MuCO: Generative Peptide Cyclization Empowered by Multi-stage Conformation Optimization
This work addresses the problem of virtual screening for cyclic peptides in drug discovery, offering a computational tool for exploring and designing them, though it appears incremental as it builds on existing methods with a multi-stage optimization approach.
The study tackled the challenge of modeling cyclic peptide conformations, which are diverse and ring-shaped, by proposing MuCO, a generative method that outperformed state-of-the-art methods in physical stability, structural diversity, secondary structure recovery, and computational efficiency on the CPSea dataset.
Modeling peptide cyclization is critical for the virtual screening of candidate peptides with desirable physical and pharmaceutical properties. This task is challenging because a cyclic peptide often exhibits diverse, ring-shaped conformations, which cannot be well captured by deterministic prediction models derived from linear peptide folding. In this study, we propose MuCO (Multi-stage Conformation Optimization), a generative peptide cyclization method that models the distribution of cyclic peptide conformations conditioned on the corresponding linear peptide. In principle, MuCO decouples the peptide cyclization task into three stages: topology-aware backbone design, generative side-chain packing, and physics-aware all-atom optimization, thereby generating and optimizing conformations of cyclic peptides in a coarse-to-fine manner. This multi-stage framework enables an efficient parallel sampling strategy for conformation generation and allows for rapid exploration of diverse, low-energy conformations. Experiments on the large-scale CPSea dataset demonstrate that MuCO significantly outperforms state-of-the-art methods in consistently in physical stability, structural diversity, secondary structure recovery, and computational efficiency, making it a promising computational tool for exploring and designing cyclic peptides.