A Novel Chemometric Method for the Prediction of Human Oral Bioavailability

TLDR

Orally administered drugs must overcome barriers such as membrane transport systems and intracellular drug‑metabolizing enzymes before reaching their target site. The study aims to incorporate P‑gp and CYP enzymes into QSAR models to predict human oral bioavailability using 805 diverse compounds. Models were built using multiple linear regression, partial least squares regression, and support‑vector machine regression, and their predictive performance was validated by five‑fold cross‑validation and independent external tests. SVR achieved the best predictive performance (R² = 0.80, SEE = 0.31), outperforming MLR (R² = 0.60, SEE = 0.40) and PLS (R² = 0.64, SEE = 0.31), indicating that all three models hold promise for predicting oral bioavailability in drug design.

Abstract

Orally administered drugs must overcome several barriers before reaching their target site. Such barriers depend largely upon specific membrane transport systems and intracellular drug-metabolizing enzymes. For the first time, the P-glycoprotein (P-gp) and cytochrome P450s, the main line of defense by limiting the oral bioavailability (OB) of drugs, were brought into construction of QSAR modeling for human OB based on 805 structurally diverse drug and drug-like molecules. The linear (multiple linear regression: MLR, and partial least squares regression: PLS) and nonlinear (support-vector machine regression: SVR) methods are used to construct the models with their predictivity verified with five-fold cross-validation and independent external tests. The performance of SVR is slightly better than that of MLR and PLS, as indicated by its determination coefficient (R2) of 0.80 and standard error of estimate (SEE) of 0.31 for test sets. For the MLR and PLS, they are relatively weak, showing prediction abilities of 0.60 and 0.64 for the training set with SEE of 0.40 and 0.31, respectively. Our study indicates that the MLR, PLS and SVR-based in silico models have good potential in facilitating the prediction of oral bioavailability and can be applied in future drug design.