Neural Network Inference of Molar Mass Distributions of Peptides during Tailor-Made Enzymatic Hydrolysis of Cheese Whey: Effects of pH and Temperature

The fine-tuning of the enzymatic hydrolysis of proteins may provide a pool of peptides with predefined molar mass distributions. However, the complex mixture of molecules (peptides and amino acids) that results after the proteolysis of cheese whey turns unfeasible the assessment of individual species. In this work, a hybrid kinetic model for the proteolysis of whey by alcalase, multipoint-immobilized on agarose, is presented, which takes into account the influence of pH (8.0-10.4) and temperature (40-55 degrees C) on the activity of the enzyme. Five ranges of peptides' molar mass have their reaction rates predicted by neural networks (NNs). The output of NNs trained for constant pH and temperatures was interpolated, instead of including these variables in the input vector of a larger NN. Thus, the model complexity was reduced. Coupled to differential mass balances, this hybrid model can be employed for the online inference of peptides' molar mass distributions. Experimental kinetic assays were carried out using a pH-stat, in a laboratory-scale (0.03 L) batch reactor. The neural-kinetic model was integrated to a supervisory system of a bench-scale continually stirred tank reactor (0.5 L), providing accurate predictions during validation tests.