Short label for this Boltz-2 run. Used in dashboard, history, and downloads; doesn’t affect results.
Multiple-sequence alignment to expose co-evolution. None = fastest. MMseqs2 = fast default.
Refinement passes through the network. More passes usually reduce clashes and improve local geometry with diminishing returns.
Sampling steps for the generator. More steps → better convergence/diversity, more compute.
Compute ΔG binding for ligand/glycan chains (if present). Choose True to enable, False to skip.
Number of independent structures Boltz-2 will generate. You’ll get n different CIF structures.
Optionally guide sampling with structural templates (CIF or PDB). Not dependent on MSA.