Automatic Classification of NMR Spectra by Ensembles of Local Experts

  • Kai Lienemann
  • Thomas Plötz
  • Gernot A. Fink
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5342)


A new approach for the automatic detection of drug-induced organ toxicities based on Nuclear Magnetic Resonance Spectroscopy data from biofluids is presented in this paper. Spectral data from biofluids contain information on the concentration of various substances, but the combination of only a small subset of these cues is putatively useful for classification of new samples. We propose to divide the spectra into several short regions and train classifiers on them, using only a limited amount of information for class discrimination. These local experts are combined in an ensemble classification system and the subset of experts for the final classification is optimized automatically. Thus, only local experts for relevant spectral regions are used for the final ensemble classification. The proposed approach has been evaluated on a real data-set from industrial pharmacology, showing an improvement in classification accuracy and indicating relevant spectral regions for classification.


Nuclear Magnetic Resonance Nuclear Magnetic Resonance Spectrum Near Neighbor Local Expert Safety Pharmacology 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Freeman, R.: Magnetic resonance in chemistry and medicine. Oxford University Press, New York (2003)Google Scholar
  2. 2.
    Lindon, J.C., et al.: Contemporary issues in toxicology the role of metabonomics in toxicology and its evaluation by the COMET project. Toxicology and Applied Pharmacology 187(3), 137–146 (2003)CrossRefGoogle Scholar
  3. 3.
    Holmes, E., et al.: Development of a model for classification of toxin-induced lesions using 1H NMR spectroscopy of urine combined with pattern recognition. NMR in Biomedicine 11(4-5), 235–244 (1998)CrossRefGoogle Scholar
  4. 4.
    Beckonert, O., et al.: NMR-based metabonomic toxicity classification: hierarchical cluster analysis and k-nearest-neighbour approaches. Analytica Chimica Acta 490, 3–15 (2003)CrossRefGoogle Scholar
  5. 5.
    Fieno, T., Viswanathan, V., Tsoukalas, L.: Neural network methodology for 1H NMR spectroscopy classification. In: ICIIS 1999: Proc. Int. Conf. on Information Intelligence and Systems, pp. 80–85. IEEE Computer Society, Los Alamitos (1999)Google Scholar
  6. 6.
    Kittler, J., Hatef, M., Duin, R.P., Matas, J.: On combining classifiers. IEEE Transactions on Pattern Analysis and Machine Intelligence 20(3), 226–239 (1998)CrossRefGoogle Scholar
  7. 7.
    Lienemann, K., Plötz, T., Fink, G.A.: On the application of SVM-Ensembles based on adapted random subspace sampling for automatic classification of NMR data. In: Haindl, M., Kittler, J., Roli, F. (eds.) MCS 2007. LNCS, vol. 4472, pp. 42–51. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  8. 8.
    Schölkopf, B., Smola, A.J.: Learning with Kernels. MIT Press, Cambridge (2002)zbMATHGoogle Scholar
  9. 9.
    Ho, T.K.: The random subspace method for constructing decision forests. IEEE Transactions on Pattern Analysis and Machine Intelligence 20(8), 832–844 (1998)CrossRefGoogle Scholar
  10. 10.
    Lienemann, K., Plötz, T., Pestel, S.: NMR-based urine analysis in rats: Prediction of proximal tubule kidney toxicity and phospholipidosis. Journal of Pharmacological and Toxicological Methods 58(1), 41–49 (2008)CrossRefGoogle Scholar
  11. 11.
    Spraul, M., et al.: Automatic reduction of NMR spectroscopic data for statistical and pattern recognition classification of samples. Journal of Pharmaceutical & Biomedical Analysis 12, 1215–1225 (1994)CrossRefGoogle Scholar
  12. 12.
    Torgrip, R.J.O., et al.: New methods of data partitioning based on pars peak alignment for improvedmultivariate biomarker/biopattern detection in 1H NMR spectroscopic metabolic profiling of urine. Metabolomics 2(1), 1–19 (2006)CrossRefGoogle Scholar
  13. 13.
    Torgrip, R.J.O., Åberg, M., Karlberg, B., Jacobsson, S.P.: Peak alignment using reduced set mapping. Journal of Chemometrics 17, 573–582 (2003)CrossRefGoogle Scholar
  14. 14.
    Skov, T., van den Berg, F., Tomasi, G., Bro, R.: Automated alignment of chromatographic data. Journal of Chemometrics 20(11-12), 484–497 (2006)CrossRefGoogle Scholar
  15. 15.
    Kuncheva, L., Bezdek, J., Duin, R.: Decision templates for multiple classifier fusion: an experimental comparison. Pattern Recognition 34, 299–314 (2001)CrossRefzbMATHGoogle Scholar
  16. 16.
    Goldberg, D.E.: Genetic Algorithms in Search, Optimization and Machine Learning. Addison-Wesley Longman Publishing Co. (1989)Google Scholar
  17. 17.
    Matthews, B.W.: Comparison of the predicted and observed secondary structure of the T4 phage lysozyme. Biochimica et Biophysica Acta 405, 442–451 (1975)CrossRefGoogle Scholar
  18. 18.
    Duda, R.O., Hart, P.E., Stork, D.G.: Pattern Classification, 2nd edn. John Wiley & Sons, Chichester (2001)zbMATHGoogle Scholar
  19. 19.
    Breiman, L.: Random forests. Machine Learning 45(1), 5–32 (2001)CrossRefzbMATHGoogle Scholar
  20. 20.
    Barnes, R.J., et al.: Standard normal variate transformation and de-trending of near-infrared diffuse reflectance spectra. Applied Spectroscopy 43(5), 772–777 (1989)CrossRefGoogle Scholar
  21. 21.
    Nord, L.I., Kenne, L., Jacobsson, S.: Multivariate analysis of 1H NMR spectra for saponins from quillaja saponaria molina. Anal. Chim. Acta 446, 197–207 (2001)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Kai Lienemann
    • 1
  • Thomas Plötz
    • 1
  • Gernot A. Fink
    • 1
  1. 1.Intelligent Systems GroupDortmund University of TechnologyGermany

Personalised recommendations