Quantitative structure–electrochemistry relationship for variously-substituted 9, 10-anthraquinones using both an heuristic method and a radial basis function neural network

Abstract Quantitative structure–property relationship models correlating the half-wave potentials ( E 1/2 ) of the dye intermediate 9, 10-anthraquinone and its derivatives were developed using both linear and non-linear modelling approaches. Descriptors calculated from molecular structures alone were used to represent the E 1/2 of the 9, 10-anthraquinones. An heuristic method was used to select the most appropriate molecular descriptors whilst a linear, quantitative structure–property relationship model was developed; using the selected descriptors, a radial basis function neural network was employed for the non-linear model development. The statistical parameters provided by the heuristic model were R 2  = 0.945; F  = 98.04; RMS = 0.0360 for the training set and R 2  = 0.863; F  = 18.903; RMS = 0.0600 for the test set. The radial basis function neural network model gave better results with R 2  = 0.960; F  = 610.336; RMS = 0.0299 for the training set and R 2  = 0.863; F  = 18.946; RMS = 0.0476 for the test set.