Node similarity-based graph convolution for link prediction in biological networks

ABSTRACT Background Link prediction is an important and well-studied problem in network biology. Recently, graph representation learning methods, including Graph Convolutional Network (GCN)-based node embedding have drawn increasing attention in link prediction. Motivation An important component of...

Full description

Saved in:
Bibliographic Details
Published in:Bioinformatics Vol. 37; no. 23; pp. 4501 - 4508
Main Authors: Coşkun, Mustafa, Koyutürk, Mehmet
Format: Journal Article
Language:English
Published: England Oxford University Press 07.12.2021
Subjects:
ISSN:1367-4803, 1367-4811, 1460-2059, 1367-4811
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract ABSTRACT Background Link prediction is an important and well-studied problem in network biology. Recently, graph representation learning methods, including Graph Convolutional Network (GCN)-based node embedding have drawn increasing attention in link prediction. Motivation An important component of GCN-based network embedding is the convolution matrix, which is used to propagate features across the network. Existing algorithms use the degree-normalized adjacency matrix for this purpose, as this matrix is closely related to the graph Laplacian, capturing the spectral properties of the network. In parallel, it has been shown that GCNs with a single layer can generate more robust embeddings by reducing the number of parameters. Laplacian-based convolution is not well suited to single-layered GCNs, as it limits the propagation of information to immediate neighbors of a node. Results Capitalizing on the rich literature on unsupervised link prediction, we propose using node similarity-based convolution matrices in GCNs to compute node embeddings for link prediction. We consider eight representative node-similarity measures (Common Neighbors, Jaccard Index, Adamic-Adar, Resource Allocation, Hub- Depressed Index, Hub-Promoted Index, Sorenson Index and Salton Index) for this purpose. We systematically compare the performance of the resulting algorithms against GCNs that use the degree-normalized adjacency matrix for convolution, as well as other link prediction algorithms. In our experiments, we use three-link prediction tasks involving biomedical networks: drug–disease association prediction, drug–drug interaction prediction and protein–protein interaction prediction. Our results show that node similarity-based convolution matrices significantly improve the link prediction performance of GCN-based embeddings. Conclusion As sophisticated machine-learning frameworks are increasingly employed in biological applications, historically well-established methods can be useful in making a head-start. Availability and implementation Our method, SiGraC, is implemented as a Python library and is freely available at https://github.com/mustafaCoskunAgu/SiGraC.
AbstractList Link prediction is an important and well-studied problem in network biology. Recently, graph representation learning methods, including Graph Convolutional Network (GCN)-based node embedding have drawn increasing attention in link prediction. An important component of GCN-based network embedding is the convolution matrix, which is used to propagate features across the network. Existing algorithms use the degree-normalized adjacency matrix for this purpose, as this matrix is closely related to the graph Laplacian, capturing the spectral properties of the network. In parallel, it has been shown that GCNs with a single layer can generate more robust embeddings by reducing the number of parameters. Laplacian-based convolution is not well suited to single-layered GCNs, as it limits the propagation of information to immediate neighbors of a node. Capitalizing on the rich literature on unsupervised link prediction, we propose using node similarity-based convolution matrices in GCNs to compute node embeddings for link prediction. We consider eight representative node-similarity measures (Common Neighbors, Jaccard Index, Adamic-Adar, Resource Allocation, Hub- Depressed Index, Hub-Promoted Index, Sorenson Index and Salton Index) for this purpose. We systematically compare the performance of the resulting algorithms against GCNs that use the degree-normalized adjacency matrix for convolution, as well as other link prediction algorithms. In our experiments, we use three-link prediction tasks involving biomedical networks: drug-disease association prediction, drug-drug interaction prediction and protein-protein interaction prediction. Our results show that node similarity-based convolution matrices significantly improve the link prediction performance of GCN-based embeddings. As sophisticated machine-learning frameworks are increasingly employed in biological applications, historically well-established methods can be useful in making a head-start. Our method, SiGraC, is implemented as a Python library and is freely available at https://github.com/mustafaCoskunAgu/SiGraC.
