Journal of Industrial Microbiology & Biotechnology

, Volume 36, Issue 9, pp 1139–1148 | Cite as

Modeling of polygalacturonase enzyme activity and biomass production by Aspergillus sojae ATCC 20235

  • Figen Tokatli
  • Canan Tari
  • S. Mehmet Unluturk
  • Nihan Gogus Baysal
Original Paper
First Online:
Received:
Accepted:

Abstract

Aspergillus sojae, which is used in the making of koji, a characteristic Japanese food, is a potential candidate for the production of polygalacturonase (PG) enzyme, which of a major industrial significance. In this study, fermentation data of an A. sojae system were modeled by multiple linear regression (MLR) and artificial neural network (ANN) approaches to estimate PG activity and biomass. Nutrient concentrations, agitation speed, inoculum ratio and final pH of the fermentation medium were used as the inputs of the system. In addition to nutrient conditions, the final pH of the fermentation medium was also shown to be an effective parameter in the estimation of biomass concentration. The ANN parameters, such as number of hidden neurons, epochs and learning rate, were determined using a statistical approach. In the determination of network architecture, a cross-validation technique was used to test the ANN models. Goodness-of-fit of the regression and ANN models was measured by the R 2 of cross-validated data and squared error of prediction. The PG activity and biomass were modeled with a 5-2-1 and 5-9-1 network topology, respectively. The models predicted enzyme activity with an R 2 of 0.84 and biomass with an R 2 value of 0.83, whereas the regression models predicted enzyme activity with an R 2 of 0.84 and biomass with an R 2 of 0.69.

Keywords

Artificial intelligence Cross-validation Filamentous fungi Polygalacturonase production Submerged culture 
This is a preview of subscription content, log in to check access.

