Integrated action crossing method for drug-drug interactions prediction in non-communicable diseases

Name: Sathien Hunta

Address: 333 Moo1, Thasud, Muang, Chiang Rai 57100

Organization : Mae Fah Luang University. School of Information Technology. Computer Engineering

Email : ask.library@mfu.ac.th

keyword: Integrated action

LCSH: Machine learning

Classification :.LCCS: Q325.5

LCSH: Non-Communicable diseases

LCSH: Drug Interactions

Abstract: A drug-drug interaction (DDI) is a modification on the effect of a drug when two or more drugs are administered together. It is one of the main causes of treatment inefficacy or overreaction in the biological systems. Drug interaction mechanism is divided into two parts: pharmacokinetic (PK) and pharmacodynamic (PD). Both mechanisms involve the actions between drugs and association targets (enzymes or receptors). Non-communicable disease (NCD) is the non-transmissible and long-lasting disease. They are the global leading cause of death. Drugs that are used in NCDs can increase probability of DDIs because they are used for longer periods of time. This work proposed an effective method to predict NCDs drug-drug interactions based on drug actions, and to determine the dataset generating method from the Linked Open Data. NCDs Drugs information was retrieved from the DrugBank database for creating the dataset to train the machine. Drug-Enzyme (CYP450) and Drug-Transporter actions include a substrate, inhibitor and inducer which all affect the PK mechanism of other drugs. They were used to create new attributes using the Action Crossing (AC) method. In addition, the Integrated Action Crossing (IAC) method that can reduce the complications by integrating the duplicated drug pairs from the AC method that was developed. NCDs datasets were generated for training the machine. The machine learning approaches, support vector machine, k-nearest neighbors, neural networks, decision tree and naive bayes were used to generate the prediction models. In addition, the deep learning method and the ensemble method of machine learning were investigated. Performance evaluation was performed through a five-fold cross validation. The difference of dataset and methods was compared. The results show that the IAC method delivered a better performance when compared to the conventional methods for the identification of NCDs DDIs.

Mae Fah Luang University. The Learning Resources and Education Media Center

Address: Chiang Rai

Email: library@mfu.ac.th

Name: Nattapol Aunsri

Role: Advisor

Email : ask.library@mfu.ac.th

Name: Thongchai Yooyativong

Role: Co-Advisor

Email : ask.library@mfu.ac.th

Created: 2561

Modified: 2019-05-21

Issued: 2562

Issued: 2019-05-21

วิทยานิพนธ์/Thesis

application/pdf

CallNumber: Thesis Q325.5 S253i 2018

eng

DegreeName: Dotor of Philosophy

Level: Doctoral Degree

Descipline: Computer Engineering

©copyrights Mae Fah Luang University

ลำดับที่.	ชื่อแฟ้มข้อมูล	ขนาดแฟ้มข้อมูล	จำนวนเข้าถึง	วัน-เวลาเข้าถึงล่าสุด
1	127021.pdf	35.33 MB	26	2025-03-29 15:45:42

ใช้เวลา

0.038204 วินาที