ABSTRACT Background Link prediction is an important and well-studied problem in network biology. Recently, graph representation learning methods, including Graph Convolutional Network (GCN)-based node embedding have drawn increasing attention in link prediction. Motivation An important component of GCN-based network embedding is the convolution matrix, which is used to propagate features across the network. Existing algorithms use the degree-normalized adjacency matrix for this purpose, as this matrix is closely related to the graph Laplacian, capturing the spectral properties of the network. In parallel, it has been shown that GCNs with a single layer can generate more robust embeddings by reducing the number of parameters. Laplacian-based convolution is not well suited to single-layered GCNs, as it limits the propagation of information to immediate neighbors of a node. Results Capitalizing on the rich literature on unsupervised link prediction, we propose using node similarity-based convolution matrices in GCNs to compute node embeddings for link prediction. We consider eight representative node-similarity measures (Common Neighbors, Jaccard Index, Adamic-Adar, Resource Allocation, Hub- Depressed Index, Hub-Promoted Index, Sorenson Index and Salton Index) for this purpose. We systematically compare the performance of the resulting algorithms against GCNs that use the degree-normalized adjacency matrix for convolution, as well as other link prediction algorithms. In our experiments, we use three-link prediction tasks involving biomedical networks: drug–disease association prediction, drug–drug interaction prediction and protein–protein interaction prediction. Our results show that node similarity-based convolution matrices significantly improve the link prediction performance of GCN-based embeddings. Conclusion As sophisticated machine-learning frameworks are increasingly employed in biological applications, historically well-established methods can be useful in making a head-start. Availability and implementation Our method, SiGraC, is implemented as a Python library and is freely available at https://github.com/mustafaCoskunAgu/SiGraC.
Link prediction is an important and well-studied problem in network biology. Recently, graph representation learning methods, including Graph Convolutional Network (GCN)-based node embedding have drawn increasing attention in link prediction.BACKGROUNDLink prediction is an important and well-studied problem in network biology. Recently, graph representation learning methods, including Graph Convolutional Network (GCN)-based node embedding have drawn increasing attention in link prediction.An important component of GCN-based network embedding is the convolution matrix, which is used to propagate features across the network. Existing algorithms use the degree-normalized adjacency matrix for this purpose, as this matrix is closely related to the graph Laplacian, capturing the spectral properties of the network. In parallel, it has been shown that GCNs with a single layer can generate more robust embeddings by reducing the number of parameters. Laplacian-based convolution is not well suited to single-layered GCNs, as it limits the propagation of information to immediate neighbors of a node.MOTIVATIONAn important component of GCN-based network embedding is the convolution matrix, which is used to propagate features across the network. Existing algorithms use the degree-normalized adjacency matrix for this purpose, as this matrix is closely related to the graph Laplacian, capturing the spectral properties of the network. In parallel, it has been shown that GCNs with a single layer can generate more robust embeddings by reducing the number of parameters. Laplacian-based convolution is not well suited to single-layered GCNs, as it limits the propagation of information to immediate neighbors of a node.Capitalizing on the rich literature on unsupervised link prediction, we propose using node similarity-based convolution matrices in GCNs to compute node embeddings for link prediction. We consider eight representative node-similarity measures (Common Neighbors, Jaccard Index, Adamic-Adar, Resource Allocation, Hub- Depressed Index, Hub-Promoted Index, Sorenson Index and Salton Index) for this purpose. We systematically compare the performance of the resulting algorithms against GCNs that use the degree-normalized adjacency matrix for convolution, as well as other link prediction algorithms. In our experiments, we use three-link prediction tasks involving biomedical networks: drug-disease association prediction, drug-drug interaction prediction and protein-protein interaction prediction. Our results show that node similarity-based convolution matrices significantly improve the link prediction performance of GCN-based embeddings.RESULTSCapitalizing on the rich literature on unsupervised link prediction, we propose using node similarity-based convolution matrices in GCNs to compute node embeddings for link prediction. We consider eight representative node-similarity measures (Common Neighbors, Jaccard Index, Adamic-Adar, Resource Allocation, Hub- Depressed Index, Hub-Promoted Index, Sorenson Index and Salton Index) for this purpose. We systematically compare the performance of the resulting algorithms against GCNs that use the degree-normalized adjacency matrix for convolution, as well as other link prediction algorithms. In our experiments, we use three-link prediction tasks involving biomedical networks: drug-disease association prediction, drug-drug interaction prediction and protein-protein interaction prediction. Our results show that node similarity-based convolution matrices significantly improve the link prediction performance of GCN-based embeddings.As sophisticated machine-learning frameworks are increasingly employed in biological applications, historically well-established methods can be useful in making a head-start.CONCLUSIONAs sophisticated machine-learning frameworks are increasingly employed in biological applications, historically well-established methods can be useful in making a head-start.Our method, SiGraC, is implemented as a Python library and is freely available at https://github.com/mustafaCoskunAgu/SiGraC.AVAILABILITY AND IMPLEMENTATIONOur method, SiGraC, is implemented as a Python library and is freely available at https://github.com/mustafaCoskunAgu/SiGraC.
