MAVGAE: a multimodal framework for predicting asymmetric drug-drug interactions based on variational graph autoencoder

Drug-drug interactions refer to the phenomena wherein the potency, duration, or effectiveness of one or multiple drugs undergo alterations of varying degrees as a result of their concurrent or sequential usage. The accurate identification of potential drug interactions plays a pivotal role in mitiga...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Computer methods in biomechanics and biomedical engineering Ročník 28; číslo 7; s. 1098 - 1110
Hlavní autoři: Deng, Zengqian, Xu, Jie, Feng, Yinfei, Dong, Liangcheng, Zhang, Yuanyuan
Médium: Journal Article
Jazyk:angličtina
Vydáno: England Taylor & Francis 19.05.2025
Témata:
ISSN:1025-5842, 1476-8259, 1476-8259
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Drug-drug interactions refer to the phenomena wherein the potency, duration, or effectiveness of one or multiple drugs undergo alterations of varying degrees as a result of their concurrent or sequential usage. The accurate identification of potential drug interactions plays a pivotal role in mitigating the risks associated with drug administration in patients, it also helps in minimizing the likelihood of hazardous situations arising during a patient's course of treatment. However, researchers have found that there is a problem of asymmetric drug interactions, where one drug may affect another but not vice versa. This adds to the difficulty of prediction, so in polypharmacy, the order of drug administration is critical to efficacy and safety, and few current studies predict asymmetric DDIs. Aiming at the above problems, we propose a framework based on multimodal data and a variational graph autoencoder named MAVGAE for predicting asymmetric drug interactions. The framework initially encodes multimodal data into low-dimensional representations and then utilizes a variational graph autoencoder for encoding and decoding. During the model training process, supervised learning is employed for the classification task with the incorporation of heterogeneity information, ensuring accurate prediction of drug interactions. Experimental validation on a large-scale drug dataset demonstrates the framework's high accuracy and reliability in predicting non-symmetrical drug interactions, offering effective support and guidance for drug research.
AbstractList Drug-drug interactions refer to the phenomena wherein the potency, duration, or effectiveness of one or multiple drugs undergo alterations of varying degrees as a result of their concurrent or sequential usage. The accurate identification of potential drug interactions plays a pivotal role in mitigating the risks associated with drug administration in patients, it also helps in minimizing the likelihood of hazardous situations arising during a patient's course of treatment. However, researchers have found that there is a problem of asymmetric drug interactions, where one drug may affect another but not vice versa. This adds to the difficulty of prediction, so in polypharmacy, the order of drug administration is critical to efficacy and safety, and few current studies predict asymmetric DDIs. Aiming at the above problems, we propose a framework based on multimodal data and a variational graph autoencoder named MAVGAE for predicting asymmetric drug interactions. The framework initially encodes multimodal data into low-dimensional representations and then utilizes a variational graph autoencoder for encoding and decoding. During the model training process, supervised learning is employed for the classification task with the incorporation of heterogeneity information, ensuring accurate prediction of drug interactions. Experimental validation on a large-scale drug dataset demonstrates the framework's high accuracy and reliability in predicting non-symmetrical drug interactions, offering effective support and guidance for drug research.
