Fingerprint-based in silico models for the prediction of P-glycoprotein substrates and inhibitors

• Published in: Bioorganic & medicinal chemistry Vol. 20; no. 18; pp. 5388 - 5395
• Main Authors: Poongavanam, Vasanthanathan, Haider, Norbert, Ecker, Gerhard F.
• Format: Journal Article
• Language: English
• Published: England Elsevier Ltd 15.09.2012; Elsevier Science
• Subjects: ADMET; Algorithms; antagonists & inhibitors; Association rule; ATP Binding Cassette Transporter, Subfamily B, Member 1; ATP Binding Cassette Transporter, Subfamily B, Member 1 - antagonists & inhibitors; ATP Binding Cassette Transporter, Subfamily B, Member 1 - chemistry; ATP Binding Cassette Transporter, Subfamily B, Member 1 - metabolism; chemistry; Computational Biology; Databases, Pharmaceutical; Drug Substitution; drugs; Fingerprint; In silico; Indexing in process; Machine learning methods; metabolism; Models, Molecular; Molecular Structure; multiple drug resistance; P-glycoprotein; pharmacokinetics; prediction; support vector machines; therapeutics; P-glycoprotein; In silico; Fingerprint; Association rule; ADMET; Machine learning methods
• ISSN: 0968-0896; 1464-3391; 1464-3391
• DOI: 10.1016/j.bmc.2012.03.045

P-Glycoprotein (P-gp, ABCB1) plays a significant role in determining the ADMET properties of drugs and drug candidates. Substrates of P-gp are not only subject to multidrug resistance (MDR) in tumor therapy, they are also associated with poor pharmacokinetic profiles. In contrast, inhibitors of P-gp have been advocated 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-gp substrate/non-substrate or an inhibitor/non-inhibitor quite challenging. In the present investigation, we used a set of fingerprints representing the presence/absence of various functional groups for machine learning based classification of a set of 484 substrates/non-substrates and a set of 1935 inhibitors/non-inhibitors. Best models were obtained using a combination of a wrapper subset evaluator (WSE) with random forest (RF), kappa nearest neighbor (kNN) and support vector machine (SVM), showing accuracies >70%. Best P-gp substrate models were further validated with three sets of external P-gp substrate sources, which include Drug Bank (n=134), TP Search (n=90) and a set compiled from literature (n=76). Association rule analysis explores the various structural feature requirements for P-gp substrates and inhibitors.