Simulation · Scripps Research
Massively parallel Lamarckian genetic algorithm docking for library screens.
No backend is configured for this model.
30min–24h
Not runnable yet
This model isn't available to run right now.Run this model
About this model
For screening a million-compound library, throughput beats per-pose accuracy. AutoDock-GPU parallelises the classical docking search across the GPU and feeds its top hits to DiffDock and Boltz-2 for refinement.
Standardized I/O contract
Every model in the Hub speaks the same contract, which is what lets the Router and the agent call any of them without special-casing.
Inputs
Receptor (PDB)
Compound library (SMILES, one per line)
Outputs
Library ranked by docking score.
