Graph generative and adversarial strategy-enhanced node feature learning and self-calibrated pairwise attribute encoding for prediction of drug-related side effects
Background: Inferring drug-related side effects is beneficial for reducing drug development cost and time. Current computational prediction methods have concentrated on graph reasoning over heterogeneous graphs comprising the drug and side effect nodes. However, the various topologies and node attri...
Uloženo v:
| Vydáno v: | Frontiers in pharmacology Ročník 14; s. 1257842 |
|---|---|
| Hlavní autoři: | , , , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Frontiers Media S.A
04.09.2023
|
| Témata: | |
| ISSN: | 1663-9812, 1663-9812 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Background:
Inferring drug-related side effects is beneficial for reducing drug development cost and time. Current computational prediction methods have concentrated on graph reasoning over heterogeneous graphs comprising the drug and side effect nodes. However, the various topologies and node attributes within multiple drug–side effect heterogeneous graphs have not been completely exploited.
Methods:
We proposed a new drug-side effect association prediction method, GGSC, to deeply integrate the diverse topologies and attributes from multiple heterogeneous graphs and the self-calibration attributes of each drug-side effect node pair. First, we created two heterogeneous graphs comprising the drug and side effect nodes and their related similarity and association connections. Since each heterogeneous graph has its specific topology and node attributes, a node feature learning strategy was designed and the learning for each graph was enhanced from a graph generative and adversarial perspective. We constructed a generator based on a graph convolutional autoencoder to encode the topological structure and node attributes from the whole heterogeneous graph and then generate the node features embedding the graph topology. A discriminator based on multilayer perceptron was designed to distinguish the generated topological features from the original ones. We also designed representation-level attention to discriminate the contributions of topological representations from multiple heterogeneous graphs and adaptively fused them. Finally, we constructed a self-calibration module based on convolutional neural networks to guide pairwise attribute learning through the features of the small latent space.
Results:
The comparison experiment results showed that GGSC had higher prediction performance than several state-of-the-art prediction methods. The ablation experiments demonstrated the effectiveness of topological enhancement learning, representation-level attention, and self-calibrated pairwise attribute learning. In addition, case studies over five drugs demonstrated GGSC’s ability in discovering the potential drug-related side effect candidates.
Conclusion:
We proposed a drug-side effect association prediction method, and the method is beneficial for screening the reliable association candidates for the biologists to discover the actual associations. |
|---|---|
| AbstractList | Background: Inferring drug-related side effects is beneficial for reducing drug development cost and time. Current computational prediction methods have concentrated on graph reasoning over heterogeneous graphs comprising the drug and side effect nodes. However, the various topologies and node attributes within multiple drug–side effect heterogeneous graphs have not been completely exploited.Methods: We proposed a new drug-side effect association prediction method, GGSC, to deeply integrate the diverse topologies and attributes from multiple heterogeneous graphs and the self-calibration attributes of each drug-side effect node pair. First, we created two heterogeneous graphs comprising the drug and side effect nodes and their related similarity and association connections. Since each heterogeneous graph has its specific topology and node attributes, a node feature learning strategy was designed and the learning for each graph was enhanced from a graph generative and adversarial perspective. We constructed a generator based on a graph convolutional autoencoder to encode the topological structure and node attributes from the whole heterogeneous graph