Drug-drug interactions refer to the phenomena wherein the potency, duration, or effectiveness of one or multiple drugs undergo alterations of varying degrees as a result of their concurrent or sequential usage. The accurate identification of potential drug interactions plays a pivotal role in mitigating the risks associated with drug administration in patients, it also helps in minimizing the likelihood of hazardous situations arising during a patient's course of treatment. However, researchers have found that there is a problem of asymmetric drug interactions, where one drug may affect another but not vice versa. This adds to the difficulty of prediction, so in polypharmacy, the order of drug administration is critical to efficacy and safety, and few current studies predict asymmetric DDIs. Aiming at the above problems, we propose a framework based on multimodal data and a variational graph autoencoder named MAVGAE for predicting asymmetric drug interactions. The framework initially encodes multimodal data into low-dimensional representations and then utilizes a variational graph autoencoder for encoding and decoding. During the model training process, supervised learning is employed for the classification task with the incorporation of heterogeneity information, ensuring accurate prediction of drug interactions. Experimental validation on a large-scale drug dataset demonstrates the framework's high accuracy and reliability in predicting non-symmetrical drug interactions, offering effective support and guidance for drug research.Drug-drug interactions refer to the phenomena wherein the potency, duration, or effectiveness of one or multiple drugs undergo alterations of varying degrees as a result of their concurrent or sequential usage. The accurate identification of potential drug interactions plays a pivotal role in mitigating the risks associated with drug administration in patients, it also helps in minimizing the likelihood of hazardous situations arising during a patient's course of treatment. However, researchers have found that there is a problem of asymmetric drug interactions, where one drug may affect another but not vice versa. This adds to the difficulty of prediction, so in polypharmacy, the order of drug administration is critical to efficacy and safety, and few current studies predict asymmetric DDIs. Aiming at the above problems, we propose a framework based on multimodal data and a variational graph autoencoder named MAVGAE for predicting asymmetric drug interactions. The framework initially encodes multimodal data into low-dimensional representations and then utilizes a variational graph autoencoder for encoding and decoding. During the model training process, supervised learning is employed for the classification task with the incorporation of heterogeneity information, ensuring accurate prediction of drug interactions. Experimental validation on a large-scale drug dataset demonstrates the framework's high accuracy and reliability in predicting non-symmetrical drug interactions, offering effective support and guidance for drug research.
