vldgroup/graph-pes
train and use graph-based ML models of potential energy surfaces
This toolkit helps materials scientists and computational chemists accurately model how atoms and molecules interact. You can input atomic structure data to train machine-learned models that predict energies and forces. These models then allow you to simulate material behavior for tasks like optimizing structures or running molecular dynamics simulations.
122 stars.
Use this if you are a researcher who needs to train and use machine-learned potential energy surface models for atomic structures, or if you are developing new methodologies for these types of models.
Not ideal if you are looking for a pre-built simulation tool without needing to train or fine-tune custom interaction models.
Stars
122
Forks
12
Language
Python
License
MIT
Category
Last pushed
Mar 09, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/vldgroup/graph-pes"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
deepmodeling/deepmd-kit
A deep learning package for many-body potential energy representation and molecular dynamics
chemprop/chemprop
Message Passing Neural Networks for Molecule Property Prediction
mir-group/nequip
NequIP is a code for building E(3)-equivariant interatomic potentials
Acellera/moleculekit
MoleculeKit: Your favorite molecule manipulation kit
CederGroupHub/chgnet
Pretrained universal neural network potential for charge-informed atomistic modeling...