VHGAE: Drug-Target Interaction Prediction Model Based on Heterogeneous Graph Variational Autoencoder

Identifying drug-target interaction (DTI) is crucial for drug discovery and repositioning. Biological identification of DTI is costly and time-consuming, so heterogeneous network methods for DTI prediction, which can speed up drug development, have drawn much attention. However, the scarcity of know...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Interdisciplinary sciences : computational life sciences
Hlavní autori: Zhang, Chen, Sun, Jiaqi, Xing, Linlin, Zhang, Longbo, Cai, Hongzhen, Che, Kai
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Germany 21.08.2025
Predmet:
ISSN:1913-2751, 1867-1462, 1867-1462
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract Identifying drug-target interaction (DTI) is crucial for drug discovery and repositioning. Biological identification of DTI is costly and time-consuming, so heterogeneous network methods for DTI prediction, which can speed up drug development, have drawn much attention. However, the scarcity of known drug-target pairs leads to an overwhelmingly sparse network structure. This sparsity makes it difficult for graph convolutional networks to fully capture the potential relationships between nodes during information transmission and feature extraction, thus challenging the prediction performance of DTI. Therefore, we propose a method, called VHGAE, based on a heterogeneous graph variational autoencoder to predict drug-target interactions. The VHGAE model integrates a wealth of prior knowledge from various sources related to drugs and targets to construct a heterogeneous network. To address the sparsity issue within the constructed heterogeneous network, first, the weighted k-nearest neighbor algorithm is used to densify the DTI network to increase the connectivity of the sparse network. Second, the weighted graph convolutional network within a variational graph autoencoder framework is employed to bolster the edge weights with limited connections. Third, a variational expectation maximization algorithm is introduced between the encoder and the decoder to recover potential relationships in the sparse network. The experimental results on two datasets show that the performance of VHGAE outperforms nine state-of-the-art DTI prediction methods, which suggests that the design of VHGAE in multi-source data fusion and sparse network processing plays an important role in improving prediction performance.
AbstractList Identifying drug-target interaction (DTI) is crucial for drug discovery and repositioning. Biological identification of DTI is costly and time-consuming, so heterogeneous network methods for DTI prediction, which can speed up drug development, have drawn much attention. However, the scarcity of known drug-target pairs leads to an overwhelmingly sparse network structure. This sparsity makes it difficult for graph convolutional networks to fully capture the potential relationships between nodes during information transmission and feature extraction, thus challenging the prediction performance of DTI. Therefore, we propose a method, called VHGAE, based on a heterogeneous graph variational autoencoder to predict drug-target interactions. The VHGAE model integrates a wealth of prior knowledge from various sources related to drugs and targets to construct a heterogeneous network. To address the sparsity issue within the constructed heterogeneous network, first, the weighted k-nearest neighbor algorithm is used to densify the DTI network to increase the connectivity of the sparse network. Second, the weighted graph convolutional network within a variational graph autoencoder framework is employed to bolster the edge weights with limited connections. Third, a variational expectation maximization algorithm is introduced between the encoder and the decoder to recover potential relationships in the sparse network. The experimental results on two datasets show that the performance of VHGAE outperforms nine state-of-the-art DTI prediction methods, which suggests that the design of VHGAE in multi-source data fusion and sparse network processing plays an important role in improving prediction performance.
