GIAE-DTI: Predicting Drug-Target Interactions Based on Heterogeneous Network and GIN-Based Graph Autoencoder

Accurate prediction of drug-target interactions (DTIs) is essential for advancing drug discovery and repurposing. However, the sparsity of DTI data limits the effectiveness of existing computational methods, which primarily focus on sparse DTI networks and have poor performance in aggregating inform...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE journal of biomedical and health informatics Jg. 29; H. 11; S. 7896 - 7909
Hauptverfasser: Wang, Mengdi, Lei, Xiujuan, Liu, Lian, Chen, Jianrui, Wu, Fang-Xiang
Format: Journal Article
Sprache:Englisch
Veröffentlicht: United States IEEE 01.11.2025
Schlagworte:
ISSN:2168-2194, 2168-2208, 2168-2208
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Accurate prediction of drug-target interactions (DTIs) is essential for advancing drug discovery and repurposing. However, the sparsity of DTI data limits the effectiveness of existing computational methods, which primarily focus on sparse DTI networks and have poor performance in aggregating information from neighboring nodes and representing isolated nodes within the network. In this study, we propose a novel deep learning framework, named GIAE-DTI, which considers cross-modal similarity of drugs and targets and constructs a heterogeneous network for DTI prediction. Firstly, the model calculates the cross-modal similarity of drugs and proteins from the relationships among drugs, proteins, diseases, and side effects, and performs similarity integration by taking the average. Then, a drug-target heterogeneous network is constructed, including drug-drug interactions, protein-protein interactions, and drug-target interactions processed by weighted K nearest known neighbors. In the heterogeneous network, a graph autoencoder based on a graph isomorphism network is employed for feature extraction, while a dual decoder is utilized to achieve better self-supervised learning, resulting in latent feature representations for drugs and targets. Finally, a deep neural network is employed to predict DTIs. The experimental results indicate that on the benchmark dataset, GIAE-DTI achieves AUC and AUPR scores of 0.9533 and 0.9619, respectively, in DTI prediction, outperforming the current state-of-the-art methods. Additionally, case studies on four 5-hydroxytryptamine receptor-related targets and five drugs related to mental diseases show the great potential of the proposed method in practical applications.
AbstractList Accurate prediction of drug-target interactions (DTIs) is essential for advancing drug discovery and repurposing. However, the sparsity of DTI data limits the effectiveness of existing computational methods, which primarily focus on sparse DTI networks and have poor performance in aggregating information from neighboring nodes and representing isolated nodes within the network. In this study, we propose a novel deep learning framework, named GIAE-DTI, which considers cross-modal similarity of drugs and targets and constructs a heterogeneous network for DTI prediction. Firstly, the model calculates the cross-modal similarity of drugs and proteins from the relationships among drugs, proteins, diseases, and side effects, and performs similarity integration by taking the average. Then, a drug-target heterogeneous network is constructed, including drug-drug interactions, protein-protein interactions, and drug-target interactions processed by weighted K nearest known neighbors. In the heterogeneous network, a graph autoencoder based on a graph isomorphism network is employed for feature extraction, while a dual decoder is utilized to achieve better self-supervised learning, resulting in latent feature representations for drugs and targets. Finally, a deep neural network is employed to predict DTIs. The experimental results indicate that on the benchmark dataset, GIAE-DTI achieves AUC and AUPR scores of 0.9533 and 0.9619, respectively, in DTI prediction, outperforming the current state-of-the-art methods. Additionally, case studies on four 5-hydroxytryptamine receptor-related targets and five drugs related to mental diseases show the great potential of the proposed method in practical applications.
