Quantitative analysis of the pyrolysis-mass spectra of complex mixtures using artificial neural networks: application to amino acids in glycogen

Pyrolysis-mass spectrometry and artificial neural networks (ANNs) were used in combination to provide quantitative analyses of mixtures of casamino acids in glycogen, as representatives of complex proteins and carbohydrates. We studied fully interconnected feedforward networks, whose weights were modified using various types of back-propagation algorithms, and which exploited a sigmoidal activation function. The ability of the ANNs to generalise was evaluated by varying the number of data points in the training set. It was found that for the algorithms and architecture employed, a set of ten samples equally spaced over the desired concentration range should be used to provide good interpolation. ANNs were poor at extrapolating beyond the range over which they had been trained. Amino acids; artificial neural networks; biotechnology; glycogen; Py-MS; pyrolysis.