Large-scale structural and textual similarity-based mining of knowledge graph to predict drug-drug interactions

Handle URI:
http://hdl.handle.net/10754/625060
Title:
Large-scale structural and textual similarity-based mining of knowledge graph to predict drug-drug interactions
Authors:
Abdelaziz, Ibrahim ( 0000-0003-1449-5115 ) ; Fokoue, Achille; Hassanzadeh, Oktie; Zhang, Ping; Sadoghi, Mohammad
Abstract:
Drug-Drug Interactions (DDIs) are a major cause of preventable Adverse Drug Reactions (ADRs), causing a significant burden on the patients’ health and the healthcare system. It is widely known that clinical studies cannot sufficiently and accurately identify DDIs for new drugs before they are made available on the market. In addition, existing public and proprietary sources of DDI information are known to be incomplete and/or inaccurate and so not reliable. As a result, there is an emerging body of research on in-silico prediction of drug-drug interactions. In this paper, we present Tiresias, a large-scale similarity-based framework that predicts DDIs through link prediction. Tiresias takes in various sources of drug-related data and knowledge as inputs, and provides DDI predictions as outputs. The process starts with semantic integration of the input data that results in a knowledge graph describing drug attributes and relationships with various related entities such as enzymes, chemical structures, and pathways. The knowledge graph is then used to compute several similarity measures between all the drugs in a scalable and distributed framework. In particular, Tiresias utilizes two classes of features in a knowledge graph: local and global features. Local features are derived from the information directly associated to each drug (i.e., one hop away) while global features are learnt by minimizing a global loss function that considers the complete structure of the knowledge graph. The resulting similarity metrics are used to build features for a large-scale logistic regression model to predict potential DDIs. We highlight the novelty of our proposed Tiresias and perform thorough evaluation of the quality of the predictions. The results show the effectiveness of Tiresias in both predicting new interactions among existing drugs as well as newly developed drugs.
KAUST Department:
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division; Computer Science Program
Citation:
Abdelaziz I, Fokoue A, Hassanzadeh O, Zhang P, Sadoghi M (2017) Large-scale structural and textual similarity-based mining of knowledge graph to predict drug-drug interactions. Web Semantics: Science, Services and Agents on the World Wide Web. Available: http://dx.doi.org/10.1016/j.websem.2017.06.002.
Publisher:
Elsevier BV
Journal:
Web Semantics: Science, Services and Agents on the World Wide Web
Issue Date:
12-Jun-2017
DOI:
10.1016/j.websem.2017.06.002
Type:
Article
ISSN:
1570-8268
Additional Links:
http://www.sciencedirect.com/science/article/pii/S157082681730029X
Appears in Collections:
Articles; Computer Science Program; Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorAbdelaziz, Ibrahimen
dc.contributor.authorFokoue, Achilleen
dc.contributor.authorHassanzadeh, Oktieen
dc.contributor.authorZhang, Pingen
dc.contributor.authorSadoghi, Mohammaden
dc.date.accessioned2017-06-19T09:21:45Z-
dc.date.available2017-06-19T09:21:45Z-
dc.date.issued2017-06-12en
dc.identifier.citationAbdelaziz I, Fokoue A, Hassanzadeh O, Zhang P, Sadoghi M (2017) Large-scale structural and textual similarity-based mining of knowledge graph to predict drug-drug interactions. Web Semantics: Science, Services and Agents on the World Wide Web. Available: http://dx.doi.org/10.1016/j.websem.2017.06.002.en
dc.identifier.issn1570-8268en
dc.identifier.doi10.1016/j.websem.2017.06.002en
dc.identifier.urihttp://hdl.handle.net/10754/625060-
dc.description.abstractDrug-Drug Interactions (DDIs) are a major cause of preventable Adverse Drug Reactions (ADRs), causing a significant burden on the patients’ health and the healthcare system. It is widely known that clinical studies cannot sufficiently and accurately identify DDIs for new drugs before they are made available on the market. In addition, existing public and proprietary sources of DDI information are known to be incomplete and/or inaccurate and so not reliable. As a result, there is an emerging body of research on in-silico prediction of drug-drug interactions. In this paper, we present Tiresias, a large-scale similarity-based framework that predicts DDIs through link prediction. Tiresias takes in various sources of drug-related data and knowledge as inputs, and provides DDI predictions as outputs. The process starts with semantic integration of the input data that results in a knowledge graph describing drug attributes and relationships with various related entities such as enzymes, chemical structures, and pathways. The knowledge graph is then used to compute several similarity measures between all the drugs in a scalable and distributed framework. In particular, Tiresias utilizes two classes of features in a knowledge graph: local and global features. Local features are derived from the information directly associated to each drug (i.e., one hop away) while global features are learnt by minimizing a global loss function that considers the complete structure of the knowledge graph. The resulting similarity metrics are used to build features for a large-scale logistic regression model to predict potential DDIs. We highlight the novelty of our proposed Tiresias and perform thorough evaluation of the quality of the predictions. The results show the effectiveness of Tiresias in both predicting new interactions among existing drugs as well as newly developed drugs.en
dc.publisherElsevier BVen
dc.relation.urlhttp://www.sciencedirect.com/science/article/pii/S157082681730029Xen
dc.rightsNOTICE: this is the author’s version of a work that was accepted for publication in Web Semantics: Science, Services and Agents on the World Wide Web. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in Web Semantics: Science, Services and Agents on the World Wide Web, [, , (2017-06-12)] DOI: 10.1016/j.websem.2017.06.002 . © 2017. This manuscript version is made available under the CC-BY-NC-ND 4.0 license http://creativecommons.org/licenses/by-nc-nd/4.0/en
dc.subjectDrug interactionen
dc.subjectSimilarity-Baseden
dc.subjectLink predictionen
dc.titleLarge-scale structural and textual similarity-based mining of knowledge graph to predict drug-drug interactionsen
dc.typeArticleen
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.contributor.departmentComputer Science Programen
dc.identifier.journalWeb Semantics: Science, Services and Agents on the World Wide Weben
dc.eprint.versionPost-printen
dc.contributor.institutionIBM T.J. Watson Research Center, Yorktown Heights, NY, USAen
dc.contributor.institutionDepartment of Computer Science, Purdue University, West Lafayette, IN, USAen
kaust.authorAbdelaziz, Ibrahimen
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.