A Machine Learning-Based Prediction Platform for P-Glycoprotein Modulators and Its Validation by Molecular Docking

Publication type:
Journal article
Metadata:
Autoren
Autoren-URL
https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=fis-test-1&SrcAuth=WosAPI&KeyUT=WOS:000497336400175&DestLinkType=FullRecord&DestApp=WOS_CPL
DOI
10.3390/cells8101286
eISSN
2073-4409
Externe Identifier
  • Clarivate Analytics Document Solution ID: JO1HP
  • PubMed Identifier: 31640190
Ausgabe der Veröffentlichung
10
Zeitschrift
CELLS
Schlüsselwörter
  • artificial intelligence
  • drug discovery
  • machine learning
  • molecular docking
  • multidrug resistance
  • P-glycoprotein
Artikelnummer
ARTN 1286
Datum der Veröffentlichung
2019
Status
Published
Titel
A Machine Learning-Based Prediction Platform for P-Glycoprotein Modulators and Its Validation by Molecular Docking
Sub types
  • Article
Ausgabe der Zeitschrift
8

Data source: Web of Science (Lite)

Other metadata sources:
Abstract
<jats:p>P-glycoprotein (P-gp) is an important determinant of multidrug resistance (MDR) because its overexpression is associated with increased efflux of various established chemotherapy drugs in many clinically resistant and refractory tumors. This leads to insufficient therapeutic targeting of tumor populations, representing a major drawback of cancer chemotherapy. Therefore, P-gp is a target for pharmacological inhibitors to overcome MDR. In the present study, we utilized machine learning strategies to establish a model for P-gp modulators to predict whether a given compound would behave as substrate or inhibitor of P-gp. Random forest feature selection algorithm-based leave-one-out random sampling was used. Testing the model with an external validation set revealed high performance scores. A P-gp modulator list of compounds from the ChEMBL database was used to test the performance, and predictions from both substrate and inhibitor classes were selected for the last step of validation with molecular docking. Predicted substrates revealed similar docking poses than that of doxorubicin, and predicted inhibitors revealed similar docking poses than that of the known P-gp inhibitor elacridar, implying the validity of the predictions. We conclude that the machine-learning approach introduced in this investigation may serve as a tool for the rapid detection of P-gp substrates and inhibitors in large chemical libraries.</jats:p>
Autoren
DOI
10.3390/cells8101286
eISSN
2073-4409
Ausgabe der Veröffentlichung
10
Zeitschrift
Cells
Sprache
en
Online publication date
2019
Paginierung
1286 - 1286
Status
Published online
Herausgeber
MDPI AG
Herausgeber URL
http://dx.doi.org/10.3390/cells8101286
Datum der Datenerfassung
2019
Titel
A Machine Learning-Based Prediction Platform for P-Glycoprotein Modulators and Its Validation by Molecular Docking
Ausgabe der Zeitschrift
8