Identifying drug-target interaction (DTI) is crucial for drug discovery and repositioning. Biological identification of DTI is costly and time-consuming, so heterogeneous network methods for DTI prediction, which can speed up drug development, have drawn much attention. However, the scarcity of known drug-target pairs leads to an overwhelmingly sparse network structure. This sparsity makes it difficult for graph convolutional networks to fully capture the potential relationships between nodes during information transmission and feature extraction, thus challenging the prediction performance of DTI. Therefore, we propose a method, called VHGAE, based on a heterogeneous graph variational autoencoder to predict drug-target interactions. The VHGAE model integrates a wealth of prior knowledge from various sources related to drugs and targets to construct a heterogeneous network. To address the sparsity issue within the constructed heterogeneous network, first, the weighted k-nearest neighbor algorithm is used to densify the DTI network to increase the connectivity of the sparse network. Second, the weighted graph convolutional network within a variational graph autoencoder framework is employed to bolster the edge weights with limited connections. Third, a variational expectation maximization algorithm is introduced between the encoder and the decoder to recover potential relationships in the sparse network. The experimental results on two datasets show that the performance of VHGAE outperforms nine state-of-the-art DTI prediction methods, which suggests that the design of VHGAE in multi-source data fusion and sparse network processing plays an important role in improving prediction performance.Identifying drug-target interaction (DTI) is crucial for drug discovery and repositioning. Biological identification of DTI is costly and time-consuming, so heterogeneous network methods for DTI prediction, which can speed up drug development, have drawn much attention. However, the scarcity of known drug-target pairs leads to an overwhelmingly sparse network structure. This sparsity makes it difficult for graph convolutional networks to fully capture the potential relationships between nodes during information transmission and feature extraction, thus challenging the prediction performance of DTI. Therefore, we propose a method, called VHGAE, based on a heterogeneous graph variational autoencoder to predict drug-target interactions. The VHGAE model integrates a wealth of prior knowledge from various sources related to drugs and targets to construct a heterogeneous network. To address the sparsity issue within the constructed heterogeneous network, first, the weighted k-nearest neighbor algorithm is used to densify the DTI network to increase the connectivity of the sparse network. Second, the weighted graph convolutional network within a variational graph autoencoder framework is employed to bolster the edge weights with limited connections. Third, a variational expectation maximization algorithm is introduced between the encoder and the decoder to recover potential relationships in the sparse network. The experimental results on two datasets show that the performance of VHGAE outperforms nine state-of-the-art DTI prediction methods, which suggests that the design of VHGAE in multi-source data fusion and sparse network processing plays an important role in improving prediction performance.
