Peptide-protein interactions are crucial for biological processes, yet accurate structural modeling remains challenging. Here, the authors introduce TopoDockQ, a topological deep learning model to enhance model selection, and ResidueX, a workflow for non-canonical amino acids integrating into custom peptide scaffolds, which represent a synergistic advancement in peptide-protein modeling and enhance more precise and versatile peptide design.
- Xuhang Dai
- Rui Wang
- Yingkai Zhang