Drug-target interaction prediction based on spatial consistency constraint and graph convolutional autoencoder

Background Drug-target interaction (DTI) prediction plays an important role in drug discovery and repositioning. However, most of the computational methods used for identifying relevant DTIs do not consider the invariance of the nearest neighbour relationships between drugs or targets. In other word...

Full description

Saved in:
Bibliographic Details
Published in:BMC bioinformatics Vol. 24; no. 1; pp. 151 - 21
Main Authors: Chen, Peng, Zheng, Haoran
Format: Journal Article
Language:English
Published: London BioMed Central 17.04.2023
BioMed Central Ltd
Springer Nature B.V
BMC
Subjects:
Algorithms
Analysis
Bioinformatics
Biomedical and Life Sciences
Computational Biology/Bioinformatics
Computer Appl. in Life Sciences
Computer applications
Datasets
Deep learning
Drug Development - methods
Drug discovery
Drug Discovery - methods
Drug interactions
Drug-target interaction
Drugs
Embedding
Graph convolutional autoencoder
Graphical representations
Invariance
Life Sciences
Ligands
Machine learning
Medical care, Cost of
Methods
Microarrays
Neural networks
Nodes
Polypharmacy
Predictions
Proteins
Spatial consistency constraint
China
Deep learning
Spatial consistency constraint
Graph convolutional autoencoder
Drug-target interaction
ISSN:1471-2105, 1471-2105
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Background Drug-target interaction (DTI) prediction plays an important role in drug discovery and repositioning. However, most of the computational methods used for identifying relevant DTIs do not consider the invariance of the nearest neighbour relationships between drugs or targets. In other words, they do not take into account the invariance of the topological relationships between nodes during representation learning. It may limit the performance of the DTI prediction methods. Results Here, we propose a novel graph convolutional autoencoder-based model, named SDGAE, to predict DTIs. As the graph convolutional network cannot handle isolated nodes in a network, a pre-processing step was applied to reduce the number of isolated nodes in the heterogeneous network and facilitate effective exploitation of the graph convolutional network. By maintaining the graph structure during representation learning, the nearest neighbour relationships between nodes in the embedding space remained as close as possible to the original space. Conclusions Overall, we demonstrated that SDGAE can automatically learn more informative and robust feature vectors of drugs and targets, thus exhibiting significantly improved predictive accuracy for DTIs.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:1471-2105
1471-2105
DOI:10.1186/s12859-023-05275-3