QSAR-based permeability model for drug-like compounds

Rafael Gozalbes, Mary Jacewicz, Robert Annand, Katya Tsaioun, Antonio Pineda-Lucena

Research output: Contribution to journalArticlepeer-review

Abstract

A QSAR model was developed for predicting intestinal drug permeability, one of the most important parameters when evaluating compounds in drug discovery projects. First, a set of relevant properties for establishing a drug-like chemical space was applied to a database of compounds with Caco-2 permeability values obtained from previous studies. Several QSAR regression models were then developed from this set of drug-like structures. The best model was selected based on the accuracy of correct classifications obtained for training and validation subsets previously defined, including 17 structures from the FDA Biopharmaceutics Classification System (BCS). Further validation of the QSAR model was performed by applying it to 21 drugs for which Caco-2 permeability values were experimentally determined by us. The good agreement between predictions and experimental values in all cases confirmed the reliability of the equation. Since the model was developed with very simple descriptors, easy to calculate, its applicability to large collections of in silico chemicals is guaranteed.

Original languageEnglish (US)
Pages (from-to)2615-2624
Number of pages10
JournalBioorganic and Medicinal Chemistry
Volume19
Issue number8
DOIs
StatePublished - Apr 15 2011
Externally publishedYes

Keywords

  • Chemical space
  • Computational chemistry
  • Drug discovery
  • Permeability
  • Quantitative structure-activity relationships (QSAR)

ASJC Scopus subject areas

  • Biochemistry
  • Molecular Medicine
  • Molecular Biology
  • Pharmaceutical Science
  • Drug Discovery
  • Clinical Biochemistry
  • Organic Chemistry

Fingerprint Dive into the research topics of 'QSAR-based permeability model for drug-like compounds'. Together they form a unique fingerprint.

Cite this