Abstract
The aim of the present work was to develop a model that supplies accurate predictions of the yields of delta-endotoxins and proteases produced by B. thuringiensis var. kurstaki HD-1. Using available medium ingredients as variables, a mathematical method, based on Plackett–Burman design (PB), was employed to analyze and compare data generated by the Bootstrap method and processed by multiple linear regressions (MLR) and artificial neural networks (ANN) including multilayer perceptron (MLP) and radial basis function (RBF) models. The predictive ability of these models was evaluated by comparison of output data through the determination of coefficient (R 2) and mean square error (MSE) values. The results demonstrate that the prediction of the yields of delta-endotoxin and protease was more accurate by ANN technique (87 and 89% for delta-endotoxin and protease determination coefficients, respectively) when compared with MLR method (73.1 and 77.2% for delta-endotoxin and protease determination coefficients, respectively), suggesting that the proposed ANNs, especially MLP, is a suitable new approach for determining yields of bacterial products that allow us to make more appropriate predictions in a shorter time and with less engineering effort.
Similar content being viewed by others
References
Adinarayana K, Ellaiah P, Prasad DS (2003) Purification and partial characterization of thermostable serine alkaline protease from a new isolated Bacillus subtilis PE-11. AAPS PharmSciTech 4:440–448. doi:10.1208/pt040456
Avignone Rossa CA, Yantorno OM, Arcas JA, Ertola RJ (1990) Organic and inorganic nitrogen source ratio effects on Bacillus thuringiensis var. israelensis delta-endotoxin production. World J Microbiol Biotechnol 6:27–31. doi:10.1007/BF01225351
Baffi G, Martin EB, Morris AJ (1999) Non-linear projection to latent structures revisited (the neural network PLS algorithm). Comp Chem Eng 23:1293–1307. doi:10.1016/S0098-1354(99)00291-4
Beale R, Jackson T (1990) Neural computing—an introduction. CRC Press, New York
Bradford M (1976) A rapid and sensitive method for the quantitation of microgram quantities of protein utilizing the principle of protein-dye binding. Anal Biochem 72:248–254. doi:10.1016/0003-2697(76)90527-3
Chao YY, Hong CY, Kao CH (2010) The decline in ascorbic acid content is associated with cadmium toxicity of rice seedlings. Plant Physiol Biochem 48:374–381. doi:10.1016/j.plaphy.2010.01.009
Charles JF, Silva-Filha MH, Nielsen-LeRoux C, Humphreys M, Berry C (1997) Binding of the 51- and 42-kDa individual components from the Bacillus sphaericus crystal toxin on mosquito larval midgut membranes from Culex and Anopheles sp. (Diptera: Culicidae). FEMS Microbiol Lett 156:153–159. doi:10.1111/j.1574-6968.1997.tb12721.x
Chen FC, Shen IF, Chak KE (2004) A facile analytical method for the identification of protease gene profiles in Bacillus thuringiensis strains. J Microbiol Methods 56:125–131
Chen Y, Huang Y, Lin R, Shang N (2010) A continuous-flow biodiesel production process using a rotating packed bed. Bioresour Technol 101:668–673. doi:10.1016/j.biortech.2009.08.081
Chu WH (2007) Optimization of extracellular alkaline protease production from species of Bacillus. J Ind Microbiol Biotechnol 34:241–245. doi:10.1007/s10295-006-0192-2
El-Bendary MA (1999) Growth physiology and production of mosquitocidal toxins from Bacillus sphaericus. Dissertation, Ain-Shams University
El-Bendary MA (2006) Bacillus thuringiensis and Bacillus sphaericus biopesticides production. J Basic Microbiol 46:158–170. doi:10.1002/jobm.200510585
Ellaiah P, Srinivasulu B, Adinarayana K (2002) A review on microbial alkaline proteases. J Sci Ind Res 61:690–704
Ennouri K, Ben Hassen H, Ben Khedher S, Zouari N (2013a) Concomitant production of proteases and delta-endotoxins of Bacillus thuringiensis subsp. kurstaki in a low-cost medium: effect of medium components. Acta Biol Szeged 57:13–19
