Folia Microbiologica

, Volume 58, Issue 5, pp 393–401 | Cite as

Real encoded genetic algorithm and response surface methodology to optimize production of an indolizidine alkaloid, swainsonine, from Metarhizium anisopliae

  • Digar Singh
  • Gurvinder KaurEmail author


Response surface methodology (RSM) and artificial neural network-real encoded genetic algorithm (ANN-REGA) were employed to develop a process for fermentative swainsonine production from Metarhizium anisopliae (ARSEF 1724). The effect of finally screened process variables viz. inoculum size, oatmeal extract, glucose, and CaCl2 were investigated through central composite design and were further utilized for training sets in ANN with training and test R values of 0.99 and 0.94, respectively. ANN-REGA was finally employed to simulate the predictive swainsonine production with best evolved media composition. ANN-REGA predicted a more precise fermentation model with 103 % (shake flask) increase in alkaloid production compared to 75.62 % (shake flask) obtained with RSM model upon validation.


Response Surface Methodology Shake Flask Inoculum Size Alkaloid Production Metarhizium Anisopliae 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.



Cell dry weight


Response surface methodology


Central composite design




One factor at a time


Genetic algorithm


Artificial neural network


Artificial neural network-real encoded genetic algorithm



We thank Indian Institute of Technology Guwahati, for providing the experimental facilities, and the Council of Scientific and Industrial research, PUSA, New Delhi, Government of India, for providing the research fellowship.

