In silico prediction of cytochrome P450 2D6 and 3A4 inhibition using Gaussian kernel weighted k-nearest neighbor and extended connectivity fingerprints, including structural fragment analysis of inhibitors versus noninhibitors.

摘要: Inhibition of cytochrome P450 (CYP) enzymes is unwanted because the risk 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 diverse sets 1153 1382 drug candidates tested inhibition human liver microsomes. For CYP2D6, 82% classified test set compounds were predicted correct class. CYP3A4, 88% correctly classified. additionally an external 14 drugs, multidimensional scaling plots showed drugs periphery training sets. Furthermore, fragment analyses performed structural fragments frequent inhibitors noninhibitors are presented.