Author Coşkun, Mustafa
Koyutürk, Mehmet
AuthorAffiliation 2 Hakkari University , Kayseri 38080, Turkey
1 Department of Computer Engineering, Abdullah Gül University , Kayseri, Turkey
3 Department of Computer and Data Sciences, Case Western Reserve University , Cleveland, OH 44106, USA
4 Center for Proteomics and Bioinformatics, Case Western Reserve University , Cleveland, OH 44106, USA
AuthorAffiliation_xml – name: 3 Department of Computer and Data Sciences, Case Western Reserve University , Cleveland, OH 44106, USA
– name: 1 Department of Computer Engineering, Abdullah Gül University , Kayseri, Turkey
– name: 2 Hakkari University , Kayseri 38080, Turkey
– name: 4 Center for Proteomics and Bioinformatics, Case Western Reserve University , Cleveland, OH 44106, USA
Author_xml – sequence: 1
  givenname: Mustafa
  orcidid: 0000-0003-4805-1416
  surname: Coşkun
  fullname: Coşkun, Mustafa
  email: mustafa.coskun@agu.edu.tr
  organization: Department of Computer Engineering, Abdullah Gül University, Kayseri, Turkey
– sequence: 2
  givenname: Mehmet
  surname: Koyutürk
  fullname: Koyutürk, Mehmet
  organization: Department of Computer and Data Sciences, Case Western Reserve University, Cleveland, OH 44106, USA
BackLink https://www.ncbi.nlm.nih.gov/pubmed/34152393$$D View this record in MEDLINE/PubMed
BookMark eNqNkVtLHTEUhUOx1OtfkHnsy2juk4FSEKlVkAqlfQ65zTE1k0yTjMV_3zmeo9S-6NMOO3utb7PXPtiJKToAjhE8QbAnp9onH4eUR1W9Kae6Kk05fQf2EOWwxZD1O8ub8K6lApJdsF_KLwgZopR-ALuEIoZJT_bA92_Juqb40QeVfX1otSrONqusptvGpHifwlx9is3CaoKPd82UnfXmsedjs-wR0sobFZro6p-U78oheD-oUNzRth6Anxdffpxfttc3X6_Oz65bQxmvLbNcY9Ex4YRwujfGQs6UhQY5RlBvORuEGByChgqhWa8s4x22puuM0hhhcgA-b3ynWY_OGhdrVkFO2Y8qP8ikvHz5E_2tXKV7KTjDEPPF4OPWIKffsytVjr4YF4KKLs1FYkZJB3lH1qzjf1nPkKdDLgOfNgMmp1KyG6TxVa2vtKB9kAjKdW7yZW5ym9si5__JnwivCtFGmObprZq_RF65dw
CitedBy_id crossref_primary_10_7717_peerj_15313
crossref_primary_10_1371_journal_pcbi_1009909
crossref_primary_10_1080_00207543_2025_2543964
crossref_primary_10_1186_s12859_024_05893_5
crossref_primary_10_1186_s12859_024_05830_6
crossref_primary_10_3390_su142114002
crossref_primary_10_1016_j_csi_2022_103655
crossref_primary_10_1088_1742_6596_2337_1_012018
crossref_primary_10_1038_s41467_023_39301_y
crossref_primary_10_1007_s10489_024_05828_w
crossref_primary_10_1145_3633518
crossref_primary_10_1109_TCBB_2024_3462730
crossref_primary_10_1016_j_asoc_2024_112616
crossref_primary_10_3390_e25111542
crossref_primary_10_1016_j_neunet_2025_107265
crossref_primary_10_1093_bioadv_vbae099
crossref_primary_10_1109_JBHI_2024_3390092
crossref_primary_10_1140_epjb_s10051_023_00495_1
crossref_primary_10_1049_cit2_12396
crossref_primary_10_1016_j_inffus_2024_102684
crossref_primary_10_1109_TAI_2023_3265947
crossref_primary_10_1186_s13321_025_01093_2
crossref_primary_10_1016_j_neucom_2023_126525
crossref_primary_10_1109_ACCESS_2022_3195222
