QSPR modeling of the AmIII / EuIII separation factor How far can we predict ?
Résumé
Exhaustive quantitative structure-property relationship (QSPR) modeling of the separation factor logSF for 46 polyazaheterocyclic ligands extracting Am3+ and Eu3+ from nitric acid aqueous solution to the 1,1,2,2 tetrachloroethane phase has been done using different computational approaches. Modeling methods included Multiple Linear Regression, Radial Basis Function Neural Networks and Associated Neural Networks; two types of descriptors (substructural molecular fragments and molecular descriptors) and different techniques of variable selection have been employed. The developed QSPR models applied for novel t-Bu-hemi-BTP ligand resulted in logSF = 1.07-1.46; these predicted values somewhat exceed the experimental value logSF = 1.0. Several hypothetical extractants potentially possessing high logSF values are proposed. An influence of uncertainties in initial experimental data as well as the choice of the theoretical approach on the performance of QSPR models are discussed.