Artificial neural network based identification of environmental bacteria by gas-chromatographic and electrophoretic data

Chemotaxonomic identification techniques are powerful tools for environmental micro-organisms, for which poor diagnostic schemes are available. Whole cellular fatty acid methyl esters (FAME) content is a stable bacterial profile, the analysis method is rapid, cheap, simple to perform and highly automated. Whole-cell protein is an even more powerful tool because it yields information at or below the species level. The description of new species and genera and subsequent continuous rearrangement provide large amounts of data, resulting in large databases. In order to set up suitable software tools to work on such large databases artificial neural network (ANN) based programs have been used to classify and identify marine bacteria at genus and species levels, starting from the fatty acid profiles and protein profiles respectively.We analysed 50 certified strains belonging to Halomonas, Marinomonas, Marinospirillum, Oceanospirillum and Pseudoalteromonas genera. Both supervised and unsupervised ANNs provide a correct classification of the marine strains analyzed. Moreover, a set of 73 marine fresh isolates were used as an example of identification using ANNs. We propose supervised and unsupervised ANNs as a reliable tool for classification of bacteria by means of their FAME and of whole-protein analyse and as a sound basis for a comprehensive artificial intelligence based system for polyphasic taxonomy