crossref_primary_10_1016_j_compbiomed_2022_106127
crossref_primary_10_2196_48115
crossref_primary_10_1371_journal_pcbi_1011597
crossref_primary_10_1109_ACCESS_2024_3435142
crossref_primary_10_3390_pr11061689
crossref_primary_10_1109_ACCESS_2022_3183103
crossref_primary_10_1007_s11063_022_11094_z
crossref_primary_10_1109_JBHI_2022_3200692
crossref_primary_10_1007_s13042_023_01817_6
Cites_doi 10.1038/msb.2011.26
10.1038/srep40321
10.1109/ICDMW.2015.195
10.1093/nar/gks1094
10.1093/nar/gky868
10.1109/2.36
10.1093/bioinformatics/btz718
10.1186/1756-0381-4-19
10.1038/nrg.2017.38
10.1093/nar/gku1003
10.1002/asi.20591
10.1016/j.jbi.2018.11.005
10.1093/bioinformatics/btaa459
10.1093/bioinformatics/btu263
10.1093/bioinformatics/bts688
10.1093/bioinformatics/btn296
10.1089/cmb.2011.0154
10.1039/C7MB00188F
10.1140/epjb/e2009-00335-8
10.1093/bioinformatics/bty637
10.1016/S0378-8733(03)00009-1
10.1016/j.physa.2010.11.027
10.1145/2939672.2939754
10.1016/j.cels.2016.10.017
10.1093/nar/gkx1037
10.1093/bioinformatics/btw770
10.1093/nar/gkh061
10.1109/TCBB.2015.2495170
ContentType Journal Article
Copyright The Author(s) 2021. Published by Oxford University Press. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com 2021
The Author(s) 2021. Published by Oxford University Press. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.
Copyright_xml – notice: The Author(s) 2021. Published by Oxford University Press. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com 2021
– notice: The Author(s) 2021. Published by Oxford University Press. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.
DBID AAYXX
CITATION
CGR
CUY
CVF
ECM
EIF
NPM
7X8
5PM
DOI 10.1093/bioinformatics/btab464
DatabaseName CrossRef
Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
MEDLINE - Academic
PubMed Central (Full Participant titles)
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: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Biology
EISSN 1460-2059
1367-4811
EndPage 4508
ExternalDocumentID PMC8652026
34152393
10_1093_bioinformatics_btab464
10.1093/bioinformatics/btab464
Genre Journal Article
Research Support, N.I.H., Extramural
GrantInformation_xml – fundername: NCI NIH HHS
  grantid: U01 CA198941
– fundername: NLM NIH HHS
  grantid: R01 LM012980
– fundername: ;
– fundername: ;
  grantid: U01-CA198941
GroupedDBID -~X
.2P
.I3
482
48X
53G
5GY
6.Y
AAIMJ
AAJKP
AAKPC
AAMVS
AAPQZ
AAPXW
AARHZ
AAVAP
ABEFU
ABNKS
ABPTD
ABSAR
ABSMQ
ABWST
ABXVV
ABZBJ
ACGFS
ACMRT
ACPQN
ACUFI
ACYTK
ADEYI
ADFTL
ADGZP
ADHKW
ADOCK
ADRIX
ADRTK
ADYVW
ADZTZ
ADZXQ
AECKG
AEGPL
AEJOX
AEKKA
AEKPW
AEKSI
AELWJ
AEPUE
AETBJ
AFFNX
AFFZL
AFOFC
AFSHK
AFXEN
AGINJ
AGKRT
AGQXC
AI.
ALMA_UNASSIGNED_HOLDINGS
ALTZX
AQDSO
ARIXL
ASAOO
ATDFG
ATTQO
AXUDD
AYOIW
AZFZN
AZVOD
BCRHZ
BHONS
CXTWN
CZ4
DFGAJ
EE~
ELUNK
F5P
F9B
FEDTE
H5~
HAR
HVGLF
HW0
IOX
KOP
KSI
KSN
MBTAY
MVM
NGC
PB-
Q1.
