Article

Prediction of bioactive compound activity against wood contaminant fungi using artificial neural networks

Henrique Vicente,^a José C. Roseiro,^b José M. Arteiro,^a José Neves,^c A. Teresa Caldeira^a

^aDepartamento de Química e Centro de Química de Évora, Escola de Ciências e Tecnologia, Universidade de Évora, Rua Romão Ramalho, 59, 7000-671 Évora, Portugal.

^bUnidade de Bioenergia, Laboratório Nacional de Energia e Geologia, Estrada do Paço do Lumiar, 22, 1649-038 Lisboa, Portugal.

^cDepartamento de Informática, Escola de Engenharia, Universidade do Minho, Campus de Gualtar, 4710-057 Braga, Portugal.

Corresponding author: A. Teresa Caldeira (e-mail: atc@uevora.pt).

Published on the web 13 August 2013.

Received April 12, 2013. Accepted August 7, 2013.

Canadian Journal of Forest Research, 2013, 43(11): 985-992, https://doi.org/10.1139/cjfr-2013-0142

Abstract

Biopesticides based on natural endophytic bacteria to control plant diseases are an ecological alternative to chemical treatments. Bacillus species produce a wide variety of metabolites with biological activity like iturinic lipopeptides. This work addresses the production of biopesticides based on natural endophytic bacteria isolated from Quercus suber L. Artificial neural networks were used to maximize the percentage of inhibition triggered by the antifungal activity of bioactive compounds produced by Bacillus amyloliquefaciens. The active compounds, produced in liquid cultures, inhibited the growth of 15 fungi and exhibited a broader spectrum of antifungal activity against surface contaminant fungi, blue stain fungi, and phytopathogenic fungi. A 19-7-6-1 neural network was selected to predict the percentage of inhibition produced by antifungal bioactive compounds. A good match among the observed and predicted values was obtained with the R² values varying between 0.9965–0.9971 and 0.9974–0.9989 for training and test sets. The 19-7-6-1 neural network was used to establish the dilution rates that maximize the production of antifungal bioactive compounds, namely, 0.25 h⁻¹ for surface contaminant fungi, 0.45 h⁻¹ for blue stain fungi, and between 0.30 and 0.40 h⁻¹ for phytopathogenic fungi. Artificial neural networks show great potential in the modelling and optimization of these bioprocesses.

