Hybrid metabolic flux analysis/artificial neural network modeling of bioprocesses

The main aim of this study is to develop a bioprocess dynamic optimisation method that integrates bioreactor transport phenomena, with metabolic flux analysis (MFA). The central metabolic pathways of many biological systems with industrial interest are currently known. Bioreactor dynamic optimisation schemes could profit from the incorporation of this knowledge. A hybrid modelling methodology is presented that integrates the aforementioned concepts. The technique was successfully validated with data of a recombinant Baby Hamster Kidney (BHK-21) culture. The method allowed to identify the time evolution of intracellular metabolic fluxes and to relate this knowledge with bioreactor decision variables.