Classification of toxin-induced changes in 1H NMR spectra of urine using an artificial neural network.

NMR spectra of urine from rats treated with a range of liver, kidney and testicular toxins at various doses were measured and classified using neural network methods. Toxin-induced changes in the levels of 18 low molecular weight endogenous urinary metabolites were assessed using a simple semi-quantitative scoring system. These scores were used as input to an artificial neural network, the use of which has been explored as a means of predicting the class of toxin. With this limited data set, based only the level of the maximal changes of these 18 metabolites, the network was able to predict the class and hence target organ of the toxins. Renal cortical toxicity was well predicted as was liver toxicity. The few examples of renal medullary toxins in the data set resulted in relatively poor training of the network although correct classification was still possible.

[1]  Geoffrey M. J. West.  Predicting phosphorus NMR shifts using neural networks , 1993, J. Chem. Inf. Comput. Sci..

[2]  J C Lindon,et al.  Application of pattern recognition methods to the analysis and classification of toxicological data derived from proton nuclear magnetic resonance spectroscopy of urine. , 1991, Molecular pharmacology.

[3]  C. Beddell,et al.  Automatic data reduction and pattern recognition methods for analysis of 1H nuclear magnetic resonance spectra of human urine from normal and pathological states. , 1994, Analytical biochemistry.

[4]  Peter C. Jurs,et al.  Simulation of polysaccharide carbon-13 nuclear magnetic resonance spectra using regression analysis and neural networks , 1993 .

[5]  A Darvill,et al.  Identification of the 1H-NMR spectra of complex oligosaccharides with artificial neural networks , 1991, Science.

[6]  B. Kowalski,et al.  Partial least-squares regression: a tutorial , 1986 .

[7]  E Holmes,et al.  Nuclear magnetic resonance spectroscopy and pattern recognition analysis of the biochemical processes associated with the progression of and recovery from nephrotoxic lesions in the rat induced by mercury(II) chloride and 2-bromoethanamine. , 1992, Molecular pharmacology.

[8]  P J Sadler,et al.  Proton NMR spectra of urine as indicators of renal damage. Mercury-induced nephrotoxicity in rats. , 1985, Molecular pharmacology.

[9]  W. Goux,et al.  The application of NMR-pattern-recognition methods to the classification of reduced, peracetylated oligosaccharide residues. , 1993, Carbohydrate research.

[10]  J. Nicholson,et al.  Investigations into the biochemical effects of region-specific nephrotoxins. , 1989, Molecular pharmacology.

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

[12]  J C Lindon,et al.  Pattern recognition classification of the site of nephrotoxicity based on metabolic data derived from proton nuclear magnetic resonance spectra of urine. , 1994, Molecular pharmacology.

[13]  Svante Wold,et al.  Pattern recognition by means of disjoint principal components models , 1976, Pattern Recognit..

[14]  Lawrence S. Anker,et al.  Prediciton of carbon-13 nuclear magnetic resonance chemical shifts by artificial neural networks , 1992 .

[15]  J. U. Thomsen,et al.  Pattern recognition of the 1H NMR spectra of sugar alditols using a neural network , 1989 .

[16]  P J Sadler,et al.  Quantitative high resolution 1H NMR urinalysis studies on the biochemical effects of cadmium in the rat. , 1989, Molecular pharmacology.

[17]  J. Prestegard,et al.  Application of neural networks to automated assignment of NMR spectra of proteins , 1994, Journal of biomolecular NMR.