File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Predicting and understanding comprehensive drug-drug interactions via semi-nonnegative matrix factorization

TitlePredicting and understanding comprehensive drug-drug interactions via semi-nonnegative matrix factorization
Authors
KeywordsBalance theory
Drug-drug interaction
Network community
Nonnegative matrix factorization
Regression
Issue Date2018
PublisherBioMed Central Ltd. The Journal's web site is located at http://www.biomedcentral.com/bmcsystbiol/
Citation
16th Asia Pacific Bioinformatics Conference (APBC 2018): Systems Biology, Yokohama, Japan, 15-17 January 2018. In BMC Systems Biology, 2018, v. 12, p. 101-110 How to Cite?
AbstractBackground: Drug-drug interactions (DDIs) always cause unexpected and even adverse drug reactions. It is important to identify DDIs before drugs are used in the market. However, preclinical identification of DDIs requires much money and time. Computational approaches have exhibited their abilities to predict potential DDIs on a large scale by utilizing pre-market drug properties (e.g. chemical structure). Nevertheless, none of them can predict two comprehensive types of DDIs, including enhancive and degressive DDIs, which increases and decreases the behaviors of the interacting drugs respectively. There is a lack of systematic analysis on the structural relationship among known DDIs. Revealing such a relationship is very important, because it is able to help understand how DDIs occur. Both the prediction of comprehensive DDIs and the discovery of structural relationship among them play an important guidance when making a co-prescription. Results: In this work, treating a set of comprehensive DDIs as a signed network, we design a novel model (DDINMF) for the prediction of enhancive and degressive DDIs based on semi-nonnegative matrix factorization. Inspiringly, DDINMF achieves the conventional DDI prediction (AUROC=0.872 and AUPR=0.605) and the comprehensive DDI prediction (AUROC=0.796 and AUPR=0.579). Compared with two state-of-the-art approaches, DDINMF shows it superiority. Finally, representing DDIs as a binary network and a signed network respectively, an analysis based on NMF reveals crucial knowledge hidden among DDIs. Conclusions: Our approach is able to predict not only conventional binary DDIs but also comprehensive DDIs. More importantly, it reveals several key points about the DDI network: (1) both binary and signed networks show fairly clear clusters, in which both drug degree and the difference between positive degree and negative degree show significant distribution; (2) the drugs having large degrees tend to have a larger difference between positive degree and negative degree; (3) though the binary DDI network contains no information about enhancive and degressive DDIs at all, it implies some of their relationship in the comprehensive DDI matrix; (4) the occurrence of signs indicating enhancive and degressive DDIs is not random because the comprehensive DDI network is equipped with a structural balance.
Persistent Identifierhttp://hdl.handle.net/10722/262468
ISSN
2018 Impact Factor: 2.048
2015 SCImago Journal Rankings: 1.493
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorYu, H-
dc.contributor.authorMao, KT-
dc.contributor.authorShi, JY-
dc.contributor.authorHuang, H-
dc.contributor.authorChen, Z-
dc.contributor.authorDong, K-
dc.contributor.authorYiu, SM-
dc.date.accessioned2018-09-28T04:59:48Z-
dc.date.available2018-09-28T04:59:48Z-
dc.date.issued2018-
dc.identifier.citation16th Asia Pacific Bioinformatics Conference (APBC 2018): Systems Biology, Yokohama, Japan, 15-17 January 2018. In BMC Systems Biology, 2018, v. 12, p. 101-110-
dc.identifier.issn1752-0509-
dc.identifier.urihttp://hdl.handle.net/10722/262468-
dc.description.abstractBackground: Drug-drug interactions (DDIs) always cause unexpected and even adverse drug reactions. It is important to identify DDIs before drugs are used in the market. However, preclinical identification of DDIs requires much money and time. Computational approaches have exhibited their abilities to predict potential DDIs on a large scale by utilizing pre-market drug properties (e.g. chemical structure). Nevertheless, none of them can predict two comprehensive types of DDIs, including enhancive and degressive DDIs, which increases and decreases the behaviors of the interacting drugs respectively. There is a lack of systematic analysis on the structural relationship among known DDIs. Revealing such a relationship is very important, because it is able to help understand how DDIs occur. Both the prediction of comprehensive DDIs and the discovery of structural relationship among them play an important guidance when making a co-prescription. Results: In this work, treating a set of comprehensive DDIs as a signed network, we design a novel model (DDINMF) for the prediction of enhancive and degressive DDIs based on semi-nonnegative matrix factorization. Inspiringly, DDINMF achieves the conventional DDI prediction (AUROC=0.872 and AUPR=0.605) and the comprehensive DDI prediction (AUROC=0.796 and AUPR=0.579). Compared with two state-of-the-art approaches, DDINMF shows it superiority. Finally, representing DDIs as a binary network and a signed network respectively, an analysis based on NMF reveals crucial knowledge hidden among DDIs. Conclusions: Our approach is able to predict not only conventional binary DDIs but also comprehensive DDIs. More importantly, it reveals several key points about the DDI network: (1) both binary and signed networks show fairly clear clusters, in which both drug degree and the difference between positive degree and negative degree show significant distribution; (2) the drugs having large degrees tend to have a larger difference between positive degree and negative degree; (3) though the binary DDI network contains no information about enhancive and degressive DDIs at all, it implies some of their relationship in the comprehensive DDI matrix; (4) the occurrence of signs indicating enhancive and degressive DDIs is not random because the comprehensive DDI network is equipped with a structural balance.-
dc.languageeng-
dc.publisherBioMed Central Ltd. The Journal's web site is located at http://www.biomedcentral.com/bmcsystbiol/-
dc.relation.ispartofBMC Systems Biology-
dc.rightsBMC Systems Biology. Copyright © BioMed Central Ltd.-
dc.rightsThis work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.-
dc.subjectBalance theory-
dc.subjectDrug-drug interaction-
dc.subjectNetwork community-
dc.subjectNonnegative matrix factorization-
dc.subjectRegression-
dc.titlePredicting and understanding comprehensive drug-drug interactions via semi-nonnegative matrix factorization-
dc.typeConference_Paper-
dc.identifier.emailYiu, SM: smyiu@cs.hku.hk-
dc.identifier.authorityYiu, SM=rp00207-
dc.description.naturepublished_or_final_version-
dc.identifier.doi10.1186/s12918-018-0532-7-
dc.identifier.scopuseid_2-s2.0-85045255246-
dc.identifier.hkuros292124-
dc.identifier.volume12-
dc.identifier.spage101-
dc.identifier.epage110-
dc.identifier.isiWOS:000430982500009-
dc.publisher.placeUnited Kingdom-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats