ADME Evaluation in Drug Discovery. 10. Predictions of P-Glycoprotein Inhibitors Using Recursive Partitioning and Naive Bayesian Classification Techniques

Abstract

P-Glycoprotein (P-gp), an efflux transporter, plays a crucial role in drug pharmacokinetic properties (ADME), and is critical for multidrug resistance (MDR) by mediating the active transport of anticancer drugs from the intracellular to the extracellular compartment. Here we reported an original database of 1273 molecules that are categorized into P-gp inhibitors and noninhibitors. The impact of various physicochemical properties on P-gp inhibition was examined. We then built the decision trees from a training set of 973 compounds using the recursive partitioning (RP) technique and validated by an external test set of 300 compounds. The best decision tree correctly predicted 83.5% of the inhibitors and 67.0% of the noninhibitors in the test set. Finally, we applied naive Bayesian categorization modeling to establish classifiers for P-gp inhibitors. The Bayesian classifier gave average correct prediction for 81.7% of 973 compounds in the training set with leave-one-out cross-validation procedure and 81.2% of 300 compounds in the test set. By establishing multiple decision trees and Bayesian classifiers, we evaluated the impact of molecular fingerprints on classification by the prediction accuracy for the test set, and we found that the inclusion of molecular fingerprints improves the prediction obviously. As an unsupervised learner without tuning parameters, the Bayesian classifier employing fingerprints highlights the important structural fragments favorable or unfavorable for P-gp transport, which provides critical information for designing new efficient P-gp inhibitors.

Reevaluation of a Quantitative Structure Pharmacokinetic Model for Biliary Excretion in Rats

“…Binding affinity for SLC or ABC proteins, and the rate-limiting step in this process for any specific compound, can be difficult to capture through simple descriptors. Although lipophilicity and hydrophobicity have been implicated as possible structural features necessary for binding to a transporter, there are no consensus models in the literature for predicting whether a drug is a substrate for a particular transporter Xing et al, 2009;Chen et al, 2011). Another complexity associated with biliary excretion is that several transporters including P-gp and MRP2 have multiple binding sites, and substrates may bind to multiple transporters (Loo et al, 2003;Zelcer et al, 2003;Callaghan et al, 2006).…”

Novel Bayesian classification models for predicting compounds blocking hERG potassium channels

“…The Bayesian classification technique was widely used in ADME/T predictions [23][24][25] . In our modeling process, the "good" samples (blockers) must be labeled first; then the model learns to distinguish the good samples from the bad samples (nonblockers).…”

Inhibition of P-Glycoprotein Leads to Improved Oral Bioavailability of Compound K, an Anticancer Metabolite of Red Ginseng Extract Produced by Gut Microflora

“…In addition, our previous study on Rh2s, a ginsenoside analog with glucose attached to the C3 position and the same molecular weight and log P value as C-K, indicates that Rh2 underwent strong P-glycoprotein (P-gp)-mediated efflux both in vitro and in vivo (Yang et al, 2011). P-gp is one of the most prevalent efflux transporters (Aller et al, 2009;Chen et al, 2011) and plays an important role in limiting the intestinal absorption of many compounds that are its substrates (Kusuhara and Sugiyama, 2002;del Amo et al, 2009). Inhibition of P-gp leads to the improvement of oral bioavailability of several anticancer drugs (Meerum Terwogt et al, 1998;Kemper et al, 2004;van Waterschoot et al, 2009), including ginsenoside Rh2 (Yang et al, 2011).…”