and then generate the node features embedding the graph topology. A discriminator based on multilayer perceptron was designed to distinguish the generated topological features from the original ones. We also designed representation-level attention to discriminate the contributions of topological representations from multiple heterogeneous graphs and adaptively fused them. Finally, we constructed a self-calibration module based on convolutional neural networks to guide pairwise attribute learning through the features of the small latent space.Results: The comparison experiment results showed that GGSC had higher prediction performance than several state-of-the-art prediction methods. The ablation experiments demonstrated the effectiveness of topological enhancement learning, representation-level attention, and self-calibrated pairwise attribute learning. In addition, case studies over five drugs demonstrated GGSC’s ability in discovering the potential drug-related side effect candidates.Conclusion: We proposed a drug-side effect association prediction method, and the method is beneficial for screening the reliable association candidates for the biologists to discover the actual associations. Background: Inferring drug-related side effects is beneficial for reducing drug development cost and time. Current computational prediction methods have concentrated on graph reasoning over heterogeneous graphs comprising the drug and side effect nodes. However, the various topologies and node attributes within multiple drug–side effect heterogeneous graphs have not been completely exploited. Methods: We proposed a new drug-side effect association prediction method, GGSC, to deeply integrate the diverse topologies and attributes from multiple heterogeneous graphs and the self-calibration attributes of each drug-side effect node pair. First, we created two heterogeneous graphs comprising the drug and side effect nodes and their related similarity and association connections. Since each heterogeneous graph has its specific topology and node attributes, a node feature learning strategy was designed and the learning for each graph was enhanced from a graph generative and adversarial perspective. We constructed a generator based on a graph convolutional autoencoder to encode the topological structure and node attributes from the whole heterogeneous graph and then generate the node features embedding the graph topology. A discriminator based on multilayer perceptron was designed to distinguish the generated topological features from the original ones. We also designed representation-level attention to discriminate the contributions of topological representations from multiple heterogeneous graphs and adaptively fused them. Finally, we constructed a self-calibration module based on convolutional neural networks to guide pairwise attribute learning through the features of the small latent space. Results: The comparison experiment results showed that GGSC had higher prediction performance than several state-of-the-art prediction methods. The ablation experiments demonstrated the effectiveness of topological enhancement learning, representation-level attention, and self-calibrated pairwise attribute learning. In addition, case studies over five drugs demonstrated GGSC’s ability in discovering the potential drug-related side effect candidates. Conclusion: We proposed a drug-side effect association prediction method, and the method is beneficial for screening the reliable association candidates for the biologists to discover the actual associations. Background: Inferring drug-related side effects is beneficial for reducing drug development cost and time. Current computational prediction methods have concentrated on graph reasoning over heterogeneous graphs comprising the drug and side effect nodes. However, the various topologies and node attributes within multiple drug-side effect heterogeneous graphs have not been completely exploited. Methods: We proposed a new drug-side effect association prediction method, GGSC, to deeply integrate the diverse topologies and attributes from multiple heterogeneous graphs and the self-calibration attributes of each drug-side effect node pair. First, we created two heterogeneous graphs comprising the drug and side effect nodes and their related