Author Cai, Hongzhen
Zhang, Chen
Sun, Jiaqi
Xing, Linlin
Che, Kai
Zhang, Longbo
Author_xml – sequence: 1
  givenname: Chen
  surname: Zhang
  fullname: Zhang, Chen
– sequence: 2
  givenname: Jiaqi
  surname: Sun
  fullname: Sun, Jiaqi
– sequence: 3
  givenname: Linlin
  surname: Xing
  fullname: Xing, Linlin
– sequence: 4
  givenname: Longbo
  surname: Zhang
  fullname: Zhang, Longbo
– sequence: 5
  givenname: Hongzhen
  surname: Cai
  fullname: Cai, Hongzhen
– sequence: 6
  givenname: Kai
  surname: Che
  fullname: Che, Kai
BackLink https://www.ncbi.nlm.nih.gov/pubmed/40841491$$D View this record in MEDLINE/PubMed
BookMark eNo9kMtOwzAQRS1URB_wAyxQlmwMfiY2u1JKW6kIFlW3lhNPS1CaFDtZ8Pe4D1jNHenM1egMUa9uakDolpIHSkj2GCiTXGPCJI6rVFhdoAFVaYapSFkvZk05ZpmkfTQM4YuQVChOrlBfECWo0HSA3Ho-G0-fkhffbfHK-i20yaJuwduiLZs6-fDgylN8axxUybMN4JK4ziFSzRZqaLqQzLzdfyZr60t7gG2VjLu2gbqIR_4aXW5sFeDmPEdo9TpdTeZ4-T5bTMZLXDCZtlhJopiAQqdFrrI0FxQcE6l0gjutnMqtyInYSJtJYFblonAamM6VErnmjI_Q_al275vvDkJrdmUooKrs8UfDYxknRAod0bsz2uU7cGbvy531P-ZPTATYCSh8E4KHzT9CiTnYNyf7Jto3R_tG8V_FL3a5
Cites_doi 10.1038/nbt1284
10.1016/j.drudis.2016.10.011
10.1186/s12859-023-05387-w
10.2174/157340911793743547
10.1093/bib/bbv066
10.1007/978-981-97-5692-6_21
10.1186/s12859-024-05904-5
10.1093/bib/bbac109
10.1109/TCBB.2023.3339645
10.1016/j.ymeth.2022.08.016
10.1093/nar/gky1049
10.1093/nar/gkw993
10.1109/ICBK.2019.00012
10.1007/s10489-021-02495-z
10.1016/S1359-6446(02)02288-2
10.1186/s12859-023-05275-3
10.1093/nar/gkx1037
10.1093/nar/gkv1075
10.1093/nar/gkq1126
10.1007/s13755-024-00287-6
10.1186/1752-0509-4-S2-S6
10.1093/bib/bbab275
10.1093/nar/gkaa971
10.1109/APCC47188.2019.9026503
10.1145/3511808.3557346
10.1093/nar/gkn892
10.1002/jcc.21256
10.1093/nar/gkaa1074
10.1038/s41467-017-00680-8
10.1093/nar/gks994
10.1038/msb.2009.98
ContentType Journal Article
Copyright 2025. International Association of Scientists in the Interdisciplinary Areas.
Copyright_xml – notice: 2025. International Association of Scientists in the Interdisciplinary Areas.
DBID AAYXX
CITATION
NPM
7X8
DOI 10.1007/s12539-025-00758-8
DatabaseName CrossRef
PubMed
MEDLINE - Academic
DatabaseTitle CrossRef
PubMed
MEDLINE - Academic
DatabaseTitleList PubMed
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 1867-1462
ExternalDocumentID 40841491
10_1007_s12539_025_00758_8
Genre Journal Article
GrantInformation_xml – fundername: National Natural Science Foundation of China
  grantid: 62202373
– fundername: National Natural Science Foundation of China
  grantid: 62002206
GroupedDBID ---
06C
06D
0R~
0VY
1N0
29~
2KG
2~H
30V
4.4
406
408
409
40D
40E
53G
67N
6NX
96X
AACDK
AAHNG
AAIAL
AAJBT
AAJKR
AANZL
AAPKM
AARTL
AASML
AATNV
AATVU
AAUYE
