Zero-Shot Cyclic Peptide Design with Composable Geometric Conditions

2025-07-05

AI Summary

To address the scarcity of training data for cyclic peptide design, which limits target-specific generation, this work introduces CP-Composer—the first zero-shot cyclic peptide generation framework based on geometrically constrained composition. CP-Composer decomposes complex cyclization patterns into composable geometric constraints—such as bond lengths, bond angles, and dihedral angles—and trains a diffusion-based graph generative model exclusively on abundant linear peptide data. By jointly encoding node and edge geometry as conditional inputs, it achieves precise structural control over cyclization topology. Crucially, CP-Composer generalizes to diverse cyclization strategies—including head-to-tail and sidechain-to-backbone cyclization—without any cyclic peptide training samples. Experimental results demonstrate a substantial improvement in design success rate, rising from 38% to 84%, thereby significantly expanding rational cyclic peptide design capabilities in data-scarce regimes.

Technology Category

• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Computer Vision: Diffusion Models for Vision
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

Cyclic peptides, characterized by geometric constraints absent in linear peptides, offer enhanced biochemical properties, presenting new opportunities to address unmet medical needs. However, designing target-specific cyclic peptides remains underexplored due to limited training data. To bridge the gap, we propose CP-Composer, a novel generative framework that enables zero-shot cyclic peptide generation via composable geometric constraints. Our approach decomposes complex cyclization patterns into unit constraints, which are incorporated into a diffusion model through geometric conditioning on nodes and edges. During training, the model learns from unit constraints and their random combinations in linear peptides, while at inference, novel constraint combinations required for cyclization are imposed as input. Experiments show that our model, despite trained with linear peptides, is capable of generating diverse target-binding cyclic peptides, reaching success rates from 38% to 84% on different cyclization strategies.

Problem

• Designing target-specific cyclic peptides with limited training data
• Generating cyclic peptides using composable geometric constraints
• Achieving high success rates for diverse cyclization strategies

Innovation

• Generative framework CP-Composer for cyclic peptides
• Composable geometric constraints in diffusion model
• Zero-shot generation via unit constraint decomposition