Protein-Protein Interaction Interface Residue Pair Prediction Based on Deep Learning Architecture
importance 5/10
ai assisted
Machine Learning in Bioinformatics protein science stage: research
Problem
Correctly predicting which residue pairs form the interface between two interacting proteins remains an open question.
Why it matters
Interface prediction guides practical experiments in the life sciences and drug discovery.
What the AI did
Developed a multi-layered LSTM deep network using nine amino-acid feature descriptors to discriminate interface from non-interface residue pairs.
Results
not stated in source
Impact
Provides a deep learning method for protein interface residue pair prediction.
Record
| Venue | IEEE Transactions on Computational Biology and Bioinformatics |
|---|---|
| Published | 2017 |
| Work type | article |
| Authors | Zhenni Zhao, Xinqi Gong |
| Citations | 38 (OpenAlex, at import time) |
| References | 20 |
| Model or method | multi-layered LSTM networks |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1109/tcbb.2017.2706682 |
| Open access | closed |
| Keywords | LSTM, protein-protein interaction, interface residues, deep learning, feature descriptors |
Importance rating
5
real but narrower advance
Interface residue pair prediction aids life-science experiments and drug discovery, but abstract gives no scale of affected populations or breakthrough claim; a useful methodological advance.