Optimization of Fed-Batch Recombinant Yeast Fermentation for Ethanol Production Using a Reduced Dynamic Flux Balance Model Based on Artificial Neural Networks

Abstract

In this work, a reduced form of dynamic flux balance model based on artificial neural networks for batch and fed-batch fermentation of xylose-utilizing engineered Saccharomyces cerevisiae RWB 218 is developed. The intracellular description of carbon metabolism in the model is simulated by a multilayer-perceptron (MLP) network. First, this hybrid model is compared to the full mechanistic dynamic flux balance analysis (DFBA) in terms of accuracy and computational time regarding available experimental data on anaerobic batch cultivation. Afterwards, it is used in a model-based sequential dynamic optimization procedure in order to maximize ethanol productivity. The initial liquid volume charged in the bioreactor, the feed flow rates in aerobic and anaerobic conditions, the final batch time, and the switching time from aerobic to anaerobic conditions are considered as decision variables. Differential evolution (DE), as a robust and efficient optimization method, is employed to solve the problem for several glucose mass fractions in the feed stream. The results show that in similar conditions a small deviation in each operating parameter from its optimal value may lead to considerable decrease in ethanol productivity.

In silico analysis of bioethanol production from glucose/xylose mixtures during fed-batch fermentation of co-culture and mono-culture systems

“…1A shows the comparison of dFBA model predictions for recombinant S. cerevisiae strain RWB218 against experimental data [33] for 1:1 glucose/xylose mixture. The kinetic parameters are taken from Eslamloueyan and Setoodeh [34]. It may be noted that the model predictions represent experimental data very Table 3.…”

Applicability of Neural Networks for the Fermentation of Propionic Acid by Propionibacterium acidipropionici

“…Over recent years, ANNs have been successfully applied to the modelling and control of various biological processes [12][13][14][15][16]. ANNs are now the most popular artificial learning tools in biotechnology, with applications ranging from pattern recognition in chromatographic spectra and expression profiles to functional analyses of genomic and proteomic sequences [17][18][19].…”

Comparative study of μ‐stat methanol feeding control in fed‐batch fermentation of Pichia pastoris producing HBsAg: an open‐loop control versus recurrent artificial neural network‐based feedback control

“…Regarding soft sensors, implementing solely mechanistic modeling for optimization and control of fed‐batch processes is often challenging and sometimes impossible. This is mainly because, in addition to the general complexity of metabolic mechanisms of microorganisms, the fed‐batch fermentation process, owing to high variation with respect to time, is a highly dynamic and nonlinear process, which makes the mathematical description very complicated . Under these conditions, artificial neural network (ANN) can be a useful soft sensor tool for predicting and controlling critical but hardly accessible parameters by finding their nonlinear relationship with accessible key parameters …”

“…This is mainly because, in addition to the general complexity of metabolic mechanisms of microorganisms, the fed-batch fermentation process, owing to high variation with respect to time, is a highly dynamic and nonlinear process, which makes the mathematical description very complicated. 46,47 Under these conditions, artificial neural network (ANN) can be a useful soft sensor tool for predicting and controlling critical but hardly accessible parameters by finding their nonlinear relationship with accessible key parameters. 37,48 In a previous study, we created a best-fit recurrent neural network (RNN) for accurate prediction of the biomass of Mut + recombinant P. pastoris producing intracellular HBsAg.…”