BindCraft
Structure-based de novo binder design on JAX, AlphaFold2 multimer, and ColabDesign. Four hour max session; results are emailed on completion.
What it is for
Pick BindCraft when you have a target PDB plus known hotspot residues and want de novo 60 to 150 aa protein binders.
BindCraft (Pacesa et al., bioRxiv 2024). De novo binder design via AlphaFold2-Multimer hallucination with hotspot-focused backpropagation, followed by ProteinMPNN sequence design and AF2 re-prediction filtering.
When it fits:
- You have a target PDB and at least one hotspot residue you want the binder to contact.
- You want de novo 50 to 150 aa protein binders (not antibodies).
- You can wait ~45 min per pilot run and want filtered hits with ipTM and pLDDT above the BindCraft default thresholds.
Inputs
You will need:
- Target structure as
.pdb,.cif, or.mmcif. - Chain ID of the target within that structure.
- At least one hotspot residue index on the target chain.
Each run uses a preset that sets the scale and scope:
- Your target, ~30 min start to first results
- BindCraft against your uploaded PDB on A100-80GB. Pick 1 to 500 trajectories. Start with a small batch (4 trajectories, ~30 to 45 min) to confirm your target and hotspots, then scale to 100+ once the small batch looks reasonable. Results emailed on completion.
Parameters you set on the form:
- Hotspot residues
- Comma-separated target-chain residue indices the binder should contact (e.g.
54,56,115). These bias AF2 backpropagation toward the intended epitope. Click residues in the 3D viewer to toggle them. - Binder length (min/max)
- Residue-count window for the generated binder chain (50 to 150). Shorter binders are easier to validate in yeast display; longer ones can target larger interfaces.
- Number of designs
- How many final filtered designs to return (1 to 5). Each passes AF2 re-prediction with ipTM and pLDDT above the BindCraft default thresholds. Pipeline cost floor is ~45 min regardless of count.
Typical runtime:
- pilot
- ~45 min
How to read the results
Filtered candidate binders with ipTM, pLDDT, shape complementarity, and downloadable PDBs. Hand off promising designs to the Ranomics yeast display CRO for in vitro validation.
Where a tool reports them, the scores mean:
- ipTM
- Predicted confidence in the binder to target interface. Higher is better. Aim above roughly 0.7 on a tractable target.
- pLDDT
- Per-residue confidence in the predicted fold. Higher means the model is more sure of that part of the structure.
- i_pAE and pAE
- Predicted alignment error, at the interface (i_pAE) or across the whole structure (pAE). Lower is better.
References
Pacesa et al., bioRxiv 2024