References

Aminov RI. 2009. The role of antibiotics and antibiotic resistance in nature. Environ. Microbiol. 11: 2970-2988 Crossref, Medline, Google Scholar.
Beer Z, Wingfieldb B, Wingfield M. 2003. The occurrence of Ophiostoma piliferum-like fungi on pulpwood chips and other wood sources in South Africa. S. Afr. J. Sci. 99: 34-36 Google Scholar.
Boone, R., and Castenholz, W. 2001. Bergey’s manual of systematic bacteriology. 2nd ed. Springer Verlag, New York. Google Scholar
Bruce, A. 1998. Biological control of wood decay. In Forest products biotechnology. Edited by A. Bruce and J.W. Palfreyman. Taylor & Francis, London. pp. 251–266. Google Scholar
Caldeira AT, Savluchinske-Feio S, Arteiro JM, Roseiro JC. 2006. Antimicrobial activity of steady state cultures of Bacillus sp. CCMI 1051 against wood contaminant fungi. Biochem. Eng. J. 30: 231-236 Crossref, Google Scholar.
Caldeira AT, Savluchinske-Feio S, Roseiro JC, Arteiro JM. 2007. Bacillus amyloliquefaciens CCMI 1051 in vitro activity against wood contaminant fungi. Ann. Microbiol. 57: 29-34 Crossref, Google Scholar.
Caldeira AT, Savluchinske-Feio S, Arteiro JM, Coelho A, Roseiro JC. 2008. Environmental dynamics of Bacillus amyloliquefaciens CCMI 1051 antifungal activity under different nitrogen patterns. J. Appl. Microbiol. 104: 808-816 Crossref, Medline, Google Scholar.
Caldeira AT, Arteiro JM, Coelho AV, Roseiro JC. 2011a. Combined use of LC–ESI-MS and antifungal tests for rapid identification of bioactive lipopeptides produced by Bacillus amyloliquefaciens CCMI 1051. Process Biochem. 46: 1738-1746 Crossref, Google Scholar.
Caldeira AT, Arteiro JM, Roseiro JC, Neves J, Vicente H. 2011b. An artificial intelligence approach to Bacillus amyloliquefaciens CCMI 1051 cultures: application to the production of anti-fungal compounds. Bioresour. Technol. 102: 1496-1502 Crossref, Medline, Google Scholar.
Cortez P, Rocha M, Neves J. 2004. Evolving time series forecasting ARMA models. J. Heuristics 10: 415-429 Crossref, Google Scholar.
El-Kassas H. 2008. Decolorization and detoxification of Direct Fast Red 8B by a marine Fungus Aspergillus japonicus HK. World Appl. Sci. J. 5: 460-468 Google Scholar.
El-Kassas H, Khairy H. 2009. A trial for biological control of a pathogenic fungus (Fusarium solani) by some marine microorganisms. Am.-Eurasian J. Agric. Environ. Sci. 5: 434-440 Crossref, Google Scholar.
Emmert EAB, Handelsman J. 1999. Biocontrol of plant disease: a (gram-) positive perspective. FEMS Microbiol. Lett. 171: 1-9 Crossref, Medline, ISI, Google Scholar.
Feio S, Barbosa A, Cabrita M, Nunes L, Esteves A, Roseiro JC, Curto MM. 2004. Antifungal activity of Bacillus subtilis 355 against wood-surface contaminant fungi. J. Ind. Microbiol. Biotechnol. 31: 199-203 Crossref, Medline, Google Scholar.
Fiddaman PJ, Rossal S. 1994. Effect of substrate on the production of antifungal volatiles from Bacillus subtilis. J. Appl. Bacteriol. 76: 395-405 Crossref, Medline, Google Scholar.
Galushkin, A.I. 2007. Neural networks theory. Springer, New York. Google Scholar
Greaves H. 1970. The effects of selected bacteria and Actnomycetes on the decay capacity of some wood-rotting fungi. Mater. Organismen 5: 265-279 Google Scholar.
Hall M, Frank E, Holmes G, Pfahringer B, Reutemann P, Witten IH. 2009. The WEKA data mining software: an update. SIGKDD Explor. 11: 10-18 Crossref, Google Scholar.
Han, J., and Kamber, M. 2006. Data mining: concepts and techniques. 2nd ed. Morgan Kauffmann Publishers, San Francisco, Calif. Google Scholar
Haykin, S. 2008. Neural networks and learning machines. 3rd ed. Prentice Hall, New York. Google Scholar
Kewley R, Embrechts M, Breneman C. 2000. Data strip mining for the virtual design of pharmaceuticals with neural networks. IEEE Trans. Neural Netw. 11: 668-679 Crossref, Medline, Google Scholar.
Koumoutsi A, Chen X-H, Henne A, Liesegang H, Hitzeroth G, Franke P, Vater J, Borriss R. 2004. Structural and functional characterization of gene clusters directing nonribosomal synthesis of bioactive cyclic lipopeptides in Bacillus amyloliquefaciens strain FZB42. J. Bacteriol. 186: 1084-1096 Crossref, Medline, ISI, Google Scholar.
