Short label for this Boltz-2 run. Used in dashboard, history, and downloads; doesn’t affect results.
Multiple-sequence alignment to expose co-evolution. MMseqs2 = fast default. Better MSA → better structure/complex accuracy, especially for conserved proteins; sparse families may gain little.
Refinement passes through the network. More passes usually reduce clashes and improve local geometry with diminishing returns. Common: 3–6; difficult targets: 8–12; beyond that rarely helps but costs compute.
Sampling steps for the generator. More steps → better convergence/diversity, more compute. Quick screens: ~100-300. Balanced: ~300-600. Stringent finals: ~600+
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.