Author Deng, Zengqian
Xu, Jie
Feng, Yinfei
Zhang, Yuanyuan
Dong, Liangcheng
Author_xml – sequence: 1
  givenname: Zengqian
  surname: Deng
  fullname: Deng, Zengqian
  organization: School of Information and Control Engineering, Qingdao University of Technology
– sequence: 2
  givenname: Jie
  surname: Xu
  fullname: Xu, Jie
  organization: School of Information Science and Engineering, Qufu Normal University
– sequence: 3
  givenname: Yinfei
  surname: Feng
  fullname: Feng, Yinfei
  organization: School of Information and Control Engineering, Qingdao University of Technology
– sequence: 4
  givenname: Liangcheng
  surname: Dong
  fullname: Dong, Liangcheng
  organization: School of Information and Control Engineering, Qingdao University of Technology
– sequence: 5
  givenname: Yuanyuan
  surname: Zhang
  fullname: Zhang, Yuanyuan
  organization: School of Information and Control Engineering, Qingdao University of Technology
BackLink https://www.ncbi.nlm.nih.gov/pubmed/38314513$$D View this record in MEDLINE/PubMed
BookMark eNqFkU2PEyEch4lZ4-5WP4KGo5epvAyU0YvNZl1N1nhRr4ThpaIDVGDW9NvL2PbiQS9AyPP7Ef7PNbiIKVoAnmO0xkigVxgRxkRP1gSRfk0oxhSzR-AK9xveCcKGi3ZuTLdAl-C6lO8IIYFF_wRcUkFxzzC9Ag8ft1_vtrevoYJhnqoPyagJuqyC_ZXyD-hShvtsjdfVxx1U5RCCrdlraPK865YF-lhtVg1IscBRFWtgivBBZa-Wu9a3y2r_Daq5Jht1MjY_BY-dmop9dtpX4Mu7288377v7T3cfbrb3naac185Ra0YulOO9xmrkw8g0xZZsNDcDw0wLy2m_YXxwo-F8JIPlm1EwrPmAuXN0BV4ee_c5_ZxtqTL4ou00qWjTXCQZCOkZQW0WK_DihM5jsEbusw8qH-R5Vg14cwR0TqVk66T29c8Pa1Z-khjJxYw8m5GLGXky09Lsr_T5gf_l3h5zPjYXQTUrk5FVHaaUm6aofZH03xW_AZWSpcw
CitedBy_id crossref_primary_10_1109_TCBBIO_2024_3502507
crossref_primary_10_3389_fphar_2025_1632775
crossref_primary_10_1038_s41746_025_01565_7
Cites_doi 10.1038/s41467-017-01929-y
10.1093/bioinformatics/btaa501
10.1073/pnas.1803294115
10.1093/bib/bbz087
10.1145/3357384.3358023
10.1093/bioinformatics/btx659
10.1021/acs.nanolett.1c01044
10.1145/3511808.3557648
10.3892/or.12.3.557
10.3389/fphar.2018.00197
10.1093/bib/bbac151
10.1186/s12859-023-05387-w
10.1109/TCBB.2020.2988018
10.1016/j.jep.2012.01.058
10.1021/acs.jcim.3c00582
10.1093/jac/dky183
10.3390/ijms21145014
10.1093/bib/bbab159
10.1158/1538-7445.AM2017-4100
10.1093/nar/gkx1037
10.1109/WACV45572.2020.9093380
10.7554/eLife.68876
10.1371/journal.pone.0273764
10.1016/j.ymeth.2019.02.009
10.1007/s13721-019-0215-3
10.1126/scitranslmed.3003377
10.1198/004017002317375064
10.1136/amiajnl-2011-000699
10.1371/journal.pcbi.1002998
ContentType Journal Article
Copyright 2024 Informa UK Limited, trading as Taylor & Francis Group 2024
Copyright_xml – notice: 2024 Informa UK Limited, trading as Taylor & Francis Group 2024
DBID AAYXX
CITATION
CGR
CUY
CVF
ECM
EIF
NPM
7X8
DOI 10.1080/10255842.2024.2311315
DatabaseName 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 - Academic
MEDLINE
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 1476-8259
EndPage 1110
ExternalDocumentID 38314513
10_1080_10255842_2024_2311315
2311315
Genre Method
Journal Article
