https://github.com/aiqm/aimnet
Atoms In Molecules Neural Network Potential
https://github.com/aiqm/aimnet
chemistry deep-learning molecular-dynamics molecular-modeling molecular-simulation neural-network quantum-chemistry quantum-mechanics
Last synced: 2 months ago
JSON representation
Atoms In Molecules Neural Network Potential
- Host: GitHub
- URL: https://github.com/aiqm/aimnet
- Owner: aiqm
- License: mit
- Created: 2018-09-26T17:28:37.000Z (over 7 years ago)
- Default Branch: master
- Last Pushed: 2019-11-21T23:49:01.000Z (over 6 years ago)
- Last Synced: 2026-04-03T19:54:04.791Z (3 months ago)
- Topics: chemistry, deep-learning, molecular-dynamics, molecular-modeling, molecular-simulation, neural-network, quantum-chemistry, quantum-mechanics
- Language: Python
- Homepage:
- Size: 19 MB
- Stars: 107
- Watchers: 9
- Forks: 29
- Open Issues: 5
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# 
AIMNet - Atoms In Molecules Neural Network Potential
This repository contains reference AIMNet implementation along with some examples and menchmarks
## Requirements
- [pytorch-1.1](https://pytorch.org/)
- [numpy](https://www.numpy.org/)
- [pyyaml](https://pyyaml.org/)
- [ase](https://wiki.fysik.dtu.dk/ase/)
- [nglview](http://nglviewer.org/nglview/latest/) (for demos)
## Citation
Accurate and transferable multitask prediction of chemical properties with an atoms-in-molecules neural network
Roman Zubatyuk, Justin S. Smith, Jerzy Leszczynski, Olexandr Isayev
_Science Advances_ *2019*: Vol. 5, no. 8, eaav6490 [DOI: 10.1126/sciadv.aav6490](https://advances.sciencemag.org/content/5/8/eaav6490)