An Integrated Coarse-Grained Simulation and Graph-Transformer Framework for the Discovery of Self-Assembling Cyclic Peptides
Abstract Self-assembling cyclic peptides are promising building blocks for functional biomaterials owing to their enhanced structural stability, proteolytic resistance, and diverse supramolecular architectures. However, how cyclization regulates peptide self-assembly remains poorly understood, and computational frameworks specifically developed for cyclic peptides are still lacking. Here, we demonstrate that disulfide-mediated cyclization fundamentally reshapes peptide self-assembly by significantly enhancing aggregation propensity (AP) and promoting the formation of diverse nanostructures compared with their linear counterparts, as confirmed by coarse-grained molecular dynamics (CGMD) simulations and experimental characterization. Motivated by these findings, we established an integrated computational-experimental framework for the prediction and rational design of self-assembling disulfide-cyclized peptides. A data set comprising 8,000 cyclic pentapeptides was generated using CGMD simulations, and multiple machine learning and deep learning models were systematically evaluated, among which a Graph-Transformer achieved the best predictive performance (R2 = 0.971). The optimized model was subsequently applied to high-throughput screening of 160,000 cyclic hexapeptides using a ranking strategy integrating AP and hydrophobicity, leading to the identification of multiple previously unreported self-assembling candidates. Experimental validation showed excellent agreement with model predictions. Furthermore, systematic sequence analysis revealed residue- and position-dependent assembly rules unique to disulfide-cyclized peptide systems. This work establishes a computational framework for the rapid discovery of self-assembling disulfide-cyclized peptides and provides new mechanistic insights and design principles for peptide-based functional materials.
Authors
- Jia Jin (ORCID: https://orcid.org/0000-0003-3315-4797)
- Shuyao Zhang (ORCID: https://orcid.org/0000-0001-5581-2063)
- Fei Ye (ORCID: https://orcid.org/0000-0003-4119-3219)
- Kui Zhang (ORCID: https://orcid.org/0000-0003-3258-2028)
- Siqi Guo
- Runqiu Ma
- Xinyu Fan
- Kelin Li
- Hao Liu
Institutions
- Zhejiang Sci-Tech University (CN)
- Nanjing Forestry University (CN)
Publication Details
- Journal
- Journal of Chemical Information and Modeling
- Published
- 2026-11-17
- DOI
- https://doi.org/10.1021/acs.jcim.6c03241
- Primary Topic
- Supramolecular Self-Assembly in Materials
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Natural Science Foundation of China
- Zhejiang Sci-Tech University
- Natural Science Foundation of Zhejiang Province
- Key Research and Development Program of Zhejiang Province