Comparison of the estimation capabilities of response surface methodology and artificial neural network for the optimization of recombinant lipase production by E. coli BL21 |
| |
Authors: | Rubina Nelofer Ramakrishnan Nagasundara Ramanan Raja Noor Zaliha Raja Abd Rahman Mahiran Basri Arbakariya B Ariff |
| |
Institution: | (1) Department of Bioprocess Technology, Faculty of Biotechnology and Biomolecular Sciences, University Putra Malaysia, 43400 Serdang, Selangor, Malaysia;(2) Chemical and Sustainable Process Engineering Research Group, School of Engineering, Monash University, 46150 Bandar Sunway, Selangor, Malaysia;(3) Department of Microbiology, Faculty of Biotechnology and Biomolecular Sciences, University Putra Malaysia, 43400 Serdang, Selangor, Malaysia;(4) Department of Chemistry, Faculty of Science, University Putra Malaysia, 43400 Serdang, Selangor, Malaysia; |
| |
Abstract: | 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°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. |
| |
Keywords: | |
本文献已被 PubMed SpringerLink 等数据库收录! |
|