GADTI: Graph Autoencoder Approach for DTI Prediction From Heterogeneous Network.

Liu, Z; Chen, Q; Lan, W; Pan, H; Hao, X; Pan, S

GADTI: Graph Autoencoder Approach for DTI Prediction From Heterogeneous Network.

Liu, Z Chen, Q Lan, W Pan, H Hao, X Pan, S

Permalink

Publisher:: FRONTIERS MEDIA SA
Publication Type:: Journal Article
Citation:: Front Genet, 2021, 12, pp. 650821
Issue Date:: 2021

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download Published versionAdobe PDF (1.45 MB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Liu, Z
dc.contributor.author	Chen, Q
dc.contributor.author	Lan, W
dc.contributor.author	Pan, H
dc.contributor.author	Hao, X
dc.contributor.author	Pan, S https://orcid.org/0000-0003-0794-527X
dc.date.accessioned	2022-03-25T04:28:07Z
dc.date.available	2021-03-12
dc.date.available	2022-03-25T04:28:07Z
dc.date.issued	2021
dc.identifier.citation	Front Genet, 2021, 12, pp. 650821
dc.identifier.issn	1664-8021
dc.identifier.issn	1664-8021
dc.identifier.uri	http://hdl.handle.net/10453/155558
dc.description.abstract	Identifying drug-target interaction (DTI) is the basis for drug development. However, the method of using biochemical experiments to discover drug-target interactions has low coverage and high costs. Many computational methods have been developed to predict potential drug-target interactions based on known drug-target interactions, but the accuracy of these methods still needs to be improved. In this article, a graph autoencoder approach for DTI prediction (GADTI) was proposed to discover potential interactions between drugs and targets using a heterogeneous network, which integrates diverse drug-related and target-related datasets. Its encoder consists of two components: a graph convolutional network (GCN) and a random walk with restart (RWR). And the decoder is DistMult, a matrix factorization model, using embedding vectors from encoder to discover potential DTIs. The combination of GCN and RWR can provide nodes with more information through a larger neighborhood, and it can also avoid over-smoothing and computational complexity caused by multi-layer message passing. Based on the 10-fold cross-validation, we conduct three experiments in different scenarios. The results show that GADTI is superior to the baseline methods in both the area under the receiver operator characteristic curve and the area under the precision-recall curve. In addition, based on the latest Drugbank dataset (V5.1.8), the case study shows that 54.8% of new approved DTIs are predicted by GADTI.
dc.format	Electronic-eCollection
dc.language	eng
dc.publisher	FRONTIERS MEDIA SA
dc.relation.ispartof	Front Genet
dc.relation.isbasedon	10.3389/fgene.2021.650821
dc.rights	info:eu-repo/semantics/openAccess
dc.subject	0604 Genetics, 1103 Clinical Sciences, 1801 Law
dc.title	GADTI: Graph Autoencoder Approach for DTI Prediction From Heterogeneous Network.
dc.type	Journal Article
utslib.citation.volume	12
utslib.location.activity	Switzerland
utslib.for	0604 Genetics
utslib.for	1103 Clinical Sciences
utslib.for	1801 Law
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
utslib.copyright.status	open_access	*
dc.date.updated	2022-03-25T04:28:01Z
pubs.publication-status	Published online
pubs.volume	12

Abstract:

Identifying drug-target interaction (DTI) is the basis for drug development. However, the method of using biochemical experiments to discover drug-target interactions has low coverage and high costs. Many computational methods have been developed to predict potential drug-target interactions based on known drug-target interactions, but the accuracy of these methods still needs to be improved. In this article, a graph autoencoder approach for DTI prediction (GADTI) was proposed to discover potential interactions between drugs and targets using a heterogeneous network, which integrates diverse drug-related and target-related datasets. Its encoder consists of two components: a graph convolutional network (GCN) and a random walk with restart (RWR). And the decoder is DistMult, a matrix factorization model, using embedding vectors from encoder to discover potential DTIs. The combination of GCN and RWR can provide nodes with more information through a larger neighborhood, and it can also avoid over-smoothing and computational complexity caused by multi-layer message passing. Based on the 10-fold cross-validation, we conduct three experiments in different scenarios. The results show that GADTI is superior to the baseline methods in both the area under the receiver operator characteristic curve and the area under the precision-recall curve. In addition, based on the latest Drugbank dataset (V5.1.8), the case study shows that 54.8% of new approved DTIs are predicted by GADTI.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/155558