SUBSPECIES DISCRIMINATION, USING PYROLYSIS MASS-SPECTROMETRY AND SELF-ORGANIZING NEURAL NETWORKS, OF PROPIONIBACTERIUM-ACNES ISOLATED FROM NORMAL HUMAN SKIN
R. Goodacre et al., SUBSPECIES DISCRIMINATION, USING PYROLYSIS MASS-SPECTROMETRY AND SELF-ORGANIZING NEURAL NETWORKS, OF PROPIONIBACTERIUM-ACNES ISOLATED FROM NORMAL HUMAN SKIN, Zentralblatt fur Bakteriologie, 284(4), 1996, pp. 501-515
Curie-point pyrolysis mass spectra were obtained from 30 Propionibacte
rium acnes strains isolated from the foreheads of six healthy humans.
Multivariate analyses and Kohonen artificial neural networks (KANNs),
employing unsupervised learning, were used successfully to discriminat
e between the P. acnes isolates from different individual hosts. The c
lassification of the isolates by KANNs was compared with the more clas
sical multivariate techniques of canonical variates analysis and hiera
rchical cluster analysis and found to give similar groupings. The comb
ination of pyrolysis mass spectrometry with these numerical methods al
so showed that more than one strain of P. acnes had been isolated from
three of the human hoses.