similarity and association connections. Since each heterogeneous graph has its specific topology and node attributes, a node feature learning strategy was designed and the learning for each graph was enhanced from a graph generative and adversarial perspective. We constructed a generator based on a graph convolutional autoencoder to encode the topological structure and node attributes from the whole heterogeneous graph and then generate the node features embedding the graph topology. A discriminator based on multilayer perceptron was designed to distinguish the generated topological features from the original ones. We also designed representation-level attention to discriminate the contributions of topological representations from multiple heterogeneous graphs and adaptively fused them. Finally, we constructed a self-calibration module based on convolutional neural networks to guide pairwise attribute learning through the features of the small latent space. Results: The comparison experiment results showed that GGSC had higher prediction performance than several state-of-the-art prediction methods. The ablation experiments demonstrated the effectiveness of topological enhancement learning, representation-level attention, and self-calibrated pairwise attribute learning. In addition, case studies over five drugs demonstrated GGSC's ability in discovering the potential drug-related side effect candidates. Conclusion: We proposed a drug-side effect association prediction method, and the method is beneficial for screening the reliable association candidates for the biologists to discover the actual associations.Background: Inferring drug-related side effects is beneficial for reducing drug development cost and time. Current computational prediction methods have concentrated on graph reasoning over heterogeneous graphs comprising the drug and side effect nodes. However, the various topologies and node attributes within multiple drug-side effect heterogeneous graphs have not been completely exploited. Methods: We proposed a new drug-side effect association prediction method, GGSC, to deeply integrate the diverse topologies and attributes from multiple heterogeneous graphs and the self-calibration attributes of each drug-side effect node pair. First, we created two heterogeneous graphs comprising the drug and side effect nodes and their related similarity and association connections. Since each heterogeneous graph has its specific topology and node attributes, a node feature learning strategy was designed and the learning for each graph was enhanced from a graph generative and adversarial perspective. We constructed a generator based on a graph convolutional autoencoder to encode the topological structure and node attributes from the whole heterogeneous graph and then generate the node features embedding the graph topology. A discriminator based on multilayer perceptron was designed to distinguish the generated topological features from the original ones. We also designed representation-level attention to discriminate the contributions of topological representations from multiple heterogeneous graphs and adaptively fused them. Finally, we constructed a self-calibration module based on convolutional neural networks to guide pairwise attribute learning through the features of the small latent space. Results: The comparison experiment results showed that GGSC had higher prediction performance than several state-of-the-art prediction methods. The ablation experiments demonstrated the effectiveness of topological enhancement learning, representation-level attention, and self-calibrated pairwise attribute learning. In addition, case studies over five drugs demonstrated GGSC's ability in discovering the potential drug-related side effect candidates. Conclusion: We proposed a drug-side effect association prediction method, and the method is beneficial for screening the reliable association candidates for the biologists to discover the actual associations. Background: Inferring drug-related side effects is beneficial for reducing drug development cost and time. Current computational prediction methods have concentrated on graph reasoning over heterogeneous graphs comprising the drug and side effect nodes. However, the various topologies and node attributes within multiple