Kowall M, Vater J, Kluge B, Stein T, Franke P, Ziessow D. 1998. Separation and characterization of surfactin isoforms produced by Bacillus subtilis OKB 105. J. Colloid Interface Sci. 204: 1-8 Crossref, Medline, Google Scholar.
Leifert C, Li H, Chidburee S, Hampson S, Workman S, Sigee D, Epton H, Harbour A. 1995. Antibiotic production and biocontrol activity by Bacillus subtilis CL27 and Bacillus pumilus CL45. J. Appl. Bacteriol. 78: 97-108 Crossref, Medline, Google Scholar.
McBride, G.B. 2005. Using statistical methods for water quality management issues, problems and solutions. John Wiley & Sons, Hoboken, N.J. Google Scholar
Moyne AL, Shelby R, Cleveland TE, Tuzun S. 2001. Bacillomycin D: an iturin with antifungal activity against Aspergillus flavus. J. Appl. Microbiol. 90: 622-629 Crossref, Medline, ISI, Google Scholar.
Nobre A, Duarte LC, Roseiro JC, Gírio FM. 2009. A physiological and enzimatic study of Debaryomyces hansenii growth on xylose and oxygen-limited chemostats. Appl. Microbiol. Biotechnol. 59: 509-516 Crossref, Medline, Google Scholar.
Ongena M, Jourdan E, Adam A, Paquot M, Brans A, Joris B, Arpigny JL, Thonart P. 2008. Surfactin and fengycin lipopeptides of Bacillus subtilis as elicitors of induced systemic resistance in plants. Environ. Microbiol. 10: 1823-1830 Crossref, Medline, Google Scholar.
Pabel CT, Vater J, Wilde C, Franke P, Hofemeister J, Adler B, Bringmann G, Hacker J, Hentschel U. 2003. Antimicrobial activities and matrix-assisted laser desorption/ionization mass spectrometry of Bacillus isolates from the marine sponge Aplysina aerophoba. Mar. Biotechnol. 5: 424-434 Crossref, Medline, Google Scholar.
Rumelhart, D., Hinton, G., and Williams, R. 1986. Learning internal representation by error propagation. In Parallel distributed processing. Edited by David E. Rumelhart and James L. McCleland. MIT Press, Cambridge, Massachusetts. pp. 318–362. Google Scholar
Sathish T, Prakasham RS. 2010. Enrichment of glutaminase production by Bacillus subtilis RSP-GLU in submerged cultivation based on neural network – genetic algorithm approach. J. Chem. Technol. Biotechnol. 85: 50-58 Crossref, Google Scholar.
Schubert M, Fink S, Schwarze F. 2008. Evaluation of Trichoderma spp. as a biocontrol agent against wood decay fungi in urban trees. Biol. Control 45: 111-123 Crossref, Google Scholar.
Silva RG, Pinotti LM, Cruz AJG, Giordano RLC, Giordano RC. 2008. Artificial neural networks to infer biomass and product concentration during the production of penicillin G acylase from Bacillus megaterium. J. Chem. Technol. Biotechnol. 83: 739-749 Crossref, Google Scholar.
Souza, J., Matwin, S., and Japkowicz, N. 2002. Evaluating data mining models: a pattern language. In Proceedings of the 9th Conference on Pattern Language of Programs, Urbana, Illinois, 8–12 September 2002. pp. 1–23. Google Scholar
Soytong K, Srinon W, Ratanacherdchai K, Kanokmedhakul S, Kanokmedhakul K. 2005. Application of antagonistic fungi to control anthracnose disease of grape. Agric. Technol. 1: 33-42 Google Scholar.
Tsuge K, Ano T, Shoda M. 1996. Isolation of a gene essential for biosynthesis of the lipopeptide antibiotics plipastatin B1 and surfactin in Bacillus subtilis YB8. Arch. Microbiol. 165: 243-251 Crossref, Medline, Google Scholar.
Vishniac W, Santer M. 1957. The Thiobacilli. Bacteriol. Rev. 21: 195-213 Medline, Google Scholar.
Weindling R. 1932. Trichoderma lignorum as a parasite of other soil fungi. Phytopathology 22: 837-845 Google Scholar.
Zafar M, Kumar S, Dhiman AK. 2012. Artificial intelligence based modeling and optimization of poly(3-hydroxybutyrate-co-3-hydroxyvalerate) production process by using Azohydromonas lata MTCC 2311 from cane molasses supplemented with volatile fatty acids: a genetic algorithm paradigm. Bioresour. Technol. 104: 631-641 Crossref, Medline, Google Scholar.