Prediction of Human Intestinal Absorption of Drug Compounds from Molecular Structure

TLDR

Drug absorption across the human intestinal epithelium is a critical property for candidate drugs, yet experimental measurement is costly and time‑consuming. QSPRs were employed to estimate percent human intestinal absorption (%HIA) as an attractive alternative to experimental assays. A neural‑network QSPR model was trained on 86 compounds with calculated molecular descriptors, optimized via a genetic algorithm. The model achieved rms errors of 9.4% (training), 19.7% (cross‑validation), and 16.0% (external prediction).

Abstract

The absorption of a drug compound through the human intestinal cell lining is an important property for potential drug candidates. Measuring this property, however, can be costly and time-consuming. The use of quantitative structure−property relationships (QSPRs) to estimate percent human intestinal absorption (%HIA) is an attractive alternative to experimental measurements. A data set of 86 drug and drug-like compounds with measured values of %HIA taken from the literature was used to develop and test a QSPR model. The compounds were encoded with calculated molecular structure descriptors. A nonlinear computational neural network model was developed by using the genetic algorithm with a neural network fitness evaluator. The calculated %HIA (cHIA) model performs well, with root-mean-square (rms) errors of 9.4%HIA units for the training set, 19.7%HIA units for the cross-validation (CV) set, and 16.0%HIA units for the external prediction set.