R. Goodacre et al., ON MASS-SPECTROMETER INSTRUMENT STANDARDIZATION AND INTERLABORATORY CALIBRATION TRANSFER USING NEURAL NETWORKS, Analytica chimica acta, 348(1-3), 1997, pp. 511-532
For pyrolysis mass spectrometry (PyMS) to be exploited in areas such a
s the routine identification of microorganisms, for quantifying determ
inands in biological and biotechnological systems, and in the producti
on of useful mass spectral libraries, it is paramount that newly acqui
red spectra be comparable to those previously collected and held in a
central reference laboratory. Artificial neural networks (ANNs) and ot
her multivariate calibration models have been used to relate mass spec
tra to the biological features of interest. However, calibration model
s developed on one mass spectrometer cannot be used with spectra colle
cted on a second instrument, because of the differences between the in
strumental responses of both instruments. We report here that an ANN-b
ased drift correction procedure can be implemented so that newly acqui
red spectra can be used to challenge models constructed using mass spe
ctra collected on different instruments. Calibration samples were run
on three different PyMS machines, and ANNs set up in which the inputs
were the 150 machine 'a' calibration masses and the outputs were the 1
50 calibration masses from the machine 'b' spectra. Such associative n
eural networks could thus be used as signal-processing elements to eff
ect the transformation of data acquired on one machine to those which
would have been acquired on a different instrument. Therefore, for the
first time PyMS could be used to acquire spectra which could usefully
be compared to those previously collected and held in a data-base, ir
respective of the mass spectrometer used. The examples reported are fo
r the quantitative assessment of the amount of lysozyme in a binary mi
xture with glycogen and the rapid identification down to the species l
evel of bacteria belonging to the genus Eubacterium. This approach is
not limited solely to pyrolysis mass spectrometry but is generally app
licable to any analytical tool which is prone to deterioration in cali
bration transfer, such as IR, ESR, NMR and other vibrational spectrosc
opies, gas and liquid chromatography, as well as other types of mass s
pectrometry.