Analysis of enzymatic hydrolysis of lactose in solutions and whey by artifitial intelligence methods

CUELLAS, ANAHÍ; ODDONE, SEBASTIÁN; SEGURA, JUAN; MAMMARELLA, ENRIQUE; RUBIOLO, AMELIA

COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE

Elsevier Sciencie B.V.

Lugar: BL Delft, The Netherlands; Año: 2006

0169-2607

The analysis of any kinetic process involves the development of a mathematical model with predictive purposes. Generally, those models have characteristic parameters that should be estimated experimentally. A typical example is Michaelis-Menten model for enzymatic hydrolysis. Even though conventional kinetic models are very useful, they are only valid under certain experimental conditions (those under which parameters were calculated). Besides, frequently large standard errors of estimated parameters are found due to the error of experimental determinations and/or insufficient number of assays. The present work explores the possibility of estimating or predicting by artificial intelligence methods. Specifically, a neural network was developed, which was trained with experimental data obtained under different hydrolysis conditions of lactose solutions or whey, and different initial concentrations of enzymes or substrates. In all cases commercial b-Galactosidase either free or immobilized in a chitosan support was used. Predicted values of lactose conversion have been validated experimentally with errors less than 5%. Even using few experimental data (120 samples) to train neural network, predictive models with acceptable performance (errors less than 10%) were obtained.