Accurate prediction of drug-target interactions (DTIs) is essential for advancing drug discovery and repurposing. However, the sparsity of DTI data limits the effectiveness of existing computational methods, which primarily focus on sparse DTI networks and have poor performance in aggregating information from neighboring nodes and representing isolated nodes within the network. In this study, we propose a novel deep learning framework, named GIAE-DTI, which considers cross-modal similarity of drugs and targets and constructs a heterogeneous network for DTI prediction. Firstly, the model calculates the cross-modal similarity of drugs and proteins from the relationships among drugs, proteins, diseases, and side effects, and performs similarity integration by taking the average. Then, a drug-target heterogeneous network is constructed, including drug-drug interactions, protein-protein interactions, and drug-target interactions processed by weighted K nearest known neighbors. In the heterogeneous network, a graph autoencoder based on a graph isomorphism network is employed for feature extraction, while a dual decoder is utilized to achieve better self-supervised learning, resulting in latent feature representations for drugs and targets. Finally, a deep neural network is employed to predict DTIs. The experimental results indicate that on the benchmark dataset, GIAE-DTI achieves AUC and AUPR scores of 0.9533 and 0.9619, respectively, in DTI prediction, outperforming the current state-of-the-art methods. Additionally, case studies on four 5-hydroxytryptamine receptor-related targets and five drugs related to mental diseases show the great potential of the proposed method in practical applications.Accurate prediction of drug-target interactions (DTIs) is essential for advancing drug discovery and repurposing. However, the sparsity of DTI data limits the effectiveness of existing computational methods, which primarily focus on sparse DTI networks and have poor performance in aggregating information from neighboring nodes and representing isolated nodes within the network. In this study, we propose a novel deep learning framework, named GIAE-DTI, which considers cross-modal similarity of drugs and targets and constructs a heterogeneous network for DTI prediction. Firstly, the model calculates the cross-modal similarity of drugs and proteins from the relationships among drugs, proteins, diseases, and side effects, and performs similarity integration by taking the average. Then, a drug-target heterogeneous network is constructed, including drug-drug interactions, protein-protein interactions, and drug-target interactions processed by weighted K nearest known neighbors. In the heterogeneous network, a graph autoencoder based on a graph isomorphism network is employed for feature extraction, while a dual decoder is utilized to achieve better self-supervised learning, resulting in latent feature representations for drugs and targets. Finally, a deep neural network is employed to predict DTIs. The experimental results indicate that on the benchmark dataset, GIAE-DTI achieves AUC and AUPR scores of 0.9533 and 0.9619, respectively, in DTI prediction, outperforming the current state-of-the-art methods. Additionally, case studies on four 5-hydroxytryptamine receptor-related targets and five drugs related to mental diseases show the great potential of the proposed method in practical applications.
Author Lei, Xiujuan
