AlphaFold3 for Non-canonical Cyclic Peptide Modeling: Hierarchical Benchmarking Reveals Accuracy and Practical Guidelines
Zhang, C.; Wang, W.; Zhu, N.; Cao, Z.; Mao, Q.; Zhu, C.; Zhang, C.; Guo, J.; Duan, H.
Show abstract
Despite the revolutionary impact of AlphaFold3 on structural biology, this models capability in predicting non-canonical cyclic peptides remains unexplored. Given the clinical significance of cyclic peptides containing unnatural residues as a therapeutic modality, we present the first systematic evaluation of AlphaFold3 for this class of molecules. To facilitate benchmarking, we developed an automated input pipeline to streamline AlphaFold3 predictions for cyclic peptides. Our study aims to: (1) quantify the hierarchical accuracy (all-atoms, C atoms, and atoms of unnatural residue levels) of AlphaFold3 in predicting both non-canonical cyclic peptide monomers and complexes; (2) assess the reliability of AlphaFold3s confidence metrics; (3) evaluate the influence of multiple sequence alignment (MSA) and structural templates; and (4) identify systematic biases in AlphaFold3s predictions. Based on these analyses, we provide practical guidelines for applying AlphaFold3 in cyclic peptide structure prediction for facilitating the related research of bioactive cyclic peptides.
Matching journals
The top 3 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Cycledesigner Leveraging RFdiffusion and HighFold to Design Cyclic Peptide Binders for Specific Targets 98%
- Influence of stereochemistry in a local approach for calculating protein conformations 96%
- To Improve Protein Sequence Profile Prediction through Image Captioning on Pairwise Residue Distance Map 96%
Similar papers in this journal
- Accurate and Rapid Prediction of Protein pKa: Protein Language Models Reveal the Sequence-pKa Relationship 96%
- A linear response theory based method for prediction of large scale protein conformational changes upon ligand binding 95%
- ANUBI: A Platform for Affinity Optimization of Proteins and Peptides in Drug Design 95%
Similar papers in this journal
Similar papers in this journal
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.