QSPR studies on soot-water partition coefficients of persistent organic pollutants by using artificial neural network

Two quantitative structure property relationship (QSPR) models for predicting soot-water partition coefficients (K(sc)) of 25 persistent organic pollutants (POPs) were developed. One model was established with linear artificial neural network (L-ANN), the other model was developed by using back propagation artificial neural network (BP-ANN). Leave one out cross validation was adopted to assess the predictive ability of the developed models. For the L-ANN model, the square of correlation coefficient (R(2)) between the predicted and experimental log K(SC) is 0.8358 and the RMS%RE is 6.32 for all the compounds. For the BP-ANN model, R(2) is 0.9628 and the RMS%RE is 4.12 for all the compounds. The result of leave one out cross validation demonstrates that both L-ANN and BP-ANN are practicable for developing the QSPR model for K(SC) of the investigated POPs. However, the model established with BP-ANN is better than the model established with L-ANN in prediction accuracy. It is shown that BP-ANN is a promising method for developing QSPR models for K(SC) of POPs.