QSPR study of Setschenow constants of organic compounds using MLR, ANN, and SVM analyses

J Comput Chem. 2011 Nov 30;32(15):3241-52. doi: 10.1002/jcc.21907. Epub 2011 Aug 12.

Abstract

A quantitative structure-property relationship (QSPR) study was performed for the prediction of the Setschenow constants (K(salt)) by sodium chloride of organic compounds. The entire set of 101 compounds was randomly divided into a training set of 71 compounds and a test set of 30 compounds. Multiple linear regression, artificial neural network (ANN), and support vector machine (SVM) were utilized to build the linear and nonlinear QSPR models, respectively. The obtained models with four descriptors involved show good predictive ability. The linear model fits the training set with R(2) = 0.8680, while ANN and SVM higher values of R(2) = 0.8898 and 0.9302, respectively. The validation results through the test set indicate that the proposed models are robust and satisfactory. The QSPR study suggests that the molecular lipophilicity is closely related to the Setschenow constants.

Publication types

  • Research Support, Non-U.S. Gov't

MeSH terms

  • Methods
  • Neural Networks, Computer
  • Organic Chemicals / chemistry*
  • Quantitative Structure-Activity Relationship*
  • Support Vector Machine*

Substances

  • Organic Chemicals