Classification of p-glycoprotein-interacting compounds using machine learning methods

© 2015 Leibniz Research Centre for Working Environment and Human Factors. All rights reserved. P-glycoprotein (Pgp) is a drug transporter that plays important roles in multidrug resistance and drug pharmacokinetics. The inhibition of Pgp has become a notable strategy for combating multidrug-resistan...

Full description

Saved in:
Bibliographic Details
Main Authors: Veda Prachayasittikul, Apilak Worachartcheewan, Watshara Shoombuatong, Virapong Prachayasittikul, Chanin Nantasenamat
Other Authors: Mahidol University
Format: Article
Published: 2018
Subjects:
Online Access:https://repository.li.mahidol.ac.th/handle/123456789/35114
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Mahidol University
id th-mahidol.35114
record_format dspace
spelling th-mahidol.351142018-11-23T16:39:19Z Classification of p-glycoprotein-interacting compounds using machine learning methods Veda Prachayasittikul Apilak Worachartcheewan Watshara Shoombuatong Virapong Prachayasittikul Chanin Nantasenamat Mahidol University Agricultural and Biological Sciences Biochemistry, Genetics and Molecular Biology © 2015 Leibniz Research Centre for Working Environment and Human Factors. All rights reserved. P-glycoprotein (Pgp) is a drug transporter that plays important roles in multidrug resistance and drug pharmacokinetics. The inhibition of Pgp has become a notable strategy for combating multidrug-resistant cancers and improving therapeutic outcomes. However, the polyspecific nature of Pgp, together with inconsistent results in experimental assays, renders the determination of endpoints for Pgp-interacting compounds a great challenge. In this study, the classification of a large set of 2,477 Pgp-interacting compounds (i.e., 1341 inhibitors, 913 noninhibitors, 197 substrates and 26 non-substrates) was performed using several machine learning methods (i.e., decision tree induction, artificial neural network modelling and support vector machine) as a function of their physicochemical properties. The models provided good predictive performance, producing MCC values in the range of 0.739-1 for internal cross-validation and 0.665-1 for external validation. The study provided simple and interpretable models for important properties that influence the activity of Pgp-interacting compounds, which are potentially beneficial for screening and rational design of Pgp inhibitors that are of clinical importance. 2018-11-23T09:29:35Z 2018-11-23T09:29:35Z 2015-08-19 Article EXCLI Journal. Vol.14, (2015), 958-970 10.17179/excli2015-374 16112156 2-s2.0-84940048822 https://repository.li.mahidol.ac.th/handle/123456789/35114 Mahidol University SCOPUS https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84940048822&origin=inward
institution Mahidol University
building Mahidol University Library
continent Asia
country Thailand
Thailand
content_provider Mahidol University Library
collection Mahidol University Institutional Repository
topic Agricultural and Biological Sciences
Biochemistry, Genetics and Molecular Biology
spellingShingle Agricultural and Biological Sciences
Biochemistry, Genetics and Molecular Biology
Veda Prachayasittikul
Apilak Worachartcheewan
Watshara Shoombuatong
Virapong Prachayasittikul
Chanin Nantasenamat
Classification of p-glycoprotein-interacting compounds using machine learning methods
description © 2015 Leibniz Research Centre for Working Environment and Human Factors. All rights reserved. P-glycoprotein (Pgp) is a drug transporter that plays important roles in multidrug resistance and drug pharmacokinetics. The inhibition of Pgp has become a notable strategy for combating multidrug-resistant cancers and improving therapeutic outcomes. However, the polyspecific nature of Pgp, together with inconsistent results in experimental assays, renders the determination of endpoints for Pgp-interacting compounds a great challenge. In this study, the classification of a large set of 2,477 Pgp-interacting compounds (i.e., 1341 inhibitors, 913 noninhibitors, 197 substrates and 26 non-substrates) was performed using several machine learning methods (i.e., decision tree induction, artificial neural network modelling and support vector machine) as a function of their physicochemical properties. The models provided good predictive performance, producing MCC values in the range of 0.739-1 for internal cross-validation and 0.665-1 for external validation. The study provided simple and interpretable models for important properties that influence the activity of Pgp-interacting compounds, which are potentially beneficial for screening and rational design of Pgp inhibitors that are of clinical importance.
author2 Mahidol University
author_facet Mahidol University
Veda Prachayasittikul
Apilak Worachartcheewan
Watshara Shoombuatong
Virapong Prachayasittikul
Chanin Nantasenamat
format Article
author Veda Prachayasittikul
Apilak Worachartcheewan
Watshara Shoombuatong
Virapong Prachayasittikul
Chanin Nantasenamat
author_sort Veda Prachayasittikul
title Classification of p-glycoprotein-interacting compounds using machine learning methods
title_short Classification of p-glycoprotein-interacting compounds using machine learning methods
title_full Classification of p-glycoprotein-interacting compounds using machine learning methods
title_fullStr Classification of p-glycoprotein-interacting compounds using machine learning methods
title_full_unstemmed Classification of p-glycoprotein-interacting compounds using machine learning methods
title_sort classification of p-glycoprotein-interacting compounds using machine learning methods
publishDate 2018
url https://repository.li.mahidol.ac.th/handle/123456789/35114
_version_ 1763491891530170368