Prediction of a model enzymatic acidolysis system using neural networks

A model for the acidolysis of triolein and palmitic acid under the catalysis of immobizied sn-1,3 specific lipase was presented in this study. A neural networks (NN) based model was developed for the prediction of the concentrations of the major reaction products of this reaction (1-palmitoyl-2,3-oleoyl-glycerol (POO), 1,3-dipalmitoyl-2-oleoyl-glycerol (POP) and triolein (000)). Substrate ratio (SR), reaction temperature (T) and reaction time (t) were used as input parameters. The optimal architecture of the proposed NN model, which consists of one input layer with three inputs, one hidden layer with seven neurons and one output layer with three outputs, was able to predict the reaction products concentration with a mean square error (MSE) of less than 1.5 and R-2 of 0.999. An explicit formulation of the proposed NN model is presented. Considerable good performance is achieved in modelling the acidolysis reaction using neural networks.