Solutions · 9 workflows
Virtual screening
Find the compounds in a library most likely to bind your target, then rescore the best hits with a stronger method.
- Screen a compound library against a targetSMILES → 3D embed → dock
- Train a target rescorer on your measured compoundsVina + GNINA + PLIP → target rescorer
- Screen a library with your target rescorerVina + GNINA + PLIP → rescore with your model → top 20
- Find top binding poses with diffusion dockingSMILES → DiffDock → top poses
- Screen an ultra-large combinatorial libraryThompson Sampling → 3D embed → dock
- Rescore docking hits with a CNN scoring functionVina triage → GNINA rescore
- Re-predict docking hits with Boltz-2 affinitiesVina triage → Boltz-2 re-predict (batch)
- Re-dock top hits with surface-aware diffusionVina triage → SurfDock (scatter)
- Validate docking protocol, then screenValidate docking protocol → screen
- Workflows
- 9
- Stages
- 6
- Tools
- 13
Your library
Imatinib Nilotinib Dasatinib Your target
A pose in the pocket
- Target
- ABL1 kinase domain
- Structure
- PDB 2HYY · 2.4 Å
- Polar contacts
- 6
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.
- simple3 steps
Screen a compound library against a target
SMILES → 3D embed → dock
Convert SMILES to 3D structures, detect pockets, then dock with AutoDock Vina.
- You provide
- Molecules (SMILES), Protein structure (PDB)
- Runs on
- CPU
- Cost cap
- $10.00 default
- advanced6 steps
Train a target rescorer on your measured compounds
Vina + GNINA + PLIP → target rescorer
Dock your measured compounds with AutoDock Vina, rescore the poses with GNINA, profile contacts with PLIP, and learn one score for your target from these signals. Labels are a CSV of SMILES and measured values; the comparison shows whether the learned score beats each single score.
- You provide
- Table (CSV), Molecules (SMILES), Model name, Protein structure (PDB)
- Runs on
- CPU · T4 GPU
- Cost cap
- $25.00 default
- advanced7 steps
Screen a library with your target rescorer
Vina + GNINA + PLIP → rescore with your model → top 20
Dock a library with the same Vina, GNINA and PLIP steps your rescorer was trained on, score every ligand with it, and keep the 20 highest.
- You provide
- Molecules (SMILES), Model id, Protein structure (PDB)
- Runs on
- CPU · T4 GPU
- Cost cap
- $25.00 default
- simple2 steps
Find top binding poses with diffusion docking
SMILES → DiffDock → top poses
Dock a SMILES library with DiffDock and keep the top-confidence poses.
- You provide
- Molecules (SMILES), Protein structure (PDB)
- Runs on
- T4 GPU
- Cost cap
- $110.00 default
- moderate4 steps
Screen an ultra-large combinatorial library
Thompson Sampling → 3D embed → dock
Screen a combinatorial library with Thompson Sampling, embed hits to 3D, detect pockets, then dock with AutoDock Vina.
- You provide
- Protein structure (PDB)
- Runs on
- CPU
- Cost cap
- $15.00 default
- moderate5 steps
Rescore docking hits with a CNN scoring function
Vina triage → GNINA rescore
Detect pockets, dock with AutoDock Vina, keep the top poses, and rescore with GNINA.
- You provide
- Molecules (SMILES), Protein structure (PDB)
- Runs on
- CPU · T4 GPU
- Cost cap
- $25.00 default
- moderate5 steps
Re-predict docking hits with Boltz-2 affinities
Vina triage → Boltz-2 re-predict (batch)
Detect pockets, dock a ligand set, keep the top poses, and re-predict affinities with Boltz-2 in batch.
- You provide
- Molecules (SMILES), Protein structure (PDB)
- Runs on
- CPU · A10 GPU
- Cost cap
- $25.00 default
- advanced6 steps
Re-dock top hits with surface-aware diffusion
Vina triage → SurfDock (scatter)
Detect pockets, dock with AutoDock Vina, keep the top hits, and re-dock each ligand with SurfDock (one GPU job per ligand).
- You provide
- Molecules (SMILES), Protein structure (PDB)
- Runs on
- CPU · A10 GPU
- Cost cap
- $25.00 default
- moderate7 steps
Validate docking protocol, then screen
Validate docking protocol → screen
Redock the co-crystallized ligand to check the box, receptor prep and engine reproduce the crystal pose; the library is docked only when the redocked pose is within the RMSD threshold.
- You provide
- Protein structure (PDB), Molecules (SMILES)
- Runs on
- CPU
- Cost cap
- $25.00 default
Related tools
Run any step on its own.
The tools behind these workflows also run individually.
- 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
- GNINA
Protein–ligand docking and pose rescoring with convolutional neural network scoring functions
- Interaction Profiler
Enumerate hydrogen bonds, hydrophobics, salt bridges, and π-stacking in docked complexes
- Target Rescorer
Learn a target-specific score from Vina, GNINA, Boltz-2, MM-GBSA and PLIP signals on your measured compounds, and see which signals predict activity
- MPNN Models
Fast structure-property inference that highlights key molecule substructures
- DiffDock
Protein-ligand docking with diffusion models and confidence-ranked poses
- Thompson Sampling
Active-learning virtual screening of un-enumerated combinatorial libraries via Thompson Sampling
- Boltz-2
Accurate in silico screening for early-stage drug discovery
- SurfDock
Surface-informed diffusion docking with a reference-ligand pocket and screen-model rescoring
- Protein Preparer
PDBFixer cleanup, PDB2PQR protonation, and dock-ready structures without MD solvation
- Docking Protocol Validator
Redock co-crystallized ligands and score pose RMSD and enrichment to validate a docking setup before screening