<p align="center">
<img src="https://raw.githubusercontent.com/NREL/polyID/master/images/polyID-logo_color-full.svg" alt="PolyID Logo" width="400"/>
</p>
PolyID<sup>TM</sup> provides a framework for building, training, and predicting polymer properities using graph neural networks. The codes leverages [nfp](https://pypi.org/project/nfp/), for building tensorflow-based message-passing neural networ, and [m2p](https://pypi.org/project/m2p/), for building polymer structures. The notebooks have been provided that demonstrate how to: (1) build polymer structures from a polymer database and split into a training/validation and test set, (2) train a message passing neural network from using the trainining/validation set, and (3) evaluate the trained network on the test set. These three notebooks follow the methodology used in the forthcoming publication.
1. [Building polymer structures](https://github.com/NREL/polyID/blob/master/examples/1_generate_polymer_structures.ipynb): `examples/1_generate_polymer_structures.ipynb`
2. [Training a message passing neural network](https://github.com/NREL/polyID/blob/master/examples/2_generate_and_train_models.ipynb): `examples/2_generate_and_train_models.ipynb`
3. [Predicting and evaluating a trained network](https://github.com/NREL/polyID/blob/master/examples/3_evaluate_model_performance_and_DoV.ipynb): `examples/3_evaluate_model_performance_and_DoV.ipynb`
Additional notebooks have been provided to provide more examples and capabilities of the PolyID code base.
4. [Checking domain of validity](https://github.com/NREL/polyID/blob/master/examples/example_determine_domain-of-validity.ipynb): `examples/example_determine_domain-of-validity.ipynb`
5. [Generating hierarchical fingerprints for performance comparison](https://github.com/NREL/polyID/blob/master/examples/example_hierarchical_fingerprints.ipynb): `examples/example_hierarchical_fingerprints.ipynb`
6. [Predicting with the trained model](https://github.com/NREL/polyID/blob/master/examples/example_predict_with_trained_models.ipynb): `examples/example_predict_with_trained_models.ipynb`
Details for the methods are forthcoming in an upcoming manuscript.
Raw data
{
"_id": null,
"home_page": "https://github.com/NREL/polyid",
"name": "polyid",
"maintainer": "",
"docs_url": null,
"requires_python": "",
"maintainer_email": "",
"keywords": "",
"author": "Kevin Shebek, Nolan Wilson",
"author_email": "nolan.wilson@nrel.gov",
"download_url": "https://files.pythonhosted.org/packages/95/a1/10d218b6de468163439956d817f8cfba290e08aa9ed39d9cd2716807de51/polyid-0.1.2.2.tar.gz",
"platform": null,
"description": "\n<p align=\"center\">\n <img src=\"https://raw.githubusercontent.com/NREL/polyID/master/images/polyID-logo_color-full.svg\" alt=\"PolyID Logo\" width=\"400\"/>\n</p>\n\nPolyID<sup>TM</sup> provides a framework for building, training, and predicting polymer properities using graph neural networks. The codes leverages [nfp](https://pypi.org/project/nfp/), for building tensorflow-based message-passing neural networ, and [m2p](https://pypi.org/project/m2p/), for building polymer structures. The notebooks have been provided that demonstrate how to: (1) build polymer structures from a polymer database and split into a training/validation and test set, (2) train a message passing neural network from using the trainining/validation set, and (3) evaluate the trained network on the test set. These three notebooks follow the methodology used in the forthcoming publication.\n\n1. [Building polymer structures](https://github.com/NREL/polyID/blob/master/examples/1_generate_polymer_structures.ipynb): `examples/1_generate_polymer_structures.ipynb`\n2. [Training a message passing neural network](https://github.com/NREL/polyID/blob/master/examples/2_generate_and_train_models.ipynb): `examples/2_generate_and_train_models.ipynb`\n3. [Predicting and evaluating a trained network](https://github.com/NREL/polyID/blob/master/examples/3_evaluate_model_performance_and_DoV.ipynb): `examples/3_evaluate_model_performance_and_DoV.ipynb`\n\nAdditional notebooks have been provided to provide more examples and capabilities of the PolyID code base.\n\n4. [Checking domain of validity](https://github.com/NREL/polyID/blob/master/examples/example_determine_domain-of-validity.ipynb): `examples/example_determine_domain-of-validity.ipynb`\n5. [Generating hierarchical fingerprints for performance comparison](https://github.com/NREL/polyID/blob/master/examples/example_hierarchical_fingerprints.ipynb): `examples/example_hierarchical_fingerprints.ipynb`\n6. [Predicting with the trained model](https://github.com/NREL/polyID/blob/master/examples/example_predict_with_trained_models.ipynb): `examples/example_predict_with_trained_models.ipynb` \n\nDetails for the methods are forthcoming in an upcoming manuscript.\n",
"bugtrack_url": null,
"license": "",
"summary": "Methods to train message passing neural network models on polymer structures.",
"version": "0.1.2.2",
"project_urls": {
"Homepage": "https://github.com/NREL/polyid",
"Source": "https://github.com/NREL/polyid"
},
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "ee15a43510c6768ab0fd46e1872e3854b7c2010fe9adef3a3f49b7df931c5ceb",
"md5": "c0862a07c55bd4fb68f47ce599a2622e",
"sha256": "dd6190ef0d9780983a86a691decf546538ec031b195783478dd96c8bae094e5d"
},
"downloads": -1,
"filename": "polyid-0.1.2.2-py3-none-any.whl",
"has_sig": false,
"md5_digest": "c0862a07c55bd4fb68f47ce599a2622e",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": null,
"size": 23081,
"upload_time": "2023-10-27T18:34:32",
"upload_time_iso_8601": "2023-10-27T18:34:32.586841Z",
"url": "https://files.pythonhosted.org/packages/ee/15/a43510c6768ab0fd46e1872e3854b7c2010fe9adef3a3f49b7df931c5ceb/polyid-0.1.2.2-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "95a110d218b6de468163439956d817f8cfba290e08aa9ed39d9cd2716807de51",
"md5": "9cb2b10407a23ca02fa878e8f11d2759",
"sha256": "957a647f4d04b452c8f3598b52ec40e27b619d70f26e920f9f525edd3859ca67"
},
"downloads": -1,
"filename": "polyid-0.1.2.2.tar.gz",
"has_sig": false,
"md5_digest": "9cb2b10407a23ca02fa878e8f11d2759",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 40634,
"upload_time": "2023-10-27T18:34:34",
"upload_time_iso_8601": "2023-10-27T18:34:34.308990Z",
"url": "https://files.pythonhosted.org/packages/95/a1/10d218b6de468163439956d817f8cfba290e08aa9ed39d9cd2716807de51/polyid-0.1.2.2.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-10-27 18:34:34",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "NREL",
"github_project": "polyid",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"tox": true,
"lcname": "polyid"
}
JSON