drug–side effect heterogeneous graphs have not been completely exploited. Methods: We proposed a new drug-side effect association prediction method, GGSC, to deeply integrate the diverse topologies and attributes from multiple heterogeneous graphs and the self-calibration attributes of each drug-side effect node pair. First, we created two heterogeneous graphs comprising the drug and side effect nodes and their related similarity and association connections. Since each heterogeneous graph has its specific topology and node attributes, a node feature learning strategy was designed and the learning for each graph was enhanced from a graph generative and adversarial perspective. We constructed a generator based on a graph convolutional autoencoder to encode the topological structure and node attributes from the whole heterogeneous graph and then generate the node features embedding the graph topology. A discriminator based on multilayer perceptron was designed to distinguish the generated topological features from the original ones. We also designed representation-level attention to discriminate the contributions of topological representations from multiple heterogeneous graphs and adaptively fused them. Finally, we constructed a self-calibration module based on convolutional neural networks to guide pairwise attribute learning through the features of the small latent space. Results: The comparison experiment results showed that GGSC had higher prediction performance than several state-of-the-art prediction methods. The ablation experiments demonstrated the effectiveness of topological enhancement learning, representation-level attention, and self-calibrated pairwise attribute learning. In addition, case studies over five drugs demonstrated GGSC’s ability in discovering the potential drug-related side effect candidates. Conclusion: We proposed a drug-side effect association prediction method, and the method is beneficial for screening the reliable association candidates for the biologists to discover the actual associations. |
| Author | Cui, Hui Xuan, Ping Zhang, Tiangang Xu, Kai Nakaguchi, Toshiya |
| AuthorAffiliation | 3 Department of Computer Science and Information Technology , La Trobe University , Melbourne , VI , Australia 1 Department of Computer Science , School of Engineering , Shantou University , Shantou , China 2 School of Computer Science and Technology , Heilongjiang University , Harbin , China 5 School of Mathematical Science , Heilongjiang University , Harbin , China 4 Center for Frontier Medical Engineering , Chiba University , Chiba , Japan |
| AuthorAffiliation_xml | – name: 3 Department of Computer Science and Information Technology , La Trobe University , Melbourne , VI , Australia – name: 5 School of Mathematical Science , Heilongjiang University , Harbin , China – name: 1 Department of Computer Science , School of Engineering , Shantou University , Shantou , China – name: 4 Center for Frontier Medical Engineering , Chiba University , Chiba , Japan – name: 2 School of Computer Science and Technology , Heilongjiang University , Harbin , China |
| Author_xml | – sequence: 1 givenname: Ping surname: Xuan fullname: Xuan, Ping – sequence: 2 givenname: Kai surname: Xu fullname: Xu, Kai – sequence: 3 givenname: Hui surname: Cui fullname: Cui, Hui – sequence: 4 givenname: Toshiya surname: Nakaguchi fullname: Nakaguchi, Toshiya – sequence: 5 givenname: Tiangang surname: Zhang fullname: Zhang, Tiangang |
| BookMark | eNp9ks1u3SAQha0qlZqmeYGuWHbjWwO2wauqito0UqRs2jUaw-BLxAUX8K3yPn3Q-v6oSrooG9DMOd8gOG-rixADVtV72mw4l8NHO28hbVjD-IayTsiWvaouad_zepCUXTw7v6muc35s1sWHgfftZfX7NsG8JRMGTFDcHgkEQ8DsMWVIDjzJZW3g9FRj2ELQaEiIBolFKEtC4hFScGE6-jJ6W2vwbjx4DJnBpV8ur9BSkhuXggSDjuagtzGROaFxurgYSLTEpGWqE_qjNbt1CFqLuuR31WsLPuP1eb-qfnz98v3mW33_cHt38_m-1nyQpUZqaQudMDB2zAId6cCNZK2wojfU9ohtgxa5RNuCHFAyYVADCoZW2t7wq-ruxDURHtWc3A7Sk4rg1LEQ06QgFac9Kstp27EBUI5dy5phlLIRY2-QCq0FG1fWpxNrXsYdGo1hfUf_AvqyE9xWTXGvaNM1gnV8JXw4E1L8uWAuaueyRu8hYFyyYrIXtJVDJ1cpO0l1ijkntH_n0EYdMqKOGVGHjKhzRlaT_MekXYHDZ6z3cf5_1j-BI8ub |
| CitedBy_id | crossref_primary_10_1021_acs_jcim_5c00136 crossref_primary_10_1016_j_compbiomed_2024_109321 crossref_primary_10_3390_ph17060795 crossref_primary_10_1007_s11704_024_31063_0 |