Q5Y
QBD
RD5
RIG
ROL
ROX
ROZ
RXO
TCN
TLC
TN5
TOX
TR2
VH1
WH7
XJT
ZGI
~91
---
-E4
.DC
0R~
23N
2WC
4.4
5WA
70D
AAIJN
AAMDB
AAOGV
AAVLN
AAYXX
ABEJV
ABEUO
ABGNP
ABIXL
ABPQP
ABQLI
ACIWK
ACPRK
ACUXJ
ADBBV
ADEZT
ADGKP
ADHZD
ADMLS
ADPDF
ADRDM
ADVEK
AEMDU
AENEX
AENZO
AEWNT
AFGWE
AFIYH
AFRAH
AGKEF
AGSYK
AHMBA
AHXPO
AIJHB
AJEEA
AJEUX
AKHUL
AKWXX
ALUQC
AMNDL
APIBT
APWMN
ASPBG
AVWKF
BAWUL
BAYMD
BQDIO
BQUQU
BSWAC
BTQHN
C45
CDBKE
CITATION
CS3
DAKXR
DIK
DILTD
DU5
D~K
EBD
EBS
EMOBN
FHSFR
FLIZI
FLUFQ
FOEOM
FQBLK
GAUVT
GJXCC
GROUPED_DOAJ
GX1
H13
HZ~
J21
JXSIZ
KAQDR
KQ8
M-Z
MK~
ML0
N9A
NLBLG
NMDNZ
NOMLY
NU-
O9-
OAWHX
ODMLO
OJQWA
OK1
OVD
OVEED
P2P
PAFKI
PEELM
PQQKQ
R44
RNS
RPM
RUSNO
RW1
SV3
TEORI
TJP
W8F
WOQ
X7H
YAYTL
YKOAZ
YXANX
ZKX
~KM
CGR
CUY
CVF
ECM
EIF
M49
NPM
7X8
5PM
ID FETCH-LOGICAL-c456t-5d6b28758e88eb9ccd065ad0c1e5319d65f88fe10c488b59ad5672dc77cab2123
IEDL.DBID TOX
ISICitedReferencesCount 46
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000733374500027&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1367-4803
1367-4811
IngestDate Thu Aug 21 13:56:28 EDT 2025
Fri Jul 11 09:04:07 EDT 2025
Wed Feb 19 02:24:19 EST 2025
Sat Nov 29 03:49:21 EST 2025
Tue Nov 18 22:43:01 EST 2025
Wed Aug 28 03:17:03 EDT 2024
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 23
Language English
License This article is published and distributed under the terms of the Oxford University Press, Standard Journals Publication Model (https://academic.oup.com/journals/pages/open_access/funder_policies/chorus/standard_publication_model)
https://academic.oup.com/journals/pages/open_access/funder_policies/chorus/standard_publication_model
The Author(s) 2021. Published by Oxford University Press. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c456t-5d6b28758e88eb9ccd065ad0c1e5319d65f88fe10c488b59ad5672dc77cab2123
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ORCID 0000-0003-4805-1416
OpenAccessLink https://www.ncbi.nlm.nih.gov/pmc/articles/8652026
PMID 34152393
PQID 2543706732
PQPubID 23479
PageCount 8
ParticipantIDs pubmedcentral_primary_oai_pubmedcentral_nih_gov_8652026
proquest_miscellaneous_2543706732
pubmed_primary_34152393
crossref_citationtrail_10_1093_bioinformatics_btab464
crossref_primary_10_1093_bioinformatics_btab464
oup_primary_10_1093_bioinformatics_btab464
PublicationCentury 2000
PublicationDate 2021-12-07
PublicationDateYYYYMMDD 2021-12-07
PublicationDate_xml – month: 12
  year: 2021
  text: 2021-12-07
  day: 07
PublicationDecade 2020
PublicationPlace England
PublicationPlace_xml – name: England
PublicationTitle Bioinformatics
PublicationTitleAlternate Bioinformatics
PublicationYear 2021
Publisher Oxford University Press
Publisher_xml – name: Oxford University Press
References Wu (2023061310492968400_btab464-B34) 2019
Veličković (2023061310492968400_btab464-B31) 2019
Cho (2023061310492968400_btab464-B4) 2016; 3
Perozzi (2023061310492968400_btab464-B25) 2014
Coşkun (2023061310492968400_btab464-B5) 2015
Szklarczyk (2023061310492968400_btab464-B28) 2015; 43
Zhang (2023061310492968400_btab464-B37) 2018; 88
Valdeolivas (2023061310492968400_btab464-B30) 2019; 35
Gottlieb (2023061310492968400_btab464-B13) 2011; 7
Li (2023061310492968400_btab464-B19) 2018
Kipf (2023061310492968400_btab464-B17) 2016
Bodenreider (2023061310492968400_btab464-B2) 2004; 32
Erten (2023061310492968400_btab464-B10) 2011; 18
Ribeiro (2023061310492968400_btab464-B26) 2017
Tang (2023061310492968400_btab464-B29) 2015
Davis (2023061310492968400_btab464-B7) 2019; 47
Wang (2023061310492968400_btab464-B32) 2017; 13
Grover (2023061310492968400_btab464-B14) 2016
Hamilton (2023061310492968400_btab464-B15) 2019
Linsker (2023061310492968400_btab464-B22) 1988; 21
Cowen (2023061310492968400_btab464-B6) 2017; 18
Zhou (2023061310492968400_btab464-B38) 2009; 71
Liben-Nowell (2023061310492968400_btab464-B21) 2007; 58
Stanfield (2023061310492968400_btab464-B27) 2017; 7
Yue (2023061310492968400_btab464-B36) 2020; 36
Adamic (2023061310492968400_btab464-B1) 2003; 25
Pandey (2023061310492968400_btab464-B24) 2008; 24
Yoo (2023061310492968400_btab464-B35) 2017; 14
Kipf (2023061310492968400_btab464-B16) 2016
Franceschini (2023061310492968400_btab464-B11) 2013; 41