GrantInformation_xml – fundername: the National Natural Science Foundation of China
  grantid: 61902430
– fundername: Natural Science Foundation of Shandong Province
  grantid: ZR2023MF053
GroupedDBID ---
.7F
.QJ
0BK
0R~
29F
2DF
30N
36B
4.4
53G
5GY
5VS
AAENE
AAGDL
AAHIA
AAJMT
AALDU
AAMIU
AAPUL
AAQRR
ABCCY
ABFIM
ABHAV
ABJNI
ABLIJ
ABPAQ
ABPEM
ABTAI
ABXUL
ABXYU
ACGEJ
ACGFS
ACIWK
ACPRK
ACTIO
ADCVX
ADGTB
ADMLS
ADXPE
AEISY
AENEX
AEOZL
AEPSL
AEYOC
AFKVX
AFRAH
AFRVT
AGDLA
AGMYJ
AHDZW
AIJEM
AIYEW
AJWEG
AKBVH
AKOOK
ALMA_UNASSIGNED_HOLDINGS
ALQZU
AQRUH
AQTUD
AVBZW
AWYRJ
BLEHA
CCCUG
CE4
CS3
DGEBU
DKSSO
DU5
EBS
EMOBN
E~A
E~B
F5P
GTTXZ
H13
HF~
H~P
IPNFZ
J.P
KYCEM
LJTGL
M4Z
NA5
P2P
RIG
RNANH
ROSJB
RTWRZ
S-T
SNACF
TASJS
TBQAZ
TDBHL
TEN
TFL
TFT
TFW
TN5
TNC
TTHFI
TUROJ
TWF
UT5
UU3
ZGOLN
~S~
AAYXX
CITATION
1TA
ACTTO
ADUMR
ADYSH
AFBWG
AFION
AGVKY
AGWUF
ALRRR
BWMZZ
CAG
CGR
COF
CUY
CVF
CYRSC
DAOYK
ECM
EIF
EJD
NPM
OPCYK
7X8
ID FETCH-LOGICAL-c366t-f3edb68af64c1ab69b5c31e27c6d9515c8e6347569fbd66b29e67b851c6916ff3
IEDL.DBID TFW
ISICitedReferencesCount 8
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001158086600001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1025-5842
1476-8259
IngestDate Sun Nov 09 11:34:31 EST 2025
Mon Jul 21 05:56:46 EDT 2025
Sat Nov 29 07:43:36 EST 2025
Tue Nov 18 21:49:02 EST 2025
Mon Oct 20 23:45:01 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 7
Keywords multimodal
asymmetric drug-drug interaction
Artificial intelligence
variational autoencoder
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c366t-f3edb68af64c1ab69b5c31e27c6d9515c8e6347569fbd66b29e67b851c6916ff3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
PMID 38314513
PQID 2922452051
PQPubID 23479
PageCount 13
ParticipantIDs informaworld_taylorfrancis_310_1080_10255842_2024_2311315
proquest_miscellaneous_2922452051
pubmed_primary_38314513
crossref_citationtrail_10_1080_10255842_2024_2311315
crossref_primary_10_1080_10255842_2024_2311315
PublicationCentury 2000
PublicationDate 2025-05-19
PublicationDateYYYYMMDD 2025-05-19
PublicationDate_xml – month: 05
  year: 2025
  text: 2025-05-19
  day: 19
PublicationDecade 2020
PublicationPlace England
PublicationPlace_xml – name: England
PublicationTitle Computer methods in biomechanics and biomedical engineering
PublicationTitleAlternate Comput Methods Biomech Biomed Engin
PublicationYear 2025
Publisher Taylor & Francis
Publisher_xml – name: Taylor & Francis
References e_1_3_3_30_1
e_1_3_3_18_1
e_1_3_3_17_1
e_1_3_3_14_1
e_1_3_3_13_1
e_1_3_3_16_1
e_1_3_3_35_1
e_1_3_3_15_1
e_1_3_3_36_1
e_1_3_3_10_1
e_1_3_3_33_1
Razek A (e_1_3_3_19_1) 1974; 34
e_1_3_3_34_1
e_1_3_3_12_1
e_1_3_3_31_1
e_1_3_3_32_1
e_1_3_3_7_1
e_1_3_3_6_1
e_1_3_3_9_1
e_1_3_3_8_1
e_1_3_3_29_1
e_1_3_3_28_1
Kalafut NC (e_1_3_3_11_1) 2023; 5
e_1_3_3_25_1
e_1_3_3_24_1
e_1_3_3_27_1
e_1_3_3_26_1
e_1_3_3_3_1
e_1_3_3_2_1
e_1_3_3_20_1
e_1_3_3_5_1
e_1_3_3_23_1
e_1_3_3_4_1
Rodziewicz TL (e_1_3_3_21_1) 2020
e_1_3_3_22_1
References_xml – ident: e_1_3_3_27_1
  doi: 10.1038/s41467-017-01929-y
– ident: e_1_3_3_6_1