| Cites_doi | 10.1093/nar/gkaa891 10.1038/s41397-021-00246-4 10.1073/pnas.0931261100 10.1136/amiajnl-2011-000699 10.1016/j.compbiolchem.2017.03.008 10.1016/j.jbi.2022.104122 10.1186/1471-2105-14-207 10.1093/bib/bbab586 10.1093/bib/bbv020 10.1021/acs.jcim.5b00330 10.1093/bioinformatics/btaa973 10.1016/j.neucom.2018.01.085 10.1093/nar/gkr299 10.1093/bioinformatics/btw770 10.1038/s41467-017-00680-8 10.1093/bioinformatics/bts383 10.1155/2020/4675395 10.1016/j.neucom.2018.10.028 10.1016/j.mbs.2018.09.010 10.1073/pnas.1000138107 10.1186/s12859-015-0774-y 10.1371/journal.pone.0118432 10.1109/TCBB.2022.3141103 10.1093/bib/bbac126 10.1038/s41467-020-18305-y 10.1093/bib/bbab449 10.1093/bioinformatics/btq241 10.1155/2020/1357630 10.1109/JBHI.2018.2883834 10.1093/nar/gkm958 10.1093/nar/gkv1075 10.1371/journal.pcbi.1000441 10.1186/s12911-021-01402-3 10.3390/molecules24203668 10.1109/TCBB.2018.2850884 10.1093/bib/bbab239 10.1186/1471-2105-12-169 10.1002/ddr.21669 10.1186/s12859-018-2563-x 10.5860/choice.52.10.1601 10.1109/access.2017.2755045 10.1093/nar/gkaa997 |
| ContentType | Journal Article |
| Copyright | Copyright © 2023 Xuan, Xu, Cui, Nakaguchi and Zhang. Copyright © 2023 Xuan, Xu, Cui, Nakaguchi and Zhang. 2023 Xuan, Xu, Cui, Nakaguchi and Zhang |
| Copyright_xml | – notice: Copyright © 2023 Xuan, Xu, Cui, Nakaguchi and Zhang. – notice: Copyright © 2023 Xuan, Xu, Cui, Nakaguchi and Zhang. 2023 Xuan, Xu, Cui, Nakaguchi and Zhang |
| DBID | AAYXX CITATION 7X8 5PM DOA |
| DOI | 10.3389/fphar.2023.1257842 |
| DatabaseName | CrossRef MEDLINE - Academic PubMed Central (Full Participant titles) DOAJ Directory of Open Access Journals |
| DatabaseTitle | CrossRef MEDLINE - Academic |
| DatabaseTitleList | MEDLINE - Academic CrossRef |
| Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Pharmacy, Therapeutics, & Pharmacology |
| DocumentTitleAlternate | Xuan et al |
| EISSN | 1663-9812 |
| ExternalDocumentID | oai_doaj_org_article_f314529ae8b54209b8807b6de17cc72b PMC10507253 10_3389_fphar_2023_1257842 |
| GroupedDBID | 53G 5VS 9T4 AAFWJ AAKDD AAYXX ACGFO ACGFS ADBBV ADRAZ AENEX AFPKN ALMA_UNASSIGNED_HOLDINGS AOIJS BAWUL BCNDV CITATION DIK EMOBN GROUPED_DOAJ GX1 HYE KQ8 M48 M~E O5R O5S OK1 P2P PGMZT RNS RPM 7X8 5PM |
| ID | FETCH-LOGICAL-c398t-e1f14a57dab52fa1b193d8247f76d1f6ee40efe38ef4a89e827decae72ef8f6d3 |
| IEDL.DBID | DOA |
| ISICitedReferencesCount | 3 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001066959600001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1663-9812 |
| IngestDate | Fri Oct 03 12:50:45 EDT 2025 Tue Sep 30 17:12:55 EDT 2025 Thu Sep 04 19:47:53 EDT 2025 Sat Nov 29 04:11:13 EST 2025 Tue Nov 18 22:04:51 EST 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Language | English |
| License | This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c398t-e1f14a57dab52fa1b193d8247f76d1f6ee40efe38ef4a89e827decae72ef8f6d3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 Li Peng, Shanxi Agricultural University, China Edited by: Thomas Hartung, Johns Hopkins University, United States Reviewed by: Wen Zhang, Huazhong Agricultural University, China |
| OpenAccessLink | https://doaj.org/article/f314529ae8b54209b8807b6de17cc72b |
| PQID | 2867148958 |
| PQPubID | 23479 |
| ParticipantIDs | doaj_primary_oai_doaj_org_article_f314529ae8b54209b8807b6de17cc72b pubmedcentral_primary_oai_pubmedcentral_nih_gov_10507253 proquest_miscellaneous_2867148958 crossref_primary_10_3389_fphar_2023_1257842 crossref_citationtrail_10_3389_fphar_2023_1257842 |
| PublicationCentury | 2000 |
| PublicationDate | 2023-09-04 |
| PublicationDateYYYYMMDD | 2023-09-04 |
| PublicationDate_xml | – month: 09 year: 2023 text: 2023-09-04 day: 04 |
| PublicationDecade | 2020 |
| PublicationTitle | Frontiers in pharmacology |
| PublicationYear | 2023 |
| Publisher | Frontiers Media S.A |
| Publisher_xml | – name: Frontiers Media S.A |
| References | Zhang (B38) 2021; 21 Mizutani (B23) 2012; 28 Saito (B27) 2015; 10 Yang (B36) 2009; 5 Zheng (B44) 2019; 19 Jiang (B13) 2018; 17 Uner (B31) 2019 Wang (B32) 2010; 26 Avram (B1) 2021; 49 Steigerwalt (B30) 2015; 52 Xu (B34) 2022; 23 Liu (B19) 2012; 19 Seo (B29) 2020; 2020 Bresso (B2) 2013; 14 Dimitri (B5) 2017; 68 Ding (B7) 2018; 23 Sachdev (B26) 2020; 81 Wishart (B33) 2008; 36 Joshi (B14) 2022; 132 Li (B17) 2016; 17 Kuhn (B15) 2016; 44 Zhang (B40) 2018; 287 Zhao (B43) 2018; 306 Cakir (B3) 2021; 21 Xuan (B35) 2022; 23 Guo (B9) 2020; 2020 Pauwels (B25) 2011; 12 Yu (B37) 2021; 37 Galeano (B8) 2020; 11 Zhang (B39) 2015; 16 Zhao (B42) 2021; 22 Luo (B20) 2011; 39 Ma (B22) 2003; 100 Lee (B16) 2017; 5 Nair (B24) 2010 Zhao (B41) 2022; 23 Hu (B11) 2019; 24 Hajian-Tilaki (B10) 2013; 4 Davis (B4) 2021; 49 Liang (B18) 2017; 33 Ding (B6) 2019; 325 Iorio (B12) 2010; 107 Sawada (B28) 2015; 55 Luo (B21) 2017; 8 |