Devkota (2023061310492968400_btab464-B8) 2020; 36
Liang (2023061310492968400_btab464-B20) 2017; 33
Cao (2023061310492968400_btab464-B3) 2014; 30
Lü (2023061310492968400_btab464-B23) 2011; 390
Wishart (2023061310492968400_btab464-B33) 2018; 46
Gilmer (2023061310492968400_btab464-B12) 2017
Erten (2023061310492968400_btab464-B9) 2011; 4
Lei (2023061310492968400_btab464-B18) 2013; 29
References_xml – volume: 7
  start-page: 496
  year: 2011
  ident: 2023061310492968400_btab464-B13
  article-title: PREDICT: a method for inferring novel drug indications with application to personalized medicine
  publication-title: Mol. Syst. Biol
  doi: 10.1038/msb.2011.26
– volume: 7
  start-page: 40321
  year: 2017
  ident: 2023061310492968400_btab464-B27
  article-title: Drug response prediction as a link prediction problem
  publication-title: Sci. Rep
  doi: 10.1038/srep40321
– start-page: 485
  volume-title: 2015 IEEE International Conference on Data Mining Workshop (ICDMW)
  year: 2015
  ident: 2023061310492968400_btab464-B5
  doi: 10.1109/ICDMW.2015.195
– volume: 41
  start-page: D808
  year: 2013
  ident: 2023061310492968400_btab464-B11
  article-title: STRING v9. 1: protein-protein interaction networks, with increased coverage and integration
  publication-title: Nucleic Acids Res
  doi: 10.1093/nar/gks1094
– volume: 47
  start-page: D948
  year: 2019
  ident: 2023061310492968400_btab464-B7
  article-title: The comparative toxicogenomics database: update 2019
  publication-title: Nucleic Acids Res
  doi: 10.1093/nar/gky868
– volume: 21
  start-page: 105
  year: 1988
  ident: 2023061310492968400_btab464-B22
  article-title: Self-organization in a perceptual network
  publication-title: Computer
  doi: 10.1109/2.36
– volume: 36
  start-page: 1241
  year: 2020
  ident: 2023061310492968400_btab464-B36
  article-title: Graph embedding on biomedical networks: methods, applications and evaluations
  publication-title: Bioinformatics
  doi: 10.1093/bioinformatics/btz718
– volume: 4
  start-page: 19
  year: 2011
  ident: 2023061310492968400_btab464-B9
  article-title: DADA: degree-aware algorithms for network-based disease gene prioritization
  publication-title: BioData Min
  doi: 10.1186/1756-0381-4-19
– year: 2019
  ident: 2023061310492968400_btab464-B15
  article-title: Representation learning on graphs: methods and applications (2017)
  publication-title: IEEE Data Engineering Bulletin
– volume: 18
  start-page: 551
  year: 2017
  ident: 2023061310492968400_btab464-B6
  article-title: Network propagation: a universal amplifier of genetic associations
  publication-title: Nat. Rev. Genet
  doi: 10.1038/nrg.2017.38
– volume: 43
  start-page: D447
  year: 2015
  ident: 2023061310492968400_btab464-B28
  article-title: STRING v10: protein–protein interaction networks, integrated over the tree of life
  publication-title: Nucleic Acids Res
  doi: 10.1093/nar/gku1003
– volume: 58
  start-page: 1019
  year: 2007
  ident: 2023061310492968400_btab464-B21
  article-title: The link-prediction problem for social networks
  publication-title: J. Am. Soc. Inf. Sci. Technol
  doi: 10.1002/asi.20591
– start-page: 385
  year: 2017
  ident: 2023061310492968400_btab464-B26
– volume: 88
  start-page: 90
  year: 2018
  ident: 2023061310492968400_btab464-B37
  article-title: Manifold regularized matrix factorization for drug-drug interaction prediction
  publication-title: J. Biomed. Inform
  doi: 10.1016/j.jbi.2018.11.005
– volume: 36
  start-page: i464
  year: 2020
  ident: 2023061310492968400_btab464-B8
  article-title: GLIDE: combining local methods and diffusion state embeddings to predict missing interactions in biological networks
  publication-title: Bioinformatics
  doi: 10.1093/bioinformatics/btaa459
– volume: 30
  start-page: i219
  year: 2014
  ident: 2023061310492968400_btab464-B3
  article-title: New directions for diffusion-based network prediction of protein function: incorporating pathways with confidence
  publication-title: Bioinformatics
  doi: 10.1093/bioinformatics/btu263
– start-page: 1263
  volume-title: Proceedings of the 34th International Conference on Machine Learning
  year: 2017
  ident: 2023061310492968400_btab464-B12
– year: 2016
