%0 Journal Article %1 taylor:1998:dpmsGP:aises %A Taylor, Janet %A Goodacre, Royston %A Wade, William G. %A Rowland, Jem J. %A Kell, Douglas B. %D 1998 %I Elsevier Science %J FEMS Microbiology Letters %K Chemometrics, Eubacterium, algorithms, genetic mass programming, pyrolysis spectrometry %P 237--246 %R doi:10.1016/S0378-1097(98)00038-X %T The deconvolution of pyrolysis mass spectra using genetic programming: application to the identification of some Eubacterium species %V 160 %X Pyrolysis mass spectrometry was used to produce complex biochemical fingerprints of Eubacterium exiguum, E. infirmum, E. tardum and E. timidum. To examine the relationship between these organisms the spectra were clustered by canonical variates analysis, and four clusters, one for each species, were observed. In an earlier study we trained artificial neural networks to identify these clinical isolates successfully; however, the information used by the neural network was not accessible from this so-called 'black box' technique. To allow the deconvolution of such complex spectra (in terms of which masses were important for discrimination) it was necessary to develop a system that itself produces 'rules' that are readily comprehensible. We here exploit the evolutionary computational technique of genetic programming; this rapidly and automatically produced simple mathematical functions that were also able to classify organisms to each of the four bacterial groups correctly and unambiguously. Since the rules used only a very limited set of masses, from a search space some 50 orders of magnitude greater than the dimensionality actually necessary, visual discrimination of the organisms on the basis of these spectral masses alone was also then possible.

@article{taylor:1998:dpmsGP:aises, abstract = {Pyrolysis mass spectrometry was used to produce complex biochemical fingerprints of Eubacterium exiguum, E. infirmum, E. tardum and E. timidum. To examine the relationship between these organisms the spectra were clustered by canonical variates analysis, and four clusters, one for each species, were observed. In an earlier study we trained artificial neural networks to identify these clinical isolates successfully; however, the information used by the neural network was not accessible from this so-called 'black box' technique. To allow the deconvolution of such complex spectra (in terms of which masses were important for discrimination) it was necessary to develop a system that itself produces 'rules' that are readily comprehensible. We here exploit the evolutionary computational technique of genetic programming; this rapidly and automatically produced simple mathematical functions that were also able to classify organisms to each of the four bacterial groups correctly and unambiguously. Since the rules used only a very limited set of masses, from a search space some 50 orders of magnitude greater than the dimensionality actually necessary, visual discrimination of the organisms on the basis of these spectral masses alone was also then possible.}, added-at = {2008-06-19T17:35:00.000+0200}, author = {Taylor, Janet and Goodacre, Royston and Wade, William G. and Rowland, Jem J. and Kell, Douglas B.}, biburl = {https://www.bibsonomy.org/bibtex/257cee07dc46a0661b2906203d468e970/brazovayeye}, doi = {doi:10.1016/S0378-1097(98)00038-X}, interhash = {a430c42abb88e516c9af89ca096f5cbc}, intrahash = {57cee07dc46a0661b2906203d468e970}, journal = {FEMS Microbiology Letters}, keywords = {Chemometrics, Eubacterium, algorithms, genetic mass programming, pyrolysis spectrometry}, notes = {PMID: 9532743}, organisation = {Federation of European Microbiological Societies}, pages = {237--246}, publisher = {Elsevier Science}, size = {10 pages}, timestamp = {2008-06-19T17:52:57.000+0200}, title = {The deconvolution of pyrolysis mass spectra using genetic programming: application to the identification of some Eubacterium species}, volume = 160, year = 1998 }