Computer Analysis of Stability of Alkaline Metal Cation M[222]+ Cryptates in Different Solvents

Computer analysis of the thermodynamic constants of complexation of [2.2.2]-cryptand with alkali metal cations (M[222] + cryptates with M = Li, Na, K, Rb, and Cs) in water and organic solvents such as methanol, ethanol, 1-propanol, acetonitrile, benzonitrile, acetone, N , N -dimethylformamide, N -methylpyrrolidone, nitrobenzene, nitromethane, 1,2-dichloroethane, and propylene carbonate at 298.15 K has been performed. Exploratory (factorial, cluster, discriminant, canonical, decision tree), regression and neural network models of effects of the properties of solvents and cations on the cation cryptates stability have been built. The neural network approximator MLP 4-7-1 and the classifiers of the stability constants of cryptates – the multilayer perceptron MLP 4-7-4 and the self-organizing Kohonen map SOFM 8-4 – have been trained. Independent data on the stability constants of alkali metal cations cryptates demonstrate the predictive capabilities of the trained MLP 4-7-1 perceptron approximator.