Recent Applications of Deep Learning Methods on Evolution- and Contact-Based Protein Structure Prediction
Problem
Predicting proteins' 3D structures from sequence is difficult; deep learning methods were applied to interpret how sequences and homology govern inter-residue contacts and structural organization.
Why it matters
Protein structures underpin drug discovery and the study of unknown protein functions.
What the AI did
The paper reviews deep learning methods for protein structure prediction, noting their significant impact on recent CASP13 and CASP14 competitions and their potential for drug-target interactions.
Results
not stated in source
Impact
The review states deep learning is expected to play crucial roles in protein structural bioinformatics and drug discovery.
Record
| Venue | International Journal of Molecular Sciences |
|---|---|
| Published | 2021 |
| Work type | article |
| Authors | Donghyuk Suh, Jai Woo Lee, Sun Choi, Yoonji Lee |
| Citations | 25 (OpenAlex, at import time) |
| References | 129 |
| Model or method | not stated in source |
| Organization | not stated in source |
| Primary source | https://doi.org/10.3390/ijms22116032 |
| Open access | gold |
| Keywords | deep learning, protein structure prediction, CASP13, CASP14, contact prediction, drug discovery |
Importance rating
major — millions of lives, an industry or a field
Protein structure prediction is a foundational scientific field underpinning drug discovery and unknown protein function study; abstract cites major CASP13/14 impact, but no scale is quantified.