GADTI: Graph Autoencoder Approach for DTI Prediction From Heterogeneous Network

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 o...

Full description

Saved in:
Bibliographic Details
Published in:Frontiers in genetics Vol. 12; p. 650821
Main Authors: Liu, Zhixian, Chen, Qingfeng, Lan, Wei, Pan, Haiming, Hao, Xinkun, Pan, Shirui
Format: Journal Article
Language:English
Published: Switzerland Frontiers Media S.A 09.04.2021
Subjects:
ISSN:1664-8021, 1664-8021
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
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.
AbstractList 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.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.
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.
Author Pan, Haiming
Lan, Wei
Pan, Shirui
Liu, Zhixian
Hao, Xinkun
Chen, Qingfeng
AuthorAffiliation 4 Department of Data Science and AI, Monash University , Melbourne, VIC , Australia
1 School of Medical, Guangxi University , Nanning , China
2 School of Electronics and Information Engineering, Beibu Gulf University , Qinzhou , China
3 School of Computer, Electronic and Information, Guangxi University , Nanning , China
AuthorAffiliation_xml – name: 2 School of Electronics and Information Engineering, Beibu Gulf University , Qinzhou , China
– name: 3 School of Computer, Electronic and Information, Guangxi University , Nanning , China
– name: 4 Department of Data Science and AI, Monash University , Melbourne, VIC , Australia
– name: 1 School of Medical, Guangxi University , Nanning , China
Author_xml – sequence: 1
  givenname: Zhixian
  surname: Liu
  fullname: Liu, Zhixian
– sequence: 2
  givenname: Qingfeng
  surname: Chen
  fullname: Chen, Qingfeng
– sequence: 3
  givenname: Wei
  surname: Lan
  fullname: Lan, Wei
– sequence: 4
  givenname: Haiming
  surname: Pan
  fullname: Pan, Haiming
– sequence: 5
  givenname: Xinkun
  surname: Hao
  fullname: Hao, Xinkun
– sequence: 6
  givenname: Shirui
  surname: Pan
  fullname: Pan, Shirui
BackLink https://www.ncbi.nlm.nih.gov/pubmed/33912218$$D View this record in MEDLINE/PubMed
BookMark eNp1kU1v1DAQhi1URD_oD-CCfOSyi7-S2ByQVoVuV6ooh3K2JvZkNyUbB8dbxL-vs9uiFglfbI1nnndm3lNy1IceCXnH2VxKbT42a-xxLpjg87JgWvBX5ISXpZrpHDp69j4m5-N4x_JRRkqp3pBjKQ0XgusTcrNcfLldfaLLCMOGLnYpYO-Cx0gXwxADuA1tQqQ5h36P6FuX2tDTyxi29AoTxjB1EXYj_Ybpd4g_35LXDXQjnj_eZ-TH5dfbi6vZ9c1ydbG4njlVFmkGQnlQzBhvPFeyaoxypjAATCN64bnPjbsKHSiQNatN00Ae2oGpkFeslGdkdeD6AHd2iO0W4h8boLX7QIhrCzG1rkMrTY2IXHjDlRK1NEIwV2LZlFyjli6zPh9Yw67eonfYpwjdC-jLn77d2HW4t5pVQmiZAR8eATH82uGY7LYdHXYd7HdjRcFNZUyhpr7fP9f6K_LkSE6oDgkuhnGM2FjXJpi2nqXbznJmJ_vt3n472W8P9udK_k_lE_z_NQ_WwbNE
CitedBy_id crossref_primary_10_1109_JBHI_2023_3240305
crossref_primary_10_1016_j_artmed_2024_102778
crossref_primary_10_1016_j_ymeth_2024_01_018
crossref_primary_10_1186_s12915_025_02231_w
crossref_primary_10_1038_s41598_024_76367_0
crossref_primary_10_1089_cmb_2023_0135
crossref_primary_10_1109_TCBB_2023_3339189
crossref_primary_10_1186_s12859_023_05275_3
crossref_primary_10_1186_s12859_025_06075_7
crossref_primary_10_1007_s12539_025_00697_4
crossref_primary_10_1186_s12859_023_05496_6
crossref_primary_10_1186_s12859_025_06198_x
