Available online at www.sciencedirect.com Sensors and Actuators B 132 (2008) 13–19 Application of GA-MLR, GA-PLS and the DFT quantum mechanical (QM) calculations for the prediction of the selectivity coefficients of a histamine-selective electrode Siavash Riahi a,b,∗ , Mohammad Reza Ganjali b , Parviz Norouzi b , Fatemeh Jafari b a Institute of Petroleum Engineering, Faculty of Engineering, University of Tehran, Tehran, Iran b Center of Excellence in Electrochemistry, Faculty of Chemistry, University of Tehran, P.O. Box 14155-6455, Tehran, Iran Received 23 September 2007; received in revised form 17 December 2007; accepted 3 January 2008 Available online 16 January 2008 Abstract Quantitative structure–property relationships (QSPRs) were developed using a genetic algorithm (GA), based on the variable-selection approach with topological descriptors. The selectivity coefficients of 26 molecules (drug, amino-acid and organic compound) of a histamine-selective electrode were efficiently estimated and predicted with the QSPR models. The most important descriptors were selected from a set of 74 topological descriptors to build the QSPR models, using the multiple linear regressions (MLRs) and the partial least squares (PLS) regression. The predictive quality of the QSPR models was tested for an external prediction set of 7 compounds, randomly chosen from 26 compounds. The PLS regression method was used to model the structure-selectivity coefficient relationships. However, the results surprisingly showed more or less the same quality for MLR and PLS modeling, according to the squared regression coefficients R 2 values, which were 0.918 and 0.915, respectively. In addition, the theoretical investigation on the interaction of the histamine and the other studied compounds with the ionophore was performed. The correlation between the interaction energies and the selectivity coefficients of the studied compounds was equal to 0.993, demonstrating the applicability of these results for the prediction of the selectivity coefficients. © 2008 Elsevier B.V. All rights reserved. Keywords: Selectivity coefficient; DFT calculation; Partial least squares (PLS); Genetic algorithm; QSPR; Chemometrics 1. Introduction The multiple linear regressions (MLRs) and the partial least squares (PLS) regression are the mostly used modeling methods in QSPRs (quantitative structure–property relationships) [1–3]. The MLR yields are simpler and easier to interpret than those of the PLS models, because these methods perform regression on the latent variables, not having physical meaning. However, due to the collinearity between the structural descriptors, MLR is not able to extract useful information from the structural data and, therefore, an overfitting problem is encountered. The appli- cation of these techniques usually requires variable selection for building well-fitted models. ∗ Corresponding author at: Institute of Petroleum Engineering, Faculty of Engineering, University of Tehran, Tehran, Iran. E-mail address: riahisv@khayam.ut.ac.ir (S. Riahi). Variable selection methods range from simple methods, such as stepwise selection [4], to more elaborate methods, such as simulated annealing [5], evolutionary programming [6] and genetic algorithms (GA) [7]. GA is a stochastic method to solve optimization problems, defined by fitness criteria applying the evolution hypothesis of Darwin and different genetic functions, i.e., crossover and mutation [8]. Compared with the traditional search and the optimization procedures, such as calculus-based and enumerative strategies, GA is robust, global and generally more straightforward to apply to situations where there is little or no a priori knowledge about the process to be controlled. Since GA does not require derivative information or a formal initial estimate of the solution region and because of the stochastic nature of the search mechanism, it is capable of searching the entire solution space with a greater likelihood of finding the global optimum. For literature on GA, the reader can refer to Goldberg [9]. Ion-selective electrodes (ISEs) are electrochemical sensors that respond selectively to the activity of ionic species [10]. In 0925-4005/$ – see front matter © 2008 Elsevier B.V. All rights reserved. doi:10.1016/j.snb.2008.01.009