ORIGINAL ARTICLE QSPR probing of Na + complexation with 15-crown-5 ethers derivatives using artificial neural network and multiple linear regression Hiua Daraei • Mohsen Irandoust • Jahan B. Ghasemi • Ali Reza Kurdian Received: 4 May 2011 / Accepted: 18 June 2011 / Published online: 7 July 2011 Ó Springer Science+Business Media B.V. 2011 Abstract A quantitative structure–property relationship (QSPR) study is performed to develop a model, relating to Na ? complex stability constant (log K) and the structure of 74 derivatives of 1,4,7,10,13-pentaoxacyclo-pentadecane ethers (15C5). Stepwise Multiple Linear Regression (SMLR) and Artificial Neural Network (ANN) methods have been exploited as linear and nonlinear methods, respectively to build the QSPR model. MOPAC software embedded in ChemOffice 2004 package was used for the minimizing energy using semi-empirical AM1 method. The optimum structures have been applied to generate more than 50 descriptors using available servers in ChemOffice 2004. The five most important constitutional, steric, electronic, ther- modynamic and molecular descriptors were selected using the common preselection method combined by SMLR method. SMLR and ANN models were constructed based on the five selected descriptors. Both proposed models effi- ciently predict log K of 15C5 complexes. However, the results of ANN were more effective respect to SMLR model. This phenomenon reveals that log K of 15C5 complexes have a deviation from linear behavior related to the selected descriptors. Keywords Quantitative structure–property relationship  1,4,7,10,13-pentaoxacyclo-pentadecane ethers  Sodium ion  Stability constant  Artificial neural network Introduction Crown ethers are compounds with multiple oxygen het- eroatoms (three or more) incorporated in a monocyclic carbon backbone. They were first synthesized by Pedersen in 1967 [1, 2]. Their generic name originates from their molecular shape, reminiscent of a royal crown [3]. Because of their selective complex formation with hard metal ions as well as their negligible water solubility, crown ethers have been extensively used as suitable ion-carriers in sol- vent–solvent and solid phase extractions [4–7], ion-trans- port [8–10], ion-selective and PVC membrane ion-selective electrode studies [11–13], and the crown ether complexes were applied as a nano-switch recently [14–16]. The complexation of these molecules with suitable well- tailored ions may be considered as trigger step accounting for this widely applications. Among plenty studied ions, alkali metal ions are under attention [17]. Therefore, pre- dicting the log K values of the complexation reactions as the most important complexation property without expend the time and cost in laboratory is a motive to use the quantitative structure property relationship (QSPR) in this branch of chemistry [3]. Quantitative structure activity and structure–property relationship (QSAR/QSPR) studies are unquestionably of great importance in modern chemistry and biochemistry [18]. Currently, these methods are increasingly employed H. Daraei Environmental Health Research Center, Kurdistan University of Medical Sciences, Sanandaj, Iran M. Irandoust (&) Department of Chemistry, Razi University, Kermanshah, Iran e-mail: irandoust1341@yahoo.com J. B. Ghasemi Department of Chemistry, K. N. Toosi University of Technology, Tehran, Iran A. R. Kurdian Department of Chemical Engineering, Razi University, Kermanshah, Iran 123 J Incl Phenom Macrocycl Chem (2012) 72:423–435 DOI 10.1007/s10847-011-0006-7