crossref_primary_10_1109_ACCESS_2022_3199667
crossref_primary_10_1186_s12915_025_02340_6
crossref_primary_10_3389_fgene_2021_718915
crossref_primary_10_1186_s12859_022_05119_6
crossref_primary_10_1039_D4MO00117F
Cites_doi 10.1038/msb.2009.98
10.1145/2487575.2487670
10.1109/TCBB.2019.2936476
10.1093/nar/gks994
10.2174/1389203721666200702145701
10.1101/539643
10.1016/j.neucom.2016.03.080
10.1021/acs.jproteome.6b00618
10.1093/bioinformatics/bts670
10.1145/2623330.2623732
10.3389/fgene.2018.00248
10.1093/bioinformatics/btz111
10.3389/fbioe.2019.00305
10.1021/ci100050t
10.1039/c2mb00002d
10.1093/bioinformatics/btu403
10.1093/nar/gkn892
10.1093/bioinformatics/btx160
10.1093/bib/bby117
10.1109/TKDE.2018.2807452
10.1016/j.ygeno.2018.12.007
10.1186/s13321-015-0089-z
10.3390/jpm10030128
10.1093/bioinformatics/bty543
10.1093/bioinformatics/btx731
10.1093/bioinformatics/btz600
10.1371/journal.pcbi.1000397
10.1016/0022-2836(81)90087-5
10.1145/3219819.3219890
10.1093/bioinformatics/bty294
10.1109/TCBB.2020.3034910
10.1021/acs.jproteome.9b00411
10.1609/aaai.v32i1.11604
10.1007/s10115-007-0094-2
10.1007/s10822-016-9938-8
10.1371/journal.pcbi.1002503
10.1093/nar/gkq1126
10.1038/s41467-017-00680-8
10.1093/bib/bbz157
10.1093/bioinformatics/bty440
ContentType Journal Article
Copyright Copyright © 2021 Liu, Chen, Lan, Pan, Hao and Pan.
Copyright © 2021 Liu, Chen, Lan, Pan, Hao and Pan. 2021 Liu, Chen, Lan, Pan, Hao and Pan
Copyright_xml – notice: Copyright © 2021 Liu, Chen, Lan, Pan, Hao and Pan.
– notice: Copyright © 2021 Liu, Chen, Lan, Pan, Hao and Pan. 2021 Liu, Chen, Lan, Pan, Hao and Pan
DBID AAYXX
CITATION
NPM
7X8
5PM
DOA
DOI 10.3389/fgene.2021.650821
DatabaseName CrossRef
PubMed
MEDLINE - Academic
PubMed Central (Full Participant titles)
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
PubMed
MEDLINE - Academic
DatabaseTitleList MEDLINE - Academic

CrossRef

PubMed
Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
– sequence: 2
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 3
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Biology
EISSN 1664-8021
ExternalDocumentID oai_doaj_org_article_39beee12d91442b39220c6e6f618e83c
PMC8072283
33912218
10_3389_fgene_2021_650821
Genre Journal Article
GroupedDBID 53G
5VS
9T4
AAFWJ
AAKDD
AAYXX
ACGFS
ADBBV
ADRAZ
AFPKN
ALMA_UNASSIGNED_HOLDINGS
AOIJS
BAWUL
BCNDV
CITATION
DIK
EMOBN
GROUPED_DOAJ
GX1
HYE
KQ8
M48
M~E
OK1
PGMZT
RNS
RPM
ACXDI
IPNFZ
NPM
RIG
7X8
5PM
ID FETCH-LOGICAL-c465t-a24da4099d9d1437f94c959aa08eed2d1d021c7eca4a3b0b9ffa389ca97e17063
IEDL.DBID DOA
ISICitedReferencesCount 33
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000643698200001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1664-8021
IngestDate Fri Oct 03 12:53:36 EDT 2025
Thu Aug 21 18:23:12 EDT 2025
Thu Sep 04 17:28:36 EDT 2025
Thu Apr 03 06:58:09 EDT 2025
Tue Nov 18 22:13:48 EST 2025
Sat Nov 29 03:02:19 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Keywords graph convolutional network
random walk
drug-target interaction prediction
autoencoder
heterogeneous network
network embedding
Language English
License Copyright © 2021 Liu, Chen, Lan, Pan, Hao and Pan.
