metatensor/metatrain
Train, fine-tune, and manipulate machine learning models for atomistic systems
This tool helps scientists and researchers in materials science and chemistry to train and evaluate machine learning models for atomistic systems. You input atomic structure data and desired target properties (like energy), and it outputs a trained model that can be directly used in various molecular dynamics simulations. It's designed for computational chemists, physicists, and materials scientists who need to simulate molecular behavior efficiently.
Used by 1 other package. Available on PyPI.
Use this if you need to quickly train or fine-tune various atomistic machine learning potential architectures and integrate them into molecular dynamics simulations.
Not ideal if your primary goal is general machine learning model development outside of atomistic simulations or if you require extensive customization beyond supported architectures.
Stars
61
Forks
24
Language
Python
License
BSD-3-Clause
Category
Last pushed
Mar 12, 2026
Commits (30d)
0
Dependencies
14
Reverse dependents
1
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/metatensor/metatrain"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
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...