| References_xml | – volume: 49 start-page: D1138 year: 2021 ident: B4 article-title: Comparative toxicogenomics database (ctd): update 2021 publication-title: Nucleic Acids Res. doi: 10.1093/nar/gkaa891 – volume: 21 start-page: 673 year: 2021 ident: B3 article-title: Side effect prediction based on drug-induced gene expression profiles and random forest with iterative feature selection publication-title: Pharmacogenomics J. doi: 10.1038/s41397-021-00246-4 – volume: 100 start-page: 5974 year: 2003 ident: B22 article-title: Gene expression profiles of human breast cancer progression publication-title: Proc. Natl. Acad. Sci. doi: 10.1073/pnas.0931261100 – volume: 19 start-page: e28 year: 2012 ident: B19 article-title: Large-scale prediction of adverse drug reactions using chemical, biological, and phenotypic properties of drugs publication-title: J. Am. Med. Inf. Assoc. doi: 10.1136/amiajnl-2011-000699 – volume: 68 start-page: 204 year: 2017 ident: B5 article-title: Drugclust: a machine learning approach for drugs side effects prediction publication-title: Comput. Biol. Chem. doi: 10.1016/j.compbiolchem.2017.03.008 – volume: 132 start-page: 104122 year: 2022 ident: B14 article-title: A knowledge graph embedding based approach to predict the adverse drug reactions using a deep neural network publication-title: J. Biomed. Inf. doi: 10.1016/j.jbi.2022.104122 – volume: 14 start-page: 207 year: 2013 ident: B2 article-title: Integrative relational machine-learning for understanding drug side-effect profiles publication-title: BMC Bioinforma. doi: 10.1186/1471-2105-14-207 – volume: 23 start-page: bbab586 year: 2022 ident: B34 article-title: Dsgat: predicting frequencies of drug side effects by graph attention networks publication-title: Briefings Bioinforma. doi: 10.1093/bib/bbab586 – volume: 17 start-page: 2 year: 2016 ident: B17 article-title: A survey of current trends in computational drug repositioning publication-title: Briefings Bioinforma. doi: 10.1093/bib/bbv020 – volume: 55 start-page: 2717 year: 2015 ident: B28 article-title: Target-based drug repositioning using large-scale chemical–protein interactome data publication-title: J. Chem. Inf. Model. doi: 10.1021/acs.jcim.5b00330 – volume: 37 start-page: 2221 year: 2021 ident: B37 article-title: Metaadedb 2.0: a comprehensive database on adverse drug events publication-title: Bioinformatics doi: 10.1093/bioinformatics/btaa973 – volume: 287 start-page: 154 year: 2018 ident: B40 article-title: Feature-derived graph regularized matrix factorization for predicting drug side effects publication-title: Neurocomputing doi: 10.1016/j.neucom.2018.01.085 – volume: 39 start-page: W492 year: 2011 ident: B20 article-title: Drar-cpi: a server for identifying drug repositioning potential and adverse drug reactions via the chemical–protein interactome publication-title: Nucleic Acids Res. doi: 10.1093/nar/gkr299 – volume: 33 start-page: 1187 year: 2017 ident: B18 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 – volume: 8 start-page: 573 year: 2017 ident: B21 article-title: A network integration approach for drug-target interaction prediction and computational drug repositioning from heterogeneous information publication-title: Nat. Commun. doi: 10.1038/s41467-017-00680-8 – volume: 28 start-page: i522 year: 2012 ident: B23 article-title: Relating drug–protein interaction network with drug side effects publication-title: Bioinformatics doi: 10.1093/bioinformatics/bts383 – volume: 2020 start-page: 4675395 year: 2020 ident: B9 article-title: A novel triple matrix factorization method for detecting drug-side effect association based on kernel target alignment publication-title: BioMed Res. Int. doi: 10.1155/2020/4675395 – volume: 325 start-page: 211 year: 2019 ident: B6 article-title: Identification of drug-side effect association via multiple information integration with centered kernel alignment publication-title: Neurocomputing doi: 