MODELING THE KINETICS OF ISOBARIC-ISOTHERMAL INACTIVATION OF BACILLUS-SUBTILIS ALPHA-AMYLASE WITH ARTIFICIAL NEURAL NETWORKS

During the isobaric-isothermal inactivation of the enzyme a-amylase a simple first order inactivation kinetic is observed. However the tempe rature and pressure dependence of the inactivation rate constant k (mi n(-1)) is more complex. A non-synergetic (cumulative) model inspired b y the Arrhenius law is proposed as a non-linear description. Significa nt model deficiency is observed at non-intermediate values of pressure and temperature. Due to the lack of sufficient knowledge of the under lying biological and physical mechanisms, in this paper a black box mo deling approach is made using artificial neural networks. The resultin g artificial neural network structure is able to predict the combined effect of pressure and temperature on the inactivation rate constant k (min(-1)) of alpha-amylase without significant increase of the model complexity as compared to the Arrhenius type model. The accuracy of th e ANN model parameters is evaluated using the concept of joint confide nce regions. (C) 1998 Elsevier Science Limited. All rights reserved.