Add Protein, RNA/DNA, and Ligand structures to your complex below.

Examples

Number of structure predictions to return

Predict Affinity

Number of rounds of refinement during structure prediction (higher values may improve accuracy but take longer)

Lower step scale means more diversity (recommended between 1 and 2)

This will submit x jobs with numSamples designs each to run in parallel

Template CIFs

Upload template CIF files to guide the structure prediction. These will be used as templates for the prediction.

Controls the distance (in Angstroms) that the prediction can deviate from the template

Use Potentials

Whether to run the original Boltz-2 model using inference time potentials (significantly improve the physical quality of the poses)

Use Multiple Sequence Alignment

When MSA is disabled, Boltz will not use MSA data for prediction.

Custom A3M Files

Upload custom a3m (multiple sequence alignment) files to use instead of generating MSAs automatically. Each a3m file should correspond to a protein chain in your complex.


Max number of sequences to use for MSA, use less for a more shallow MSA which may result in prediction closer to your template

Choose which sequence database to search when building the MSA. UniRef30 searches are extended with the ColabFold environmental database (BFD/MGnify-derived). SwissProt restricts the search to curated SwissProt sequences.

Generate IPSAE metrics

Generate IPSAE metrics for protein-protein complex interfaces

Please add one or more structures to your complex





Structure Prediction