A genetic algorithm-Bayesian network approach for the analysis of metabolomics and spectroscopic data: application to the rapid identification of Bacillus spores and classification of Bacillus species

Table 4 Species: classification results for sporulated bacilli only.

Confusion Matrices Species - sporulated bacilli only
		predicted class
		all 150 m / z intensities							39 GA selected m / z intensities
		sph	sub	lic	lat	cer	amy	meg	sph	sub	lic	lat	cer	amy	meg
actual class	sph sub lic lat cer amy meg	14 0 0 0 1 0 0	0 21 0 0 0 1 0	0 0 14 0 0 0 0	0 0 0 11 0 0 1	1 0 0 1 14 0 0	0 0 1 0 0 14 0	0 0 0 0 0 0 14	15 0 0 1 0 0 0	0 21 0 0 0 0 0	0 0 14 0 0 0 0	0 0 0 11 0 0 0	0 0 0 0 15 0 0	0 0 1 0 0 15 0	0 0 0 0 0 0 15
	Statistics
	class	TP	FP	precision	sensitivity				TP	FP	precision	sensitivity
		all 150 m/z intensities							39 GA selected m/z intensities
	sph	0.933	0.011	0.933	0.933				1	0.011	0.938	1
	sub	1	0.011	0.955	1				1	0	1	1
	lic	0.933	0	1	0.933				0.933	0	1	0.933
	lat	0.917	0.01	0.917	0.917				0.917	0	1	0.917
	cer	0.933	0.022	0.875	0.933				1	0	1	1
	amy	0.933	0.011	0.933	0.933				1	0.011	0.938	1
	meg	0.933	0	1	0.933				1	0	1	1
	w. avg.	0.944	0.009	0.946	0.944				0.981	0.003	0.983	0.981

ISSN: 1471-2105