Data source: Crossref

Abstract
P-glycoprotein (P-gp) is an important determinant of multidrug resistance (MDR) because its overexpression is associated with increased efflux of various established chemotherapy drugs in many clinically resistant and refractory tumors. This leads to insufficient therapeutic targeting of tumor populations, representing a major drawback of cancer chemotherapy. Therefore, P-gp is a target for pharmacological inhibitors to overcome MDR. In the present study, we utilized machine learning strategies to establish a model for P-gp modulators to predict whether a given compound would behave as substrate or inhibitor of P-gp. Random forest feature selection algorithm-based leave-one-out random sampling was used. Testing the model with an external validation set revealed high performance scores. A P-gp modulator list of compounds from the ChEMBL database was used to test the performance, and predictions from both substrate and inhibitor classes were selected for the last step of validation with molecular docking. Predicted substrates revealed similar docking poses than that of doxorubicin, and predicted inhibitors revealed similar docking poses than that of the known P-gp inhibitor elacridar, implying the validity of the predictions. We conclude that the machine-learning approach introduced in this investigation may serve as a tool for the rapid detection of P-gp substrates and inhibitors in large chemical libraries.
Addresses
  • Department of Pharmaceutical Biology, Institute of Pharmacy and Biochemistry, Johannes Gutenberg University, 55128 Mainz, Germany. kadioglu@uni-mainz.de.
Autoren
DOI
10.3390/cells8101286
eISSN
2073-4409
Externe Identifier
  • PubMed Identifier: 31640190
  • PubMed Central ID: PMC6829872
Open access
true
ISSN
2073-4409
Ausgabe der Veröffentlichung
10
Zeitschrift
Cells
Schlüsselwörter
  • Humans
  • Artificial Intelligence
  • Software
  • Drug Discovery
  • Molecular Docking Simulation
  • Machine Learning
  • ATP Binding Cassette Transporter, Subfamily B, Member 1
Sprache
eng
Medium
Electronic
Online publication date
2019
Open access status
Open Access
Paginierung
E1286
Datum der Veröffentlichung
2019
Status
Published
Publisher licence
CC BY
Datum der Datenerfassung
2019
Titel
A Machine Learning-Based Prediction Platform for P-Glycoprotein Modulators and Its Validation by Molecular Docking.
Sub types
  • Research Support, Non-U.S. Gov't
  • research-article
  • Journal Article
Ausgabe der Zeitschrift
8

Files

https://www.mdpi.com/2073-4409/8/10/1286/pdf https://europepmc.org/articles/PMC6829872?pdf=render

Data source: Europe PubMed Central

Abstract
P-glycoprotein (P-gp) is an important determinant of multidrug resistance (MDR) because its overexpression is associated with increased efflux of various established chemotherapy drugs in many clinically resistant and refractory tumors. This leads to insufficient therapeutic targeting of tumor populations, representing a major drawback of cancer chemotherapy. Therefore, P-gp is a target for pharmacological inhibitors to overcome MDR. In the present study, we utilized machine learning strategies to establish a model for P-gp modulators to predict whether a given compound would behave as substrate or inhibitor of P-gp. Random forest feature selection algorithm-based leave-one-out random sampling was used. Testing the model with an external validation set revealed high performance scores. A P-gp modulator list of compounds from the ChEMBL database was used to test the performance, and predictions from both substrate and inhibitor classes were selected for the last step of validation with molecular docking. Predicted substrates revealed similar docking poses than that of doxorubicin, and predicted inhibitors revealed similar docking poses than that of the known P-gp inhibitor elacridar, implying the validity of the predictions. We conclude that the machine-learning approach introduced in this investigation may serve as a tool for the rapid detection of P-gp substrates and inhibitors in large chemical libraries.
Date of acceptance
2019
Autoren
Autoren-URL
https://www.ncbi.nlm.nih.gov/pubmed/31640190
DOI
10.3390/cells8101286
eISSN
2073-4409
Externe Identifier
  • PubMed Central ID: PMC6829872
Ausgabe der Veröffentlichung
10
Zeitschrift
Cells
Schlüsselwörter
  • P-glycoprotein
  • artificial intelligence
  • drug discovery
  • machine learning
  • molecular docking
  • multidrug resistance
  • ATP Binding Cassette Transporter, Subfamily B, Member 1
  • Artificial Intelligence
  • Drug Discovery
  • Humans
  • Machine Learning
  • Molecular Docking Simulation
  • Software
Sprache
eng
Country
Switzerland
PII
cells8101286
Datum der Veröffentlichung
2019
Status
Published online
Datum, an dem der Datensatz öffentlich gemacht wurde
2020
Titel
A Machine Learning-Based Prediction Platform for P-Glycoprotein Modulators and Its Validation by Molecular Docking.
Sub types
  • Journal Article
  • Research Support, Non-U.S. Gov't
Ausgabe der Zeitschrift
8

Data source: PubMed

Beziehungen:
Property of

Tools