Multisource Attention-Mechanism-Based Encoder-Decoder Model for Predicting Drug-Drug Interaction Events

Many computational methods have been proposed to predict drug-drug interactions (DDIs), which can occur when combining drugs to treat various diseases, but most mainly utilize single-source features of drugs, which is inadequate for drug representation. To fill this gap, we propose two attention-mec...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of chemical information and modeling Jg. 62; H. 23; S. 6258
Hauptverfasser: Pan, Deng, Quan, Lijun, Jin, Zhi, Chen, Taoning, Wang, Xuejiao, Xie, Jingxin, Wu, Tingfang, Lyu, Qiang
Format: Journal Article
Sprache:Englisch
Veröffentlicht: United States 12.12.2022
Schlagworte:
ISSN:1549-960X, 1549-960X
Online-Zugang:Weitere Angaben
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Many computational methods have been proposed to predict drug-drug interactions (DDIs), which can occur when combining drugs to treat various diseases, but most mainly utilize single-source features of drugs, which is inadequate for drug representation. To fill this gap, we propose two attention-mechanism-based encoder-decoder models that incorporate multisource information: one is MAEDDI, which can predict DDIs, and the other is MAEDDIE, which can make further DDI-associated event predictions for drug pairs with DDIs. To better express the drug feature, we used three encoding methods to encode the drugs, integrating the self-attention mechanism, cross-attention mechanism, and graph attention network to construct a multisource feature fusion network. Experiments showed that both MAEDDI and MAEDDIE performed better than some state-of-the-art methods in various validation attempts at different experimental tasks. The visualization analysis showed that the semantic features of drug pairs learned from our models had a good drug representation. In practice, MAEDDIE successfully screened 43 DDI events on favipiravir, an influenza antiviral drug, with a success rate of nearly 50%. Our model achieved competitive results, mainly owing to the design of sequence-based, structural, biochemical, and statistical multisource features. Moreover, different encoders constructed based on different features learn the interrelationship information between drug pairs, and the different representations of these drug pairs are incorporated to predict the target problem. All of these encoders were designed to better characterize the complex DDI relationships, allowing us to achieve high generalization in DDI and DDI-associated event predations.
AbstractList Many computational methods have been proposed to predict drug-drug interactions (DDIs), which can occur when combining drugs to treat various diseases, but most mainly utilize single-source features of drugs, which is inadequate for drug representation. To fill this gap, we propose two attention-mechanism-based encoder-decoder models that incorporate multisource information: one is MAEDDI, which can predict DDIs, and the other is MAEDDIE, which can make further DDI-associated event predictions for drug pairs with DDIs. To better express the drug feature, we used three encoding methods to encode the drugs, integrating the self-attention mechanism, cross-attention mechanism, and graph attention network to construct a multisource feature fusion network. Experiments showed that both MAEDDI and MAEDDIE performed better than some state-of-the-art methods in various validation attempts at different experimental tasks. The visualization analysis showed that the semantic features of drug pairs learned from our models had a good drug representation. In practice, MAEDDIE successfully screened 43 DDI events on favipiravir, an influenza antiviral drug, with a success rate of nearly 50%. Our model achieved competitive results, mainly owing to the design of sequence-based, structural, biochemical, and statistical multisource features. Moreover, different encoders constructed based on different features learn the interrelationship information between drug pairs, and the different representations of these drug pairs are incorporated to predict the target problem. All of these encoders were designed to better characterize the complex DDI relationships, allowing us to achieve high generalization in DDI and DDI-associated event predations.
