Maximizing the recombinant protein yield necessitates optimizing the production medium. This can be done using a variety of methods, including the conventional “one-factor-at-a-time” approach and more recent statistical and mathematical methods like the artificial neural network ANN (artificial neural network), GA (genetic algorithm), etc. Every approach has advantages and disadvantages of its own, yet even when a technique has flaws, it is nevertheless used to get the best results. Here, one categorical variable and four numerical parameters including post-induction time, inducer concentration, post-induction temperature, and cell density of induction time were optimized using the 232 experimental assays of the CCD (central composite design). The direct and indirect effects of factors on the yield of anti-EpEx (anti-EpCAM extracellular domain) fragment antibody were examined using statistical methods. Induction at the cell density of 0.7 and an IPTG (Isopropyl β-D-1-thiogalactopyranoside) concentration of 0.6 mM for 32 hours at 30 °C in BW25113 was the ideal culture condition leading to the protein yield of 259.51 mg/L. Under the optimum condition, the output values predicted by the ANN model (259.83 mg/L) was more in line with the experimental data (259.51 mg/L) than the RSM (response surface methodology) (276.13 mg/L) expected value. This outcome demonstrated that the ANN model outperforms the RSM in terms of prediction accuracy.

Increasing demand for recombinant therapeutic proteins highlights the necessity of their yield improvement. Culture medium formulation is a popular approach for bioprocess optimization to improve therapeutic protein production. Constraint-based modeling can empower high-precision optimization through information on how media compounds affect metabolism and cell growth. In the current study, a genome-scale metabolic model (GEMM) of Escherichia coli cells was employed to design strategies of minimal medium supplementation for higher antiEpEX-scFv production. Dynamic flux balance analysis of the recombinant E. coli cell model predicted that ammonium was depleted during the process. Based on the simulations, three amino acids (Asn, Gln and Arg) were chosen to be added to the medium to compensate for ammonium depletion. Experimental validation suggested that the addition of these amino acids (one-by-one, or in combinations) can indeed improve cell growth and recombinant protein production. Then, design of experiment was used to optimize the concentrations of amino acids in the growth medium. About two-fold increase in the growth rate and total scFv expression level was observed using this strategy. We conclude that the GEMM-based approach can provide insights into an effective feeding strategy to improve the production of recombinant protein in E. coli.