Heterogeneous Data Fusion to Type Brain Tumor Biopsies

  • Vangelis Metsis
  • Heng Huang
  • Fillia Makedon
  • Aria Tzika
Part of the IFIP International Federation for Information Processing book series (IFIPAICT, volume 296)


Current research in biomedical informatics involves analysis of multiple heterogeneous data sets. This includes patient demographics, clinical and pathology data, treatment history, patient outcomes as well as gene expression, DNA sequences and other information sources such as gene ontology. Analysis of these data sets could lead to better disease diagnosis, prognosis, treatment and drug discovery. In this paper, we use machine learning algorithms to create a novel framework to perform the heterogeneous data fusion on both metabolic and molecular datasets, including state-of-the-art high-resolution magic angle spinning (HRMAS) proton (1H) Magnetic Resonance Spectroscopy and gene transcriptome profiling, to intact brain tumor biopsies and to identify different profiles of brain tumors. Our experimental results show our novel framework outperforms any analysis using individual dataset.


Support Vector Machine Feature Selection Information Gain Feature Selection Method Magnetic Resonance Spectroscopic 
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.
    LG Astrakas, D Zurakowski, and AA Tzika et al. Noninvasive magnetic resonance spectroscopic imaging biomarkers to predict the clinical grade of pediatric brain tumors. Clin Cancer Res, 10:8220–8228, 2004.CrossRefGoogle Scholar
  2. 2.
    H. Chai and C. Domeniconi. An Evaluation of Gene Selection Methods for Multi-class Microarray Data Classification. ECML/PKDD 2004.Google Scholar
  3. 3.
    L.L. Cheng, D.C. Anthony, A.R. Comite, P.M. Black, A.A. Tzika, and R.G. Gonzalez. Quantification of microheterogeneity in glioblastoma multiforme with ex vivo highresolution magic-angle spinning (HRMAS) proton magnetic resonance spectroscopy. Neuro-Oncology, 2(2):87–95, 2000.Google Scholar
  4. 4.
    M Diehn, C Nardini, and et al. Identification of noninvasive imaging surrogates for brain tumor gene-expression modules. Proc Natl Acad Sci, 105(13):5213–5218, 2008.CrossRefGoogle Scholar
  5. 5.
    C. Ding and H. Peng. Minimum redundancy feature selection from microarray gene expression data. Journal of Bioinformatics and Computational Biology, 3(2):185–205, 2005.MathSciNetCrossRefGoogle Scholar
  6. 6.
    Carlson MR et al. Relationship between survival and edema in malignant gliomas: role of vascular endothelial growth factor and neuronal pentraxin. Clin Cancer Res., 13(9):2592–2598, 2007.CrossRefGoogle Scholar
  7. 7.
    Hobbs SK et al. Magnetic resonance image-guided proteomics of human glioblastoma multiforme. Magn. Reson. Imaging, 18(5):530–536, 2003.CrossRefGoogle Scholar
  8. 8.
    J.N. Rich et al. Gene expression profiling and genetic markers in glioblastoma survival. Cancer Research, 65:4051–4058, 2005.CrossRefGoogle Scholar
  9. 9.
    Guyon and A. Elisseeff. An introduction to variable and feature selection. The Journal of Machine Learning Research, 3:1157–1182, 2003.MATHGoogle Scholar
  10. 10.
    R.A. Irizarry, B. Hobbs, F. Collin, Y.D. Beazer-Barclay, K.J. Antonellis, Uwe Scherf, and T.P. Speed. Exploration, normalization, and summaries of high density oligonucleotide array probe level data. Biostatistics, 4(2):249, 2003.CrossRefMATHGoogle Scholar
  11. 11.
    Kononenko. Estimating Attributes: Analysis and Extensions of Relief. Lecture Notes in Computer Science, pages 171–171, 1994.Google Scholar
  12. 12.
    T. Li, C. Zhang, and M. Ogihara. A comparative study of feature selection and multiclass classification methods for tissue classification based on gene expression, 2004.Google Scholar
  13. 13.
    H. Liu and R. Setiono. Chi2: Feature selection and discretization of numeric attributes. In Proceedings 7th International Conference on Tools with Artificial Intelligence, page 88. IEEE Computer Society Washington, DC, 1995.Google Scholar
  14. 14.
    V. Metsis, I. Androutsopoulos, and G. Paliouras. Spam filtering with naive bayes — which naive bayes. In Third Conference on Email and Anti-Spam (CEAS), 2006.Google Scholar
  15. 15.
    T.M. Mitchell. Machine Learning. 1997. Burr Ridge, IL: McGraw Hill.MATHGoogle Scholar
  16. 16.
    D. Morvan, A. Demidem, J. Papon, M. De Latour, and J.C. Madelmont. Melanoma Tumors Acquire a New Phospholipid Metabolism Phenotype under Cystemustine As Revealed by High-Resolution Magic Angle Spinning Proton Nuclear Magnetic Resonance Spectroscopy of Intact Tumor Samples 1, 2002.Google Scholar
  17. 17.
    C.L. Nutt, DR Mani, R.A. Betensky, P. Tamayo, J.G. Cairncross, C. Ladd, U. Pohl, C. Hartmann, M.E. McLaughlin, T.T. Batchelor, et al. Gene Expression-based Classification of Malignant Gliomas Correlates Better with Survival than Histological Classification 1, 2003.Google Scholar
  18. 18.
    F. Podo. Tumour phospholipid metabolism. NMR in Biomedicine, 12(7):413–439, 1999.CrossRefGoogle Scholar
  19. 19.
    MJ Renan. How many mutations are required for tumorigenesis? Implications from human cancer data. Mol Carcinog, 7(3):139–46, 1993.CrossRefGoogle Scholar
  20. 20.
    PN Tan, M. Steinbach, and V. Kumar. Introduction to Data Mining. 2005.Google Scholar
  21. 21.
    A.A. Tzika, L. Astrakas, H. Cao, D. Mintzopoulos, O.C. Andronesi, M. Mindrinos, J. Zhang, L.G. Rahme, K.D. Blekas, A.C. Likas, et al. Combination of high-resolution magic angle spinning proton magnetic resonance spectroscopy and microscale genomics to type brain tumor biopsies. International Journal of Molecular Medicine, 20(2):199, 2007.Google Scholar
  22. 22.
    V. Vapnik. Statistical Learning Theory. 1998. NY Wiley.Google Scholar
  23. 23.
    S.J. Watson, F. Meng, R.C. Thompson, and H. Akil. The chip as a specific genetic tool. Biol Psychiatry, 48:1147–1156, 2000.CrossRefGoogle Scholar

Copyright information

© IFIP International Federation for Information Processing 2009

Authors and Affiliations

  • Vangelis Metsis
    • 2
  • Heng Huang
    • 2
  • Fillia Makedon
    • 2
  • Aria Tzika
    • 1
  1. 1.NMR Surgical Laboratory, Department of SurgeryHarvard Medical School and Massachusetts General HospitalBostonUSA
  2. 2.University of Texas at ArlingtonArlingtonUSA

Personalised recommendations