Using the Variable-Nearest Neighbor Method To Identify P‑Glycoprotein Substrates and Inhibitors

Permeability glycoprotein
(Pgp) is an essential membrane-bound
transporter that efficiently extracts compounds from a cell. As such,
it is a critical determinant of the pharmacokinetic properties of
drugs. Multidrug resistance in cancer is often associated with overexpression
of Pgp, which increases the efflux of chemotherapeutic agents from
the cell. This, in turn, may prevent an effective treatment by reducing
the effective intracellular concentrations of such agents. Consequently,
identifying compounds that can either be transported out of the cell
by Pgp (substrates) or impair Pgp function (inhibitors) is of great
interest. Herein, using publically available data, we developed quantitative
structure–activity relationship (QSAR) models of Pgp substrates
and inhibitors. These models employed a variable-nearest neighbor
(v-NN) method that calculated the structural similarity between molecules
and hence possessed an applicability domain, that is, they used all
nearest neighbors that met a minimum similarity constraint. The performance
characteristics of these v-NN-based models were comparable or at times
superior to those of other model constructs. The best v-NN models
for identifying either Pgp substrates or inhibitors showed overall
accuracies of >80% and κ values of >0.60 when tested on
external
data sets with candidate Pgp substrates and inhibitors. The v-NN prediction
model with a well-defined applicability domain gave accurate and reliable
results. The v-NN method is computationally efficient and requires
no retraining of the prediction model when new assay information becomes
availablean important feature when keeping QSAR models up-to-date
and maintaining their performance at high levels.