Ennouri K, Ben Hassen H, Zouari N (2013b) Optimization of bioinsecticides overproduction by Bacillus thuringiensis subsp. kurstaki using linear regression. Pol J Microbiol 62:287–293
Ennouri K, Ben Khedher S, Jaoua S, Zouari N (2013c) Correlation between delta-endotoxin and proteolytic activities produced by Bacillus thuringiensis subsp. kurstaki growing in an economic production medium. Biocontrol Sci Technol 23(7):756–767
Frankena J, Van Verseveld HW, Stouthamer AH (1985) A continuous culture study of the bioenergetic aspects of growth and production of exocellular protease in Bacillus licheniformis. Appl Microbiol Biotechnol 22:169–176. doi:10.1007/BF00253604
Ghribi D, Zouari N, Jaoua S (2004) Improvement of bioinsecticide production through mutagenesis of Bacillus thuringiensis by U.V. and nitrous acid affecting metabolic pathways and/or delta-endotoxin synthesis. J Appl Microbiol 97:338–346. doi:10.1111/j.1365-2672.2004.02323.x
Ghribi D, Zouari N, Trigui W, Jaoua S (2007) Use of sea water as salts source in starch- and soya bean-based media, for the production of Bacillus thuringiensis bioinsecticides. Process Biochem 42:374–378. doi:10.1016/j.procbio.2006.09.006
Haq IU, Mukhtar H, Umber H (2006) Production of protease by Penicillium chrysogenum through optimization of environmental conditions. J Agric Soc Sci 2:23–25
Hartley BS (1960) Proteolytic enzymes. Annu Rev Biochem 29:45–72
Hotha S, Banik RM (1997) Production of alkaline protease by Bacillus thuringiensis H14 in aqueous two-phase systems. J Chem Tech Biotechnol 69:5–10. doi:10.1002/(SICI)1097-4660(199705)69:1<5:AID-JCTB661>3.0.CO;2-I
Johnveshy B, Naik G (2001) Production of bleach-stable and halo-tolerant alkaline protease by an alkalophilic Bacillus pumilus JB-05 isolated from cement industry effluents. J Microbiol Biotechnol 11:558–563
Joo HS, Kumar CG, Park GC, Kim KT, Paik SR, Chang CS (2002) Optimization of the production of an extracellular alkaline protease from Bacillus horikoshii. Process Biochem 38:155–159. doi:10.1016/S0032-9592(02)00061-4
Khaouane L, Benkortbi O, Hanini S, Si-Moussa C (2013) Modeling of an industrial process of pleuromutilin fermentation using feed-forward neural networks. Braz J Chem Eng 30:105–116. doi:10.1590/S0104-66322013000100012
Krishnan S, Prapulla SG, Rajalakshmi D, Misra MC, Karanth NG (1998) Screening and selection of media components for lactic-acid production using Plackett–Burman design. Bioprocess Eng 19:61–65. doi:10.1007/PL00009003
Lachhab K (2001) Production of Bacillus thuringiensis biopesticides using wastewater sludge as a raw material: effect of inoculum and sludge solids. Process Biochem 37:197–208. doi:10.1016/S0032-9592(01)00198-4
Lee DS, Park JM (1999) Neural network modeling for on-line estimation of nutrient dynamics in a sequentially-operated batch reactor. J Biotechnol 75:229–239. doi:10.1016/S0168-1656(99)00171-6
Malinova T, Guo ZX (2004) Artificial neural network modelling of hydrogen storage properties of Mg-based alloys. Mater Sci Eng A 365:219–227. doi:10.1016/j.msea.2003.09.031
McKellar RC, Cholette H (1984) Synthesis of extracellular proteinase by Pseudomonas fluorescens under conditions of limiting carbon, nitrogen, and phosphate. Appl Environ Microbiol 47:1224–1227
Miller JN, Miller JC (2000) Statistics and chemometrics for analytical chemistry. Prentice Hall, London
Montgomery DC (1997) Design and analysis of experiments, 4th edn. Wiley, New York
Moon SH, Parulekar SJ (1991) A parametric study of protease production in batch and fed-batch cultures of Bacillus firmus. Biotechnol Bioeng 37:467–483
Nabney IT (2002) Netlab: algorithms for pattern recognition. Springer, Great Britain
Navon A (2000) Bacillus thuringiensis application in agriculture. In: Charles JF, Delécluse A, Nielsen-Le Roux C (eds) Entomopathogenic bacteria: from laboratory to field application. Kluwer Academic Publishers, Dordrecht, pp 355–369
