Drug-target interaction prediction based on graph convolutional autoencoder with dynamic weighting residual GCN

Background The exploration of drug-target interactions (DTIs) is a critical step in drug discovery and drug repurposing. Recently, network-based methods have emerged as a prominent research area for predicting DTIs. These methods excel by extracting both topological and feature information from DTIs...

Full description

Saved in:
Bibliographic Details
Published in:BMC bioinformatics Vol. 26; no. 1; pp. 200 - 29
Main Authors: Zeng, Ming, Wang, Min, Xie, Fuqiang, Ji, Zhiwei
Format: Journal Article
Language:English
Published: London BioMed Central 29.07.2025
BioMed Central Ltd
Springer Nature B.V
BMC
Subjects:
Algorithms
Autoencoder
Bioinformatics
Bioinformatics and chemoinformatics in drug discovery
Biomedical and Life Sciences
Case studies
Computational Biology - methods
Computational Biology/Bioinformatics
Computer Appl. in Life Sciences
Datasets
Deep learning
Drug development
Drug discovery
Drug Discovery - methods
Drug interactions
Drug Repositioning
Drug-target interaction
Dual self-supervised joint training mechanism
Dynamic weighting convolutional residual connection
Generative adversarial network
Graph convolutional autoencoder
Graph neural networks
Humans
Learning
Life Sciences
Ligands
Machine learning
Microarrays
Neural networks
Neural Networks, Computer
Optimization
Pandemics
Pharmaceutical research
Predictions
Proteins
R&D
Representations
Research & development
Technology application
Training
Weighting
China
New York
Dynamic weighting convolutional residual connection
Graph convolutional autoencoder
Dual self-supervised joint training mechanism
Drug-target interaction
Generative adversarial network
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 The exploration of drug-target interactions (DTIs) is a critical step in drug discovery and drug repurposing. Recently, network-based methods have emerged as a prominent research area for predicting DTIs. These methods excel by extracting both topological and feature information from DTIs networks, thereby achieving superior DTIs prediction performance. However, the majority of existing GCN-based methods utilize shallow graph neural networks, which are incapable of extracting higher-level semantic information. Additionally, the current training of models lacks an effective guiding mechanism, leading to the insufficient improvement of network’s representation capabilities. Results In this paper, we propose a graph convolutional autoencoder model, named DDGAE, for DTIs prediction. We develop a DWR-GCN module, which incorporates dynamic weighting graph convolution with residual connection, to improve the representation capability for DTI heterogeneous networks. Further, to improve the learning efficiency of the model, we devise a dual self-supervised joint training mechanism. Specifically, this mechanism integrates DWR-GCN and a graph convolutional autoencoder into a cohesive system, enhancing both the learning performance and stability of DDGAE. Conclusion Experimental results show that DDGAE significantly outperforms several SOTA models in DTIs prediction, achieving optimal performance and the reliability of our method is verified by case study.
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/s12859-025-06198-x