Conflict of interest



  1. Bhatti MS, Kapoor D, Kalia RK, Reddy AS, Thukral AK (2011) RSM and ANN modelling for electro-coagulation of copper from simulated wastewater: multi objective optimization using genetic algorithm approach. Desalination 274:74–80CrossRefGoogle Scholar
  2. Braun K, Romero J, Liddell C, Creamer R (2003) Production of swainsonine by fungal endophytes of locoweed. Mycol Res 107:980–988CrossRefPubMedGoogle Scholar
  3. Caldeira AT, Arteiro JM, Roseiro JC, Neves J, Vicente H (2011) An artificial intelligence approach to Bacillus amyloliquefaciens CCMI 1051 cultures: application to the production of anti-fungal compounds. Bioresour Technol 102:1496–1502CrossRefPubMedGoogle Scholar
  4. Colegate SM, Huxtable CR, Dorling PR (1979) Spectroscopic investigation of swainsonine and α-mannosidase inhibitor isolated from Swainsona canescens. Aust J Chem 32:2257–2264CrossRefGoogle Scholar
  5. Desai KM, Survase SA, Saudagar PS, Lele SS, Singhal RS (2008) Comparison of artificial neural network (ANN) and response surface methodology (RSM) in fermentation media optimization: case study of fermentative production of scleroglucan. Biochem Eng J 41:266–273CrossRefGoogle Scholar
  6. Elbein AD, Szumilo T, Sanford BA, Sharpless KB, Adams C (1987) Effect of isomers of swainsonine on glycosidase. Biochemistry 26:2502–2510CrossRefPubMedGoogle Scholar
  7. Fellows LE, Fleet GWJ (1989) In: Wagman GH, Cooper R (eds) Natural products isolation, separation methods for antimicrobials, antivirals and enzyme inhibitors. Elsevier, Amsterdam, p 539CrossRefGoogle Scholar
  8. Fox JD, Robyt JF (1991) Miniaturization of three carbohydrate analyses using micro sample plate reader. Anal Biochem 19:593–596Google Scholar
  9. Gen M, Cheng R (2000) Genetic algorithms and engineering optimization. Wiley, New YorkGoogle Scholar
  10. Goh ATC (1995) Back-propagation neural networks for modelling complex systems. Artif Intell Eng 9:143–151CrossRefGoogle Scholar
  11. Goldberg DE (1991) Real-coded genetic algorithms, virtual alphabets and blocking. Complex Syst 5:139–167Google Scholar
  12. Haider MA, Pakshirajan K, Singh A, Chaudhry S (2008) Artificial neural network-genetic algorithm approach to optimize media constituents for enhancing lipase production by a soil microorganism. Appl Biochem Biotechnol 144:225–235CrossRefPubMedGoogle Scholar
  13. Hao DC, Zhu PH, Yang SL, Yang L (2006) Optimization of recombinant cytochrome P450 2C9 protein production in Escherichia coli DH5a by statistically-based experimental design. World J Microbiol Biotechnol 22:1169–1176CrossRefGoogle Scholar
  14. Haykin S (2008) Neural networks and learning machines, 3rd edn. Prentice-Hall, New JerseyGoogle Scholar
  15. Herrera F, Lozano M, Verdegay JL (1998) Tackling real coded genetic algorithms: operators and tools for behavioural analysis. Artif Intell Rev 12:265–319CrossRefGoogle Scholar
  16. Imandi SB, Karanam SK, Garapati HR (2008) Optimization of fermentation medium for the production of lipopeptide using artificial neural network and genetic algorithms. Int J Nat Eng Sci 2:105–109Google Scholar
  17. Jackson SL, Heath IB (1993) Roles of calcium ions in hyphal tip growth. Microbiol Rev 57:367–382PubMedGoogle Scholar
  18. Leardi R (2009) Experimental design in chemistry: a tutorial. Anal Chim Acta 652:161–172CrossRefPubMedGoogle Scholar
  19. Mundra P, Desai K, Lele SS (2007) Application of response surface methodology to cell immobilization for the production of palatinose. Bioresour Technol 98:2892–2896CrossRefPubMedGoogle Scholar
  20. Nemr AE (2000) Synthetic methods for the streoisomers of swainsonine and its analogues. Tetrahedron 56:8579–8629CrossRefGoogle Scholar
  21. Patrick MS, Maxwell W, Adlar MW, Keshavarz T (1995) Swainsonine production in fed-batch fermentations of Metarhizium anisopliae in stirred-tank reactors. Biotechnol Lett 17:433–438CrossRefGoogle Scholar
  22. Plackett RL, Burman JP (1946) The design of optimum multi factorial experiments. Biometrika 33:305–325CrossRefGoogle Scholar
  23. Schneider MJ, Ungernach FS, Broquist HP, Harris TM (1983) (1S,2R,8R,8 a R )-1, 2, 8-Trihydroxyoctahydroindolizine (swainsonine), an α-mannosidase inhibitor from Rhizoctonia legumicola. Tetrahedron 39:29–32CrossRefGoogle Scholar
  24. Sim KL, Perry D (1995) Swainsonine production by Metarhizium anisopliae determined by means of an enzymatic assay. Mycol Res 99:1078–1082CrossRefGoogle Scholar
  25. Singh D, Kaur G (2012) Optimization of different process variables for the production an indolizidine alkaloid, swainsonine from Metarhizium anisopliae. J Basic Microbiol 52:590–597CrossRefPubMedGoogle Scholar
  26. Tabandeh F, Khodabandeh M, Yakhchali B (2008) Response surface methodology for optimizing the induction conditions of recombinant interferon beta during high cell density culture. Chem Eng Sci 63:2477–2483CrossRefGoogle Scholar
  27. Tamerler C, Keshavarz T (1999) Optimization of agitation for production of swainsonine from Metarhizium anisopliae in stirred tank and airlift reactors. Biotechnol Lett 21:501–504CrossRefGoogle Scholar
  28. Yoon Y, Kim YH (2012) The roles of crossover and mutation in real encoded genetic algorithms. In: Shangce Gao (ed) Bioinspired computational algorithms and their applications, InTech, doi:  10.5772/2358
  29. Zhang Y, Xu, Yuan Z, Xu H, Yu Q (2010) Artificial neural network-genetic algorithm based optimization for the immobilization of cellulose on the smart polymer Eudragit L-100. Bioresour Technol 101:3153–3158CrossRefPubMedGoogle Scholar

Copyright information

© Institute of Microbiology, Academy of Sciences of the Czech Republic, v.v.i. 2013

Authors and Affiliations

  1. 1.Department of BiotechnologyIndian Institute of Technology GuwahatiGuwahatiIndia

Personalised recommendations