Metadata-Version: 2.2
Name: mgktools
Version: 3.1.0
Summary: Marginalized Graph Kernel Library for Molecular Property Prediction
Author-email: Yan Xiang <yan.xiang@duke.edu>
License: MIT
Project-URL: source, https://github.com/xiangyan93/mgktools
Project-URL: PyPi, https://pypi.org/project/mgktools/
Keywords: chemistry,machine learning,molecular property prediction,marginalized graph kernel,drug discovery
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.12
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.9
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: rdkit==2023.9.6
Requires-Dist: descriptastorus==2.6.1
Requires-Dist: numpy==1.26.4
Requires-Dist: mendeleev==0.19.0
Requires-Dist: typed-argument-parser
Requires-Dist: scikit-learn
Requires-Dist: rxntools
Requires-Dist: optuna
Requires-Dist: hyperopt
Requires-Dist: ipython
Requires-Dist: pytest

# 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
```

## 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)
