A novel integrated action crossing method for drug-drug interaction prediction in non-communicable diseases. (September 2018)

• Record Type: Journal Article
• Authors: Hunta, Sathien; Yooyativong, Thongchai; Aunsri, Nattapol
• Is Part Of: Computer methods and programs in biomedicine. Volume 163(2018)
• Page Start: 183
• Page End: 193
• Publication Date: 2018-09
• Subjects: Integrated action crossing -- Machine learning -- Drug-drug interaction -- Non-communicable disease; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2018.06.013
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: A new feature formulation technique, called IAC, for Drug-Drug Interactions(DDIs) analysis is introduced, focusing on Pharmacokinetics (PK) interactions of drugs used for NCDs. The IAC substantially reduces the size of features for training and testing processes. Using the new feature for non-communicable diseases (NCDs) DDIs delivers greater results than using the conventional method. The most excellent result from the proposed method is 83% (AUC 0.901). With the AIC, predictions of unreported DDIs are obtained with more than 80% of confidence. Abstract: Background and objective: Drug-drug interaction (DDI) is one of the main causes of toxicity and treatment inefficacy. This work focuses on non-communicable diseases (NCDs), the non-transmissible and long-lasting diseases since they are the leading cause of death globally. Drugs that are used in NCDs increase the probability of DDIs as a result of long time usage. This work proposes an Integrated Action Crossing (IAC) method that is effective in predicting the NCDs DDIs based on pharmacokinetic (PK) mechanism. Methods: Drug-Enzyme (CYP450) and Drug-Transporter actions including substrate, inhibitor and inducer affect the PK mechanism of other drugs. Hence, this paper proposes an enzyme and transporter protein integrated action crossing method for DDIs prediction in NCDs. The NCDs Drugs information was retrieved from the DrugBank database and the actions of enzymes and transporter proteins that were crossed and integrated. The datasets were generated for machine training. Results: Three machine learning approaches: Support Vector Machine, k-Nearest Neighbors, and Neural Networks were used for the assessment of the method. Performance evaluation was performed through five-fold cross validation and the different datasets and learning methods were compared. Two layers NNs achieved the best performance at the accuracy of 83.15% (F-Measure 85.23% and AUC 0.901). Conclusions: The IAC method delivers better performance compared to the conventional method for the identification of NCDs DDIs.