论文部分内容阅读
Michaelis-Menten constant,Km,and maximum metabolic rate,Vmax,are two important kinetic parameters for human physiological pharmacokinetic/pharmacodynamic (PK/PD) models.We developed human CYP450 kinetic parameter models for the hydroxylation reaction catalyzed by five CYP P450 enzymes:1A2,2C9,2C19,2D6,and 3A4.Models were developed using Artificial Neural Network Ensemble methodology and molecular descriptors as implemented in the software ADMET PredictorTM.The dataset contained 40~70 substrates for each enzyme,with kinetic parameters measured from in-vitro metabolic studies on cloned virus-infected cells expressing human enzyme-specific microsomes.For the five logKm models,squared correlation coefficient,R2,was in the range of 0.6~0.9 and root-mean-squared error (RMSE) was in the range of 0.3~0.5 log units; Q2 and RMSE for the external test sets were in the range of 0.4~0.9 and 0.4~0.5 log units,respectively.For the five logVmax models,R2 was in the range of 0.6~0.7 and RMSE was in the range of 0.4~0.7 log units; Q2 and RMSE of the external test sets were in the range of 0.3~0.8 and 0.3~0.6 log units,respectively.Predicted parameter values from these models are expected to be used in early human PK models for purposes of risk assessment and to support decision-making in drug discovery.