Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/simonboothroyd/descent

Optimize classical force field parameters against reference data
https://github.com/simonboothroyd/descent

Last synced: 2 months ago
JSON representation

Optimize classical force field parameters against reference data

Host: GitHub
URL: https://github.com/simonboothroyd/descent
Owner: SimonBoothroyd
License: mit
Created: 2021-05-27T14:01:29.000Z (over 3 years ago)
Default Branch: main
Last Pushed: 2024-07-27T18:55:44.000Z (5 months ago)
Last Synced: 2024-07-27T19:44:39.631Z (5 months ago)
Language: Python
Homepage: https://simonboothroyd.github.io/descent/
Size: 1.59 MB
Stars: 8
Watchers: 2
Forks: 3
Open Issues: 1
Metadata Files:
- Readme: README.md
- License: LICENSE

Awesome Lists containing this project

README

DESCENT

Optimize force field parameters against reference data

---

The `descent` framework aims to offer a modern API for training classical force field parameters (either from a
traditional format such as SMIRNOFF or from some ML model) against reference data using `pytorch`.

This framework benefited hugely from [ForceBalance](https://github.com/leeping/forcebalance), and a significant
number of learning from that project, and from Lee-Ping, have influenced the design of this one.

***Warning**: This code is currently experimental and under active development. If you are using this it, please be
aware that it is not guaranteed to provide correct results, the documentation and testing maybe be incomplete, and the
API can change without notice.*

## Installation

This package can be installed using `conda` (or `mamba`, a faster version of `conda`):

```shell
mamba install -c conda-forge descent
```

The example notebooks further require you install `jupyter`:

```shell
mamba install -c conda-forge jupyter
```

## Getting Started

To get started, see the [examples](examples).