Deep learning in target prediction and drug repositioning: Recent advances and challenges

•Basic principles of commonly used deep learning architectures.•Drug–target interactions based deep learning approaches for drug repositioning.•Heterogeneous networks based deep learning approaches for drug repositioning.•Current challenges of deep learning in drug repositioning.•Possible ways to im...

Full description

Saved in:
Bibliographic Details
Published in:Drug discovery today 2022-07, Vol.27 (7), p.1796-1814
Main Authors: Yu, Jun-Lin, Dai, Qing-Qing, Li, Guo-Bo
Format: Article
Language:English
Subjects:
Deep learning
Drug discovery
Drug repositioning
Drug–target interaction
Heterogeneous network
Target prediction
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:•Basic principles of commonly used deep learning architectures.•Drug–target interactions based deep learning approaches for drug repositioning.•Heterogeneous networks based deep learning approaches for drug repositioning.•Current challenges of deep learning in drug repositioning.•Possible ways to improve deep learning methods for drug repositioning. Drug repositioning is an attractive strategy for discovering new therapeutic uses for approved or investigational drugs, with potentially shorter development timelines and lower development costs. Various computational methods have been used in drug repositioning, promoting the efficiency and success rates of this approach. Recently, deep learning (DL) has attracted wide attention for its potential in target prediction and drug repositioning. Here, we provide an overview of the basic principles of commonly used DL architectures and their applications in target prediction and drug repositioning, and discuss possible ways of dealing with current challenges to help achieve its expected potential for drug repositioning.
ISSN:1359-6446
1878-5832
DOI:10.1016/j.drudis.2021.10.010