Wu, Fang-Xiang
Chen, Jianrui
Wang, Mengdi
Liu, Lian
Author_xml – sequence: 1
  givenname: Mengdi
  surname: Wang
  fullname: Wang, Mengdi
  organization: School of Computer Science, Shaanxi Normal University, Xi'an, China
– sequence: 2
  givenname: Xiujuan
  orcidid: 0000-0002-9901-1732
  surname: Lei
  fullname: Lei, Xiujuan
  email: xjlei@snnu.edu.cn
  organization: School of Computer Science, Shaanxi Normal University, Xi'an, China
– sequence: 3
  givenname: Lian
  orcidid: 0000-0001-5778-5230
  surname: Liu
  fullname: Liu, Lian
  organization: School of Computer Science, Shaanxi Normal University, Xi'an, China
– sequence: 4
  givenname: Jianrui
  orcidid: 0000-0001-9104-4540
  surname: Chen
  fullname: Chen, Jianrui
  organization: School of Computer Science, Shaanxi Normal University, Xi'an, China
– sequence: 5
  givenname: Fang-Xiang
  orcidid: 0000-0002-4593-9332
  surname: Wu
  fullname: Wu, Fang-Xiang
  email: faw341@mail.usask.ca
  organization: Division of Biomedical Engineering and Department of Mechanical Engineering and Department of Computer Science, University of Saskatchewan, Saskatoon, SK, Canada
BackLink https://www.ncbi.nlm.nih.gov/pubmed/39259623$$D View this record in MEDLINE/PubMed
BookMark eNp9kUtvGjEUha2KqhCSHxCpirzMZqhfMx5nRx6FqVDSBV2PjOdCph1sYntU9d_HFIiiLno3vjr6jm2dc4YG1llA6JKSCaVEffl2O68mjDAx4SIvpRIf0IjRoswYI-XgtFMlhugihJ8kTZkkVXxCQ65YrgrGR6ibVdOH7H5Z3eDvHprWxNZu8L3vN9lS-w1EXNkIXifd2YBvdYAGO4vnkFS3AQuuD_gR4m_nf2FtGzyrHrMDNvN694ynfXRgjWvAn6OPa90FuDieY_Tj68Pybp4tnmbV3XSRGc5YzEyT56oxXHKjuQRphNJSFKyQtNTUcLFelVpRxg03OVHQ5HxdUsJXlBClkjpG14d7d9699BBivW2Dga7Tf79b8wQLkUuWJ_TqiParLTT1zrdb7f_Up4QSQA-A8S4ED-s3hJJ6X0S9L6LeF1Efi0ge-Y_HtFHvE4xet91_nZ8PzhYA3r1UyIKzgr8CcKOTPA
CODEN IJBHA9
CitedBy_id crossref_primary_10_3389_fgene_2025_1608490
crossref_primary_10_1016_j_ymeth_2025_05_005
crossref_primary_10_1007_s12539_025_00713_7
Cites_doi 10.1007/s12539-023-00550-6
10.1093/bfgp/elab031
10.1039/d1sc05180f
10.2174/1389203718666161108091609
10.23919/cje.2022.00.361
10.1093/bioinformatics/btaa524
10.1093/bib/bbab275
10.1093/bioinformatics/btaa880
10.1016/j.jmgm.2023.108498
10.1109/tcbb.2021.3088614
10.1109/jbhi.2021.3088342
10.1016/j.drudis.2020.03.003
10.1038/s41467-017-00680-8
10.1038/416653a
10.1093/bioinformatics/btab715
10.23919/cje.2022.00.384
10.1016/j.compbiomed.2022.106524
10.1093/bib/bbv066
10.1145/2487575.2487670
10.1093/bioinformatics/btac048
10.1586/ecp.12.74
10.1093/bib/bbx017
10.1109/tcbb.2016.2530062
10.1038/448645a
10.1109/tcbb.2021.3065562
10.1039/c5mb00650c
10.1109/tcbb.2021.3077905
10.1038/nrd1202
10.1016/j.knosys.2023.111329
10.1186/s12859-020-03677-1
10.1038/nchembio.118
10.1371/journal.pone.0037608
10.1371/journal.pcbi.1010812
10.1016/j.knosys.2023.111337
10.1093/bib/bbac184
10.1002/jcc.21256
10.1038/s41586-021-03376-8
10.1093/bioinformatics/bty543
10.1093/bib/bbac446
ContentType Journal Article
DBID 97E
RIA
RIE
AAYXX
CITATION
CGR
CUY
CVF
ECM
EIF
NPM
7X8
DOI 10.1109/JBHI.2024.3458794
DatabaseName IEEE All-Society Periodicals Package (ASPP) 2005–Present
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Xplore: IEL
CrossRef
Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
MEDLINE - Academic
DatabaseTitle CrossRef
MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
MEDLINE - Academic
DatabaseTitleList
MEDLINE
MEDLINE - Academic
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: RIE
  name: IEEE/IET Electronic Library
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
