Novel Neural Network Approach to Predict Drug-Target Interactions Based on Drug Side Effects and Genome-Wide Association Studies

Jeanette Prinz, Mohamad Koohi-Moghadam, Hongzhe Sun, Jean-Pierre Kocher, Junwen Wang

Research output: Contribution to journalArticle

Abstract

Aims: We propose a novel machine learning approach to expand the knowledge about drug-target interactions. Our method may help to develop effective, less harmful treatment strategies and to enable the detection of novel indications for existing drugs. Methods: We developed a novel machine learning strategy to predict drug-target interactions based on drug side effects and traits from genome-wide association studies. We integrated data from the databases SIDER and GWASdb and utilized them in a unique way by a neural network approach. Results: We validate our method using drug-target interactions from the STITCH database. In addition, we compare the chemical similarity of the predicted target to known targets of the drug under consideration and present literature-based evidence for predicted interactions. We find drug combination warnings for drugs we predict to target the same protein, hinting to synergistic effects aggravating harmful events. This substantiates the translational value of our approach, because we are able to detect drugs that should be taken together with care due to common mechanisms of action. Conclusion: Taken together, we conclude that our approach is able to generate a novel and clinically applicable insight into the molecular determinants of drug action.

Original languageEnglish (US)
Pages (from-to)79-91
Number of pages13
JournalHuman Heredity
DOIs
StateAccepted/In press - Jan 1 2018

Fingerprint

Genome-Wide Association Study
Drug-Related Side Effects and Adverse Reactions
Drug Interactions
Pharmaceutical Preparations
Databases
Drug Combinations
Proteins
Machine Learning

Keywords

  • Drug side effect
  • Drug-target interaction
  • Genome-wide association studies
  • Neural network
  • Principal component analysis

ASJC Scopus subject areas

  • Genetics
  • Genetics(clinical)

Cite this

Novel Neural Network Approach to Predict Drug-Target Interactions Based on Drug Side Effects and Genome-Wide Association Studies. / Prinz, Jeanette; Koohi-Moghadam, Mohamad; Sun, Hongzhe; Kocher, Jean-Pierre; Wang, Junwen.

In: Human Heredity, 01.01.2018, p. 79-91.

Research output: Contribution to journalArticle

@article{ef40d34f9eaf44b48a970175b460282d,
title = "Novel Neural Network Approach to Predict Drug-Target Interactions Based on Drug Side Effects and Genome-Wide Association Studies",
abstract = "Aims: We propose a novel machine learning approach to expand the knowledge about drug-target interactions. Our method may help to develop effective, less harmful treatment strategies and to enable the detection of novel indications for existing drugs. Methods: We developed a novel machine learning strategy to predict drug-target interactions based on drug side effects and traits from genome-wide association studies. We integrated data from the databases SIDER and GWASdb and utilized them in a unique way by a neural network approach. Results: We validate our method using drug-target interactions from the STITCH database. In addition, we compare the chemical similarity of the predicted target to known targets of the drug under consideration and present literature-based evidence for predicted interactions. We find drug combination warnings for drugs we predict to target the same protein, hinting to synergistic effects aggravating harmful events. This substantiates the translational value of our approach, because we are able to detect drugs that should be taken together with care due to common mechanisms of action. Conclusion: Taken together, we conclude that our approach is able to generate a novel and clinically applicable insight into the molecular determinants of drug action.",
keywords = "Drug side effect, Drug-target interaction, Genome-wide association studies, Neural network, Principal component analysis",
author = "Jeanette Prinz and Mohamad Koohi-Moghadam and Hongzhe Sun and Jean-Pierre Kocher and Junwen Wang",
year = "2018",
month = "1",
day = "1",
doi = "10.1159/000492574",
language = "English (US)",
pages = "79--91",
journal = "Human Heredity",
issn = "0001-5652",
publisher = "S. Karger AG",

}

TY - JOUR

T1 - Novel Neural Network Approach to Predict Drug-Target Interactions Based on Drug Side Effects and Genome-Wide Association Studies

AU - Prinz, Jeanette

AU - Koohi-Moghadam, Mohamad

AU - Sun, Hongzhe

AU - Kocher, Jean-Pierre

AU - Wang, Junwen

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Aims: We propose a novel machine learning approach to expand the knowledge about drug-target interactions. Our method may help to develop effective, less harmful treatment strategies and to enable the detection of novel indications for existing drugs. Methods: We developed a novel machine learning strategy to predict drug-target interactions based on drug side effects and traits from genome-wide association studies. We integrated data from the databases SIDER and GWASdb and utilized them in a unique way by a neural network approach. Results: We validate our method using drug-target interactions from the STITCH database. In addition, we compare the chemical similarity of the predicted target to known targets of the drug under consideration and present literature-based evidence for predicted interactions. We find drug combination warnings for drugs we predict to target the same protein, hinting to synergistic effects aggravating harmful events. This substantiates the translational value of our approach, because we are able to detect drugs that should be taken together with care due to common mechanisms of action. Conclusion: Taken together, we conclude that our approach is able to generate a novel and clinically applicable insight into the molecular determinants of drug action.

AB - Aims: We propose a novel machine learning approach to expand the knowledge about drug-target interactions. Our method may help to develop effective, less harmful treatment strategies and to enable the detection of novel indications for existing drugs. Methods: We developed a novel machine learning strategy to predict drug-target interactions based on drug side effects and traits from genome-wide association studies. We integrated data from the databases SIDER and GWASdb and utilized them in a unique way by a neural network approach. Results: We validate our method using drug-target interactions from the STITCH database. In addition, we compare the chemical similarity of the predicted target to known targets of the drug under consideration and present literature-based evidence for predicted interactions. We find drug combination warnings for drugs we predict to target the same protein, hinting to synergistic effects aggravating harmful events. This substantiates the translational value of our approach, because we are able to detect drugs that should be taken together with care due to common mechanisms of action. Conclusion: Taken together, we conclude that our approach is able to generate a novel and clinically applicable insight into the molecular determinants of drug action.

KW - Drug side effect

KW - Drug-target interaction

KW - Genome-wide association studies

KW - Neural network

KW - Principal component analysis

UR - http://www.scopus.com/inward/record.url?scp=85055625493&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85055625493&partnerID=8YFLogxK

U2 - 10.1159/000492574

DO - 10.1159/000492574

M3 - Article

SP - 79

EP - 91

JO - Human Heredity

JF - Human Heredity

SN - 0001-5652

ER -