P-glycoprotein Substrate Models Using Support Vector Machines Based on a Comprehensive Data set

Abstract

P-glycoprotein (P-gp) is one of the major ABC transporters and involved in many essential processes such as lipid and steroid transport across cell membranes but also in the uptake of drugs such as HIV protease and reverse transcriptase inhibitors. Despite its importance, reliable models predicting substrates of P-gp are scarce. In this study, we have built several computational models to predict whether or not a compound is a P-gp substrate, based on the largest data set yet published, employing 332 distinct structures. Each molecule is represented by ADRIANA.Code, MOE, and ECFP_4 fingerprint descriptors. The models are computed using a support vector machine based on a training set which includes 131 substrates and 81 nonsubstrates that were evaluated by 5-, 10-fold, and leave-one-out (LOO) cross-validation. The best model gives a Matthews Correlation Coefficient of 0.73 and a prediction accuracy of 0.88 on the test set. Examination of the model based on ECFP_4 fingerprints revealed several substructures which could have significance in separating substrates and nonsubstrates of P-gp, such as the nitrile and sulfoxide functional groups which have a higher frequency in nonsubstrates than in substrates. In addition structural isomerism in sugars was found to result in remarkable differences regarding the likelihood of a compound to be a substrate for P-gp.

SwissADME: a free web tool to evaluate pharmacokinetics, drug-likeness and medicinal chemistry friendliness of small molecules

“…In that case, accuracy measurements are overestimated and prone to mislead the construction and the evaluation of the model. Moreover, some SVM models were published with small training and test sets (P-gp of refs 15 and 57), which imply questionable capacity of generalization and broadness of applicability domains. We emphasize that for SwissADME classifiers, both training and test sets were carefully cleansed and checked for size, diversity and balance between classes.…”

QSAR Models for P-Glycoprotein Transport Based on a Highly Consistent Data Set

“…This explains why for this work, as well as for most of the Pgp models presented so far, the specificity is generally lower than the sensitivity. 25,26,28,30 Recently Gupta et al 18 presented a model for Pgp transport based on 43408 compounds. In this data set, borderline substrates were included in the Pgp nonsubstrates class, and, consistently, models derived had high specificity and lower sensitivity.…”

Inhibition of the Multidrug Resistance P-Glycoprotein: Time for a Change of Strategy?

“…The broad or polyspecificity of P-gp is legendary (or infamous), and the list of compounds known to interact with this transporter is well in excess of 300 (Wang et al, 2011;. It is apparent that many of the much touted "new generation" anticancer compounds (e.g., kinase inhibitors) are also substrates for transport by P-gp (Hegedus et al, 2002;Wang and Fu, 2010).…”