An Investigation into the Factors Governing Drug Absorption and Food Effect Prediction Based on Data Mining Methodology

Abstract

Drug absorption is a complex process governed by a number of interrelatedphysicochemical, biopharmaceutical, and pharmacokinetic factors. In order to explore complexrelationships among these factors, multivariate exploratory analysis was performed on thedataset of drugs with diverse bioperformance. The investigated dataset included subset of drugsfor which bioequivalence between solid dosage form and oral solution has been reported, andsubset of drugs described in the literature as low solubility/low permeability compounds.Discriminatory power of hierarchical clustering on principal components was somewhat higherwhen applied on the data subsets of drugs with similar bioperformance, while analysis of theintegrated dataset indicated existence of two groups of drugs with the boundaries reflected in Peffvalue of approximately 2 × 10−4cm/s and Fa and Fm values higher than 85% and 50%,respectively. Majority of the investigated drugs within the integrated dataset were grouped withintheir initial subset indicating that overall drug bioperformance is closely related to itsphysicochemical, biopharmaceutical and pharmacokinetic properties. Classification modelsconstructed using the random forest (RF) and support vector machine with polynomial kernelfunction were able to predict food effect based on drug dose/solubility ratio (D/S), effectivepermeability (Peff), percent of dose metabolized (Fm), and elimination half-life (τ1/2). Althoughboth models performed well during training and testing, only RF kept satisfying performancewhen applied on the external dataset (kappa value > 0.4). The results obtained indicate that datamining can be employed as useful tool in biopharmaceutical drug characterization which meritsfurther investigation