  ident: 2023061310492968400_btab464-B16
  article-title: Semi-supervised classification with graph convolutional networks
– volume: 29
  start-page: 355
  year: 2013
  ident: 2023061310492968400_btab464-B18
  article-title: A novel link prediction algorithm for reconstructing protein–protein interaction networks by topological similarity
  publication-title: Bioinformatics
  doi: 10.1093/bioinformatics/bts688
– year: 2019
  ident: 2023061310492968400_btab464-B31
– year: 2018
  ident: 2023061310492968400_btab464-B19
– volume: 24
  start-page: i28
  year: 2008
  ident: 2023061310492968400_btab464-B24
  article-title: Functional coherence in domain interaction networks
  publication-title: Bioinformatics
  doi: 10.1093/bioinformatics/btn296
– volume: 18
  start-page: 1561
  year: 2011
  ident: 2023061310492968400_btab464-B10
  article-title: Vavien: an algorithm for prioritizing candidate disease genes based on topological similarity of proteins in interaction networks
  publication-title: J. Comput. Biol
  doi: 10.1089/cmb.2011.0154
– year: 2016
  ident: 2023061310492968400_btab464-B17
  article-title: Variational graph auto-encoders
– volume: 13
  start-page: 1336
  year: 2017
  ident: 2023061310492968400_btab464-B32
  article-title: Predicting protein–protein interactions from protein sequences by a stacked sparse autoencoder deep neural network
  publication-title: Mol. Biosyst
  doi: 10.1039/C7MB00188F
– volume: 71
  start-page: 623
  year: 2009
  ident: 2023061310492968400_btab464-B38
  article-title: Predicting missing links via local information
  publication-title: Eur. Phys. J. B
  doi: 10.1140/epjb/e2009-00335-8
– volume: 35
  start-page: 497
  year: 2019
  ident: 2023061310492968400_btab464-B30
  article-title: Random walk with restart on multiplex and heterogeneous biological networks
  publication-title: Bioinformatics
  doi: 10.1093/bioinformatics/bty637
– volume: 25
  start-page: 211
  year: 2003
  ident: 2023061310492968400_btab464-B1
  article-title: Friends and neighbors on the web
  publication-title: Soc. Netw
  doi: 10.1016/S0378-8733(03)00009-1
– volume: 390
  start-page: 1150
  year: 2011
  ident: 2023061310492968400_btab464-B23
  article-title: Link prediction in complex networks: a survey
  publication-title: Physica A
  doi: 10.1016/j.physa.2010.11.027
– start-page: 701
  year: 2014
  ident: 2023061310492968400_btab464-B25
– start-page: 855
  volume-title: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
  year: 2016
  ident: 2023061310492968400_btab464-B14
  doi: 10.1145/2939672.2939754
– volume: 3
  start-page: 540
  year: 2016
  ident: 2023061310492968400_btab464-B4
  article-title: Compact integration of multi-network topology for functional analysis of genes
  publication-title: Cell Syst
  doi: 10.1016/j.cels.2016.10.017
– volume: 46
  start-page: D1074
  year: 2018
  ident: 2023061310492968400_btab464-B33
  article-title: DrugBank 5.0: a major update to the DrugBank database for 2018
  publication-title: Nucleic Acids Res
  doi: 10.1093/nar/gkx1037
– volume: 33
  start-page: 1187
  year: 2017
  ident: 2023061310492968400_btab464-B20
  article-title: LRSSL: predict and interpret drug–disease associations based on data integration using sparse subspace learning
  publication-title: Bioinformatics
  doi: 10.1093/bioinformatics/btw770
– year: 2019
  ident: 2023061310492968400_btab464-B34
– volume: 32
  start-page: D267
  year: 2004
  ident: 2023061310492968400_btab464-B2
  article-title: The unified medical language system (UMLS): integrating biomedical terminology
  publication-title: Nucleic Acids Res
  doi: 10.1093/nar/gkh061
– volume: 14
  start-page: 1056
  year: 2017
  ident: 2023061310492968400_btab464-B35
  article-title: Improving identification of key players in aging via network de-noising and core inference
  publication-title: IEEE/ACM Trans. Comput. Biol. Bioinform
  doi: 10.1109/TCBB.2015.2495170
– start-page: 1067
  year: 2015
  ident: 2023061310492968400_btab464-B29
SSID ssj0051444
ssj0005056
Score 2.586622
Snippet ABSTRACT Background Link prediction is an important and well-studied problem in network biology. Recently, graph representation learning methods, including...