AAWCG
AAYIU
AAYQN
AAYXX
AAZMS
ABAKF
ABBRH
ABBXA
ABDBE
ABDZT
ABECU
ABFTV
ABHQN
ABJNI
ABJOX
ABKCH
ABMQK
ABQBU
ABRTQ
ABSXP
ABTEG
ABTHY
ABTKH
ABTMW
ABWNU
ABXPI
ACAOD
ACDTI
ACGFS
ACHSB
ACIWK
ACKNC
ACMDZ
ACMLO
ACOKC
ACOMO
ACPIV
ACPRK
ACZOJ
ADBBV
ADHHG
ADHIR
ADKNI
ADRFC
ADURQ
ADYFF
ADZKW
AEFQL
AEGNC
AEJHL
AEJRE
AEMSY
AEOHA
AEPYU
AEVLU
AEXYK
AFDZB
AFOHR
AFQWF
AFRAH
AFWTZ
AFZKB
AGAYW
AGDGC
AGMZJ
AGQEE
AGQMX
AGRTI
AGWZB
AGYKE
AHAVH
AHBYD
AHKAY
AHMBA
AHPBZ
AHYZX
AIAKS
AIGIU
AIIXL
AILAN
AITGF
AJRNO
AJZVZ
ALFXC
ALMA_UNASSIGNED_HOLDINGS
AMKLP
AMXSW
AMYLF
AMYQR
ANMIH
AOCGG
ASPBG
ATHPR
AUKKA
AVWKF
AXYYD
AYFIA
AZFZN
BA0
BGNMA
CITATION
DDRTE
DNIVK
DPUIP
EBLON
EBS
EIOEI
ESBYG
F5P
FERAY
FFXSO
FIGPU
FNLPD
FRRFC
FYJPI
G-Y
G-Z
GGCAI
GGRSB
GJIRD
GQ7
GQ8
GXS
HG6
HLICF
HMJXF
HQYDN
HRMNR
I0C
IJ-
IKXTQ
IWAJR
IZIGR
I~X
J-C
JBSCW
JCJTX
JZLTJ
KOV
LLZTM
M0K
M4Y
M7P
NPVJJ
NQJWS
NU0
O9J
PT4
QOR
QOS
R89
RLLFE
ROL
RSV
S1Z
S27
S3A
S3B
SBL
SCL
SDH
SHX
SJYHP
SNE
SNPRN
SNX
SOHCF
SOJ
SPISZ
SRMVM
SSLCW
STPWE
T13
TSG
U2A
U9L
UG4
UOJIU
UTJUX
UZXMN
VC2
VFIZW
W48
WK8
ZMTXR
ZOVNA
~A9
AAYZH
AESKC
NPM
7X8
PYCSY
ID FETCH-LOGICAL-c256t-850824ec96cb876b41ed2465d43d98d8ba4b04f5a75e2a8b4cd9e29b884b9323
IEDL.DBID RSV
ISICitedReferencesCount 0
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001555875900001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1913-2751
1867-1462
IngestDate Sat Nov 01 13:58:38 EDT 2025
Thu Sep 04 05:01:26 EDT 2025
Sat Nov 29 07:36:56 EST 2025
IsPeerReviewed false
IsScholarly true
Keywords Drug-target interaction prediction
Heterogeneous graph
Variational inference
Variational graph autoencoder
Language English
License 2025. International Association of Scientists in the Interdisciplinary Areas.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c256t-850824ec96cb876b41ed2465d43d98d8ba4b04f5a75e2a8b4cd9e29b884b9323
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
PMID 40841491
PQID 3246300549
PQPubID 23479
ParticipantIDs proquest_miscellaneous_3246300549
pubmed_primary_40841491
crossref_primary_10_1007_s12539_025_00758_8
PublicationCentury 2000
PublicationDate 2025-08-21
PublicationDateYYYYMMDD 2025-08-21
PublicationDate_xml – month: 08
  year: 2025
  text: 2025-08-21
  day: 21
PublicationDecade 2020
PublicationPlace Germany
PublicationPlace_xml – name: Germany
PublicationTitle Interdisciplinary sciences : computational life sciences
PublicationTitleAlternate Interdiscip Sci
PublicationYear 2025
References M Rudrapal (758_CR1) 2020
W Shi (758_CR9) 2024; 12
T Keshava Prasad (758_CR20) 2008; 37
S Kim (758_CR33) 2021; 49
758_CR23
DS Wishart (758_CR22) 2018; 46
Q An (758_CR11) 2021; 22
758_CR21
P Chen (758_CR26) 2023; 24
B Liu (758_CR31) 2022; 52
Z Xia (758_CR3) 2010; 4
C Acharya (758_CR7) 2011; 7
GM Morris (758_CR5) 2009; 30
A Davis (758_CR18) 2012; 41
Y Zhang (758_CR27) 2023; 24
GR Langley (758_CR4) 2017; 22
Y Luo (758_CR10) 2017; 8
D Szklarczyk (758_CR25) 2021; D1
B Zhang (758_CR29) 2024; 25
C Knox (758_CR17) 2010; 39
758_CR34
758_CR14
758_CR30
D Butina (758_CR8) 2002; 7
758_CR15
M Kuhn (758_CR19) 2010; 6
758_CR16