10.1016/j.neucom.2018.10.028 – volume: 306 start-page: 136 year: 2018 ident: B43 article-title: A similarity-based method for prediction of drug side effects with heterogeneous information publication-title: Math. Biosci. doi: 10.1016/j.mbs.2018.09.010 – volume: 107 start-page: 14621 year: 2010 ident: B12 article-title: Discovery of drug mode of action and drug repositioning from transcriptional responses publication-title: Proc. Natl. Acad. Sci. doi: 10.1073/pnas.1000138107 – volume: 16 start-page: 1 year: 2015 ident: B39 article-title: Predicting drug side effects by multi-label learning and ensemble learning publication-title: BMC Bioinforma. doi: 10.1186/s12859-015-0774-y – volume: 10 start-page: e0118432 year: 2015 ident: B27 article-title: The precision-recall plot is more informative than the roc plot when evaluating binary classifiers on imbalanced datasets publication-title: PloS one doi: 10.1371/journal.pone.0118432 – start-page: 843029 year: 2019 ident: B31 article-title: Deepside: a deep learning framework for drug side effect prediction publication-title: Biorxiv doi: 10.1109/TCBB.2022.3141103 – volume: 23 start-page: bbac126 year: 2022 ident: B35 article-title: Integrating specific and common topologies of heterogeneous graphs and pairwise attributes for drug-related side effect prediction publication-title: Briefings Bioinforma. doi: 10.1093/bib/bbac126 – volume: 11 start-page: 4575 year: 2020 ident: B8 article-title: Predicting the frequencies of drug side effects publication-title: Nat. Commun. doi: 10.1038/s41467-020-18305-y – volume: 23 start-page: bbab449 year: 2022 ident: B41 article-title: A similarity-based deep learning approach for determining the frequencies of drug side effects publication-title: Briefings Bioinforma. doi: 10.1093/bib/bbab449 – volume: 26 start-page: 1644 year: 2010 ident: B32 article-title: Inferring the human microrna functional similarity and functional network based on microrna-associated diseases publication-title: Bioinformatics doi: 10.1093/bioinformatics/btq241 – volume: 2020 start-page: 1357630 year: 2020 ident: B29 article-title: Prediction of side effects using comprehensive similarity measures publication-title: BioMed Res. Int. doi: 10.1155/2020/1357630 – volume: 23 start-page: 2619 year: 2018 ident: B7 article-title: Identification of drug-side effect association via semisupervised model and multiple kernel learning publication-title: IEEE J. Biomed. Health Inf. doi: 10.1109/JBHI.2018.2883834 – volume: 36 start-page: D901 year: 2008 ident: B33 article-title: Drugbank: a knowledgebase for drugs, drug actions and drug targets publication-title: Nucleic acids Res. doi: 10.1093/nar/gkm958 – volume: 44 start-page: D1075 year: 2016 ident: B15 article-title: The sider database of drugs and side effects publication-title: Nucleic Acids Res. doi: 10.1093/nar/gkv1075 – volume: 5 start-page: e1000441 year: 2009 ident: B36 article-title: Harvesting candidate genes responsible for serious adverse drug reactions from a chemical-protein interactome publication-title: PLoS Comput. Biol. doi: 10.1371/journal.pcbi.1000441 – volume: 21 start-page: 38 year: 2021 ident: B38 article-title: Prediction of adverse drug reactions based on knowledge graph embedding publication-title: BMC Med. Inf. Decis. Mak. doi: 10.1186/s12911-021-01402-3 – volume: 24 start-page: 3668 year: 2019 ident: B11 article-title: Drug side-effect prediction via random walk on the signed heterogeneous drug network publication-title: Molecules doi: 10.3390/molecules24203668 – volume: 17 start-page: 402 year: 2018 ident: B13 article-title: Drug side-effect profiles prediction: from empirical to structural risk minimization publication-title: IEEE/ACM Trans. Comput. Biol. Bioinforma. doi: 10.1109/TCBB.2018.2850884 – volume: 22 start-page: bbab239 year: 2021 ident: B42 article-title: A novel graph attention model for predicting frequencies of drug–side effects from multi-view data publication-title: Briefings Bioinforma. doi: 10.1093/bib/bbab239 – volume: 12 start-page: 169 year: 2011 ident: B25 article-title: Predicting drug side-effect profiles: a chemical fragment-based approach publication-title: BMC Bioinforma. doi: 10.1186/1471-2105-12-169 – volume: 81 start-page: 650 year: 2020 ident: B26 article-title: A comprehensive review of computational techniques