Designing Cyclic Peptides via Harmonic SDE with Atom-Bond Modeling

2025-05-27

AI Summary

Addressing key challenges in cyclic peptide drug design—including scarcity of 3D structural data, stringent cyclization geometric constraints, and difficulty modeling non-canonical amino acids—this work introduces the first harmonic stochastic differential equation (SDE)-driven, all-atom generative framework, AtomSDE, synergistically coupled with ResRouter, a sequence-routing predictor. Our iterative co-design enables de novo generation of cyclic peptides with explicit joint modeling of atomic coordinates and chemical bond topology, supporting closed-loop structures incorporating non-standard residues. Crucially, the method operates without prior knowledge of the target protein structure. Quantitative evaluation demonstrates substantial improvements over state-of-the-art approaches in structural diversity, conformational stability, and predicted target binding affinity. This work establishes a novel, structure-agnostic paradigm for rational cyclic peptide design.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Search and Optimization: Mixed Discrete/Continuous Search
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications

Abstract

Cyclic peptides offer inherent advantages in pharmaceuticals. For example, cyclic peptides are more resistant to enzymatic hydrolysis compared to linear peptides and usually exhibit excellent stability and affinity. Although deep generative models have achieved great success in linear peptide design, several challenges prevent the development of computational methods for designing diverse types of cyclic peptides. These challenges include the scarcity of 3D structural data on target proteins and associated cyclic peptide ligands, the geometric constraints that cyclization imposes, and the involvement of non-canonical amino acids in cyclization. To address the above challenges, we introduce CpSDE, which consists of two key components: AtomSDE, a generative structure prediction model based on harmonic SDE, and ResRouter, a residue type predictor. Utilizing a routed sampling algorithm that alternates between these two models to iteratively update sequences and structures, CpSDE facilitates the generation of cyclic peptides. By employing explicit all-atom and bond modeling, CpSDE overcomes existing data limitations and is proficient in designing a wide variety of cyclic peptides. Our experimental results demonstrate that the cyclic peptides designed by our method exhibit reliable stability and affinity.

Problem

• Designing diverse cyclic peptides with computational methods
• Overcoming scarcity of 3D structural data for cyclic peptides
• Addressing geometric constraints in cyclic peptide generation

Innovation

• Harmonic SDE for cyclic peptide generation
• Atom-bond modeling overcomes data limitations
• Routed sampling updates sequences and structures