TY - JOUR
T1 - Comparison of the estimation capabilities of response surface methodology and artificial neural network for the optimization of recombinant lipase production by E. coli BL21
AU - Rubina, Nelofer
AU - Ramakrishnan, Nagasundara Ramanan
AU - Abd Rahman, Raja Noor Zaliha
AU - Basri, Mahiran
AU - Ariff, Arbakariya B
PY - 2012
Y1 - 2012
N2 - 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 (R-2) and adjusted R-2 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 R-2, adjusted R 2, 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 degrees C and 2.12 h, and those by ANN are 25 g/L, 3 g/L, 30 degrees 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.
AB - 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 (R-2) and adjusted R-2 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 R-2, adjusted R 2, 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 degrees C and 2.12 h, and those by ANN are 25 g/L, 3 g/L, 30 degrees 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.
UR - http://link.springer.com/article/10.1007%2Fs10295-011-1019-3
U2 - 10.1007/s10295-011-1019-3
DO - 10.1007/s10295-011-1019-3
M3 - Article
SN - 1367-5435
VL - 39
SP - 243
EP - 254
JO - Journal of Industrial Microbiology and Biotechnology
JF - Journal of Industrial Microbiology and Biotechnology
IS - 2
ER -