for the prediction of drug side effects publication-title: Drug Dev. Res. doi: 10.1002/ddr.21669 – volume: 19 start-page: 554 year: 2019 ident: B44 article-title: Inverse similarity and reliable negative samples for drug side-effect prediction publication-title: BMC Bioinforma. doi: 10.1186/s12859-018-2563-x – start-page: 807 year: 2010 ident: B24 article-title: Rectified linear units improve restricted boltzmann machines – volume: 52 start-page: 1601 year: 2015 ident: B30 article-title: Online drug information resources publication-title: Choice (Chicago, Ill.) doi: 10.5860/choice.52.10.1601 – volume: 4 start-page: 627 year: 2013 ident: B10 article-title: Receiver operating characteristic (roc) curve analysis for medical diagnostic test evaluation publication-title: Casp. J. Intern. Med. – volume: 5 start-page: 20449 year: 2017 ident: B16 article-title: Predicting drug side effects using data analytics and the integration of multiple data sources publication-title: IEEE Access doi: 10.1109/access.2017.2755045 – volume: 49 start-page: D1160 year: 2021 ident: B1 article-title: Drugcentral 2021 supports drug discovery and repositioning publication-title: Nucleic acids Res. doi: 10.1093/nar/gkaa997 |
| SSID | ssj0000399364 |
| Score | 2.3442364 |
| Snippet | Background:
Inferring drug-related side effects is beneficial for reducing drug development cost and time. Current computational prediction methods have... Background: Inferring drug-related side effects is beneficial for reducing drug development cost and time. Current computational prediction methods have... |
| SourceID | doaj pubmedcentral proquest crossref |
| SourceType | Open Website Open Access Repository Aggregation Database Enrichment Source Index Database |
| StartPage | 1257842 |
| SubjectTerms | graph convolutional autoencoder graph generative and adversarial strategy Pharmacology representation-level attention self-calibrated pairwise attributes topologies and attributes from heterogeneous graphs |
| Title | Graph generative and adversarial strategy-enhanced node feature learning and self-calibrated pairwise attribute encoding for prediction of drug-related side effects |
| URI | https://www.proquest.com/docview/2867148958 https://pubmed.ncbi.nlm.nih.gov/PMC10507253 https://doaj.org/article/f314529ae8b54209b8807b6de17cc72b |
| Volume | 14 |
| WOSCitedRecordID | wos001066959600001&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: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 1663-9812 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000399364 issn: 1663-9812 databaseCode: DOA dateStart: 20100101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 1663-9812 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000399364 issn: 1663-9812 databaseCode: M~E dateStart: 20100101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Nb9QwELWg4sAF8Sm2QGUk1As1jR0nto-AWjhAtYeC9hY59nh3pSq7SnZBe-HX8EPxOGm7ucCFSw6JnTiZF88befyGkDdFXpaF1zlTRjgmvQ3MFIEz50Oc-9BlpCoR37-oiws9m5npXqkvzAnr5YH7D3caco5rgxZ0XUiRmToCTtWlB66cU6LG2Teynr1gKs3B6HdL2e-SiVGYOQ3rhUX9T5G_4whTKUaeKAn2j1jmOEdyz-mcPyQPBrZI3_ejfETuQPOYHE97uendCb283T3VndBjOr0Vot49Ib8_oRo1nSdlaZzWqG08tViCubMIPNr12rQ7Bs0ipQLQZuWBBkhyn3QoKTFP_Tq4CixaFOPrSFPp2i7bn8su3nTTV80CiqKY6AtpZMJ03eIaENqdrgL17XbO0saZ2BVLhNIhk-Qp-XZ-dvnxMxuqMjCXG71hwAOXtlDe1oUIlteRAnotpAqq9DyUADKDALmGIK02oIXy4CwoAUGH0ufPyEGzauA5odZ4mXkpMfCTzjldg8pEiKCKvD8zakL4tYUqN0iWY-WMqyqGLmjVKlm1QqtWg1Un5O1Nn3Uv2PHX1h_Q8DctUWw7nYgQrAYIVv-C4IS8voZNFX9OXHGxDay2XSVQPVBqU-gJ0SM8jZ44vtIsF0nmOzLfTIkiP_wfY3xB7uN7p-w4-ZIcbNotvCL33I_NsmuPyF0100fpF4rHr7_O_gA5zigx |
| linkProvider | Directory of Open Access Journals |
| 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=Graph+generative+and+adversarial+strategy-enhanced+node+feature+learning+and+self-calibrated+pairwise+attribute+encoding+for+prediction+of+drug-related+side+effects&rft.jtitle=Frontiers+in+pharmacology&rft.au=Xuan%2C+Ping&rft.au=Xu%2C+Kai&rft.au=Cui%2C+Hui&rft.au=Nakaguchi%2C+Toshiya&rft.date=2023-09-04&rft.pub=Frontiers+Media+S.A&rft.eissn=1663-9812&rft.volume=14&rft_id=info:doi/10.3389%2Ffphar.2023.1257842&rft.externalDocID=PMC10507253 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1663-9812&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1663-9812&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1663-9812&client=summon |