Evaluation of regression models in metabolic physiology: predicting fluxes from isotopic data without knowledge of the pathway
 Maciek R. Antoniewicz,
 Gregory Stephanopoulos,
 Joanne K. Kelleher
 … show all 3 hide
This study explores the ability of regression models, with no knowledge of the underlying physiology, to estimate physiological parameters relevant for metabolism and endocrinology. Four regression models were compared: multiple linear regression (MLR), principal component regression (PCR), partial leastsquares regression (PLS) and regression using artificial neural networks (ANN). The pathway of mammalian gluconeogenesis was analyzed using [U−^{13}C]glucose as tracer. A set of data was simulated by randomly selecting physiologically appropriate metabolic fluxes for the 9 steps of this pathway as independent variables. The isotope labeling patterns of key intermediates in the pathway were then calculated for each set of fluxes, yielding 29 dependent variables. Two thousand sets were created, allowing independent training and test data. Regression models were asked to predict the nine fluxes, given only the 29 isotopomers. For large training sets (>50) the artificial neural network model was superior, capturing 95% of the variability in the gluconeogenic flux, whereas the three linear models captured only 75%. This reflects the ability of neural networks to capture the inherent nonlinearities of the metabolic system. The effect of error in the variables and the addition of random variables to the data set was considered. Model sensitivities were used to find the isotopomers that most influenced the predicted flux values. These studies provide the first test of multivariate regression models for the analysis of isotopomer flux data. They provide insight for metabolomics and the future of isotopic tracers in metabolic research where the underlying physiology is complex or unknown.
 Benigni R., Giuliani A. (1994) Quantitative modeling and biology: the multivariate approach. Am. J. Physiol 266:R1697–R1704
 Bishop, C.M. (1996). Neural Networks for Pattern Recognition. Oxford University Press.
 Causton D.R. (1987). A Biologist’s Advanced Mathematics. London, Allen & Unwin
 Chatfield C., Collins A.J. (1981). Introduction to Multivariate Analysis. London, Chapman & Hall
 Dillon W.R., Goldstein M. (1984) Multivariate Analysis Methods and Applications. Wiley, New York
 Eddy C.V., Flanigan M., Arnold M.A. (2003) Nearinfrared spectroscopic measurement of urea in dialysate samples collected during hemodialysis treatments. Appl. Spectrosc. 57:1230–1235 CrossRef
 ElDeredy W., Ashmore S.M., Branston N.M., Darling J.L., Williams S.R., Thomas D.G. (1997). Pretreatment prediction of the chemotherapeutic response of human glioma cell cultures using nuclear magnetic resonance spectroscopy and artificial neural networks. Cancer Res. 57:4196–4199
 Geladi P., Kowalski B.R. (1986). Partial leastsquares regression: a tutorial. Anal. Chim. Acta 185:1–17 CrossRef
 German J.B., Roberts M.A., Fay L., Watkins S.M. (2002). Metabolomics and individual metabolic assessment: the next great challenge for nutrition. J. Nutr. 132:2486–2487
 Haykin, S.S. (1998) Neural Networks: A Comprehensive Foundation. Prentice Hall.
 Haymond M.W., Sunehag A.L. (2000). The reciprocal pool model for the measurement of gluconeogenesis by use of [U(13)C]glucose. Am. J. Physiol. Endocrinol. Metab. 278:E140–E145
 Irudayaraj J., Tewari J. (2003) Simultaneous monitoring of organic acids and sugars in fresh and processed apple juice by Fourier transform infraredattenuated total reflection spectroscopy. Appl. Spectrosc. 57:1599–1604 CrossRef
 Ishikawa M. (2000). Rule extraction by successive regularization. Neural Netw. 13:1171–1183 CrossRef
