MuCO: Generative Peptide Cyclization Empowered by Multi-stage Conformation Optimization

TL;DR

MuCO is a multi-stage generative framework for peptide cyclization that models diverse cyclic peptide conformations efficiently, improving stability, diversity, and design capabilities over existing methods.

Contribution

MuCO introduces a novel multi-stage approach that decouples backbone design, side-chain packing, and atom-level optimization for cyclic peptide modeling.

Findings

Outperforms state-of-the-art methods in stability and diversity

Achieves faster conformation sampling and optimization

Demonstrates effectiveness on large-scale datasets

Abstract

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.