Prediction of Drug-Drug Interactions Based on Multi-layer Feature Selection and Data Balance

Drug-drug interactions （DDIs） occur when two drugs react with each others which may cause unexpected side effects and even death of the patient. Methods that use adverse event reports to predict unexpected DDIs are limited by two critical yet challenging issues. One is the difficulty of selecting di...

Full description

Saved in:
Bibliographic Details
Published inChinese Journal of Electronics Vol. 26; no. 3; pp. 585 - 590
Main Authors Yue, Kejuan, Zou, Beiji, Wang, Lei, Li, Xiao, Zeng, Min, Wei, Faran
Format Journal Article
LanguageEnglish
Published Published by the IET on behalf of the CIE 01.05.2017
Subjects
Adverse event reports
Canada vigilance adverse reaction online database
Data balance
data handling
data imbalance
DDI detection
discriminative feature selectiON
drug pairs
drugs
drugs.com
drug‐drug interaction Prediction
Drug‐drug interactions (DDIs)
Feature selection
information services
medical administrative data processing
multilayer feature selection
over‐sampling technique
patient care
patient death
side effects
USA
over-sampling technique
multilayer feature selection
USA
DDI detection
drugs
data balance
Canada vigilance adverse reaction online database
patient care
information services
discriminative feature selectiON
drugs.com
drug pairs
data imbalance
Adverse event reports
side effects
Drug-drug interactions (DDIs)
data handling
medical administrative data processing
patient death
drug-drug interaction Prediction
feature selection
Online AccessGet full text

Cover

More Information
Summary:Drug-drug interactions （DDIs） occur when two drugs react with each others which may cause unexpected side effects and even death of the patient. Methods that use adverse event reports to predict unexpected DDIs are limited by two critical yet challenging issues. One is the difficulty of selecting discriminative features from numerous redundant and irrelevant adverse events for modeling. The other is the data imbalance, i.e., the drug pairs causing adverse effects are far less than those not causing adverse effects, which leads to poor accuracy of DDIs detection. We propose a multi-layer feature selection method to select discriminative adverse events and apply an over-sampling technique to make the data balanced. The experimental results show that the validation accuracy of positive DDIs on the Canada Vigilance Adverse Reaction Online Database increases to two times, and 110 DDIs are identified on the drug interactions checker of Drugs.corn in USA.
Bibliography:Adverse event reports, Drug-drug interactions （DDIs）, Feature selection, Data balance.
Drug-drug interactions （DDIs） occur when two drugs react with each others which may cause unexpected side effects and even death of the patient. Methods that use adverse event reports to predict unexpected DDIs are limited by two critical yet challenging issues. One is the difficulty of selecting discriminative features from numerous redundant and irrelevant adverse events for modeling. The other is the data imbalance, i.e., the drug pairs causing adverse effects are far less than those not causing adverse effects, which leads to poor accuracy of DDIs detection. We propose a multi-layer feature selection method to select discriminative adverse events and apply an over-sampling technique to make the data balanced. The experimental results show that the validation accuracy of positive DDIs on the Canada Vigilance Adverse Reaction Online Database increases to two times, and 110 DDIs are identified on the drug interactions checker of Drugs.corn in USA.
10-1284/TN
ISSN:1022-4653
2075-5597
DOI:10.1049/cje.2017.04.005