diffdock
k-dense-ai1.7k installs
Candidate docking poses for proteins and ligands.
What it does
Generates confidence-ranked candidate binding poses for proteins and small molecules using DiffDock.
When to use it
Use for single-pair docking, batch docking, or receptor ensembles, not binding-affinity prediction.
How to use it
Give it prepared receptor and ligand inputs; it generates ranked pose files and summarizes their confidence for validation.
What you provide
- Your files
Uses
DI
Good to know
- advertises something the task does not need
Latest review
What you need · 3
Requires the upstream v1.1.3 checkout and environment, including PyTorch 1.13.1, fair-esm 2.0.0, and RDKit/PyG, or its Docker image.
The upstream environment pins Python 3.9.18; the checker does not verify other Python minor versions.
Access · 3
This skill
DiffDock
Read
Downloads docking and protein-model weights
arXiv
Read
Fetches current paper citation details