 Jenkins H., Hardy N., Beckmann M., Draper J., Smith A.R., Taylor J., Fiehn O., Goodacre R., Bino R.J., Hall R., Kopka J., Lane G.A., Lange B.M., Liu J.R., Mendes P., Nikolau B.J., Oliver S.G., Paton N.W., Rhee S., RoessnerTunali U., Saito K., Smedsgaard J., Sumner L.W., Wang T., Walsh S., Wurtele E.S., Kell D.B. (2004) A proposed framework for the description of plant metabolomics experiments and their results. Nat. Biotechnol. 22:1601–1606 CrossRef
 Kelleher J.K. (1999) Estimating gluconeogenesis with [U13C]glucose: molecular condensation requires a molecular approach. Am. J. Physiol. 277:E395–E400
 Landau B.R., Wahren J., Ekberg K., Previs S.F., Yang D., Brunengraber H. (1998) Limitations in estimating gluconeogenesis and Cori cycling from mass isotopomer distributions using [U13C6]glucose. Am. J. Physiol. 274:t61
 Manly B.F.J. (1994) Multivariate Statistical Methods: A Primer. London, Chapman & Hall
 Martens H., Naes T. (1989). Multivariate Calibration. Chichester, John Wiley
 Mendes P., Kell D.B. (1996). On the analysis of the inverse problem of metabolic pathways using artificial neural networks. Biosystems 38:15–28 CrossRef
 Misra J., Schmitt W., Hwang D., Hsiao L.L., Gullans S., Stephanopoulos G., Stephanopoulos G. (2002) Interactive exploration of microarray gene expression patterns in a reduced dimensional space. Genome Res. 12:1112–1120 CrossRef
 Raamsdonk L.M., Teusink B., Broadhurst D., Zhang N., Hayes A., Walsh M.C., Berden J.A., Brindle K.M., Kell D.B., Rowland J.J., Westerhoff H.V., van Dam K., Oliver S.G. (2001). A functional genomics strategy that uses metabolome data to reveal the phenotype of silent mutations. Nat. Biotechnol. 19:45–50 CrossRef
 Saito K., Nakano R. (2002) Extracting regression rules from neural networks. Neural Netw. 15:1279–1288 CrossRef
 Schmidt K., Carlsen M., Nielsen J., Villadsen J. (1997) Modeling isotopomer distributions in biochemical networks using isotopomer mapping matrices. Biotechnol. Bioeng. 55:831–840 CrossRef
 Stephanopoulos G., Hwang D., Schmitt W.A., Misra J., Stephanopoulos G. (2002) Mapping physiological states from microarray expression measurements. Bioinformatics 18:1054–1063 CrossRef
 Tabachnick B.G., Fidell L.S. (2001) Using Multivariate Statistics. Boston, Allyn and Bacon
 Tayek J.A., Katz J. (1997) Glucose production, recycling, Cori cycle, and gluconeogenesis in humans: relationship to serum cortisol. Am. J. Physiol. 272:E476–E484
 White H. (1992) Artificial Neural Networks: Approximation and Learning Theory. Oxford, Blackwell
 Wiechert W., Mollney M., Isermann N., Wurzel M., De Graaf A.A. (1999) Bidirectional reaction steps in metabolic networks: III. Explicit solution and analysis of isotopomer labeling systems. Biotechnol. Bioeng. 66:69–85 CrossRef
 Zupke C., Stephanopoulos G. (1994) Modeling of isotope distributions and intracellular fluxes in metabolic networks using atom mapping matrices. Biotechnol. Prog. 10:489–498 CrossRef
 Title
 Evaluation of regression models in metabolic physiology: predicting fluxes from isotopic data without knowledge of the pathway
 Open Access
 Available under Open Access This content is freely available online to anyone, anywhere at any time.
 Journal

Metabolomics
Volume 2, Issue 1 , pp 4152
 Cover Date
 20060301
 DOI
 10.1007/s1130600600182
 Print ISSN
 15733882
 Online ISSN
 15733890
 Publisher
 Springer US
 Additional Links
 Topics
 Keywords

 systems biology
 multivariate regression
 stable isotopes
 metabolism
 gluconeogenesis
 Industry Sectors
 Authors

 Maciek R. Antoniewicz ^{(1)}
 Gregory Stephanopoulos ^{(1)}
 Joanne K. Kelleher ^{(1)}
 Author Affiliations

 1. Department of Chemical Engineering, Bioinformatics and Metabolic Engineering Laboratory, Massachusetts Institute of Technology, 77 Massachusetts Avenue, Cambridge, MA, 02139, USA