Quantitative structure/property relationship analysis of Caco‐2 permeability using a genetic algorithm‐based partial least squares method

• Published in: Journal of pharmaceutical sciences Vol. 91; no. 10; pp. 2230 - 2239
• Main Authors: Yamashita, Fumiyoshi, Wanchana, Suchada, Hashida, Mitsuru
• Format: Journal Article
• Language: English
• Published: New York Elsevier Inc 01.10.2002; Wiley Subscription Services, Inc., A Wiley Company; Wiley; American Pharmaceutical Association
• Subjects: Algorithms; Analysis; Biological and medical sciences; Caco-2 Cells; Caco-2 permeability; Cell Membrane Permeability - physiology; Databases, Genetic; General pharmacology; genetic algorithm; Genetics - statistics & numerical data; Humans; Least-Squares Analysis; Medical sciences; Molconn-Z; Molecular Weight; partial least squares; Pharmacokinetics. Pharmacogenetics. Drug-receptor interactions; Pharmacology. Drug treatments; Quantitative Structure-Activity Relationship; quantitative structure-property relationship; genetic algorithm; Caco‐2 permeability; partial least squares; Molconn‐Z; quantitative structure–property relationship; Human; Caco-2 permeability; Digestive system; quantitative structure-property relationship; Gut; Permeation; Prediction; Permeability; Absorption; Genetic algorithm; Least squares method; Established cell line; Property structure relationship; Molconn-Z; Partial least squares; Tumor cell; Quantitative analysis
• ISSN: 0022-3549; 1520-6017
• DOI: 10.1002/jps.10214

Caco‐2 cell monolayers are widely used systems for predicting human intestinal absorption. This study was carried out to develop a quantitative structure–property relationship (QSPR) model of Caco‐2 permeability using a novel genetic algorithm‐based partial least squares (GA‐PLS) method. The Caco‐2 permeability data for 73 compounds were taken from the literature. Molconn‐Z descriptors of these compounds were calculated as molecular descriptors, and the optimal subset of the descriptors was explored by GA‐PLS analysis. A fitness function considering both goodness‐of‐fit to the training data and predictability of the testing data was adopted throughout the genetic algorithm‐driven optimization procedure. The final PLS model consisting of 24 descriptors gave a correlation coefficient (r) of 0.886 for the entire dataset and a predictive correlation coefficient (rpred) of 0.825 that was evaluated by a leave‐some‐out cross‐validation procedure. Thus, the GA‐PLS analysis proved to be a reasonable QSPR modeling approach for predicting Caco‐2 permeability. © 2002 Wiley‐Liss Inc. and the American Pharmaceutical Association J Pharm Sci 91:2230–2239, 2002