Metadata-Version: 2.1
Name: mgktools
Version: 2.2.0
Summary: Marginalized graph kernel library for molecular property prediction
Home-page: https://github.com/xiangyan93/mgktools
Author: Yan Xiang
Author-email: 1993.xiangyan@gmail.com
Classifier: Programming Language :: Python
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.10
License-File: LICENSE
Requires-Dist: scikit-learn>=0.24.1
Requires-Dist: tqdm>=4.62.0
Requires-Dist: hyperopt>=0.2.5
Requires-Dist: optuna>=3.6.0
Requires-Dist: scipy>=1.6.2
Requires-Dist: mendeleev>=0.7
Requires-Dist: rxntools>=0.0.2
Requires-Dist: pycuda>=2022.1
Requires-Dist: rdkit>=2022.9.2
Requires-Dist: deepchem==2.7.2.dev20231207083329
Requires-Dist: typed-argument-parser
Requires-Dist: ipython

# mgktools
Python Package using marginalized graph kernel (MGK) to predict molecular properties.

## Installation
Suggested Package Versions:
Python==3.10, GCC==11.2, CUDA==11.7.
```
pip install numpy==1.22.3 git+https://gitlab.com/Xiangyan93/graphdot.git@feature/xy git+https://github.com/bp-kelley/descriptastorus
pip install mgktools
```

## Usage
See [notebooks](https://github.com/Xiangyan93/mgktools/tree/main/notebooks)

## 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)