  doi: 10.1093/bioinformatics/btaa501
– ident: e_1_3_3_23_1
  doi: 10.1073/pnas.1803294115
– ident: e_1_3_3_32_1
  doi: 10.1093/bib/bbz087
– volume-title: StatPearls
  year: 2020
  ident: e_1_3_3_21_1
– ident: e_1_3_3_24_1
  doi: 10.1145/3357384.3358023
– ident: e_1_3_3_35_1
  doi: 10.1093/bioinformatics/btx659
– ident: e_1_3_3_5_1
  doi: 10.1021/acs.nanolett.1c01044
– ident: e_1_3_3_36_1
  doi: 10.1145/3511808.3557648
– volume: 34
  start-page: 1857
  issue: 8
  year: 1974
  ident: e_1_3_3_19_1
  article-title: Optimum time sequence for the administration of vincristine and cyclophosphamide in vivo
  publication-title: Cancer Res
– ident: e_1_3_3_13_1
– ident: e_1_3_3_15_1
  doi: 10.3892/or.12.3.557
– ident: e_1_3_3_18_1
  doi: 10.3389/fphar.2018.00197
– ident: e_1_3_3_7_1
  doi: 10.1093/bib/bbac151
– ident: e_1_3_3_34_1
  doi: 10.1186/s12859-023-05387-w
– ident: e_1_3_3_29_1
  doi: 10.1109/TCBB.2020.2988018
– ident: e_1_3_3_31_1
  doi: 10.1016/j.jep.2012.01.058
– ident: e_1_3_3_33_1
  doi: 10.1021/acs.jcim.3c00582
– ident: e_1_3_3_16_1
  doi: 10.1093/jac/dky183
– ident: e_1_3_3_30_1
  doi: 10.3390/ijms21145014
– volume: 5
  start-page: 1
  issue: 6
  year: 2023
  ident: e_1_3_3_11_1
  article-title: Joint variational autoencoders for multimodal imputation and embedding
  publication-title: Nat Mach Intell
– ident: e_1_3_3_20_1
– ident: e_1_3_3_9_1
  doi: 10.1093/bib/bbab159
– ident: e_1_3_3_2_1
  doi: 10.1158/1538-7445.AM2017-4100
– ident: e_1_3_3_28_1
  doi: 10.1093/nar/gkx1037
– ident: e_1_3_3_4_1
  doi: 10.1109/WACV45572.2020.9093380
– ident: e_1_3_3_3_1
  doi: 10.7554/eLife.68876
– ident: e_1_3_3_12_1
  doi: 10.1371/journal.pone.0273764
– ident: e_1_3_3_25_1
  doi: 10.1016/j.ymeth.2019.02.009
– ident: e_1_3_3_22_1
  doi: 10.1007/s13721-019-0215-3
– ident: e_1_3_3_26_1
  doi: 10.1126/scitranslmed.3003377
– ident: e_1_3_3_8_1
  doi: 10.1198/004017002317375064
– ident: e_1_3_3_14_1
– ident: e_1_3_3_17_1
  doi: 10.1136/amiajnl-2011-000699
– ident: e_1_3_3_10_1
  doi: 10.1371/journal.pcbi.1002998
SSID ssj0008184
Score 2.4303489
Snippet Drug-drug interactions refer to the phenomena wherein the potency, duration, or effectiveness of one or multiple drugs undergo alterations of varying degrees...
SourceID proquest
pubmed
crossref
informaworld
SourceType Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 1098
SubjectTerms Algorithms
Artificial intelligence
asymmetric drug-drug interaction
Autoencoder
Drug Interactions
multimodal
variational autoencoder
Title MAVGAE: a multimodal framework for predicting asymmetric drug-drug interactions based on variational graph autoencoder
URI https://www.tandfonline.com/doi/abs/10.1080/10255842.2024.2311315
https://www.ncbi.nlm.nih.gov/pubmed/38314513
https://www.proquest.com/docview/2922452051
Volume 28
WOSCitedRecordID wos001158086600001&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: PRVAWR
  databaseName: Taylor & Francis Journals Complete
  customDbUrl:
  eissn: 1476-8259
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0008184
