Multiclass Classifier for P-Glycoprotein Substrates, Inhibitors, and Non-Active Compounds

Abstract

P-glycoprotein (P-gp) is a transmembrane protein that actively transports a wide variety of chemically diverse compounds out of the cell. It is highly associated with the ADMET (absorption, distribution, metabolism, excretion and toxicity) properties of drugs/drug candidates and contributes to decreasing toxicity by eliminating compounds from cells, thereby preventing intracellular accumulation. Therefore, in the drug discovery and toxicological assessment process it is advisable to pay attention to whether a compound under development could be transported by P-gp or not. In this study, an in silico multiclass classification model capable of predicting the probability of a compound to interact with P-gp was developed using a counter-propagation artificial neural network (CP ANN) based on a set of 2D molecular descriptors, as well as an extensive dataset of 2512 compounds (1178 P-gp inhibitors, 477 P-gp substrates and 857 P-gp non-active compounds). The model provided a good classification performance, producing non error rate (NER) values of 0.93 for the training set and 0.85 for the test set, while the average precision (AvPr) was 0.93 for the training set and 0.87 for the test set. An external validation set of 385 compounds was used to challenge the model’s performance. On the external validation set the NER and AvPr values were 0.70 for both indices. We believe that this in silico classifier could be effectively used as a reliable virtual screening tool for identifying potential P-gp ligands.

Structure–Function Relationships in the Human P-Glycoprotein (ABCB1): Insights from Molecular Dynamics Simulations

“…The diversity of conformations in which the P-gp structure has been solved demonstrates the flexibility of the transporter [ 11 , 12 ], a property associated with its polyspecificity, i.e., the ability to bind a large number of chemically diverse compounds. Over time, numerous ligand-based models have been developed to predict the P-gp activity, such as quantitative structure–activity relationship (QSAR) models [ 13 , 14 , 15 , 16 ] and structure-based models based on molecular docking and the use of the mouse P-gp ( m P-gp) 3D structure [ 17 , 18 ], or homology models of the human P-gp ( h P-gp) [ 19 ], in which the binding modes of substrates and inhibitors have been well characterized. Nonetheless, the molecular details of the effects of these molecules on the conformational dynamics of P-gp are not well known.…”

Homology Modeling of the Human P-glycoprotein (ABCB1) and Insights into Ligand Binding through Molecular Docking Studies

“…Quantitative structure-activity relationship (QSAR), a traditional ligand-based method, has been extensively applied in predicting the biological activity providing rapid and cost-effective screening platforms for identifying P-gp inhibitors or substrates. A P-gp classification model was also developed in the authors' previous study [11]. On the other hand, structure-based methods (e.g., molecular docking) allow the investigation of ligand-receptor interactions at atomistic level when high-resolution structures of the receptors are available.…”

Synthesis and Characterization of Some New Quinoxalin-2(1H)one and 2-Methyl-3H-quinazolin-4-one Derivatives Targeting the Onset and Progression of CRC with SAR, Molecular Docking, and ADMET Analyses

“…However, the efflux ability may result in chemotherapeutic resistance and reduce the effectiveness of certain drugs such as anticancer, antibiotic, HIV protease inhibitors, and others [ 43 ]. In various human tumors this protein is commonly overexpressed and acts to lower the drug’s concentration at the intracellular target site to subtherapeutic level resulting in resisting apoptosis and failure of the treatment by many anticancer drugs such as vinblastine and daunorubicin [ 44 ].…”