Classification of ion mobility spectra by functional groups using neural networks

Neural networks were trained using whole ion mobility spectra from a standa rdized database of 3137 spectra for 204 chemicals at various concentrations . Performance of the network was measured by the success of classification into ten chemical classes. Eleven stages for evaluation of spectra and of s pectral pre-processing were employed and minimums established for response thresholds and spectral purity. After optimization of the database, network , and pre-processing routines, the fraction of successful classifications b y functional group was 0.91 throughout a range of concentrations. Network c lassification relied on a combination of features, including drift times, n umber of peaks, relative intensities, and other factors apparently includin g peak shape. The network was opportunistic, exploiting different features within different chemical classes. Application of neural networks in a two- tier design where chemicals were first identified by class and then individ ually eliminated all but one false positive out of 161 test spectra. These findings establish that ion mobility spectra, even with low resolution inst rumentation, contain sufficient detail to permit the development of automat ed identification systems. (C) 1999 Elsevier Science B.V. All rights reserv ed.