M. Spraul et al., AUTOMATIC REDUCTION OF NMR SPECTROSCOPIC DATA FOR STATISTICAL AND PATTERN-RECOGNITION CLASSIFICATION OF SAMPLES, Journal of pharmaceutical and biomedical analysis, 12(10), 1994, pp. 1215-1225
A general method of automatically reducing NMR spectra to provide nume
rical descriptors of samples has been developed and investigated. Thes
e descriptors can be used as input to pattern recognition or multivari
ate algorithms for sample classification. The methods have been tested
using 600 MHz one-dimensional H-1 NMR spectra of biofluids which are
complex mixtures. The approach is, in principle, applicable to multidi
mensional and heteronuclear NMR spectra and to other types of liquid s
amples such as oils and foodstuffs as well as to situations such as H-
1 or P-31 NMR in vivo and solid state NMR in drug formulation analysis
. The method relies upon apportioning the information in the spectra t
o individual contiguous segments and allowing specified regions of the
spectra to be omitted. Three approaches, based on the number of peaks
, the summed peak heights and the summed peak areas respectively in ea
ch segment, have been tested. The effect of segment width and overlap
and the effects of manipulation of the NMR spectra have been evaluated
in terms of the classification of the samples using principal compone
nts analysis. A simple method of generating NMR based spectral descrip
tors for object classification is thus proposed.