K Shao (758_CR12) 2022; 23
W Wang (758_CR13) 2022; 206
MJ Keiser (758_CR6) 2007; 25
W Wang (758_CR28) 2023; 21
M Kuhn (758_CR24) 2016; D1
O Ursu (758_CR32) 2016; 45
X Chen (758_CR2) 2016; 17
References_xml – volume: 25
  start-page: 197
  year: 2007
  ident: 758_CR6
  publication-title: Nat Biotechnol
  doi: 10.1038/nbt1284
– volume: 22
  start-page: 327
  year: 2017
  ident: 758_CR4
  publication-title: Drug Discov Today
  doi: 10.1016/j.drudis.2016.10.011
– volume: 24
  start-page: 278
  year: 2023
  ident: 758_CR27
  publication-title: BMC Bioinform
  doi: 10.1186/s12859-023-05387-w
– volume: 7
  start-page: 10
  year: 2011
  ident: 758_CR7
  publication-title: Curr Comput Aided Drug Des
  doi: 10.2174/157340911793743547
– ident: 758_CR34
– volume: 17
  start-page: 696
  year: 2016
  ident: 758_CR2
  publication-title: Brief Bioinform
  doi: 10.1093/bib/bbv066
– ident: 758_CR30
  doi: 10.1007/978-981-97-5692-6_21
– volume: 25
  start-page: 275
  year: 2024
  ident: 758_CR29
  publication-title: BMC Bioinform
  doi: 10.1186/s12859-024-05904-5
– volume: 23
  start-page: 109
  year: 2022
  ident: 758_CR12
  publication-title: Brief Bioinform
  doi: 10.1093/bib/bbac109
– volume: 21
  start-page: 143
  year: 2023
  ident: 758_CR28
  publication-title: IEEE ACM T Comput Bi
  doi: 10.1109/TCBB.2023.3339645
– volume: 206
  start-page: 101
  year: 2022
  ident: 758_CR13
  publication-title: Methods
  doi: 10.1016/j.ymeth.2022.08.016
– ident: 758_CR16
– ident: 758_CR23
  doi: 10.1093/nar/gky1049
– volume: 45
  start-page: D932
  year: 2016
  ident: 758_CR32
  publication-title: Nucleic Acids Res
  doi: 10.1093/nar/gkw993
– ident: 758_CR15
  doi: 10.1109/ICBK.2019.00012
– volume: 52
  start-page: 3705
  year: 2022
  ident: 758_CR31
  publication-title: Appl Intell
  doi: 10.1007/s10489-021-02495-z
– volume: 7
  start-page: S83
  year: 2002
  ident: 758_CR8
  publication-title: Drug Discov Today
  doi: 10.1016/S1359-6446(02)02288-2
– volume: 24
  start-page: 151
  year: 2023
  ident: 758_CR26
  publication-title: BMC Bioinform
  doi: 10.1186/s12859-023-05275-3
– volume: 46
  start-page: D1074
  year: 2018
  ident: 758_CR22
  publication-title: Nucleic Acids Res
  doi: 10.1093/nar/gkx1037
– volume: D1
  start-page: D1075
  year: 2016
  ident: 758_CR24
  publication-title: Nucleic Acids Res
  doi: 10.1093/nar/gkv1075
– volume: 39
  start-page: 1035
  year: 2010
  ident: 758_CR17
  publication-title: Nucleic Acids Res
  doi: 10.1093/nar/gkq1126
– volume: 12
  start-page: 30
  year: 2024
  ident: 758_CR9
  publication-title: Health Inf Sci Syst
  doi: 10.1007/s13755-024-00287-6
– volume: 4
  start-page: 1
  year: 2010
  ident: 758_CR3
  publication-title: BMC Syst Biol
  doi: 10.1186/1752-0509-4-S2-S6
– volume: 22
  start-page: 275
  year: 2021
  ident: 758_CR11
  publication-title: Brief Bioinform
  doi: 10.1093/bib/bbab275
– volume: 49
  start-page: 1388
  year: 2021
  ident: 758_CR33
  publication-title: Nucleic Acids Res
  doi: 10.1093/nar/gkaa971
– ident: 758_CR14
  doi: 10.1109/APCC47188.2019.9026503
– ident: 758_CR21