This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c465t-a24da4099d9d1437f94c959aa08eed2d1d021c7eca4a3b0b9ffa389ca97e17063
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
Edited by: Xiangxiang Zeng, Hunan University, China
This article was submitted to Computational Genomics, a section of the journal Frontiers in Genetics
Reviewed by: Khanh N. Q. Le, Taipei Medical University, Taiwan; Yusen Zhang, Shandong University, China
OpenAccessLink https://doaj.org/article/39beee12d91442b39220c6e6f618e83c
PMID 33912218
PQID 2519799546
PQPubID 23479
ParticipantIDs doaj_primary_oai_doaj_org_article_39beee12d91442b39220c6e6f618e83c
pubmedcentral_primary_oai_pubmedcentral_nih_gov_8072283
proquest_miscellaneous_2519799546
pubmed_primary_33912218
crossref_citationtrail_10_3389_fgene_2021_650821
crossref_primary_10_3389_fgene_2021_650821
PublicationCentury 2000
PublicationDate 2021-04-09
PublicationDateYYYYMMDD 2021-04-09
PublicationDate_xml – month: 04
  year: 2021
  text: 2021-04-09
  day: 09
PublicationDecade 2020
PublicationPlace Switzerland
PublicationPlace_xml – name: Switzerland
PublicationTitle Frontiers in genetics
PublicationTitleAlternate Front Genet
PublicationYear 2021
Publisher Frontiers Media S.A
Publisher_xml – name: Frontiers Media S.A
References B23
Tong (B39) 2008; 14
Wen (B42) 2017; 16
Rogers (B34) 2010; 50
Seal (B35) 2015; 7
Ma (B26) 2018
Wan (B40) 2019; 35
Su (B38) 2018; 21
Smith (B37) 1981; 147
Cai (B2) 2017; 30
Pan (B32) 2018
Ying (B45) 2018
Luo (B25) 2017; 8
B31
Gligorijevic (B7) 2018; 33
Perozzi (B33) 2014
Davis (B6) 2013; 41
Goodfellow (B8) 2014
Grover (B9) 2016
Zong (B49) 2017; 33
Zitnik (B48) 2018; 34
Cheng (B5) 2012; 8
Le (B22) 2019; 7
Jin (B10) 2019
B44
Mohamed (B28) 2019; 36
Knox (B16) 2011; 39
Lan (B18) 2020
Le (B20) 2019; 18
Mei (B27) 2013; 29
Chen (B3) 2019
Shi (B36) 2019; 111
B50
Karimi (B11) 2019; 35
Xu (B43) 2018
Kearnes (B12) 2016; 30
B14
B15
Zheng (B46) 2013
Zhu (B47) 2018; 9
Lan (B19) 2016; 206
Liu (B24) 2020; 21
Chen (B4) 2012; 8
Bagherian (B1) 2020; 22
Wang (B41) 2014; 30
Le (B21) 2020; 10
Kuhn (B17) 2010; 6
Nagamine (B29) 2009; 5
Olayan (B30) 2018; 34
Keshava Prasad (B13) 2009; 37
References_xml – volume: 6
  start-page: 343
  year: 2010
  ident: B17
  article-title: A side effect resource to capture phenotypic effects of drugs
  publication-title: Mol. Syst. Biol.
  doi: 10.1038/msb.2009.98
– start-page: 2609
  volume-title: The 27th International Joint Conference on Artificial Intelligence
  year: 2018
  ident: B32
  article-title: Adversarially regularized graph autoencoder for graph embedding,
– start-page: 1025
  volume-title: The 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
  year: 2013
  ident: B46
  article-title: Collaborative matrix factorization with multiple similarities for predicting drug-target interactions,
  doi: 10.1145/2487575.2487670
– year: 2019
  ident: B3
  article-title: ILDMSF: inferring associations between long non-coding RNA and disease based on multi-similarity fusion
  publication-title: IEEE/ACM Trans. Comput. Biol. Bioinform.
  doi: 10.1109/TCBB.2019.2936476
– volume: 41
  start-page: D1104
  year: 2013
  ident: B6
  article-title: The comparative toxicogenomics database: update 2013
  publication-title: Nucleic Acids Res.
  doi: 10.1093/nar/gks994
– volume: 21
  start-page: 1
  year: 2020
  ident: B24
  article-title: A survey of network embedding for drug analysis and prediction
  publication-title: Curr. Protein Peptide Sci.
