A deep-learning framework for multi-level peptide–protein interaction prediction
Problem
Identifying which peptides bind which proteins is essential for designing peptide therapeutics, but most existing computational predictors depend on high-resolution structural data.
Why it matters
Peptide drug design depends on knowing peptide-protein interactions and binding residues.
What the AI did
CAMP, a deep learning framework, predicts binary peptide-protein interactions and identifies peptide binding residues without requiring high-resolution structure data.
Results
Outperformed other state-of-the-art methods on binary peptide-protein interaction prediction; no numeric metrics stated in abstract.
Impact
Provides a working tool for peptide-protein interaction prediction and binding residue identification.
Record
| Venue | Nature Communications |
|---|---|
| Published | 2021 |
| Work type | article |
| Authors | Yipin Lei, Shuya Li, Ziyi Liu, Fang Wan, Tingzhong Tian, Shao Li, Dan Yang Zhao, Jianyang Zeng |
| Citations | 222 (OpenAlex, at import time) |
| References | 60 |
| Model or method | CAMP (deep learning framework) |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1038/s41467-021-25772-4 |
| Open access | gold |
| Keywords | deep learning, peptide-protein interactions, binding residues, CAMP, peptide therapeutics |
Importance rating
real but narrower advance
Peptide-protein interactions are crucial for peptide therapeutics design per abstract; useful drug-discovery capability but no scale or impact numbers stated.