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

Abstract 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.

[1]  Anders Krogh,et al.  Introduction to the theory of neural computation , 1994, The advanced book program.

[2]  Royston Goodacre,et al.  The use of pyrolysis—mass spectrometry to detect the fimbrial adhesive antigen F41 from Escherichia coli HB101 (pSLM204) , 1991 .

[3]  Gregory A. Mack,et al.  Chemometrics: A Textbook , 1990 .

[4]  Second Edition,et al.  Statistical Package for the Social Sciences , 1970 .

[5]  Halbert White,et al.  Connectionist nonparametric regression: Multilayer feedforward networks can learn arbitrary mappings , 1990, Neural Networks.

[6]  Teuvo Kohonen,et al.  Self-Organization and Associative Memory , 1988 .

[7]  R. Freeman,et al.  Strain differentiation of capsule type 23 penicillin‐resistant Streptococcus pneumoniae from nosocomial infections by pyrolysis mass spectrometry , 1991 .

[8]  Daniel J. Amit,et al.  Modeling brain function: the world of attractor neural networks, 1st Edition , 1989 .

[9]  Scott E. Fahlman,et al.  An empirical study of learning speed in back-propagation networks , 1988 .

[10]  David E. Rumelhart,et al.  MSnet: A Neural Network which Classifies Mass Spectra , 1990 .

[11]  Kurt Hornik,et al.  Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networks , 1990, Neural Networks.

[12]  R. E. Aries,et al.  Evaluation of a low-cost, automated pyrolysis-mass spectrometer , 1986 .

[13]  W. Windig,et al.  Chemical interpretation of differences in pyrolysis—mass spectra of simulated mixtures of biopolymers by factor analysis with graphical rotation , 1982 .

[14]  Royston Goodacre,et al.  Detection of small genotypic changes in Escherichia coli by pyrolysis mass spectroscopy , 1990 .

[15]  L. Larsson,et al.  Gas chromatography/mass spectrometry: applications in microbiology. , 1984 .

[16]  Patricia L. Smith.  Chemometrics: Applications of Mathematics and Statistics to Laboratory Systems , 1993 .

[17]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[18]  R. Kajioka,et al.  Curie-point pyrolysis—mass spectrometry of Legionella species , 1984 .

[19]  H. Meuzelaar,et al.  Pyrolysis mass spectrometry: a new method to differentiate between the mycobacteria of the 'tuberculosis complex' and other mycobacteria. , 1981, Journal of general microbiology.

[20]  Thomas Jackson,et al.  Neural Computing - An Introduction , 1990 .

[21]  Teuvo Kohonen,et al.  An introduction to neural computing , 1988, Neural Networks.

[22]  Yoh-Han Pao,et al.  Adaptive pattern recognition and neural networks , 1989 .

[23]  Geoffrey E. Hinton,et al.  A Learning Algorithm for Boltzmann Machines , 1985, Cogn. Sci..

[24]  R. Freeman,et al.  Rapid inter-strain comparison by pyrolysis mass spectrometry of coagulase-negative staphylococci from persistent CAPD peritonitis , 1991, Epidemiology and Infection.

[25]  W. J. Irwin,et al.  Analytical pyrolysis : a comprehensive guide , 1982 .

[26]  R. Freeman,et al.  Incrimination of an environmental source of a case of Legionnaires' disease by pyrolysis mass spectrometry , 1991, Epidemiology and Infection.

[27]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[28]  J. T. Magee,et al.  Epidemiological typing of Streptococcus pyogenes by pyrolysis mass spectrometry. , 1989, Journal of medical microbiology.

[29]  Mariko Ishiwatari,et al.  J. Anal. Appl. Pyrolysis , 1995 .

[30]  D. Drucker.  Chapter III. Gas-Liquid Chromatographic Chemotaxonomy , 1976 .

[31]  W. Windig,et al.  Nonsupervised numerical component extraction from pyrolysis mass spectra of complex mixtures. , 1984, Analytical chemistry.

[32]  Philip D. Wasserman,et al.  Neural computing - theory and practice , 1989 .

[33]  Russell C. Eberhart,et al.  Neural network PC tools , 1990 .

[34]  Philip D. Wasserman,et al.  Neuralsource: The Bibliographic Guide to Artificial Neural Networks , 1990 .

[35]  C. Lee Giles,et al.  Neural Information Processing Systems 7 , 1995 .

[36]  C. Gutteridge,et al.  Curie-point pyrolysis mass spectrometry applied to characterization and identification of selected Bacillus species. , 1984, Journal of general microbiology.

[37]  R. Freeman,et al.  Inter-strain comparison by pyrolysis mass spectrometry in the investigation of Staphylococcus aureus nosocomial infection. , 1991, The Journal of hospital infection.

[38]  S Mangrulkar,et al.  Artificial neural systems. , 1990, ISA transactions.

[39]  R. Freeman,et al.  Pyrolysis-mass spectrometry (Py-MS) for the rapid epidemiological typing of clinically significant bacterial pathogens. , 1990, Journal of medical microbiology.

[40]  Royston Goodacre,et al.  Neural networks and olive oil , 1992, Nature.

[41]  C. Gutteridge.  6 Characterization of Microorganisms by Pyrolysis Mass Spectrometry , 1988 .

[42]  James L. McClelland,et al.  Explorations in parallel distributed processing: a handbook of models, programs, and exercises , 1988 .