  doi: 10.2174/1389203721666200702145701
– ident: B50
  doi: 10.1101/539643
– volume: 206
  start-page: 50
  year: 2016
  ident: B19
  article-title: Predicting drug-target interaction using positive-unlabeled learning
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2016.03.080
– volume-title: The 7th International Conference on Learning Representations: OpenReview.net
  year: 2019
  ident: B10
  article-title: Learning multimodal graph-to-graph translation for molecular optimization,
– volume: 16
  start-page: 1401
  year: 2017
  ident: B42
  article-title: Deep-learning-based drug-target interaction prediction
  publication-title: J. Proteome Res.
  doi: 10.1021/acs.jproteome.6b00618
– ident: B31
– volume: 29
  start-page: 238
  year: 2013
  ident: B27
  article-title: Drug-target interaction prediction by learning from local information and neighbors
  publication-title: Bioinformatics
  doi: 10.1093/bioinformatics/bts670
– start-page: 701
  volume-title: The 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
  year: 2014
  ident: B33
  article-title: DeepWalk: online learning of social representations,
  doi: 10.1145/2623330.2623732
– volume: 9
  start-page: 248
  year: 2018
  ident: B47
  article-title: Prediction of drug-gene interaction by Using Metapath2vec
  publication-title: Front. Genet.
  doi: 10.3389/fgene.2018.00248
– volume: 35
  start-page: 3329
  year: 2019
  ident: B11
  article-title: DeepAffinity: interpretable deep learning of compound-protein affinity through unified recurrent and convolutional neural networks
  publication-title: Bioinformatics
  doi: 10.1093/bioinformatics/btz111
– volume: 7
  start-page: 305
  year: 2019
  ident: B22
  article-title: Classifying promoters by interpreting the hidden information of DNA sequences via deep learning and combination of continuous fasttext N-grams
  publication-title: Front. Bioeng. Biotechnol.
  doi: 10.3389/fbioe.2019.00305
– volume: 50
  start-page: 742
  year: 2010
  ident: B34
  article-title: Extended-connectivity fingerprints
  publication-title: J Chem Inf Model
  doi: 10.1021/ci100050t
– ident: B44
– volume: 8
  start-page: 1970
  year: 2012
  ident: B4
  article-title: Drug-target interaction prediction by random walk on the heterogeneous network
  publication-title: Mol. Biosyst.
  doi: 10.1039/c2mb00002d
– volume: 30
  start-page: 2923
  year: 2014
  ident: B41
  article-title: Drug repositioning by integrating target information through a heterogeneous network model
  publication-title: Bioinformatics
  doi: 10.1093/bioinformatics/btu403
– volume: 37
  start-page: D767
  year: 2009
  ident: B13
  article-title: Human protein reference database 2009 update
  publication-title: Nucleic Acids Res.
  doi: 10.1093/nar/gkn892
– volume: 33
  start-page: 2337
  year: 2017
  ident: B49
  article-title: Deep mining heterogeneous networks of biomedical linked data to predict novel drug-target associations
  publication-title: Bioinformatics
  doi: 10.1093/bioinformatics/btx160
– volume: 21
  start-page: 182
  year: 2018
  ident: B38
  article-title: Network embedding in biomedical data science
  publication-title: Brief. Bioinform.
  doi: 10.1093/bib/bby117
– ident: B14
– volume: 30
  start-page: 1616
  year: 2017
  ident: B2
  article-title: A comprehensive survey of graph embedding: problems, techniques and applications
  publication-title: IEEE Trans. Knowl. Data Eng.
  doi: 10.1109/TKDE.2018.2807452
– volume: 111
  start-page: 1839
  year: 2019
  ident: B36
  article-title: Predicting drug-target interactions using Lasso with random forest based on evolutionary information and chemical structure
  publication-title: Genomics
  doi: 10.1016/j.ygeno.2018.12.007
– volume: 7
  start-page: 40
  year: 2015
  ident: B35
  article-title: Optimizing drug-target interaction prediction based on random walk on heterogeneous networks
  publication-title: J. Cheminform.
  doi: 10.1186/s13321-015-0089-z
– volume: 10
  start-page: 128
  year: 2020
  ident: B21
  article-title: XGBoost improves classification of MGMT promoter methylation status in IDH1 wildtype glioblastoma
  publication-title: J Pers. Med.
