Application of artificial neural network and fuzzy control for fed-batch cultivation of recombinant Saccharomyces cerevisiae

Abstract A recombinant Saccharomyces cerevisiae expressing β-galactosidase under the control of the GAL10 promoter was constructed. The strain was used as a model to study fuzzy control with neural network, which served as state estimators for fed-batch cultivation of recombinant cells. To optimize the expression of β-galactosidase the effects of medium enrichment and induction on cell growth and expression were investigated. The activity of β-galactosidase was 2-fold higher in the presence compared with in the absence of yeast extract in the basal medium. Furthermore, the specific activity of β-galactosidase increased with increasing galactose concentration up to 30 g/ l . Two artificial neural networks (ANNs) were developed to estimate glucose and galactose concentrations using on-line measurements of ethanol and biomass concentrations, culture volume and the amount of carbon source fed to the fermentor. To improve productivity and product yield of β-galactosidase two multi-variable fuzzy controllers were used to control the glucose and galactose feed rates during the cell growth and production phases, respectively. Experimental data show that under fuzzy control with neural network estimators, the productivity was 2.7-fold higher than that in the case of exponential feeding, and 1.7-fold higher than that in the case of exponential feeding with feedback compensation using ethanol concentration.

[1]  S Shioya,et al.  Optimal production of glutathione by controlling the specific growth rate of yeast in fed‐batch culture , 1991, Biotechnology and bioengineering.

[2]  Y H Zhu,et al.  Neural network programming in bioprocess variable estimation and state prediction. , 1991, Journal of biotechnology.

[3]  A. Kingsman,et al.  Efficient synthesis of enzymatically active calf chymosin in Saccharomyces cerevisiae. , 1983, Gene.

[4]  Suteaki Shioya,et al.  Optimal Production of Glutathione by Controlling the Specific Growth Rate of Yeast in Fed-Batch Culture , 1991 .

[5]  N. Harada,et al.  Expression of synthetic human-lysozyme gene in Saccharomyces cerevisiae: use of a synthetic chicken-lysozyme signal sequence for secretion and processing. , 1986, Gene.

[6]  R. Koski,et al.  Controlled expression and purification of human immune interferon from high‐cell‐density fermentations of Saccharomyces cerevisiae , 1987, Biotechnology and bioengineering.

[7]  M. Ptashne,et al.  Use of lacZ fusions to delimit regulatory elements of the inducible divergent GAL1-GAL10 promoter in Saccharomyces cerevisiae , 1984, Molecular and cellular biology.

[8]  Yoshio Nishida,et al.  Improvement of cloned α‐amylase gene expression in fed‐batch culture of recombinant Saccharomyces cerevisiae by regulating both glucose and ethanol concentrations using a fuzzy controller , 1994 .

[9]  N. D. Da Silva,et al.  Improved protein synthesis and secretion through medium enrichment in a stable recombinant yeast strain , 1993, Biotechnology and bioengineering.

[10]  L. T. Fan,et al.  Modular Neural Networks for Identification of Starches in Manufacturing Food Products , 1993 .

[11]  M N Karim,et al.  Artificial neural networks in bioprocess state estimation. , 1992, Advances in biochemical engineering/biotechnology.

[12]  J. Nikawa,et al.  A dominant mutation that alters the regulation of INO1 expression in Saccharomyces cerevisiae. , 1992, Journal of biochemistry.

[13]  K Shimizu,et al.  Efficient fuzzy control strategies for the application of pH-stat to fed-batch cultivation of genetically engineered Escherichia coli. , 1994, Journal of chemical technology and biotechnology.

[14]  K C Chen,et al.  On‐line optimal control for fed‐batch culture of baker's yeast production , 1985, Biotechnology and bioengineering.

[15]  C. Scorer,et al.  Foreign gene expression in yeast: a review , 1992, Yeast.

[16]  J. Nikawa,et al.  Differential regulation of two myo‐inositol transporter genes of Saccharomyces cerevisiae , 1993, Molecular microbiology.

[17]  I. Sadowski,et al.  GAL4 is regulated by a glucose‐responsive functional domain. , 1993, The EMBO journal.

[18]  C L Cooney,et al.  Design and evalution of control strategies for high cell density fermentations , 1992, Biotechnology and bioengineering.

[19]  Kazuyuki Shimizu,et al.  Fuzzy neural network for the control of high cell density cultivation of recombinant Escherichia coli , 1994 .

[20]  Takeshi Kobayashi,et al.  Optimization of the expression of a foreign gene from galactose-inducible promoter in a recombinant yeast , 1991 .

[21]  K. Shimizu,et al.  Metabolic pathway analysis of recombinant Saccharomyces cerevisiae with a galactose-inducible promoter based on a signal flow modeling approach , 1995 .

[22]  H C Lim,et al.  Modeling and optimization of cloned invertase expression in Saccharomyces cerevisiae , 1993, Biotechnology and bioengineering.

[23]  Fred Winston,et al.  Methods in Yeast Genetics: A Laboratory Course Manual , 1990 .

[24]  M. Mizumoto.  Realization of PID controls by fuzzy control methods , 1995 .

[25]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1989, Math. Control. Signals Syst..

[26]  P. Greenfield,et al.  A Model for β‐Galactosidase Production with a Recombinant Yeast Saccharomyces cerevisiae in Fed‐Batch Culture , 1992, Biotechnology progress.

[27]  P. Dhurjati,et al.  A mathematical description of recombinant yeast , 1990, Biotechnology and bioengineering.

[28]  Kazuyuki Shimizu,et al.  An overview on the control system design of bioreactors , 1993 .