Response surface methodology (RSM) and artificial neural network (ANN) were used to optimize the effect of four independent variables, viz. glucose, sodium chloride (NaCl), temperature and induction time, on lipase production by a recombinant Escherichia coli BL21. The optimization and prediction capabilities of RSM and ANN were then compared. RSM predicted the dependent variable with a good coefficient of correlation determination (R² and adjusted R² values for the model. Although the R (2) value showed a good fit, absolute average deviation (AAD) and root mean square error (RMSE) values did not support the accuracy of the model and this was due to the inferiority in predicting the values towards the edges of the design points. On the other hand, ANN-predicted values were closer to the observed values with better R², adjusted R², AAD and RMSE values and this was due to the capability of predicting the values throughout the selected range of the design points. Similar to RSM, ANN could also be used to rank the effect of variables. However, ANN could not predict the interactive effect between the variables as performed by RSM. The optimum levels for glucose, NaCl, temperature and induction time predicted by RSM are 32 g/L, 5 g/L, 32°C and 2.12 h, and those by ANN are 25 g/L, 3 g/L, 30°C and 2 h, respectively. The ANN-predicted optimal levels gave higher lipase activity (55.8 IU/mL) as compared to RSM-predicted levels (50.2 IU/mL) and the predicted lipase activity was also closer to the observed data at these levels, suggesting that ANN is a better optimization method than RSM for lipase production by the recombinant strain.
This study was carried out to express human epidermal growth factor (hEGF) in Pichia pastoris GS115. For this aim, the hEGF gene was cloned into the pPIC9K expression vector, and then integrated into P. pastoris by electroporation. ELISA-based assay showed that the amount of hEGF secreted into the medium can be affected by the fermentation conditions especially by culture medium, pH and temperature. The best medium for the optimal hEGF production was BMMY buffered at a pH range of 6.0 and 7.0. The highest amount of hEGF with an average yield of 2.27μg/mL was obtained through an induction of the culture with 0.5% (v/v) methanol for 60h. The artificial neural network (ANN) analysis revealed that changes in both pH and temperature significantly affected the hEGF production with the pH change had slightly higher impact on hEGF production than variations in the temperature.