– sequence: 3
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
EISSN 2168-2208
EndPage 7909
ExternalDocumentID 39259623
10_1109_JBHI_2024_3458794
10676326
Genre orig-research
Journal Article
GrantInformation_xml – fundername: National Natural Science Foundation of China
  grantid: 62272288
  funderid: 10.13039/501100001809
– fundername: Fundamental Research Funds for the Central Universities, Shaanxi Normal University
  grantid: GK202302006; GK202406008
– fundername: Natural Science Basic Research Program of Shaanxi
  grantid: 2024JC-YBQN-0624
GroupedDBID 0R~
4.4
6IF
6IH
6IK
97E
AAJGR
AASAJ
AAWTH
ABAZT
ABQJQ
ABVLG
ACIWK
ACPRK
AENEX
AFRAH
AGQYO
AGSQL
AHBIQ
AKJIK
AKQYR
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
EBS
EJD
HZ~
IFIPE
IPLJI
JAVBF
M43
O9-
OCL
PQQKQ
RIA
RIE
RNS
AAYXX
CITATION
CGR
CUY
CVF
ECM
EIF
NPM
7X8
ID FETCH-LOGICAL-c322t-cd559dc373ca37e7c49a74626718a1c34fb8a9123c3c509ed53f8103b100993c3
IEDL.DBID RIE
ISICitedReferencesCount 4
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001611081000047&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2168-2194
2168-2208
IngestDate Thu Oct 02 20:32:12 EDT 2025
Sat Nov 08 03:22:21 EST 2025
Sat Nov 29 06:54:03 EST 2025
Tue Nov 18 22:33:10 EST 2025
Wed Nov 19 08:27:19 EST 2025
IsPeerReviewed true
IsScholarly true
Issue 11
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
https://doi.org/10.15223/policy-029
https://doi.org/10.15223/policy-037
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c322t-cd559dc373ca37e7c49a74626718a1c34fb8a9123c3c509ed53f8103b100993c3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ORCID 0000-0001-9104-4540
0000-0001-5778-5230
0000-0002-9901-1732
0000-0002-4593-9332
PMID 39259623
PQID 3103445725
PQPubID 23479
PageCount 14
ParticipantIDs crossref_primary_10_1109_JBHI_2024_3458794
pubmed_primary_39259623
crossref_citationtrail_10_1109_JBHI_2024_3458794
proquest_miscellaneous_3103445725
ieee_primary_10676326
PublicationCentury 2000
PublicationDate 2025-11-01
PublicationDateYYYYMMDD 2025-11-01
PublicationDate_xml – month: 11
  year: 2025
  text: 2025-11-01
  day: 01
PublicationDecade 2020
PublicationPlace United States
PublicationPlace_xml – name: United States
PublicationTitle IEEE journal of biomedical and health informatics
PublicationTitleAbbrev JBHI
PublicationTitleAlternate IEEE J Biomed Health Inform
PublicationYear 2025
Publisher IEEE
Publisher_xml – name: IEEE
References ref13
ref35
ref12
ref34
ref37
ref14
ref31
ref30
ref11
ref33
ref10
ref32
ref2
ref1
ref17
ref39
ref16
ref38
ref19
ref18
Xu (ref36) 2019
Jiajie (ref15) 2021; 22
ref24
ref23
ref26
ref25
ref20
ref42
Yanghe (ref5) 2017; 2017
ref41
ref22
ref21
ref28
ref27
ref29
ref8
ref7
ref9
ref4
ref3
ref6
ref40
References_xml – ident: ref29
  doi: 10.1007/s12539-023-00550-6
– ident: ref3
  doi: 10.1093/bfgp/elab031
– ident: ref20
  doi: 10.1039/d1sc05180f
– ident: ref2
  doi: 10.2174/1389203718666161108091609
– ident: ref32
  doi: 10.23919/cje.2022.00.361
– ident: ref38
  doi: 10.1093/bioinformatics/btaa524
– ident: ref18
  doi: 10.1093/bib/bbab275
– ident: ref22
  doi: 10.1093/bioinformatics/btaa880
– ident: ref39
  doi: 10.1016/j.jmgm.2023.108498
– ident: ref27
  doi: 10.1109/tcbb.2021.3088614
– ident: ref33
  doi: 10.1109/jbhi.2021.3088342
– volume: 2017
  issue: 1
  year: 2017
  ident: ref5
  article-title: Drug target protein-protein interaction networks: A systematic perspective
  publication-title: Biomed. Res. Int.