Link prediction is an important and well-studied problem in network biology. Recently, graph representation learning methods, including Graph Convolutional...
SourceID pubmedcentral
proquest
pubmed
crossref
oup
SourceType Open Access Repository
Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 4501
SubjectTerms Algorithms
Gene Library
Libraries
Machine Learning
Original Papers
Title Node similarity-based graph convolution for link prediction in biological networks
URI https://www.ncbi.nlm.nih.gov/pubmed/34152393
https://www.proquest.com/docview/2543706732
https://pubmed.ncbi.nlm.nih.gov/PMC8652026
Volume 37
WOSCitedRecordID wos000733374500027&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: PRVASL
  databaseName: Oxford Journals Open Access (Activated by CARLI)
  customDbUrl:
  eissn: 1460-2059
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0005056
  issn: 1367-4803
  databaseCode: TOX
  dateStart: 19850101
  isFulltext: true
  titleUrlDefault: https://academic.oup.com/journals/
  providerName: Oxford University Press
– providerCode: PRVASL
  databaseName: Oxford Journals Open Access (Activated by CARLI)
  customDbUrl:
  eissn: 1460-2059
  dateEnd: 20220930
  omitProxy: false
  ssIdentifier: ssj0005056
  issn: 1367-4803
  databaseCode: TOX
  dateStart: 19850101
  isFulltext: true
  titleUrlDefault: https://academic.oup.com/journals/
  providerName: Oxford University Press
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1ZS8NAEB5qUfDF-6hHWcEnITTXZjePIopPVaRC30L2CAY0KT0E_7072bQ2BfF4zGazJLMzzDeZ2W8ALoOQmnE_dTIvcp0QfzTFOlKO8qhKqQ65r1XVbIL1-3w4jB9b4M3Pwqym8OOgJ_KyJhFF4uKemKYijJAB1KMcexYMHoZfRR0uUsPYCwMFQtvTFqm9uRvMDwh_u2bDNzXOuy3BztXqySV3dLf9jw_Zga0ae5Jrqyy70NLFHmzYbpQf-_DUL5Umk_wtN9GuAecOejhFKkprgtXptZYSszjBxC8ZjTHNU43lBbF8TrjppLDF5ZMDeL67HdzcO3XLBUcaJDV1qIqEiaEo15xrEUupDERJlSs9jcaqIppxnmnPlcbwBY1TRSPmK8mYTAV6wUNoF2Whj4FoyblBi9rTgoahYsLMM8FeJjMmtYn8OkDnwk5kzUeObTFeE5sXD5KmvJJaXh3oLZ4bWUaOH5-4Mnv568kX8y1PjKVh-iQtdDmbJEgbwLCvj9-BI6sCizUDxEFBHHSANZRjMQFZvJt3ivylYvPmEfWNOE7-8pKnsOljbQ2W1bAzaE_HM30O6_J9mk_GXVhjQ96tDOMT_hIW0g
linkProvider Oxford University Press
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=Node+similarity-based+graph+convolution+for+link+prediction+in+biological+networks&rft.jtitle=Bioinformatics+%28Oxford%2C+England%29&rft.au=Co%C5%9Fkun%2C+Mustafa&rft.au=Koyut%C3%BCrk%2C+Mehmet&rft.date=2021-12-07&rft.eissn=1367-4811&rft.volume=37&rft.issue=23&rft.spage=4501&rft_id=info:doi/10.1093%2Fbioinformatics%2Fbtab464&rft_id=info%3Apmid%2F34152393&rft.externalDocID=34152393
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1367-4803&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1367-4803&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1367-4803&client=summon