References

  1. 1.
    Aguado D, Ferrer A, Seco A, Ferrer J (2006) Comparison of different predictive models for nutrient estimation in a sequencing batch reactor for wastewater treatment. Chemom Intell Lab Syst 84:75–81. doi: 10.1016/j.chemolab.2006.03.009 CrossRefGoogle Scholar
  2. 2.
    Barthus RC, Mazo LH, Poppi RJ (2005) Simultaneous determination of vitamins C, B6 and PP in pharmaceutics using differential pulse voltammetry with a glass carbon electrode and multivariate calibration tools. J Pharm Biomed Anal 38:94–99PubMedGoogle Scholar
  3. 3.
    Chen CR, Ramaswamy HS (2003) Analysis of critical control points in deviant thermal processes using artificial neural networks. J Food Eng 57:225–235. doi: 10.1016/S0260-8774(02)00301-1 CrossRefGoogle Scholar
  4. 4.
    Garcia-Gimeno RM, Hervas-Martinez C, Rodriguez-Perez R, Zurera-Cosano G (2005) Modeling the growth of Leuconostoc mesenteroides by artificial neural networks. Int J Food Microbiol 105:317–332. doi: 10.1016/j.ijfoodmicro.2005.04.013 PubMedCrossRefGoogle Scholar
  5. 5.
    Kiviharju K, Salonen K, Leisola M, Eerikäinen T (2006) Modeling and simulation of Streptomyces peucetius var. caesius N47 cultivation and ε-rhodomycinone production with kinetic equations and neural networks. J Biotechnol 126:365–373. doi: 10.1016/j.jbiotec.2006.04.034 PubMedCrossRefGoogle Scholar
  6. 6.
    Kenedy M, Krouse D (1999) Strategies for improving fermentation medium performance: a review. J Ind Microbiol Biotechnol 23:456–475. doi: 10.1038/sj.jim.2900755 CrossRefGoogle Scholar
  7. 7.
    Torrecilla JS, Aragon JM, Palancar MC (2005) Modeling the drying of a high-moisture solid with an artificial neural network. Ind Eng Chem Res 44:8057–8066. doi: 10.1021/ie0490435 CrossRefGoogle Scholar
  8. 8.
    Moreira G, Micheloud GA, Beccaria AJ, Goicoechea HC (2007) Optimization of the Bacillus thuringiensis var. kurstaki HD-1 δ-endotoxins production by using experimental mixture design and artificial neural networks. Biochem Eng J 35:48–55. doi: 10.1016/j.bej.2006.12.025 CrossRefGoogle Scholar
  9. 9.
    Razmi-Rad E, Ghanbarzadeh B, Mousavi SM, Emam-Djomeh Z, Khazaei J (2007) Prediction of rheological properties of Iranian bread dough from chemical composition of wheat flour by artificial neural networks. J Food Eng 81:728–734. doi: 10.1016/j.jfoodeng.2007.01.009 CrossRefGoogle Scholar
  10. 10.
    Bas D, Boyaci I (2007) Modeling and optimization II: comparison of estimation capabilities of response surface methodology with artificial neural networks in a biochemical reaction. J Food Eng 78:846–854. doi: 10.1016/j.jfoodeng.2005.11.025 CrossRefGoogle Scholar
  11. 11.
    Huang J, Mei L, Xia J (2006) Application of artificial neural network coupling particle swarm optimization algorithm to biocatalytic production of GABA. Biotechnol Bioeng 96:924–931. doi: 10.1002/bit.21162 CrossRefGoogle Scholar
  12. 12.
    Desai KM, Akolkar SK, Badhe YP, Tambe SS, Lele SS (2006) Optimization of fermentation media for exopolysaccharide production from Lactobacillus plantarum using artificial intelligence-based techniques. Process Biochem 41:1842–1848. doi: 10.1016/j.procbio.2006.03.037 CrossRefGoogle Scholar
  13. 13.
    Alonso-Salces R, Herrero C, Barranco A, Lopez-Marquez D, Berrueta L, Gallo B, Vicente F (2006) Polyphenolic compositions of basque natural ciders: chemometric study. Food Chem 97:438–446. doi: 10.1016/j.foodchem.2005.05.022 CrossRefGoogle Scholar
  14. 14.
    Hervas-Martinez C, Garcia-Gimeno R, Martinez-Estudillo A, Martinez-Estudillo F, Zurera-Cosano G (2006) Improving microbial growth prediction by product unit neural networks. J Food Sci 71:M31–M38. doi: 10.1111/j.1750-3841.2006.00029.x CrossRefGoogle Scholar
  15. 15.
    Yuste A, Dorado P (2006) A neural network approach to simulate biodiesel production from waste olive oil. Energy Fuels 20:399–402. doi: 10.1021/ef050226t CrossRefGoogle Scholar
  16. 16.
    Esnoz A, Periago PM, Conesa R, Palop A (2006) Application of artificial neural networks to describe the combined effect of pH and NaCl on the heat resistance of Bacillus stearothermophilus. Int J Food Microbiol 106:153–158. doi: 10.1016/j.ijfoodmicro.2005.06.016 PubMedCrossRefGoogle Scholar
  17. 17.
    Alonso-Salces RM, Herrero C, Barranco A, Berrueta LA, Gallo B, Vicente F (2005) Classification of apple fruits according to their maturity state by the pattern recognition analysis of their polyphenolic compositions. Food Chem 93:113–123. doi: 10.1016/j.foodchem.2004.10.013 CrossRefGoogle Scholar
  18. 18.
    Hongwen C, Baishan F, Zongding H (2005) Optimization of process parameters for key enzymes accumulation of 1, 3-propanediol production from Klebsiella pneumaniae. Biochem Eng J 25:47–53. doi: 10.1016/j.bej.2005.03.011 CrossRefGoogle Scholar
  19. 19.