Many computational methods have been proposed to predict drug-drug interactions (DDIs), which can occur when combining drugs to treat various diseases, but most mainly utilize single-source features of drugs, which is inadequate for drug representation. To fill this gap, we propose two attention-mechanism-based encoder-decoder models that incorporate multisource information: one is MAEDDI, which can predict DDIs, and the other is MAEDDIE, which can make further DDI-associated event predictions for drug pairs with DDIs. To better express the drug feature, we used three encoding methods to encode the drugs, integrating the self-attention mechanism, cross-attention mechanism, and graph attention network to construct a multisource feature fusion network. Experiments showed that both MAEDDI and MAEDDIE performed better than some state-of-the-art methods in various validation attempts at different experimental tasks. The visualization analysis showed that the semantic features of drug pairs learned from our models had a good drug representation. In practice, MAEDDIE successfully screened 43 DDI events on favipiravir, an influenza antiviral drug, with a success rate of nearly 50%. Our model achieved competitive results, mainly owing to the design of sequence-based, structural, biochemical, and statistical multisource features. Moreover, different encoders constructed based on different features learn the interrelationship information between drug pairs, and the different representations of these drug pairs are incorporated to predict the target problem. All of these encoders were designed to better characterize the complex DDI relationships, allowing us to achieve high generalization in DDI and DDI-associated event predations.Many computational methods have been proposed to predict drug-drug interactions (DDIs), which can occur when combining drugs to treat various diseases, but most mainly utilize single-source features of drugs, which is inadequate for drug representation. To fill this gap, we propose two attention-mechanism-based encoder-decoder models that incorporate multisource information: one is MAEDDI, which can predict DDIs, and the other is MAEDDIE, which can make further DDI-associated event predictions for drug pairs with DDIs. To better express the drug feature, we used three encoding methods to encode the drugs, integrating the self-attention mechanism, cross-attention mechanism, and graph attention network to construct a multisource feature fusion network. Experiments showed that both MAEDDI and MAEDDIE performed better than some state-of-the-art methods in various validation attempts at different experimental tasks. The visualization analysis showed that the semantic features of drug pairs learned from our models had a good drug representation. In practice, MAEDDIE successfully screened 43 DDI events on favipiravir, an influenza antiviral drug, with a success rate of nearly 50%. Our model achieved competitive results, mainly owing to the design of sequence-based, structural, biochemical, and statistical multisource features. Moreover, different encoders constructed based on different features learn the interrelationship information between drug pairs, and the different representations of these drug pairs are incorporated to predict the target problem. All of these encoders were designed to better characterize the complex DDI relationships, allowing us to achieve high generalization in DDI and DDI-associated event predations.
Author Pan, Deng
Wang, Xuejiao
Xie, Jingxin
Lyu, Qiang
Wu, Tingfang
Quan, Lijun
Chen, Taoning
Jin, Zhi
Author_xml – sequence: 1
  givenname: Deng
  surname: Pan
  fullname: Pan, Deng
  organization: School of Computer Science and Technology, Soochow University, Suzhou215006, China
– sequence: 2
  givenname: Lijun
  orcidid: 0000-0003-4551-4198
  surname: Quan
  fullname: Quan, Lijun
  organization: Collaborative Innovation Center of Novel Software Technology and Industrialization, Nanjing210000, China
– sequence: 3
  givenname: Zhi
  surname: Jin
  fullname: Jin, Zhi
  organization: School of Computer Science and Technology, Soochow University, Suzhou215006, China
– sequence: 4
  givenname: Taoning
  surname: Chen
  fullname: Chen, Taoning
  organization: School of Computer Science and Technology, Soochow University, Suzhou215006, China
– sequence: 5
  givenname: Xuejiao
  surname: Wang
  fullname: Wang, Xuejiao
  organization: School of Computer Science and Technology, Soochow University, Suzhou215006, China
– sequence: 6
  givenname: Jingxin
  surname: Xie
  fullname: Xie, Jingxin
  organization: School of Computer Science and Technology, Soochow University, Suzhou215006, China
