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.

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.

Patients often receive several medications at the same time, and if the drugs involved compete for the same enzymes to be metabolized, it can lead to undesired effects with the risk of fatal results. Therefore, early knowledge about the cytochrome P450 (CYP) interaction potential of a drug candidate is central and in silico tools can provide such information even on virtual structures. Most of the in silico CYP information in the literature is on substrates and is based on molecular and protein modeling. However, in early screening information of CYP substrates is rarely available and sometimes only a single concentration is used in screening assays. Recently, in silico CYP modeling applying statistical tools has appeared in the literature and the aim of this review is to give an overview of published in silico prediction studies of CYP inhibition for four of the clinically most important isotypes, namely: CYP1A2, CYP2C9, CYP2D6, and CYP3A4. Furthermore, in the review, we discuss inhibition data, different descriptors and statistical methods applied for in silico prediction of CYP inhibition, and we point to promising approaches in the development of accurate in silico prediction tools of CYP inhibitors. Drug Dev. Res. 67:417-429, 2006.