  issn: 1025-5842
  databaseCode: TFW
  dateStart: 19970101
  isFulltext: true
  titleUrlDefault: https://www.tandfonline.com
  providerName: Taylor & Francis
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1La9wwEBZpSKGX5tHXNg8U6NVLLcmy1NsSssklIYck3ZuQ9SiBrB1s70L-fTWyvXQPyx6ai43BY8vyjGakGX0fQj8KpgHHMktyl5qEaeYSTYRJDMsA_k4YbU0km8hvb8VsJu_6asKmL6uEObTvgCLiWA3GrYtmqIgL5xAHCwbbqAgbhwAlpXGbeXD9YJr309-rsTi4o5hXBtJWEBn28Gx6ypp3WsMu3RyBRk803X-DbzhAH_swFE86vTlEO648Qu87YsrXT2h5M3m8mlz-whrHisN5ZcPdfijkwqHB-KWGHA9UTWPdvM7nQM1lsK0XfxI4YACiqLttEw0GZ2lxVeJlmJv36484gmVjvWgrQNO0rv6MHqaX9xfXSc_QkBjKeZt46mzBhfacmVQXXBaZoakjueE2hG6ZEY5Tlmdc-sJyXhDpeF6EIM_wEJZ6T7-g3bIq3TeEw1UWnGkqXAQMIlpT4qUm1JKfOpd6hNjwZ5Tp4cuBReNZpT3K6dClCrpU9V06QuOV2EuH37FNQP7721UbF058x3Ki6BbZ80FHVLBSSL3o0lWLRhFJIMUdRsAR-topz6o5VFCgS6bf_-PNx-gDAR0HWFl5gnbbeuFO0Z5Ztk9NfYbe5TNxFi3jL27ZB00
linkProvider Taylor & Francis
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LT-MwELZWXdByWR77oMvLSHtNRWzHifdWrSisgJ4K9GY5fqCVtglK00r8-_U4SUUPiANcEkXKJI4z9ow9M9-H0M-cKcCxTKLUxjpiitlIkUxHmiUAf5dpZXQgm0jH42w6Fc9rYSCtEtbQrgGKCHM1DG7YjO5S4vzZO8IZgzoqwgbeQ4kp1Jl_TLytBfz8yeh-NRt7gxQiy0DbCjJdFc9Lj1mzT2vopS_7oMEWjbbf4yt20OfWE8XDRnV20Qdb7KHNhpvy6Qta3gzvLobnv7DCIelwVhp_t-tyubBvMX6sIMwDidNYzZ9mM2Dn0thUi4cIDhiwKKqmcmKOwV4aXBZ46Zfn7RYkDnjZWC3qEgA1ja2-otvR-eT3ZdSSNESacl5HjlqT80w5znSsci7yRNPYklRz4723RGeWU5YmXLjccJ4TYXmaez9Pc--ZOke_oV5RFnYfYX-VeHsaZzZgBhGlKHFCEWrImUqF6iPW_RqpWwRzINL4J-MW6LTrUgldKtsu7aPBSuyxgfB4TUA8_--yDnsnriE6kfQV2dNOSaQfqBB9UYUtF3NJBIEot58E--h7oz2r5tCMAmMy_fGGN5-gT5eTm2t5_Wd8dYC2CCg8oMyKQ9Srq4U9Qht6Wf-dV8dhgPwH50oKjw
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1NT9wwELUQtBWXUmihWygYiWsQsR0n7m0FbEEtKw6UcrMcfyAkNlkl2ZX493icZAUHxAEuiSJlEscZe8aemfcQOsiZAhzLJEptrCOmmI0UyXSkWQLwd5lWRgeyiXQ8zm5uxGWXTVh3aZWwhnYtUESYq2FwT43rM-L82fvBGYMyKsIOvYMSUygzX_GuMwclvxr9X0zG3h6FwDKwtoJMX8Tz0mOemadn4KUvu6DBFI3W3uEjvqDPnR-Kh63irKMlW2ygjy0z5cNXNL8YXv8env7CCoeUw0lp_N2uz-TCvsF4WkGQB9KmsaofJhPg5tLYVLPbCA4YkCiqtm6ixmAtDS4LPPeL824DEge0bKxmTQlwmsZW39C_0enV8VnUUTREmnLeRI5ak_NMOc50rHIu8kTT2JJUc-N9t0RnllOWJly43HCeE2F5mnsvT3PvlzpHN9FyURb2O8L-KvHWNM5sQAwiSlHihCLUkCOVCjVArP8zUnf45UCjcS_jDua071IJXSq7Lh2gw4XYtAXweE1APP3tsgk7J66lOZH0Fdn9XkekH6YQe1GFLWe1JIJAjNtPgQO01SrPojk0o8CXTH-84c176NPlyUj-PR__2UarBNQdIGbFDlpuqpn9iT7oeXNXV7theDwCsrEJQQ
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=MAVGAE%3A+a+multimodal+framework+for+predicting+asymmetric+drug-drug+interactions+based+on+variational+graph+autoencoder&rft.jtitle=Computer+methods+in+biomechanics+and+biomedical+engineering&rft.au=Deng%2C+Zengqian&rft.au=Xu%2C+Jie&rft.au=Feng%2C+Yinfei&rft.au=Dong%2C+Liangcheng&rft.date=2025-05-19&rft.pub=Taylor+%26+Francis&rft.issn=1025-5842&rft.eissn=1476-8259&rft.volume=28&rft.issue=7&rft.spage=1098&rft.epage=1110&rft_id=info:doi/10.1080%2F10255842.2024.2311315&rft.externalDocID=2311315
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1025-5842&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1025-5842&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1025-5842&client=summon