Algorithms Overview

PandaDock v3.0 provides a streamlined set of docking algorithms optimized for accuracy and reliability.

Primary Algorithm

Hierarchical Docking (``pandadock``)

The main docking algorithm uses a multi-stage hierarchical search:

This algorithm achieves:

Usage:

pandadock dock -r protein.pdb -l ligand.sdf \
               --center 10 20 30 --box 20 20 20

Vina Scoring (Default)

Implements AutoDock Vina-style scoring with:

pandadock dock -r protein.pdb -l ligand.sdf \
               --scoring vina ...

Physics-Based Scoring

Alternative scoring with:

pandadock dock -r protein.pdb -l ligand.sdf \
               --scoring physics_based ...

PandaDock-GNN

For best accuracy, use the SE(3)-equivariant GNN scoring function:

Use via hybrid docking:

pandadock hybrid -r protein.pdb -l ligand.sdf \
                 --center 10 20 30 --box 20 20 20 \
                 -m model.pt

Flexible Docking (pandadock-flex)

Induced-fit docking with receptor flexibility:

pandadock-flex -r protein.pdb -l ligand.sdf \
               --center 10 20 30 --radius 15

Metal Docking (pandadock-metal)

Specialized for metalloproteins (Zn, Fe, Mg, Ca, etc.):

pandadock-metal dock -r metalloprotein.pdb -l ligand.sdf ...

Tethered Docking (pandadock-tethered)

Constrained docking for validation:

pandadock-tethered dock -r protein.pdb -l ligand.sdf \
                        --reference crystal_ligand.pdb

On ULVSH benchmark (942 compounds):