rivas-lab/Smiles2Dock

Smiles2Dock: an open large-scale multi-task dataset for ML-based molecular docking (NeurIPS 2025 AI for Science Workshop)

27
/ 100
Experimental

This project offers a massive, ready-to-use dataset for predicting how well small molecules bind to target proteins. It takes chemical structures (SMILES strings) and protein structures (from AlphaFold) as input and outputs predicted binding scores. Medicinal chemists, computational biologists, and drug discovery researchers can use this to develop and benchmark machine learning models for virtual screening.

Use this if you are a researcher in drug discovery looking for a comprehensive dataset to train and validate machine learning models for molecular docking.

Not ideal if you are looking for an out-of-the-box tool to perform single molecular docking predictions without developing or training your own ML models.

drug-discovery molecular-docking virtual-screening medicinal-chemistry computational-biology
No Package No Dependents
Maintenance 6 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

10

Forks

Language

Python

License

Apache-2.0

Last pushed

Nov 16, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/rivas-lab/Smiles2Dock"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.