Development of a highly specific ensemble of topological models for early identification of P‐glycoprotein substrates

Abstract

a P-glycoprotein (Pgp) is an ATP-dependent efflux transporter protein associated with multidrug resistance in several diseases such as cancer, epilepsy and AIDS. It is preferentially expressed in organs and tissues that function as a barrier (e.g. the gut walls or the blood-brain barrier) or promote the elimination of xenobiotics from the organism (e.g. liver and kidney). Pgp limits drug bioavailability; thus, the recognition of Pgp substrates at the early stages of the drug development cycle is essential for the development of new chemotherapeutic agents to deal with multidrug resistance issues. Here we present the development of several classifier models based on topological descriptors to identify potential Pgp substrates, aimed to be applied as secondary filter in virtual screening campaigns. Receiver Operating characteristic (ROC) curves show that combination of individual models, through data fusion, in a three-model ensemble, allows attaining higher areas under the curve and an overall better behavior in terms of sensitivity or specificity. The individual discriminant functions (dfs) presented have a performance similar to that of the previously reported models and, remarkably, our models only include low-dimensional (up to 2D) molecular descriptors, which makes them adequate for the virtual screening of increasingly large virtual chemical repositories.

Computer-Aided Recognition of ABC Transporters Substrates and Its Application to the Development of New Drugs for Refractory Epilepsy

“…In this regard, back in 2011 Di Ianni and colleagues reported a 3-model ensemble of 2D QSAR classifiers capable of differentiating P-gp substrates from nonsubstrates [75]. For this purpose, a 250-compound dataset including 104 P-gp substrates and non-substrates was compiled from literature.…”

“…This information is employed in docking protocols to find P-gp substrates/inhibitors. They have, in general, less accuracy than ligand-based approaches [81,75,82]. However, there are successful examples in relation to the identification of P-gp substrates/inhibitors by means of docking simulations, and some of them provide information about the conformations of the binders in the active site [79 and refs therein].…”

Several New Diverse Anticonvulsant Agents Discovered in a Virtual Screening Campaign Aimed at Novel Antiepileptic Drugs to Treat Refractory Epilepsy

“…18−21 Recently, we have reported a highly specific three-model ensemble of 2D classifiers capable of differentiating Pgp-substrates from nonsubstrates. 22 Here, we have applied this model ensemble in combination with a previously reported topological model capable of identifying anticonvulsants active in the Maximal Electroshock Seizure (MES) test 23−25 to ZINC 5 and DrugBank databases, 26,27 in order to find possible candidates for the treatment of Pgp-mediated refractory epilepsy. From the database compounds chosen as candidates, a subset of 380 molecules was selected for a structure-based virtual screening by docking.…”

“…To prioritize the early identification of non substrates of efflux transporters, initially we applied a three-model ensemble of 2D classifiers capable of differentiating Pgp-substrates from nonsubstrates. 22 Briefly, the average output of the following three models is used to predict whether a given drug candidate is or is not a Pgpsubstrate:…”

“…P-glycoprotein (Pgp) is one of the ABC efflux transporters linked to refractory epilepsy, being up-regulated at the blood–brain barrier and epileptic loci of patients with intractable epilepsy. − Recently, we have reported a highly specific three-model ensemble of 2D classifiers capable of differentiating Pgp-substrates from nonsubstrates . Here, we have applied this model ensemble in combination with a previously reported topological model capable of identifying anticonvulsants active in the Maximal Electroshock Seizure (MES) test − to ZINC 5 and DrugBank databases, , in order to find possible candidates for the treatment of Pgp-mediated refractory epilepsy.…”