Prediction of Biliary Excretion in Rats and Humans Using Molecular Weight and Quantitative Structure–Pharmacokinetic Relationships

The aims were (1) to evaluate the molecular weight (MW) dependence of biliary excretion and (2) to develop quantitative structure–pharmacokinetic relationships (QSPKR) to predict biliary clearance (CLb) and percentage of administered dose excreted in bile as parent drug (PDb) in rats and humans. CLb and PDb data were collected from the literature for rats and humans. Receiver operating characteristic curve analysis was utilized to determine whether a MW threshold exists for PDb. Stepwise multiple linear regression (MLR) was used to derive QSPKR models. The predictive performance of the models was evaluated by internal validation using the leave-one-out method and external test groups. A MW threshold of 400 Da was determined for PDb for anions in rats, while 475 Da was the cutoff for anions in humans. MW thresholds were not present for cations or cations/neutral compounds in either rats or humans. The QSPKR model for human CLb showed a significant correlation (R2 = 0.819) with good prediction performance (Q2 = 0.722). The model was further assessed using a test group, yielding a geometric mean fold-error of 2.68. QSPKR models with significant correlation and good predictability were also developed for CLb in rats and PDb data for anions or cation/neutral compounds in rats and humans. Both CLb and PDb data were further evaluated for subsets of MRP2 or P-glycoprotein substrates, and significant relationships were derived. QSPKR models were successfully developed for biliary excretion of non-congeneric compounds in rats and humans, providing a quantitative prediction of biliary clearance of compounds.