FlowDock
FlowDock predicts protein-ligand structures and binding affinities using geometric flow matching, enabling multi-ligand docking and fast virtual drug screening.
FlowDock is a generative framework for protein-ligand docking and binding affinity estimation. Leveraging geometric flow matching, it enables accurate predictions of protein-ligand complex structures and their binding affinities, supporting flexible docking for multiple ligands simultaneously. FlowDock incorporates state-of-the-art techniques like ESMFold and harmonic ligand priors to map unbound (apo) structures to their bound (holo) counterparts, providing confidence scores and affinity predictions for virtual screening. Benchmark results highlight its efficacy on datasets like PoseBusters and DockGen-E, achieving competitive docking success rates and top-5 affinity prediction performance in the CASP16 competition.
Estimated resource cost: 0.001178
Categories: Molecular Docking & Interactions
Tags: Affinity Prediction Proteins Protein–Ligand Docking Small Molecules
Key Capabilities
- Integrates geometric flow matching to predict protein-ligand structures and binding affinities.
- Supports flexible docking for multiple ligands simultaneously.
- Achieves state-of-the-art performance in docking success rates on challenging datasets like PoseBusters and DockGen-E.
- Uses ESMFold-based protein priors and harmonic ligand priors for accurate apo-to-holo mappings.
Runtime Statistics
| Metric | Value |
|---|---|
| runtime_mean | 158 |
| runtime_median | 103 |
| runtime_std | 505 |
| runtime_90th_percentile | 162 |
| runtime_max | 9197 |
Similar Tools
- AutoDock Vina (smina)
- DiffDock-L
- DynamicBind
- GNINA
Ready to submit your job?
Review your configuration, then confirm the estimated credit cost before you run the job. Note that credit estimates are not guaranteed and runtime can vary depending on inputs and settings.
Estimated Credits: 0.001178
Invite-only, limited-time access. Please contact ztang@getantibody.com.
Invite-only, limited-time access. Please contact ztang@getantibody.com.