Artificial Neural Networks for Classification in Metabolomic Studies of Whole Cells Using 1H Nuclear Magnetic Resonance

We report the successful classification, by artificial neural networks (ANNs), of 1H NMR spectroscopic data recorded on whole-cell culture samples of four different lung carcinoma cell lines, which display different drug resistance patterns. The robustness of the approach was demonstrated by its ability to classify the cell line correctly in 100% of cases, despite the demonstrated presence of operator-induced sources of variation, and irrespective of which spectra are used for training and for validation. The study demonstrates the potential of ANN for lung carcinoma classification in realistic situations.

[1]  M. Clynes,et al.  Cytogenetic comparison of two poorly differentiated human lung squamous cell carcinoma lines. , 1992, Cancer genetics and cytogenetics.

[2]  M. Bloom,et al.  Complete proton magnetic resonance in whole cells , 1986 .

[3]  M. Clynes,et al.  Enhancement of chemotherapeutic drug toxicity to human tumour cells in vitro by a subset of non-steroidal anti-inflammatory drugs (NSAIDs). , 1998, European journal of cancer.

[4]  L. Martí-Bonmatí,et al.  Metabolite identification in human liver needle biopsies by high‐resolution magic angle spinning 1H NMR spectroscopy , 2006, NMR in biomedicine.

[5]  J. Havel,et al.  Content of aliphatic hydrocarbons in limpets as a new way for classification of species using artificial neural networks. , 2004, Chemosphere.

[6]  Y. Yoshioka,et al.  In vitro characterization of lung cancers by the use of 1H nuclear magnetic resonance spectroscopy of tissue extracts and discriminant factor analysis , 1993, Magnetic resonance in medicine.

[7]  E Holmes,et al.  Automatic reduction of NMR spectroscopic data for statistical and pattern recognition classification of samples. , 1994, Journal of pharmaceutical and biomedical analysis.

[8]  D. Brougham,et al.  Metabolomic studies of human lung carcinoma cell lines using in vitro 1H NMR of whole cells and cellular extracts , 2008, NMR in biomedicine.

[9]  Mathias Hoehn,et al.  Metabolic differences between primary and recurrent human brain tumors: a 1H NMR spectroscopic investigation , 2005, NMR in biomedicine.

[10]  L. Martí-Bonmatí,et al.  1H and 13C HR‐MAS spectroscopy of intact biopsy samples ex vivo and in vivo 1H MRS study of human high grade gliomas , 2004, NMR in biomedicine.

[11]  J. Lindon,et al.  'Metabonomics': understanding the metabolic responses of living systems to pathophysiological stimuli via multivariate statistical analysis of biological NMR spectroscopic data. , 1999, Xenobiotica; the fate of foreign compounds in biological systems.

[12]  Himanshu Bhat,et al.  Fast quantification of proton magnetic resonance spectroscopic imaging with artificial neural networks. , 2006, Journal of magnetic resonance.

[13]  A. W. Simonetti,et al.  Development of a decision support system for diagnosis and grading of brain tumours using in vivo magnetic resonance single voxel spectra , 2006, NMR in biomedicine.

[14]  J. Havel,et al.  Thrips (Thysanoptera) identification using artificial neural networks , 2008, Bulletin of Entomological Research.

[15]  John C. Lindon,et al.  Pattern recognition methods and applications in biomedical magnetic resonance , 2001 .

[16]  P. Indovina,et al.  The relationship between 1H-NMR mobile lipid intensity and cholesterol in two human tumor multidrug resistant cell lines (MCF-7 and LoVo). , 2001, Biochimica et biophysica acta.

[17]  Kishore Bhakoo,et al.  Spectral profiles of cultured neuronal and glial cells derived from HRMAS 1H NMR spectroscopy , 2002, NMR in biomedicine.

[18]  D. Zipser,et al.  Identification models of the nervous system , 1992, Neuroscience.

[19]  J. Nicholson,et al.  NMR and pattern recognition studies on liver extracts and intact livers from rats treated with alpha-naphthylisothiocyanate. , 2002, Biochemical pharmacology.

[20]  R. Kauppinen,et al.  Assignment of 1H nuclear magnetic resonance visible polyunsaturated fatty acids in BT4C gliomas undergoing ganciclovir-thymidine kinase gene therapy-induced programmed cell death. , 2003, Cancer research.

[21]  M. Tanner,et al.  Metabonomic investigations in mice infected with Schistosoma mansoni: an approach for biomarker identification. , 2004, Proceedings of the National Academy of Sciences of the United States of America.

[22]  M. Hoehn,et al.  1H‐ and 31P‐MR spectroscopy of primary and recurrent human brain tumors in vitro: malignancy‐characteristic profiles of water soluble and lipophilic spectral components , 2001, NMR in biomedicine.

[23]  K. Kaski,et al.  1H NMR metabonomics of plasma lipoprotein subclasses: elucidation of metabolic clustering by self‐organising maps , 2007, NMR in biomedicine.

[24]  L. O’Driscoll,et al.  Isolation from a human MDR lung cell line of multiple clonal subpopulations which exhibit significantly different drug resistance , 1997, International journal of cancer.

[25]  R. B. Kingsley,et al.  WET, a T1- and B1-insensitive water-suppression method for in vivo localized 1H NMR spectroscopy. , 1994, Journal of magnetic resonance. Series B.

[26]  Jouni Kaartinen,et al.  Quantification of human brain metabolites from in vivo 1H NMR magnitude spectra using automated artificial neural network analysis. , 2002, Journal of magnetic resonance.

[27]  V. Govindaraju,et al.  Proton NMR chemical shifts and coupling constants for brain metabolites , 2000, NMR in biomedicine.

[28]  E Holmes,et al.  Development of a model for classification of toxin‐induced lesions using 1H NMR spectroscopy of urine combined with pattern recognition , 1998, NMR in biomedicine.

[29]  M. Clynes,et al.  Altered cell cycle response of drug-resistant lung carcinoma cells to doxorubicin. , 2000, European journal of cancer.

[30]  D. Thomas,et al.  Pretreatment prediction of the chemotherapeutic response of human glioma cell cultures using nuclear magnetic resonance spectroscopy and artificial neural networks. , 1997, Cancer research.

[31]  J R Griffiths,et al.  Pattern recognition analysis of 1H NMR spectra from perchloric acid extracts of human brain tumor biopsies , 1998, Magnetic resonance in medicine.

[32]  V. Larue,et al.  Magnetic resonance spectroscopy of cellular lipid extracts from sensitive, resistant and reverting K562 cells and flow cytometry for investigating the P‐glycoprotein function in resistance reversion , 2000, NMR in biomedicine.

[33]  J. D. de Certaines,et al.  Differentiation of the P-gp and MRP1 multidrug resistance systems by mobile lipid 1H-NMR spectroscopy and phosphatidylserine externalization. , 2001, Anticancer research.

[34]  N R Jagannathan,et al.  Biochemical characterization of metastatic lymph nodes of breast cancer patients by in vitro 1H magnetic resonance spectroscopy: a pilot study. , 2004, Magnetic resonance imaging.

[35]  L. Le Moyec,et al.  Cell and membrane lipid analysis by proton magnetic resonance spectroscopy in five breast cancer cell lines. , 1992, British Journal of Cancer.