{"id":13751768,"url":"https://github.com/MolecularAI/Reinvent","last_synced_at":"2025-05-09T18:32:07.441Z","repository":{"id":37416832,"uuid":"248080601","full_name":"MolecularAI/Reinvent","owner":"MolecularAI","description":null,"archived":true,"fork":false,"pushed_at":"2023-10-19T05:26:16.000Z","size":123499,"stargazers_count":335,"open_issues_count":1,"forks_count":108,"subscribers_count":21,"default_branch":"master","last_synced_at":"2024-08-03T09:03:17.830Z","etag":null,"topics":["astrazeneca","cheminformatics","denovo-design","neural-networks","reinforcement-learning","transfer-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":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/MolecularAI.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,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2020-03-17T21:54:26.000Z","updated_at":"2024-08-01T06:10:43.000Z","dependencies_parsed_at":"2024-08-03T09:02:46.944Z","dependency_job_id":null,"html_url":"https://github.com/MolecularAI/Reinvent","commit_stats":null,"previous_names":[],"tags_count":3,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MolecularAI%2FReinvent","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MolecularAI%2FReinvent/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MolecularAI%2FReinvent/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MolecularAI%2FReinvent/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/MolecularAI","download_url":"https://codeload.github.com/MolecularAI/Reinvent/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":224876976,"owners_count":17384699,"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":["astrazeneca","cheminformatics","denovo-design","neural-networks","reinforcement-learning","transfer-learning"],"created_at":"2024-08-03T09:00:54.354Z","updated_at":"2024-11-16T04:31:35.875Z","avatar_url":"https://github.com/MolecularAI.png","language":"Python","funding_links":[],"categories":["Machine Learning Tasks and Models","Ranked by starred repositories","🔬 Domain-Specific Applications"],"sub_categories":["Drug Discovery","🧬 Biology \u0026 Medicine"],"readme":"** IMPORTANT: This repository is in archive mode meaning that it is read only and will not undergo further changes.  All further development will be done on REINVENT 4. **\n\nREINVENT 3.2\n=================================================================================================================\n\nInstallation\n-------------\n\n1. Install [Conda](https://conda.io/projects/conda/en/latest/index.html)\n2. Clone this Git repository\n3. Open a shell, and go to the repository and create the Conda environment:\n   \n        $ conda env create -f reinvent.yml\n\n4. Activate the environment:\n   \n        $ conda activate reinvent.v3.2\n\n5. Use the tool.\n\n     \nSystem Requirements\n-------------------\n\n* Python 3.7\n* Cuda-enabled GPU\n* `REINVENT` has been tested on Linux\n\n\nTutorials / `jupyter` notebooks\n-----\nThere is another repository containing useful `jupyter` notebooks related to `REINVENT` \ncalled [ReinventCommunity](https://github.com/MolecularAI/ReinventCommunity). Note, that it uses a\ndifferent `conda` environment to execute, so you have to set up a separate environment.\n\n\nUsage\n-----\n\nFor concrete examples, you can check out the Jupyter notebook examples in the ReinventCommunity repo.\nRunning each example will result in a template file.There are templates for many running modes. \nEach running mode can be executed by `python input.py some_running_mode.json` after activating the environment.\n    \n   Templates can be manually edited before using. The only thing that needs modification for a standard run are the file \n   and folder paths. Most running modes produce logs that can be monitored by `tensorboard`.\n\n\nTests \n-----\nThe REINVENT project uses the `unittest` framework for its tests; before you run them you first have to create a \nconfiguration, which the tests will use. In the project directory, create a `config.json` file in the `configs/` directory; \nyou can use the example config (`example.config.json`) as a base. The simplest way is to make a copy of the `example.config.json`\nand name it `config.json`. At this point, `REINVENT` can be executed. If you want to further run the unit tests, relevant paths \nwill need to be specified in your 'config.json' file, e.g, if testing reinforcement learning, the corresponding unit tests \nwill require a prior: specify the path to the prior in the \"PRIOR_PATH\" field.\n\nImportant: Make sure that you set `MAIN_TEST_PATH` to a non-existent directory; it is where temporary files will be\nwritten during the tests; if it is set to an existing directory, that directory will be removed once the tests have finished.\n\nSome tests require a proprietary OpenEye license; you have to set up a few things to make the tests read your\nlicense.  The simple way is to just set the `OE_LICENSE` environment variable to the path of the file containing the\nlicense.  If you just want to set the license in the `reinvent_scoring` Conda environment, it is a bit more complicated,\nbut you only have to do it once.\n\n```\n(reinvent-scoring) $ cd $CONDA_PREFIX\n$ mkdir -p etc/conda/activate.d\n$ mkdir -p etc/conda/deactivate.d\n```\n\nPut the following in `etc/conda/activate.d/env_vars.sh`.\n\n```\n#!/bin/sh\nexport OE_LICENSE='\u003c/path/to/your/oe_license/file\u003e'\n```\n\nAnd put the following in `etc/conda/deactivate.d/env_vars.sh`.\n\n```\n#!/bin/sh\nunset OE_LICENSE\n```\n\nOnce you have created the files, deactivate and re-activate the environment, and `echo $OE_LICENSE` should output the\npath to the license file.\nOnce you have a configuration and your license can be read, you can run the tests.\n\n```\n$ python main_test.py\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FMolecularAI%2FReinvent","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FMolecularAI%2FReinvent","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FMolecularAI%2FReinvent/lists"}