  doi: 10.3390/jpm10030128
– volume: 35
  start-page: 104
  year: 2019
  ident: B40
  article-title: NeoDTI: neural integration of neighbor information from a heterogeneous network for discovering new drug-target interactions
  publication-title: Bioinformatics
  doi: 10.1093/bioinformatics/bty543
– volume: 34
  start-page: 1164
  year: 2018
  ident: B30
  article-title: DDR: Efficient computational method to predict drug-target interactions using graph mining and machine learning approaches
  publication-title: Bioinformatics
  doi: 10.1093/bioinformatics/btx731
– volume: 36
  start-page: 603
  year: 2019
  ident: B28
  article-title: Discovering protein drug targets using knowledge graph embeddings
  publication-title: Bioinformatics
  doi: 10.1093/bioinformatics/btz600
– volume: 5
  start-page: e1000397
  year: 2009
  ident: B29
  article-title: Integrating statistical predictions and experimental verifications for enhancing protein-chemical interaction predictions in virtual screening
  publication-title: PLOS Comput. Biol.
  doi: 10.1371/journal.pcbi.1000397
– volume: 147
  start-page: 195
  year: 1981
  ident: B37
  article-title: Identification of common molecular subsequences
  publication-title: J. Mol. Biol.
  doi: 10.1016/0022-2836(81)90087-5
– start-page: 974
  volume-title: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
  year: 2018
  ident: B45
  article-title: Graph convolutional neural networks for web-scale recommender systems,
  doi: 10.1145/3219819.3219890
– volume: 34
  start-page: 457
  year: 2018
  ident: B48
  article-title: Modeling polypharmacy side effects with graph convolutional networks
  publication-title: Bioinformatics
  doi: 10.1093/bioinformatics/bty294
– year: 2020
  ident: B18
  article-title: LDICDL: LncRNA-disease association identification based on Collaborative Deep Learning
  publication-title: IEEE/ACM Trans. Comput. Biol. Bioinform.
  doi: 10.1109/TCBB.2020.3034910
– start-page: 5449
  volume-title: The 35th International Conference on Machine Learning
  year: 2018
  ident: B43
  article-title: Representation learning on graphs with jumping knowledge networks,
– volume: 18
  start-page: 3503
  year: 2019
  ident: B20
  article-title: Fertility-GRU: identifying fertility-related proteins by incorporating deep-gated recurrent units and original position-specific scoring matrix profiles
  publication-title: J Proteome Res
  doi: 10.1021/acs.jproteome.9b00411
– ident: B23
  doi: 10.1609/aaai.v32i1.11604
– volume: 14
  start-page: 327
  year: 2008
  ident: B39
  article-title: Random walk with restart: fast solutions and applications
  publication-title: Knowl. Inform. Syst.
  doi: 10.1007/s10115-007-0094-2
– start-page: 855
  volume-title: Conference on Knowledge Discovery and Data Mining
  year: 2016
  ident: B9
  article-title: node2vec: Scalable Feature Learning for Networks,
– volume: 30
  start-page: 1
  year: 2016
  ident: B12
  article-title: Molecular graph convolutions: moving beyond fingerprints
  publication-title: J. Comput. Aided Mol. Des.
  doi: 10.1007/s10822-016-9938-8
– volume: 8
  start-page: e1002503
  year: 2012
  ident: B5
  article-title: Prediction of drug-target interactions and drug repositioning via network-based inference
  publication-title: PLoS Comput. Biol.
  doi: 10.1371/journal.pcbi.1002503
– start-page: 3477
  volume-title: The 27th International Joint Conference on Artificial Intelligence
  year: 2018
  ident: B26
  article-title: Drug similarity integration through attentive multi-view graph auto-encoders,
– volume-title: Proceedings of the 27th International Conference on Neural Information Processing Systems
  year: 2014
  ident: B8
  article-title: Generative adversarial nets,
– volume: 39
  start-page: D1035
  year: 2011
  ident: B16
  article-title: DrugBank 3.0: a comprehensive resource for ‘omics’ research on drugs
  publication-title: Nucleic Acids Res.