Olori VE, Brotherstone S, Hill WG, McGuirk BJ (1999) Fit of standard models of the lactation curve to weekly records of milk production of cows in a single herd. Livest Prod Sci 58:55–63. doi:10.1016/S0301-6226(98)00194-8
Ozkan M, Dilek FB, Yetis U, Ozcengiz G (2003) Nutritional and cultural parameters influencing antidipteran delta-endotoxin production. Res Microbiol 154:49–53. doi:10.1016/S0923-2508(02)00006-2
Pachepsky YA, Timlin D, Varallyay G (1996) Artificial neural networks to estimate soil water retention from easily measurable data. Soil Sci Soc Am J 60:727–733. doi:10.2136/sssaj1996.03615995006000030007x
Pujari V, Chandra TS (2000) Statistical optimization of medium components for improved synthesis of riboflavin by Eremothecium ashbyii. Bioprocess Biosyst Eng 23:303–307. doi:10.1007/PL00009127
Shafizadeh-Moghadem H, Hagenauer J, Farajzadeh M, Helbich M (2015) Performance analysis of radial basis function networks and multi-layer perceptron networks in modeling urban change: a case study. Int J Geogr Inf Sci 29:606–623. doi:10.1080/13658816.2014.993989
Singh J, Vohra RM, Sahoo DK (2004) Enhanced production of alkaline proteases by Bacillus sphaericus using fed-batch culture. Process Biochem 39:1093–1101
Song RG, Zhang QZ, Tseng MK, Zhang BJ (1995) The application of artificial neural networks to the investigation of aging dynamics in 7175 aluminium alloys. Mater Sci Eng C 3:39–41. doi:10.1016/0928-4931(95)00068-2
Stanbury PF, Whitakar A, Hall SJ (1997) Principles of fermentation technology. Aditya Books, New Delhi
Strauch MA, Hoch JA (1993) Transition-state regulators: Sentinels of Bacillus subtilis post-exponential phase gene expression. Mol Microbiol 7:337–342. doi:10.1111/j.1365-2958.1993.tb01125.x
Tadeusiewicz R (1993) Neural networks. AOW, Warsaw
Tyagi RD, Sikati Foko V, Barnabe S, Vidyarthi A, Valero JR, Surampalli RY (2002) Simultaneous production of biopesticide and alkaline protease by Bacillus thuringiensis using waste water as a raw material. Water Sci Technol 46:247–254
Van Frankenhuyzen K (2013) Cross-order and cross-phylum activity of Bacillus thuringiensis pesticidal proteins. J Invertebr Pathol 114:76–85. doi:10.1016/j.jip.2013.05.010
Van Liew MW, Arnold JG, Garbrecht JD (2003) Hydrologic simulation on agricultural watersheds: choosing between two models. Trans ASAE 46:1539–1551. doi:10.13031/2013.15643
Zare M, Pourghasemi HR, Vafakhah M, Pradhan B (2013) Landslide susceptibility mapping at Vaz Watershed (Iran) using an artificial neural network model: a comparison between multilayer perceptron (MLP) and radial basic function (RBF) algorithms. Arab JGeosci 6:2873–2888. doi:10.1007/s12517-012-0610-x
Zouari N, Jaoua S (1999) Production and characterization of metalloproteases synthesized concomitantly with δ-endotoxin by Bacillus thuringiensis subsp. kurstaki strain grown on gruel-based media. Enzyme Microb Technol 25(3):364–371
Zouari N, Dhouib A, Ellouz R, Jaoua S (1998) Nutritional requirements of strain of Bacillus thuringiensis subsp. kurstaki and use of gruel hydrolysate, for the formulation of a new medium for delta-endotoxin production. Appl Biochem Biotechnol 69:41–52
Acknowledgements
This work was supported by grants from the ‘‘Ministère de l’Enseignement Supérieur et de la Recherche Scientifique” of Tunisia. The authors are grateful to Kamel MAALOUL, translator and English professor, for having proofread the manuscript.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors did not declare any conflict of interest.
Rights and permissions
About this article
Cite this article
Ennouri, K., Ben Ayed, R., Triki, M.A. et al. Multiple linear regression and artificial neural networks for delta-endotoxin and protease yields modelling of Bacillus thuringiensis . 3 Biotech 7, 187 (2017). https://doi.org/10.1007/s13205-017-0799-1
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s13205-017-0799-1