Solutions · 3 workflows
Hit-to-lead validation
Take your docking hits and check they survive physics: simulate the complex in explicit solvent, rescore with MM-GBSA, rank analogs by relative binding free energy, and profile the contacts that survive.
- Workflows
- 3
- Stages
- 5
- Tools
- 11
Workflows
Pick the one that fits.
Open any of them in the builder: signed out you get a read-only preview, signed in you can add your inputs, see the estimate for your plan, and run. The cost cap is the default; you can change it at launch, and a run pauses instead of spending past it.
- advanced11 steps
Stress-test top docking poses with explicit-solvent MD
Dock → MD stress test → MM-GBSA
Dock with AutoDock Vina, run the three best poses in explicit water for a short simulation (0.4 ns by default; one GPU job per pose), then cluster each trajectory and rescore the representative frames with MM-GBSA. Frames are predictions to inspect, not validated binding modes.
- You provide
- Molecules (SMILES), Protein structure (PDB)
- Runs on
- CPU · T4 GPU
- Cost cap
- $40.00 default
- moderate8 steps
Rescore docking hits with MM-GBSA and see the contacts
Dock → MM-GBSA → contacts
Dock with AutoDock Vina, keep the top ten poses, rescore them with implicit-solvent MM-GBSA, and profile the protein-ligand contacts of the best five with PLIP.
- You provide
- Molecules (SMILES), Protein structure (PDB)
- Runs on
- CPU
- Cost cap
- $25.00 default
- advanced10 steps
Rank analogs by relative binding free energy
Dock → GNINA → relative free energy
Dock a small analog series, rescore the best five poses with GNINA, then run relative binding free energy on the perturbation pairs you name. Name each pair by the pose titles (the free-energy step lists the titles it found if one is wrong) and connect every analog into one network: free energies are relative within a network, so ligands in separate networks cannot be ranked together. Keeps analogs whose uncertainty is at most 1 kcal/mol and ranks them by free energy, with uncertainties. Rankings are predictions to test, not measured affinities.
- You provide
- Molecules (SMILES), Protein structure (PDB)
- Runs on
- CPU · L40S GPU · T4 GPU
- Cost cap
- $120.00 default
Related tools
Run any step on its own.
The tools behind these workflows also run individually.
- Protein Preparer
PDBFixer cleanup, PDB2PQR protonation, and dock-ready structures without MD solvation
- Molecule Conversion
Convert molecules between SMILES, InChI, SELFIES, MOL/SDF, PDB, and other formats, optionally in 3D
- Binding-Site Detector
Find ligandable pockets and emit Vina-shaped docking boxes for fold-to-dock workflows
- AutoDock Vina
High performance molecular docking and virtual screening for drug discovery
- Small-Molecule Force-Field Parameterizer
Assign OpenFF Sage force-field parameters and partial charges to small molecules for simulation
- OpenMM MD
Prepare, solvate, and equilibrate proteins, small molecules, or membrane systems with OpenMM molecular dynamics
- MD Trajectory Analyzer
Compute RMSD, Rg, RMSF, ligand H-bond occupancy, and representative frames from OpenMM trajectories
- MM-GBSA Rescoring
End-point implicit-solvent MM-GBSA rescoring of docked poses or protein–ligand complexes
- Interaction Profiler
Enumerate hydrogen bonds, hydrophobics, salt bridges, and π-stacking in docked complexes
- GNINA
Protein–ligand docking and pose rescoring with convolutional neural network scoring functions
- Relative Binding Free Energy
Alchemical relative binding ΔΔG across ligand perturbation networks, absolute hydration ΔG, and REST2 replica-exchange sampling of protein–ligand complexes