    Spanila M, Pazourek J, Farkova M, Havel J (2005) Optimization of solid-phase extraction using artificial neural networks in combination with experimental design for determination of resveratrol by capillary zone electrophoresis in wines. J Chromatogr A 1084:180–185. doi: 10.1016/j.chroma.2004.10.007 PubMedCrossRefGoogle Scholar
  20. 20.
    Pazourek J, Gajdosova M, Spanila M, Farkova M, Novotna K, Havel J (2005) Analysis of polyphenols in wines: correlation between total phenolic content and antioxidant potential from photometric measurements: prediction of cultivars and vintage from capillary zone electrophoresis fingerprints using artificial neural network. J Chromatogr A 1081:48–54. doi: 10.1016/j.chroma.2005.02.056 PubMedCrossRefGoogle Scholar
  21. 21.
    Dutta J, Dutta P, Banerjee R (2004) Optimization of culture parameters for extracellular protease production from newly isolated Pseudomonas sp. using response surface and artificial neural network models. Process Biochem 39:2193–2198. doi: 10.1016/j.procbio.2003.11.009 CrossRefGoogle Scholar
  22. 22.
    Perez-Magarino S, Ortega-Heras M, Gonzalez-San Jose ML, Boger Z (2004) Comparative study of artificial neural network and multivariate methods to classify Spanish DO rose wines. Talanta 62:983–990. doi: 10.1016/j.talanta.2003.10.019 PubMedCrossRefGoogle Scholar
  23. 23.
    Irudayaraj J, Xu F, Tewari J (2003) Rapid determination of invert cane sugar adulteration in honey using FTIR spectroscopy and multivariate analysis. J Food Sci 68:2040–2045. doi: 10.1111/j.1365-2621.2003.tb07015.x CrossRefGoogle Scholar
  24. 24.
    Coleman MC, Buck KKS, Block DE (2003) An integrated approach to optimization of Escherichia coli Fermentations using historical data. Biotechnol Bioeng 84:274–285. doi: 10.1002/bit.10719 PubMedCrossRefGoogle Scholar
  25. 25.
    Castellanos JA, Palancar MC, Aragon JM (2002) Designing and optimizing a neural network for the modeling of a fluidized-bed drying process. Ind Eng Chem Res 41:2262–2269. doi: 10.1021/ie000950t CrossRefGoogle Scholar
  26. 26.
    Iizuka K, Aishima T (1997) Soy sauce classification by geographic region based on NIR spectra and chemometrics pattern recognition. J Food Sci 62:101–104. doi: 10.1111/j.1365-2621.1997.tb04377.x CrossRefGoogle Scholar
  27. 27.
    Sun L, Danzer K, Thiel G (1997) Classification of wine samples by means of artificial neural networks and discrimination analytical methods. Fresenius J Anal Chem 359:143–149. doi: 10.1007/s002160050551 CrossRefGoogle Scholar
  28. 28.
    Alkorta I, Garbisu C, Llama MJ, Serra JL (1998) Industrial application of pectic enzymes: a review. Process Biochem 33:21–28. doi: 10.1016/S0032-9592(97)00046-0 CrossRefGoogle Scholar
  29. 29.
    Nighojkar S, Phanse Y, Sinha D, Nighojkar A, Kumar A (2006) Production of polygalacturonase by immobilized cells of Aspergillus niger using orange peel as inducer. Process Biochem 41:1136–1140. doi: 10.1016/j.procbio.2005.12.009 CrossRefGoogle Scholar
  30. 30.
    Tari C, Gogus N, Tokatli F (2007) Optimization of biomass, pellet size and polygalacturonase production by Aspergillus sojae ATCC 20235 using response surface methodology. Enzyme Microb Technol 40:1108–1116. doi: 10.1016/j.enzmictec.2006.08.016 CrossRefGoogle Scholar
  31. 31.
    Panda T, Naidu GSN, Sinha J (1999) Multiresponse analysis of microbiological parameters affecting the production of pectolytic enzymes by Aspergillus niger: a statistical approach. Process Biochem 35:187–195. doi: 10.1016/S0032-9592(99)00050-3 CrossRefGoogle Scholar
  32. 32.
    Nguyen D, Widrow B (1990) Improving the learning speed of 2-layer neural networks by choosing initial values of the adaptive weights. Proc IJCNN 3:21–26. doi: 10.1109/IJCNN.1990.137819 Google Scholar
  33. 33.
    Masters T (1993) Practical neural network recipies in C++. Academic Press, San FranciscoGoogle Scholar
  34. 34.
    Gevrey M, Dimopoulos I, Lek S (2006) Two-way interaction of input variables in the sensitivity analysis of neural network models. Ecol Modell 195:43–50. doi: 10.1016/j.ecolmodel.2005.11.008 CrossRefGoogle Scholar
  35. 35.
    Molga EJ (2003) Neural network approach to support modeling of chemical reactors: problems, resolutions, criteria of application. Chem Eng Process 42:675–695. doi: 10.1016/S0255-2701(02)00205-2 CrossRefGoogle Scholar
  36. 36.
    Mevik B, Cederkvist HR (2004) Mean squared error of prediction (MSEP) estimates for principal component regression (PCR) and partial least squares regression (PLSR). J Chemometr 8:422–429. doi: 10.1002/cem.887 CrossRefGoogle Scholar

Copyright information

© Society for Industrial Microbiology 2009

Authors and Affiliations

  • Figen Tokatli
    • 1
  • Canan Tari
    • 1
  • S. Mehmet Unluturk
    • 2
  • Nihan Gogus Baysal
    • 1
  1. 1.Department of Food EngineeringIzmir Institute of TechnologyUrla-IzmirTurkey
  2. 2.Department of Software EngineeringIzmir University of EconomicsBalçova-IzmirTurkey

Personalised recommendations