– sequence: 7
  givenname: Tingfang
  surname: Wu
  fullname: Wu, Tingfang
  organization: Collaborative Innovation Center of Novel Software Technology and Industrialization, Nanjing210000, China
– sequence: 8
  givenname: Qiang
  surname: Lyu
  fullname: Lyu, Qiang
  organization: Collaborative Innovation Center of Novel Software Technology and Industrialization, Nanjing210000, China
BackLink https://www.ncbi.nlm.nih.gov/pubmed/36449561$$D View this record in MEDLINE/PubMed
BookMark eNpNkDtPwzAUhS1URB-wMyGPLC5-xGkylrY8pFYwdGCLbmynuEqcYjtI_HtSKBLDOecOR5-O7hgNXOsMQteMThnl7A5UmO6VbaZcUcYYP0MjJpOc5Cl9G_y7h2gcwp5SIfKUX6ChSJMklykbod2mq6MNbeeVwfMYjYu2dWRj1Ds4GxpyD8FovHKq1caTpflJvOm9xlXr8as32qpo3Q4vfbcjR8PPLhoP6ojCq8-eGS7ReQV1MFennKDtw2q7eCLrl8fnxXxNoN8UiQChs1JRnkEFNKMVSEggS4UWuSxLRqXUJVAQVS_NqVAlTyQ1GRMyzzM-Qbe_2INvPzoTYtHYoExdgzNtFwo-S4TsIbOkr96cql3ZGF0cvG3AfxV_v-HfoZBqOA
CitedBy_id crossref_primary_10_1109_JBHI_2023_3246225
crossref_primary_10_1109_TBDATA_2025_3536924
crossref_primary_10_1016_j_neucom_2023_127203
ContentType Journal Article
DBID CGR
CUY
CVF
ECM
EIF
NPM
7X8
DOI 10.1021/acs.jcim.2c01112
DatabaseName Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
MEDLINE - Academic
DatabaseTitle 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 no_fulltext_linktorsrc
Discipline Chemistry
EISSN 1549-960X
ExternalDocumentID 36449561
Genre Journal Article
GroupedDBID ---
-~X
4.4
55A
5GY
5VS
7~N
AABXI
ABJNI
ABMVS
ABQRX
ABUCX
ACGFS
ACIWK
ACNCT
ACS
ADHLV
AEESW
AENEX
AFEFF
AHGAQ
ALMA_UNASSIGNED_HOLDINGS
AQSVZ
CGR
CUPRZ
CUY
CVF
D0L
DU5
EBS
ECM
ED~
EIF
F5P
GGK
GNL
IH9
JG~
NPM
P2P
PQQKQ
RNS
ROL
UI2
VF5
VG9
W1F
7X8
ABBLG
ABLBI
ID FETCH-LOGICAL-a364t-3a3d8bc028afa080fa5a4a863d395bb1055dba0a3f0a3d203cb2450e81359982
IEDL.DBID 7X8
ISICitedReferencesCount 5
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000892124900001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1549-960X
IngestDate Fri Jul 11 08:31:34 EDT 2025
Thu Jan 02 22:53:11 EST 2025
IsPeerReviewed true
IsScholarly true
Issue 23
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-a364t-3a3d8bc028afa080fa5a4a863d395bb1055dba0a3f0a3d203cb2450e81359982
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ORCID 0000-0003-4551-4198
PMID 36449561
PQID 2743505574
PQPubID 23479
ParticipantIDs proquest_miscellaneous_2743505574
pubmed_primary_36449561
PublicationCentury 2000
PublicationDate 2022-Dec-12
20221212
PublicationDateYYYYMMDD 2022-12-12
PublicationDate_xml – month: 12
  year: 2022
  text: 2022-Dec-12
  day: 12
PublicationDecade 2020
PublicationPlace United States
PublicationPlace_xml – name: United States
PublicationTitle Journal of chemical information and modeling
PublicationTitleAlternate J Chem Inf Model
PublicationYear 2022
SSID ssj0033962
Score 2.419898
Snippet Many computational methods have been proposed to predict drug-drug interactions (DDIs), which can occur when combining drugs to treat various diseases, but...
SourceID proquest
pubmed
SourceType Aggregation Database
Index Database
StartPage 6258
SubjectTerms Drug Interactions
Semantics
Title Multisource Attention-Mechanism-Based Encoder-Decoder Model for Predicting Drug-Drug Interaction Events
URI https://www.ncbi.nlm.nih.gov/pubmed/36449561
https://www.proquest.com/docview/2743505574
Volume 62
WOSCitedRecordID wos000892124900001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV07T8MwELaAIsHC-1FeMhKr29ROmnRCpQ-xtOrQIVt0dpyqiKYlafn93CUpTEhISIk9RXLss--7lz_GnrQOfBfaiTCBY9BAoSBhJ46FdiGxum1x2XVBNuGPx0EYdiaVwy2v0iq3Z2JxUMdLQz7yJlpPyqMLo9zn1Ycg1iiKrlYUGrusphDKkFT74XcUQalOQShKt5AJROphFaZEtdYEkzfezHzRkIbY1uXvALNQNMPj_w7xhB1VEJN3S5k4ZTs2PWMHvS2z2zmbFVW3pdued9frMuNRjCxVAc_zhXhB1RbzQUr17pno26LnRJv2zhHk8klG4R1KmOb9bDMT1PDCt1iWSfABZVHmF2w6HEx7r6IiXBCg2u5aKFBxoA1CDkgAoWQCHrgQtFWsOp7WxKUZa3BAJfjG0lFGS9dzbNBSHppt8pLtpcvUXjMuncQDRIsASrlG4qbXvnSVAUu8HolfZ4_bKYzw5ylIAaldbvLoZxLr7Kpch2hVXrwR4SDJnmvd_OHrW3YoqVKhRc8dqyW4m-092zefOMHZQyEo2I4noy8DK8np
linkProvider ProQuest
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=Multisource+Attention-Mechanism-Based+Encoder-Decoder+Model+for+Predicting+Drug-Drug+Interaction+Events&rft.jtitle=Journal+of+chemical+information+and+modeling&rft.au=Pan%2C+Deng&rft.au=Quan%2C+Lijun&rft.au=Jin%2C+Zhi&rft.au=Chen%2C+Taoning&rft.date=2022-12-12&rft.eissn=1549-960X&rft.volume=62&rft.issue=23&rft.spage=6258&rft_id=info:doi/10.1021%2Facs.jcim.2c01112&rft_id=info%3Apmid%2F36449561&rft_id=info%3Apmid%2F36449561&rft.externalDocID=36449561
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1549-960X&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1549-960X&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1549-960X&client=summon