yuyangw/MolCLR

Implementation of MolCLR: "Molecular Contrastive Learning of Representations via Graph Neural Networks" in PyG.

49
/ 100
Emerging

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.

computational chemistry drug discovery materials science molecular design property prediction
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 23 / 25

How are scores calculated?

Stars

318

Forks

75

Language

Python

License

MIT

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.