New paper on bacterial identifcation with ANNs published

[Roy Goodacre]

Accessible via http://gepasi.dbs.aber.ac.uk/roy/chemom.htm:

Identification of oral abscess bacteria from hospital patients - Goodacre, R., 
Hiom, S.J., Cheeseman, S.L. Murdoch, D., Weightman, A.J. & Wade, W.G. (1996) 
Identification and discrimination of oral asaccharolytic Eubacterium spp. by  
pyrolysis mass spectrometry and artificial neural networks.  Current 
Microbiology 32, 77-84.

ABSTRACT:
Curie-point pyrolysis mass spectra were obtained from 29 oral asaccharolytic 
Eubacterium strains, and 6 abscess isolates previously identified as 
Peptostreptococcus heliotrinreducens. Pyrolysis mass spectrometry (PyMS) with 
cluster analysis was able to clarify the taxonomic position of this group of 
organisms. Artificial neural networks (ANNs) were then trained by supervised 
learning (with the back-propagation algorithm) to recognise the strains from 
their pyrolysis mass spectra; all Eubacterium strains were correctly identifi
ed and the abscess isolates were identified as un-named Eubacterium taxon C2 
and were distinct from the type strain of P. heliotrinreducens. These results 
demonstrate that the combination of PyMS and ANNs provides a rapid and 
accurate identification technique.


Roy


Dr Roy Goodacre
E-mail: rrg at aber.ac.uk      http://gepasi.dbs.aber.ac.uk/roy/rgcv.htm		
Voice : +44 (0)1970 621947                    Fax: +44 (0)1970 622354			
Snail : Inst Biol Sci, Univ Wales, Aberystwyth, Dyfed SY23 3DA, WALES