An Advanced Approach Based on Artificial Neural Networks to Identify Environmental Bacteria

Environmental micro-organisms include a large number of taxa and some species that are generally considered nonpathogenic, but can represent a risk in certain conditions, especially for elderly people and immunocompromised individuals. Chemotaxonomic identification techniques are powerful tools for environmental micro-organisms, and cellular fatty acid methyl esters (FAME) content is a powerful fingerprinting identification technique. A system based on an unsupervised artificial neural network (ANN) was set up using the fatty acid profiles of standard bacterial strains, obtained by gas-chromatography, used as learning data. We analysed 45 certified strains belonging to Acinetobacter, Aeromonas, Alcaligenes, Aquaspirillum, Arthrobacter, Bacillus, Brevundimonas, Enterobacter, Flavobacterium, Micrococcus, Pseudomonas, Serratia, Shewanella and Vibrio genera. A set of 79 bacteria isolated from a drinking water line (AMGA, the major water supply system in Genoa) were used as an example for identification compared to standard MIDI method. The resulting ANN output map was found to be a very powerful tool to identify these fresh isolates. Keywords— cellular fatty acid methyl esters, environmental bacteria, gas-chromatography, unsupervised ANN.

[1]  Duc Truong Pham,et al.  Neural Networks for Identification, Prediction and Control , 1995 .

[2]  L. Miller.  Single derivatization method for routine analysis of bacterial whole-cell fatty acid methyl esters, including hydroxy acids , 1982, Journal of clinical microbiology.

[3]  Donna L. Hudson,et al.  Neural networks and artificial intelligence for biomedical engineering , 1999 .

[4]  M Giacomini,et al.  Objective evaluation of two markers of HIV-1 infection (p24 antigen concentration and CD4+ cell counts) by a self organizing neural network. , 1996, Medical informatics = Medecine et informatique.

[5]  P. de Vos,et al.  Polyphasic Taxonomy , a Consensus Approach to Bacterial Systematics , 1996 .

[6]  M. Handfield,et al.  Aeromonas hydrophila isolated from food and drinking water: hemagglutination, hemolysis, and cytotoxicity for a human intestinal cell line (HT-29) , 1996, Applied and environmental microbiology.

[7]  P. Payment,et al.  Blood agar to detect virulence factors in tap water heterotrophic bacteria , 1994, Applied and environmental microbiology.

[8]  M. Lechevallier,et al.  A Pilot Study of Bacteriological Population Changes through Potable Water Treatment and Distribution , 2000, Applied and Environmental Microbiology.

[9]  C. Ruggiero,et al.  Automated systems for identification of heterotrophic marine bacteria on the basis of their Fatty Acid composition , 1996, Applied and environmental microbiology.

[10]  Teuvo Kohonen,et al.  The self-organizing map , 1990 .

[11]  C. Ruggiero,et al.  Artificial neural network identification of heterotrophic marine bacteria based on their fatty-acid composition , 1997, IEEE Transactions on Biomedical Engineering.

[12]  M Giacomini,et al.  Artificial neural network based identification of environmental bacteria by gas-chromatographic and electrophoretic data. , 2000, Journal of microbiological methods.

[13]  Lechevalier Mp.  Lipids in Bacterial Taxonomy - A Taxonomist's View , 1977 .