yuyangw/MolCLR
Implementation of MolCLR: "Molecular Contrastive Learning of Representations via Graph Neural Networks" in PyG.
MolCLR helps chemists and materials scientists predict properties of new molecules more accurately. It takes a large set of unlabeled molecular structures and learns their underlying patterns. This knowledge is then used to improve predictions on specific tasks like drug discovery or materials design, outperforming models trained on smaller, labeled datasets alone.
318 stars. No commits in the last 6 months.
Use this if you need to improve the predictive accuracy of your models for molecular properties, especially when you have access to many unlabeled molecular structures but limited labeled data for your specific task.
Not ideal if you are not working with molecular data or if you need a quick, off-the-shelf solution without any model pre-training or fine-tuning steps.
Stars
318
Forks
75
Language
Python
License
MIT
Category
Last pushed
Nov 04, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/yuyangw/MolCLR"
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
Acellera/moleculekit
MoleculeKit: Your favorite molecule manipulation kit
mir-group/nequip
NequIP is a code for building E(3)-equivariant interatomic potentials
CederGroupHub/chgnet
Pretrained universal neural network potential for charge-informed atomistic modeling...