Machine Learning Models for Human <i>In Vivo</i> Pharmacokinetic Parameters with In-House Validation

Abstract

Prior to clinical development, a comprehensive pharmacokinetic characterization of a novel drug is required to understand its exposure at the site of action and elimination. Accordingly, <i>in vitro</i> assays and animal pharmacokinetic studies are regularly employed to predict drug exposure in humans, which is often costly and time-consuming. For this reason, the prediction of human pharmacokinetics at the point of design would be of high value for drug discovery. Therefore, we have established a comprehensive data curation protocol that enables machine learning evaluation of 12 human <i>in vivo</i> pharmacokinetic parameters using only chemical structure information and available doses for 1001 unique compounds. These machine learning models were thoroughly investigated and validated using both an independent hold-out test set and AstraZeneca clinical data. In addition, the availability of preclinical predictions for a subset of internal clinical candidates allowed us to compare our <i>in silico</i> approach with state-of-the-art pharmacokinetic predictions. Based on this evaluation, three fit-for-purpose models for AUC PO (<i>R</i>_test² = 0.63; RMSE_test = 0.76), <i>C</i>_max PO (<i>R</i>_test² = 0.68; RMSE_test = 0.62), and Vd_ss IV (<i>R</i>_test² = 0.47; RMSE_test = 0.50) were identified. Based on the findings, our machine learning models have considerable potential for practical applications in drug discovery, such as influencing decision-making in drug discovery projects and progression of drug candidates toward the clinic.