Abstract
Cyclic peptides are promising therapeutics, but their flexible docking remains challenging. We present a protocol based on the well-established CABS-dock method, enhanced with cyclic restraints and Rosetta refinement. The approach was evaluated on 38 benchmark complexes previously used in other docking method studies. While selecting the truly best model remains difficult, near-native solutions are frequently sampled. CABS-dock offers global, unbiased docking without prior binding site knowledge, making it valuable for pose generation, structural ensemble modeling, and integration into AI-driven peptide-protein docking workflows.