Designing Cyclic Peptides via Harmonic SDE with Atom-Bond Modeling
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 36 of its 119 references that are in the map. First posted on arXiv 27 May 2025.
Builds on
36 of 119 references.
References · 36
- 2020Denoising Diffusion Probabilistic Modelscited by 21,076
- 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
- 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
- 2022Classifier-Free Diffusion Guidancecited by 5,847
- 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
- 2021E(n) Equivariant Graph Neural Networkscited by 965
- 2020Learning from Protein Structure with Geometric Vector Perceptronscited by 313
- 2022DiffDock: Diffusion Steps, Twists, and Turns for Molecular Dockingcited by 313
- 2024Generative Flows on Discrete State-Spaces: Enabling Multimodal Flows with Applications to Protein Co-Designcited by 305
- 2023SE(3) diffusion model with application to protein backbone generationcited by 219
- 2022EquiBind: Geometric Deep Learning for Drug Binding Structure Predictioncited by 144
- 2024Diffusion Language Models Are Versatile Protein Learnerscited by 98
24 more
- 2021Iterative Refinement Graph Neural Network for Antibody Sequence-Structure Co-designcited by 86
- 2022PiFold: Toward effective and efficient protein inverse foldingcited by 83
- 2023Structure-informed Language Models Are Protein Designerscited by 68
- 2024DPLM-2: A Multimodal Diffusion Protein Language Modelcited by 64
- 2023EigenFold: Generative Protein Structure Prediction with Diffusion Modelscited by 63
- 2023End-to-End Full-Atom Antibody Designcited by 49
- 2023Graph Denoising Diffusion for Inverse Protein Foldingcited by 44
- 2024Improved motif-scaffolding with SE(3) flow matchingcited by 43
- 2024PepTune: De Novo Generation of Therapeutic Peptides with Multi-Objective-Guided Discrete Diffusioncited by 37
- 2022State-specific protein-ligand complex structure prediction with a multi-scale deep generative modelcited by 35
- 2023AbDiffuser: Full-Atom Generation of in vitro Functioning Antibodiescited by 35
- 2024Full-Atom Peptide Design based on Multi-modal Flow Matchingcited by 34
- 2024Antigen-Specific Antibody Design via Direct Energy-based Preference Optimizationcited by 30
- 2024DecompOpt: Controllable and Decomposed Diffusion Models for Structure-based Molecular Optimizationcited by 27
- 2024PPFlow: Target-aware Peptide Design with Torsional Flow Matchingcited by 26
- 2024ProteinBench: A Holistic Evaluation of Protein Foundation Modelscited by 25
- 2024Re-Dock: Towards Flexible and Realistic Molecular Docking with Diffusion Bridgecited by 16
- 2023De novo protein design using geometric vector field networkscited by 14
- 2024Reprogramming Pretrained Target-Specific Diffusion Models for Dual-Target Drug Designcited by 11
- 2025An All-Atom Generative Model for Designing Protein Complexescited by 10
- 2024Stabilizing Policy Gradients for Stochastic Differential Equations via Consistency with Perturbation Processcited by 8
- 2024Improving Antibody Design with Force-Guided Sampling in Diffusion Modelscited by 7
- 2025Group Ligands Docking to Protein Pocketscited by 2
- 2025Integrating Protein Dynamics into Structure-Based Drug Design via Full-Atom Stochastic Flowscited by 2
Built on by
Citing papers per year: 2026: 2.
2 papers.