ncfrey/litmatter
Rapid experimentation and scaling of deep learning models on molecular and crystal graphs.
This project helps chemists and materials scientists rapidly build and test new deep learning models for understanding molecules and crystals. You provide your molecular or crystal graph data and your model's PyTorch code, and it helps you train your model efficiently, even on large computing clusters. It's designed for researchers who want to quickly experiment with and scale up their deep learning methods in chemistry and materials science.
No commits in the last 6 months.
Use this if you are a researcher in chemistry or materials science developing new deep learning models and need a streamlined way to experiment, train, and scale them without getting bogged down in boilerplate code.
Not ideal if you are looking for a pre-built, ready-to-use model for molecular or crystal prediction, as this project is a framework for developing your own.
Stars
76
Forks
17
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Oct 23, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ncfrey/litmatter"
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...