– ident: ref1
  doi: 10.1016/j.drudis.2020.03.003
– ident: ref25
  doi: 10.1038/s41467-017-00680-8
– ident: ref13
  doi: 10.1038/416653a
– ident: ref19
  doi: 10.1093/bioinformatics/btab715
– ident: ref28
  doi: 10.23919/cje.2022.00.384
– ident: ref34
  doi: 10.1016/j.compbiomed.2022.106524
– ident: ref7
  doi: 10.1093/bib/bbv066
– ident: ref37
  doi: 10.1145/2487575.2487670
– ident: ref24
  doi: 10.1093/bioinformatics/btac048
– ident: ref9
  doi: 10.1586/ecp.12.74
– ident: ref4
  doi: 10.1093/bib/bbx017
– ident: ref35
  doi: 10.1109/tcbb.2016.2530062
– ident: ref10
  doi: 10.1038/448645a
– volume-title: Proc. Int. Conf. Lern. Representations
  year: 2019
  ident: ref36
  article-title: How powerful are graph neural networks
– ident: ref14
  doi: 10.1109/tcbb.2021.3065562
– ident: ref16
  doi: 10.1039/c5mb00650c
– ident: ref21
  doi: 10.1109/tcbb.2021.3077905
– ident: ref6
  doi: 10.1038/nrd1202
– ident: ref11
  doi: 10.1016/j.knosys.2023.111329
– ident: ref26
  doi: 10.1186/s12859-020-03677-1
– ident: ref8
  doi: 10.1038/nchembio.118
– ident: ref12
  doi: 10.1371/journal.pone.0037608
– volume: 22
  issue: 5
  year: 2021
  ident: ref15
  article-title: An end-to-end heterogeneous graph representation learning-based framework for drugtarget interaction prediction
  publication-title: Brief. Bioinf.
– ident: ref30
  doi: 10.1371/journal.pcbi.1010812
– ident: ref31
  doi: 10.1016/j.knosys.2023.111337
– ident: ref41
  doi: 10.1093/bib/bbac184
– ident: ref17
  doi: 10.1002/jcc.21256
– ident: ref42
  doi: 10.1038/s41586-021-03376-8
– ident: ref40
  doi: 10.1093/bioinformatics/bty543
– ident: ref23
  doi: 10.1093/bib/bbac446
SSID ssj0000816896
Score 2.482682
Snippet Accurate prediction of drug-target interactions (DTIs) is essential for advancing drug discovery and repurposing. However, the sparsity of DTI data limits the...
