Computational predictive models for P-glycoprotein inhibition of in-house chalcone derivatives and drug-bank compounds.

The human P-glycoprotein (P-gp) efflux pump is of great interest for medicinal chemists because of its important role in multidrug resistance (MDR). Because of the high polyspecificity as well as the unavailability of high-resolution X-ray crystal structures of this transmembrane protein, ligand-based, and structure-based approaches which were machine learning, homology modeling, and molecular docking were combined for this study. In ligand-based approach, individual two-dimensional quantitative structure-activity relationship models were developed using different machine learning algorithms and subsequently combined into the Ensemble model which showed good performance on both the diverse training set and the validation sets.

Virtual screening for novel Staphylococcus Aureus NorA efflux pump inhibitors from natural products.

NorA is a member of the Major Facilitator Superfamily (MFS) drug efflux pumps that have been shown to mediate antibiotic resistance in Staphylococcus aureus (SA). In this study, QSAR analysis, virtual screening and molecular docking were implemented in an effort to discover novel SA NorA efflux pump inhibitors. Originally, a set of 47 structurally diverse compounds compiled from the literature was used to develop linear QSAR models and another set of 15 different compounds were chosen for extra validation.

Pharmacophore modeling for antitargets.

The pharmacophore modeling in modern drug research has been applied for both bioactivity profiling and early stage of risk assessment of potential side effects and toxicity due to interactions of drug candidates with antitargets namely P-glycoprotein, hERG, cytochrome P450 and pregnane X-receptor. In this article, an existing state concerning with pharmacophore modeling applied for promiscuous proteins in drug research were updated and reviewed. In an attempt to create new safe medicines faster, the partial overlap of substrate properties of hERG, P-glycoprotein, pregnane X-receptor and cytochrome P450 has to be considered and drug safety has to be dealt on a system level on the off-targets.

A support vector machine classification model for benzo[c]phenathridine analogues with toposiomerase-I inhibitory activity.

Benzo[c]phenanthridine (BCP) derivatives were identified as topoisomerase I (TOP-I) targeting agents with pronounced antitumor activity. In this study, a support vector machine model was performed on a series of 73 analogues to classify BCP derivatives according to TOP-I inhibitory activity. The best SVM model with total accuracy of 93% for training set was achieved using a set of 7 descriptors identified from a large set via a random forest algorithm.