https://github.com/simonboothroyd/nagl

A playground for applying graph convolutional networks to molecules.
https://github.com/simonboothroyd/nagl

Last synced: 20 days ago
JSON representation

A playground for applying graph convolutional networks to molecules.

• Host: GitHub
• URL: https://github.com/simonboothroyd/nagl
• Owner: SimonBoothroyd
• License: other
• Created: 2020-12-03T11:34:33.000Z (almost 4 years ago)
• Default Branch: main
• Last Pushed: 2023-12-04T12:18:13.000Z (12 months ago)
• Last Synced: 2023-12-04T13:26:29.911Z (12 months ago)
• Language: Python
• Size: 371 KB
• Stars: 6
• Watchers: 3
• Forks: 4
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • Changelog: CHANGELOG.md
  • Contributing: .github/CONTRIBUTING.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# NAGL

[![test](https://github.com/SimonBoothroyd/nagl/actions/workflows/ci.yaml/badge.svg?branch=main)](https://github.com/SimonBoothroyd/nagl/actions/workflows/ci.yaml/badge.svg?branch=main)

[![codecov](https://codecov.io/gh/SimonBoothroyd/nagl/branch/main/graph/badge.svg?token=Aa8STE8WBZ)](https://codecov.io/gh/SimonBoothroyd/nagl)

[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)

A playground for applying graph convolutional networks to molecules, with a focus on learning continuous "atom-type"

embeddings and from these classical molecule force field parameters.

This framework is mostly based upon the [*End-to-End Differentiable Molecular Mechanics Force Field Construction*](https://arxiv.org/abs/2010.01196) 

preprint by Wang, Fass and Chodera.

## Getting Started

Examples for using this framework can be found in the [`examples`](examples) directory.

## Installation

The required dependencies for this framework can be installed using `conda`:

```

conda install -c conda-forge -c dglteam nagl "dgl >=0.7"

```

### Optional dependencies

To make the full use of the framework, it is recommended to install the following 

#### [OpenFF Toolkit](https://github.com/openforcefield/openff-toolkit):

```

# Molecule labelling

conda install -c conda-forge openff-toolkit

```

## License

The main package is release under the [MIT license](LICENSE). Parts of the package are inspired by / modified from a 

number of third party packages whose licenses are included in the [3rd party license file](LICENSE-3RD-PARTY).

## Copyright

Copyright (c) 2021, Simon Boothroyd