  doi: 10.1093/nar/gkq1126
– volume: 8
  start-page: 573
  year: 2017
  ident: B25
  article-title: A network integration approach for drug-target interaction prediction and computational drug repositioning from heterogeneous information
  publication-title: Nat. Commun.
  doi: 10.1038/s41467-017-00680-8
– ident: B15
– volume: 22
  start-page: 247
  year: 2020
  ident: B1
  article-title: Machine learning approaches and databases for prediction of drug-target interaction: a survey paper
  publication-title: Brief. Bioinform.
  doi: 10.1093/bib/bbz157
– volume: 33
  start-page: 3873
  year: 2018
  ident: B7
  article-title: deepNF: Deep network fusion for protein function prediction
  publication-title: Bioinformatics
  doi: 10.1093/bioinformatics/bty440
SSID ssj0000493334
Score 2.4079034
Snippet Identifying drug–target interaction (DTI) is the basis for drug development. However, the method of using biochemical experiments to discover drug-target...
Identifying drug-target interaction (DTI) is the basis for drug development. However, the method of using biochemical experiments to discover drug-target...
SourceID doaj
pubmedcentral
proquest
pubmed
crossref
SourceType Open Website
Open Access Repository
Aggregation Database
Index Database
Enrichment Source
StartPage 650821
SubjectTerms autoencoder
drug-target interaction prediction
Genetics
graph convolutional network
heterogeneous network
network embedding
random walk
Title GADTI: Graph Autoencoder Approach for DTI Prediction From Heterogeneous Network
URI https://www.ncbi.nlm.nih.gov/pubmed/33912218
https://www.proquest.com/docview/2519799546
https://pubmed.ncbi.nlm.nih.gov/PMC8072283
https://doaj.org/article/39beee12d91442b39220c6e6f618e83c
Volume 12
WOSCitedRecordID wos000643698200001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 1664-8021
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000493334
  issn: 1664-8021
  databaseCode: DOA
  dateStart: 20100101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 1664-8021
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000493334
  issn: 1664-8021
  databaseCode: M~E
  dateStart: 20100101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Nb9QwEB1BBRIXxDfhozISJ6TQxPbaGW4LdFsOLD0UaW-RYzuiiG6qdBeJC7-dmThd7SIEFy45JI4yeTPOPMuTNwAvg_IoK6Nzh97kutIxx4kNuSduKh1lEOlTswk7n1eLBZ5stfrimrAkD5yAO1DYxBhLGZCov2woncvCm2haU1axUp6_voXFrcXU18R7lVI6bWPSKgwPWvIHy2LK8jWTElnuJKJBr_9PJPP3Wsmt5DO7A7dH1iimydq7cC0u78HN1Efyx334dDR9f_rhjThi9WkxXa86lqcMsRfTUTJcEDcVNEac9Lwzw94Qs747F8dcDtOx1d36UsxTUfgD-Dw7PH13nI-dEnKvzWSVO6kDAYsYMBABsi1qjxN0rqgoB8pQBnpvb6N32qmmaLBtHYHiHdrI-jnqIewtu2V8DMJHbIsyKuNd1K3WDc1Y206M1z40zjQZFFew1X6UEeduFt9qWk4w0vWAdM1I1wnpDF5tbrlIGhp_G_yWfbEZyPLXwwkKinoMivpfQZHBiytP1jRdeA_EDTjWw4-6rIFnMniUPLt5lFJYSqI8Gdgdn-_YsntlefZlkOSuCss6Qk_-h_FP4RbjMZQH4TPYW_Xr-Bxu-O-rs8t-H67bRbU_RDsdP_48_AUjNASl
linkProvider Directory of Open Access Journals
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=GADTI%3A+Graph+Autoencoder+Approach+for+DTI+Prediction+From+Heterogeneous+Network&rft.jtitle=Frontiers+in+genetics&rft.au=Liu%2C+Zhixian&rft.au=Chen%2C+Qingfeng&rft.au=Lan%2C+Wei&rft.au=Pan%2C+Haiming&rft.date=2021-04-09&rft.issn=1664-8021&rft.eissn=1664-8021&rft.volume=12&rft.spage=650821&rft_id=info:doi/10.3389%2Ffgene.2021.650821&rft_id=info%3Apmid%2F33912218&rft.externalDocID=33912218
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1664-8021&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1664-8021&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1664-8021&client=summon