# mgktools
Python Package using marginalized graph kernel (MGK) to predict molecular properties.
## Installation
Suggested Package Versions:
Python>=3.9, GCC==11.2, CUDA==11.7.
```
pip install git+https://gitlab.com/Xiangyan93/graphdot.git@feature/xy
pip install mgktools
```
## QuickStart with Google Colab
GPU is required to compute graph kernel.
- [Interpretability Marginalized Graph Kernel](https://colab.research.google.com/drive/1Z6tx4_3FBhZB9SwOvxex9jIP-XZ40hi9?usp=sharing)
## Hyperparameters
[hyperparameters](https://github.com/Xiangyan93/mgktools/tree/main/mgktools/hyperparameters) contains the JSON files that
define the hyperparameters for MGK.
## Related work
* [Predicting Single-Substance Phase Diagrams: A Kernel Approach on Graph Representations of Molecules](https://pubs.acs.org/doi/full/10.1021/acs.jpca.1c02391)
* [A Comparative Study of Marginalized Graph Kernel and Message-Passing Neural Network](https://pubs.acs.org/doi/full/10.1021/acs.jcim.1c01118)
* [Interpretable Molecular Property Predictions Using Marginalized Graph Kernels](https://pubs.acs.org/doi/full/10.1021/acs.jcim.3c00396)
Raw data
{
"_id": null,
"home_page": null,
"name": "mgktools",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.10",
"maintainer_email": null,
"keywords": "chemistry, machine learning, molecular property prediction, marginalized graph kernel, drug discovery",
"author": null,
"author_email": "Yan Xiang <yan.xiang@duke.edu>",
"download_url": "https://files.pythonhosted.org/packages/02/ad/77eb11deac13667646cd18fad05723ec2bc79fd35d2aae55a5bcb0bdf45b/mgktools-3.2.0.tar.gz",
"platform": null,
"description": "# mgktools\nPython Package using marginalized graph kernel (MGK) to predict molecular properties.\n\n## Installation\nSuggested Package Versions:\nPython>=3.9, GCC==11.2, CUDA==11.7.\n```\npip install git+https://gitlab.com/Xiangyan93/graphdot.git@feature/xy\npip install mgktools\n```\n\n## QuickStart with Google Colab\nGPU is required to compute graph kernel. \n- [Interpretability Marginalized Graph Kernel](https://colab.research.google.com/drive/1Z6tx4_3FBhZB9SwOvxex9jIP-XZ40hi9?usp=sharing)\n\n## Hyperparameters\n[hyperparameters](https://github.com/Xiangyan93/mgktools/tree/main/mgktools/hyperparameters) contains the JSON files that\ndefine the hyperparameters for MGK.\n\n## Related work\n* [Predicting Single-Substance Phase Diagrams: A Kernel Approach on Graph Representations of Molecules](https://pubs.acs.org/doi/full/10.1021/acs.jpca.1c02391)\n* [A Comparative Study of Marginalized Graph Kernel and Message-Passing Neural Network](https://pubs.acs.org/doi/full/10.1021/acs.jcim.1c01118)\n* [Interpretable Molecular Property Predictions Using Marginalized Graph Kernels](https://pubs.acs.org/doi/full/10.1021/acs.jcim.3c00396)\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "Marginalized Graph Kernel Library for Molecular Property Prediction",
"version": "3.2.0",
"project_urls": {
"PyPi": "https://pypi.org/project/mgktools/",
"source": "https://github.com/xiangyan93/mgktools"
},
"split_keywords": [
"chemistry",
" machine learning",
" molecular property prediction",
" marginalized graph kernel",
" drug discovery"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "634d7617acd021dda9e91fe8f3eead12732f7a5f6af0e79f7e1569fd3e0d719d",
"md5": "1b65c21895f071f2daf4ccec020fb496",
"sha256": "c33ac0a2008404b277cc04d60197757be98d05c21945b8adb95f5fad906de2a7"
},
"downloads": -1,
"filename": "mgktools-3.2.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "1b65c21895f071f2daf4ccec020fb496",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.10",
"size": 73194,
"upload_time": "2025-10-15T14:49:17",
"upload_time_iso_8601": "2025-10-15T14:49:17.784816Z",
"url": "https://files.pythonhosted.org/packages/63/4d/7617acd021dda9e91fe8f3eead12732f7a5f6af0e79f7e1569fd3e0d719d/mgktools-3.2.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "02ad77eb11deac13667646cd18fad05723ec2bc79fd35d2aae55a5bcb0bdf45b",
"md5": "9593681053174ea618a1522b4a2af682",
"sha256": "688758e17e8d07e9226e8c04dd18337b452cf8c0bbabd742be67661f98e72f71"
},
"downloads": -1,
"filename": "mgktools-3.2.0.tar.gz",
"has_sig": false,
"md5_digest": "9593681053174ea618a1522b4a2af682",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.10",
"size": 56531,
"upload_time": "2025-10-15T14:49:18",
"upload_time_iso_8601": "2025-10-15T14:49:18.963330Z",
"url": "https://files.pythonhosted.org/packages/02/ad/77eb11deac13667646cd18fad05723ec2bc79fd35d2aae55a5bcb0bdf45b/mgktools-3.2.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-10-15 14:49:18",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "xiangyan93",
"github_project": "mgktools",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"lcname": "mgktools"
}
JSON
