pgp - publications
Predict more pgp - ligand interactions now!
1. Bioorg Med Chem. 2012 Mar 29. [Epub ahead of print]Fingerprint-based in silico models for the prediction of P-glycoproteinsubstrates and inhibitors.Poongavanam V, Haider N, Ecker GF.University of Vienna, Department of Medicinal Chemistry, Althanstrasse 14, 1090Vienna, Austria.P-Glycoprotein (P-gp, ABCB1) plays a significant role in determining the ADMETproperties of drugs and drug candidates. Substrates of P-gp are not only subject to multidrug resistance (MDR) in tumor therapy, they are also associated withpoor pharmacokinetic profiles. In contrast, inhibitors of P-gp have beenadvocated as modulators of MDR. However, due to the polyspecificity of P-gp,knowledge on the molecular basis of ligand-transporter interaction is still poor,which renders the prediction of whether a compound is a P-gpsubstrate/non-substrate or an inhibitor/non-inhibitor quite challenging. In thepresent investigation, we used a set of fingerprints representing thepresence/absence of various functional groups for machine learning basedclassification of a set of 484 substrates/non-substrates and a set of 1935inhibitors/non-inhibitors. Best models were obtained using a combination of awrapper subset evaluator (WSE) with random forest (RF), kappa nearest neighbor(kNN) and support vector machine (SVM), showing accuracies >70%. Best P-gpsubstrate models were further validated with three sets of external P-gpsubstrate sources, which include Drug Bank (n=134), TP Search (n=90) and a setcompiled from literature (n=76). Association rule analysis explores the variousstructural feature requirements for P-gp substrates and inhibitors.Copyright © 2012 Elsevier Ltd. All rights reserved.PMID: 22595422 [PubMed - as supplied by publisher]