A computational model for enhancing recombinant Penicillin G Acylase production from Escherichia coli DH5α

An attempt was made to develop a computational model based on artificial neural network and ant colony optimization to estimate the composition of medium components for maximizing the productivity of Penicillin G Acylase (PGA) enzyme from Escherichia coli DH5α strain harboring the plasmid pPROPAC. As a first step, an artificial neural network (ANN) model was developed to predict the PGA activity by considering the concentrations of seven important components of the medium. Design of experiments employing central composite design technique was used to obtain the training samples. In the second step, ant colony optimization technique for continuous domain was employed to maximize the PGA activity by finding the optimal inputs for the developed ANN model. Further, the effect of a combination of ant colony optimization for continuous domain with a preferential local search strategy was studied to analyze the performance. For a comparative study, the training samples were fed into the response surface methodology optimization software to maximize the PGA production. The obtained PGA activity (56.94 U/mL) by the proposed approach was found to be higher than that of the obtained value (45.60 U/mL) with the response surface methodology. The optimum solution obtained computationally was experimentally verified. The observed PGA activity (55.60 U/mL) exhibited a close agreement with the model predictions.