Designing Cyclic Peptides via Harmonic SDE with Atom-Bond Modeling

Xiangxin Zhou, Mingyu Li, Yi Xiao, Jiahan Li, Dongyu Xue, Zaixiang Zheng, Jianzhu Ma, Quanquan Gu

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.

Lay Summary:

Cyclic peptides are tiny, ring-shaped proteins that show a lot of potential for medicine. Their circular form helps them stay stable and prevents them from easily breaking down in the body, unlike the more common linear peptides. However, designing them using computers presents unique challenges. These challenges include the lack of detailed 3D structures of proteins and cyclic peptides, the complex shapes required for cyclization, and the use of uncommon amino acids.

To overcome these challenges, we have created a novel approach called CpSDE. This approach uses two main tools: AtomSDE, which predicts the structure of these peptides, and ResRouter, which determines the type of amino acids to use. By using a back-and-forth method between these two tools, CpSDE can effectively design new cyclic peptides.

Our research shows that the cyclic peptides generated with CpSDE are not only stable but also maintain high levels of effectiveness, making them strong candidates for future pharmaceutical developments.

Primary Area: Applications

Keywords: cyclic peptide, peptide design, SDE-based generative model

Submission Number: 12856