QSPR study on normal boiling point of acyclic oxygen containing organic compounds by radial basis function artificial neural network

• A RBF-ANN model is proposed for normal boiling points prediction.
• Significant molecular descriptors are selected by multi-stepwise regression method.
• Key parameters of RBF-ANN are determined by biharmonic response surface analysis.
• The obtained RBF-ANN model shows better performance than the best MLR model.

Radial basis function artificial neural network (RBF-ANN) model was developed to predict the normal boiling point (NBP) of 240 acyclic oxygen containing organic compounds, including alcohols, ethers, aldehydes, ketones, carboxylic acids and esters. The total database was randomly divided into a training set (192), a validation set (24) and a test set (24). 8 significant molecular descriptors, which were used to build the RBF-ANN model, were selected from a pool of descriptors by multi-stepwise regression method. The RBF-ANN model was trained by the Orthogonal Least Squares (OLS) learning algorithm. The biharmonic response surface analysis was used for the optimization of two main tuning parameters in the neural network. The final optimum RBF-ANN model represented by [8-22(32)-1] was tested and evaluated by graphic and statistical methods. Y-randomization test and a random split cross validation confirmed the robustness of the RBF-ANN model. The comparison results with the best multiple linear regression function and literature QSPR models showed the superiority of the RBF-ANN model.