ABSTRACT
Inhibition of cytochrome P450 (CYP) enzymes is unwanted because of the risk of severe side effects due to drug-drug interactions. We present two in silico Gaussian kernel weighted k-nearest neighbor models based on extended connectivity fingerprints that classify CYP2D6 and CYP3A4 inhibition. Data used for modeling consisted of diverse sets of 1153 and 1382 drug candidates tested for CYP2D6 and CYP3A4 inhibition in human liver microsomes. For CYP2D6, 82% of the classified test set compounds were predicted to the correct class. For CYP3A4, 88% of the classified compounds were correctly classified. CYP2D6 and CYP3A4 inhibition were additionally classified for an external test set on 14 drugs, and multidimensional scaling plots showed that the drugs in the external test set were in the periphery of the training sets. Furthermore, fragment analyses were performed and structural fragments frequent in CYP2D6 and CYP3A4 inhibitors and noninhibitors are presented.
Subject(s)
Cytochrome P-450 CYP2D6 Inhibitors , Cytochrome P-450 CYP2D6/chemistry , Cytochrome P-450 Enzyme Inhibitors , Cytochrome P-450 Enzyme System/chemistry , Enzyme Inhibitors/chemistry , Models, Molecular , Pharmaceutical Preparations/chemistry , Quantitative Structure-Activity Relationship , Cluster Analysis , Cytochrome P-450 CYP3A , Databases, Factual , Humans , In Vitro Techniques , Microsomes, Liver/drug effects , Microsomes, Liver/enzymologyABSTRACT
A data set consisting of 712 compounds was used for classification into two classes with respect to membrane permeation in a cell-based assay: (0) apparent permeability (P(app)) below 4 x 10(-6) cm/s and (1) P(app) on 4 x 10(-6) cm/s or higher. Nine molecular descriptors were calculated for each compound and Nearest-Neighbor classification was applied using five neighbors as optimized by full cross-validation. A model based on five descriptors, number of flex bonds, number of hydrogen bond acceptors and donors, and molecular and polar surface area, was selected by variable selection. In an external test set of 112 compounds, 104 compounds were classified and 8 compounds were judged as "unknown". Among the 104 compounds, 16 were misclassified corresponding to a misclassification rate of 15% and no compounds were falsely predicted in the nonpermeable class.
Subject(s)
Cell Membrane Permeability , Intestinal Absorption , Models, Biological , Pharmaceutical Preparations/chemistry , Animals , Cell Line , Diffusion , Dogs , Humans , Pharmaceutical Preparations/metabolism , Quantitative Structure-Activity RelationshipABSTRACT
The metabolic stability of a drug is an important property for potential drug candidates. Measuring this property, however, can be costly and time-consuming. The use of quantitative structure-activity relationships (QSAR) to estimate the in vitro stability is an attractive alternative to experimental measurements. A data set of 130 calcitriol analogs with known values of in vitro metabolic stability was used to develop QSAR models. The analogs were encoded with molecular structure descriptors computed mainly with the commercial software QikProp and DiverseSolutions. Variable selection was carried out by five different variable selection techniques and Partial Least Squares Regression (PLS) models were generated from the 130 analogs. The models were used for prediction of the metabolic stability of 244 virtual calcitriol analogs. Twenty of the 244 analogs were selected and the in vitro metabolic stability was determined experimentally. The PLS models were able to predict the correct metabolic stability for 17 of the 20 selected analogs, corresponding to a prediction performance of 85%. The results clearly demonstrate the utility of QSAR models in predicting the in vitro metabolic stability of calcitriol analogs.