  doi: 10.1145/3511808.3557346
– volume: 37
  start-page: 767
  year: 2008
  ident: 758_CR20
  publication-title: Nucleic Acids Res
  doi: 10.1093/nar/gkn892
– volume: 30
  start-page: 2785
  year: 2009
  ident: 758_CR5
  publication-title: J Comput Chem
  doi: 10.1002/jcc.21256
– volume: D1
  start-page: D605
  year: 2021
  ident: 758_CR25
  publication-title: Nucleic Acids Res
  doi: 10.1093/nar/gkaa1074
– volume: 8
  start-page: 573
  year: 2017
  ident: 758_CR10
  publication-title: Nat Commu
  doi: 10.1038/s41467-017-00680-8
– volume: 41
  start-page: 1104
  year: 2012
  ident: 758_CR18
  publication-title: Nucleic Acids Res
  doi: 10.1093/nar/gks994
– start-page: 10
  volume-title: Drug Repurposing
  year: 2020
  ident: 758_CR1
– volume: 6
  start-page: 343
  year: 2010
  ident: 758_CR19
  publication-title: Mol Syst Biol
  doi: 10.1038/msb.2009.98
SSID ssj0064830
Score 2.3278592
Snippet Identifying drug-target interaction (DTI) is crucial for drug discovery and repositioning. Biological identification of DTI is costly and time-consuming, so...
SourceID proquest
pubmed
crossref
SourceType Aggregation Database
Index Database
Title VHGAE: Drug-Target Interaction Prediction Model Based on Heterogeneous Graph Variational Autoencoder
URI https://www.ncbi.nlm.nih.gov/pubmed/40841491
https://www.proquest.com/docview/3246300549
WOSCitedRecordID wos001555875900001&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: PRVAVX
  databaseName: SpringerLINK Contemporary 1997-Present
  customDbUrl:
  eissn: 1867-1462
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0064830
  issn: 1913-2751
  databaseCode: RSV
  dateStart: 20090301
  isFulltext: true
  titleUrlDefault: https://link.springer.com/search?facet-content-type=%22Journal%22
  providerName: Springer Nature
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT8MwDLYGAokL78d4KUjcIIKmbptwGzDYAU0TTNVuVdNkCAltqNuQ-Pc4aQdCggO39pK0tuXvcxzbAKchDoPYRMgJTg3HRAuuYoU8GEoPGQZ9xjR9SLpdORioXgPO_8zgX0wIgkPF3dhVh2-Su8reIBZuXMHjUzp3uzFKP1iE4o-QiyQK6gqZ35f4iUJ_UEsPMXdr__u4dVitqSRrVbrfgIYdbcJyNVzyYwtM2rlvta_YbTl75n1_4Zv587-qlIH1Spej8Y9uINoruyZAM4xeO-6KzJgsy45nE3bvWlqzlGLq-tyQtWbTset_aWy5Df27dv-mw-uZCrwgbUy5JEIm0BYqLjQ5Qo2BNQLjyGBolDRS56gvcRjlSWRFLjUWRlmhtJSoieqFO7A4Go_sHjBFXC0fCuPybMS5ZF4Qk8itJHzTcZBjE87mIs7eqs4Z2XePZCe2jMSWebFlsgkncy1kZOAua5H7v8yI8bm2YBTHNmG3Us_XengpkUK8YP9fex3AivAaIx8RHMLitJzZI1gq3qcvk_IYFpKBPPa29Ql1kMG5
linkProvider Springer Nature
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=VHGAE%3A+Drug-Target+Interaction+Prediction+Model+Based+on+Heterogeneous+Graph+Variational+Autoencoder&rft.jtitle=Interdisciplinary+sciences+%3A+computational+life+sciences&rft.au=Zhang%2C+Chen&rft.au=Sun%2C+Jiaqi&rft.au=Xing%2C+Linlin&rft.au=Zhang%2C+Longbo&rft.date=2025-08-21&rft.issn=1867-1462&rft.eissn=1867-1462&rft_id=info:doi/10.1007%2Fs12539-025-00758-8&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1913-2751&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1913-2751&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1913-2751&client=summon