2Fmoldqn-pytorch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faksub99%2Fmoldqn-pytorch/lists"}