An artificial intelligence approach to Bacillus amyloliquefaciens CCMI 1051 cultures: application to the production of anti-fungal compounds.

The combined effect of incubation time (IT) and aspartic acid concentration (AA) on the predicted biomass concentration (BC), Bacillus sporulation (BS) and anti-fungal activity of compounds (AFA) produced by Bacillus amyloliquefaciens CCMI 1051, was studied using Artificial Neural Networks (ANNs). The values predicted by ANN were in good agreement with experimental results, and were better than those obtained when using Response Surface Methodology. The database used to train and validate ANNs contains experimental data of B. amyloliquefaciens cultures (AFA, BS and BC) with different incubation times (1-9 days) using aspartic acid (3-42 mM) as nitrogen source. After the training and validation stages, the 2-7-6-3 neural network results showed that maximum AFA can be achieved with 19.5 mM AA on day 9; however, maximum AFA can also be obtained with an incubation time as short as 6 days with 36.6 mM AA. Furthermore, the model results showed two distinct behaviors for AFA, depending on IT.

[1]  R. Losick,et al.  Bacillus Subtilis and Other Gram-Positive Bacteria: Biochemistry, Physiology, and Molecular Genetics , 1993 .

[2]  David H. Doehlert,et al.  Uniform Shell Designs , 1970 .

[3]  Ian H. Witten,et al.  The WEKA data mining software: an update , 2009, SKDD.

[4]  G. Hartman,et al.  Production of iturin A by Bacillus amyloliquefaciens suppressing Rhizoctonia solani , 2002 .

[5]  Youn-Tae Chi,et al.  Purification and characterization of a lipopeptide produced by Bacillus thuringiensis CMB26 , 2004, Journal of applied microbiology.

[6]  F. Peypoux,et al.  Iturins, a special class of pore-forming lipopeptides: biological and physicochemical properties. , 1994, Toxicology.

[7]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[8]  F. Besson,et al.  Effect of various growth conditions on spore formation and bacillomycin L production in Bacillus subtilis. , 1986, Canadian journal of microbiology.

[9]  R. Dieckmann,et al.  Synthesis of (di)adenosine polyphosphates by non-ribosomal peptide synthetases (NRPS). , 2001, Biochimica et biophysica acta.

[10]  H. Goicoechea,et al.  Optimization of the Bacillus thuringiensis var. kurstaki HD-1 δ-endotoxins production by using experimental mixture design and artificial neural networks , 2007 .

[11]  J. Lancelin,et al.  NMR structure of antibiotics plipastatins A and B from Bacillus subtilis inhibitors of phospholipase A2 , 2000, FEBS letters.

[12]  T. Stein.  Bacillus subtilis antibiotics: structures, syntheses and specific functions , 2005, Molecular microbiology.

[13]  Alexander I. Galushkin,et al.  Neural Networks Theory , 2007 .

[14]  H. Engelberg-Kulka,et al.  Cannibals Defy Starvation and Avoid Sporulation , 2003, Science.

[15]  Peter Setlow,et al.  Spore germination. , 2003, Current opinion in microbiology.

[16]  H. Paulus.  Biosynthesis of the Aspartate Family of Amino Acids , 1993 .

[17]  James L. McClelland,et al.  James L. McClelland, David Rumelhart and the PDP Research Group, Parallel distributed processing: explorations in the microstructure of cognition . Vol. 1. Foundations . Vol. 2. Psychological and biological models . Cambridge MA: M.I.T. Press, 1987. , 1989, Journal of Child Language.

[18]  Avishek Majumder,et al.  Artificial intelligence based optimization of exocellular glucansucrase production from Leuconostoc dextranicum NRRL B-1146. , 2008, Bioresource technology.

[19]  J. Varley,et al.  The production of Surfactin in batch culture by Bacillus subtilis ATCC 21332 is strongly influenced by the conditions of nitrogen metabolism , 1999 .

[20]  E. Bottone,et al.  Production by Bacillus pumilus (MSH) of an antifungal compound that is active against Mucoraceae and Aspergillus species: preliminary report. , 2003, Journal of medical microbiology.

[21]  W. Vishniac,et al.  THE THIOBACILLI, , 1957, Bacteriological reviews.

[22]  J. Roseiro,et al.  Antifungal activity of Bacillus subtilis 355 against wood-surface contaminant fungi , 2004, Journal of Industrial Microbiology and Biotechnology.

[23]  A. Illanes,et al.  Isolation and partial purification of a metabolite from a mutant strain of Bacillus sp. with antibiotic activity against plant pathogenic agents , 2002 .

[24]  J. Roseiro,et al.  Antimicrobial activity of steady-state cultures of Bacillus sp. CCMI 1051 against wood contaminant fungi , 2006 .

[25]  R. Losick,et al.  Molecular genetics of sporulation in Bacillus subtilis. , 1996, Annual review of genetics.

[26]  J. Roseiro,et al.  Environmental dynamics of Bacillus amyloliquefaciens CCMI 1051 antifungal activity under different nitrogen patterns , 2008, Journal of applied microbiology.

[27]  J. Roseiro,et al.  Bacillus amyloliquefaciens CCMI 1051in vitro activity against wood contaminant fungi , 2007, Annals of Microbiology.

[28]  L. Torgo,et al.  Inductive learning of tree-based regression models , 1999 .

[29]  B. Neilan,et al.  The expansion of mechanistic and organismic diversity associated with non-ribosomal peptides. , 2000, FEMS microbiology letters.

[30]  Simon Haykin,et al.  Neural Networks and Learning Machines , 2010 .

[31]  T. Cleveland,et al.  Bacillomycin D: an iturin with antifungal activity against Aspergillus flavus , 2001, Journal of applied microbiology.

[32]  C. Varela,et al.  Engineering bacterial strains through the chromosomal insertion of the chlorocatechol catabolism tfdI CDEF gene cluster, to improve degradation of typical bleached Kraft pulp mill effluent pollutants , 2002 .

[33]  F. Besson,et al.  Influence of the culture medium on the production of iturin A by Bacillus subtilis. , 1987, Journal of general microbiology.

[34]  Soo-Jin Cho,et al.  Detection and characterization of the Gloeosporium gloeosporioides growth inhibitory compound iturin A from Bacillus subtilis strain KS03. , 2003, FEMS microbiology letters.

[35]  R. Losick,et al.  Cannibalism by Sporulating Bacteria , 2003, Science.

[36]  C. Hervás-Martínez,et al.  Modelling the growth of Leuconostoc mesenteroides by Artificial Neural Networks. , 2005, International journal of food microbiology.

[37]  M. Santer,et al.  THE THIOBACILLI, 12 , 1957 .

[38]  M. Nakano,et al.  Regulation of peptide antibiotic production in Bacillus , 1993, Molecular microbiology.