SourceID proquest
pubmed
crossref
ieee
SourceType Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 7896
SubjectTerms Algorithms
Autoencoder
Computational Biology - methods
Deep Learning
Diffusion tensor imaging
Diseases
Drug Discovery - methods
Drug Interactions
Drug Repositioning - methods
Drug-target interactions
Drugs
Feature extraction
graph auto-encoder
graph isomorphism network
heterogeneous network
Heterogeneous networks
Humans
Neural Networks, Computer
Proteins
Vectors
Title GIAE-DTI: Predicting Drug-Target Interactions Based on Heterogeneous Network and GIN-Based Graph Autoencoder
URI https://ieeexplore.ieee.org/document/10676326
https://www.ncbi.nlm.nih.gov/pubmed/39259623
https://www.proquest.com/docview/3103445725
Volume 29
WOSCitedRecordID wos001611081000047&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: PRVIEE
  databaseName: IEEE/IET Electronic Library
  customDbUrl:
  eissn: 2168-2208
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000816896
  issn: 2168-2194
  databaseCode: RIE
  dateStart: 20130101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3dT9swED8NNCFeYOOzbKuMtCckQxLbdby3MujHxCoeCupblNoGIaEEpc3-_t05acUeQJryYllnK_KddXe-jx_A95i6gqvccOWl5tKphBvlNTc9byQ6FNE8QLLc3-jJJJ3NzG1brB5qYbz3IfnMn9MwxPJdaWt6Krugdmc9tDc2YEPrXlOstX5QCQgSAY8rwQHHmyjbKGYcmYtfl6MxeoOJPBdSpSiE27CFpgFhz4h_VFLAWHnb3AxqZ7D7nz_8CXZa-5L1G4H4DB98sQdbv9sI-j48D8f9a341Hf9gtxXNUtozu6rqRz4NSeEsvBE25Q4LdolKzrGyYCNKmylR2nxZL9ikSR5neeHYcDzhDdmQml-zfr0sqTum89UB3A2upz9HvEVc4BYv9pJbhw6Gs0ILmwvttZUm1xJ9HtRgeWyFfJinuUFlZ4VFS8M7JR7SOBLzmCxNnD2EzaIs_DEwHc-Vwk2t7aHRE7k0dSanzzpL7co7EK0OPbNtO3JCxXjOglsSmYxYlhHLspZlHThbL3lpenG8R3xA_HhF2LCiA6cr1mZ4kyg8koejywhxTUqlE9WBo4bn69UrUTl5Y9cvsJ0QMHAoUvwKm8uq9t_go_2zfFpUXRTXWdoN4voXSjrfxg
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9QwEB5BQaUXKFDaLY8aiROS2yS21zG37Ws3sI16WFBvUdZ2EVKVVNlNf39nnOwKDq2EcrGssRV5xpoZz-MD-BJTV3BVGq681Fw6lXCjvOZm6I1EhyKaB0iWX1Od5-nVlbnsi9VDLYz3PiSf-UMahli-q21LT2VH1O5siPbGU3hG0FmmK9daP6kEDImAyJXggONdlH0cM47M0ffjSYb-YCIPhVQpiuEWbKJxQOgz4h-lFFBWHjY4g-I5f_Wfv7wNL3sLk406kXgNT3z1BjYv-hj6W7gZZ6MzfjrLvrHLhmYp8ZmdNu1vPgtp4Sy8EnYFDwt2jGrOsbpiE0qcqVHefN0uWN6lj7Oycmyc5bwjG1P7azZqlzX1x3S-2YGf52ezkwnvMRe4xau95Nahi-Gs0MKWQnttpSm1RK8HdVgZWyGv52lpUN1ZYdHW8E6J6zSOxDwmWxNn38FGVVd-D5iO50rhptYO0eyJXJo6U9JnnaWG5QOIVode2L4hOeFi3BTBMYlMQSwriGVFz7IBfF0vue26cTxGvEP8-IuwY8UAPq9YW-BdogBJGY6uIMw1KZVO1AB2O56vV69EZf-BXQ_gxWR2MS2mWf7jPWwlBBMcShY_wMayaf1HeG7vln8WzacgtPfn6-It
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=GIAE-DTI%3A+Predicting+Drug-Target+Interactions+Based+on+Heterogeneous+Network+and+GIN-based+Graph+Autoencoder&rft.jtitle=IEEE+journal+of+biomedical+and+health+informatics&rft.au=Wang%2C+Mengdi&rft.au=Lei%2C+Xiujuan&rft.au=Liu%2C+Lian&rft.au=Chen%2C+Jianrui&rft.date=2025-11-01&rft.issn=2168-2208&rft.eissn=2168-2208&rft.volume=PP&rft_id=info:doi/10.1109%2FJBHI.2024.3458794&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2168-2194&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2168-2194&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2168-2194&client=summon