Regression methods for developing QSAR and QSPR models to predict compounds of specific pharmacodynamic, pharmacokinetic and toxicological properties

C. W. Yap, H. Li, Z. L. Ji, Y. Z. Chen

Research output: Contribution to journalArticlepeer-review

52 Scopus citations

Abstract

Quantitative structure-activity relationship (QSAR) and quantitative structure-property relationship (QSPR) models have been extensively used for predicting compounds of specific pharmacodynamic, pharmacokinetic, or toxicological property from structure-derived physicochemical and structural features. These models can be developed by using various regression methods including conventional approaches (multiple linear regression and partial least squares) and more recently explored genetic (genetic function approximation) and machine learning (k-nearest neighbour, neural networks, and support vector regression) approaches. This article describes the algorithm of these methods, evaluates their advantages and disadvantages, and discusses the application potential of did recently explored methods. Freely available online and commercial software for these regression methods and the areas of their applications are also presented.

Original languageEnglish (US)
Pages (from-to)1097-1107
Number of pages11
JournalMini-Reviews in Medicinal Chemistry
Volume7
Issue number11
DOIs
StatePublished - Nov 2007

Keywords

  • ADME
  • ADMET
  • Compound
  • Drug
  • Pharmacodynamics
  • Pharmacokinetics
  • QSAR
  • QSPR
  • Statistical learning methods
  • Structure-activity relationship
  • Toxicity

ASJC Scopus subject areas

  • Molecular Medicine
  • Pharmacology
  • Drug Discovery
  • Cancer Research

Fingerprint

Dive into the research topics of 'Regression methods for developing QSAR and QSPR models to predict compounds of specific pharmacodynamic, pharmacokinetic and toxicological properties'. Together they form a unique fingerprint.

Cite this