QSPR study for estimation of Kovats retention indices of some of Adamantane derivatives using genetic algorithm (GA) and multiple linear regression (MLR) analysis by Hartree –Fock method

The Kovats retention indices values are expressed as a important property of Adamantane derivatives.A linear quantitative structure–Property relationship (QSPR) model is presented for the modelling and prediction for the Kovats retention indices of Adamantane derivatives. The model was produced using the multiple linear regression (MLR) technique on a database that consisted of 65 adamantane derivatives compounds. Among the different constitutional, topological, geometrical, electrostatic and quantum-chemical descriptors that were considered as inputs to the model, seven variables were selected using the genetic algorithm subset selection method (GA). A multi-parametric equation containing maximum two descriptors at the Hartree– Fock level with 6-31+G** basis set , with good statistical qualities ( R2train=0.922 , Ftrain=109.038, Q2 LOO=0.904 , R2 adj=0.914, Q2LGO=0.863) was obtained by Multiple Linear Regression using stepwise method.The accuracy of the proposed MLR model was illustrated using the following evaluation techniques: cross-validation, validation through an external test set, and Y-randomisation. The predictive ability of the model was found to be satisfactory and could be used for designing a similar group of compounds.

Author(s): M. Fakoor Yzdan Abad and Z. Bayat

Abstract | PDF

Share This Article