Display options
Cite
Inglese P, McKenzie JS, Mroz A, et al. Deep learning and 3D-DESI imaging reveal the hidden metabolic heterogeneity of cancer. Chem Sci. 2017;8(5):3500-3511doi: 10.1039/c6sc03738k.
Inglese, P., McKenzie, J. S., Mroz, A., Kinross, J., Veselkov, K., Holmes, E., Takats, Z., Nicholson, J. K., & Glen, R. C. (2017). Deep learning and 3D-DESI imaging reveal the hidden metabolic heterogeneity of cancer. Chemical science, 8(5), 3500-3511. https://doi.org/10.1039/c6sc03738k
Inglese, Paolo, et al. "Deep learning and 3D-DESI imaging reveal the hidden metabolic heterogeneity of cancer." Chemical science vol. 8,5 (2017): 3500-3511. doi: https://doi.org/10.1039/c6sc03738k
Inglese P, McKenzie JS, Mroz A, Kinross J, Veselkov K, Holmes E, Takats Z, Nicholson JK, Glen RC. Deep learning and 3D-DESI imaging reveal the hidden metabolic heterogeneity of cancer. Chem Sci. 2017 May 01;8(5):3500-3511. doi: 10.1039/c6sc03738k. Epub 2017 Feb 21. PMID: 28507724; PMCID: PMC5418631.
Copy Download .nbib Format: NLM
Share it on

Chem Sci. 2017 May 01;8(5):3500-3511. doi: 10.1039/c6sc03738k. Epub 2017 Feb 21.

Deep learning and 3D-DESI imaging reveal the hidden metabolic heterogeneity of cancer.

Chemical science

Paolo Inglese, James S McKenzie, Anna Mroz, James Kinross, Kirill Veselkov, Elaine Holmes, Zoltan Takats, Jeremy K Nicholson, Robert C Glen

Affiliations

  1. Department of Surgery and Cancer - Division of Computational and Systems Medicine , Imperial College London , London , UK . Email: [email protected] ; Email: [email protected] ; Email: [email protected].
  2. Centre for Molecular Informatics , Department of Chemistry , University of Cambridge , Cambridge , UK.

PMID: 28507724 PMCID: PMC5418631 DOI: 10.1039/c6sc03738k

Abstract

Visual inspection of tumour tissues does not reveal the complex metabolic changes that differentiate cancer and its sub-types from healthy tissues. Mass spectrometry imaging, which quantifies the underlying chemistry, represents a powerful tool for the molecular exploration of tumour tissues. A 3-dimensional topological description of the chemical properties of the tumour permits the formulation of hypotheses about the biological composition and interactions and the possible causes of its heterogeneous structure. The large amount of information contained in such datasets requires powerful tools for its analysis, visualisation and interpretation. Linear methods for unsupervised dimensionality reduction, such as PCA, are inadequate to capture the complex non-linear relationships present in these data. For this reason, a deep unsupervised neural network based technique, parametric t-SNE, is adopted to map a 3D-DESI-MS dataset from a human colorectal adenocarcinoma biopsy onto a 2-dimensional manifold. This technique allows the identification of clusters not visible with linear methods. The unsupervised clustering of the tumour tissue results in the identification of sub-regions characterised by the abundance of identified metabolites, making possible the formulation of hypotheses to account for their significance and the underlying biological heterogeneity in the tumour.

References

  1. Genome Res. 2003 Nov;13(11):2498-504 - PubMed
  2. IEEE Trans Image Process. 2004 Apr;13(4):600-12 - PubMed
  3. Bioinformatics. 2005 Aug 1;21(15):3201-12 - PubMed
  4. Mol Cell Biochem. 2005 Aug;276(1-2):113-9 - PubMed
  5. Anal Chem. 2005 Oct 1;77(19):6118-24 - PubMed
  6. Proteomics. 2005 Nov;5(16):4107-17 - PubMed
  7. BMC Genomics. 2006 Jun 08;7:142 - PubMed
  8. Mol Cell Proteomics. 2006 Oct;5(10):1975-83 - PubMed
  9. Science. 2006 Jul 28;313(5786):504-7 - PubMed
  10. Nucleic Acids Res. 2007 Jul;35(Web Server issue):W606-12 - PubMed
  11. Rapid Commun Mass Spectrom. 2008 May;22(10):1503-9 - PubMed
  12. J Proteome Res. 2009 Jan;8(1):352-61 - PubMed
  13. J Proteome Res. 2008 Dec;7(12):5230-6 - PubMed
  14. Molecules. 2009 Nov 30;14(12):4892-914 - PubMed
  15. J Proteome Res. 2010 May 7;9(5):2182-90 - PubMed
  16. Nat Rev Cancer. 2010 Sep;10(9):639-46 - PubMed
  17. Anal Chem. 2011 Aug 1;83(15):5864-72 - PubMed
  18. Cancer Inform. 2011 Mar 22;10:65-82 - PubMed
  19. IEEE Trans Pattern Anal Mach Intell. 1979 Feb;1(2):224-7 - PubMed
  20. PLoS One. 2011;6(9):e24913 - PubMed
  21. BMC Bioinformatics. 2011 Nov 09;12:436 - PubMed
  22. Cancer Res. 2012 Feb 1;72(3):645-54 - PubMed
  23. Anal Bioanal Chem. 2012 Jun;403(8):2315-25 - PubMed
  24. J Proteomics. 2012 Aug 30;75(16):5106-10 - PubMed
  25. BMC Bioinformatics. 2012;13 Suppl 16:S11 - PubMed
  26. Nat Rev Cancer. 2013 Jan;13(1):51-65 - PubMed
  27. Anal Chem. 2013 Feb 5;85(3):1415-23 - PubMed
  28. Analyst. 2013 Mar 21;138(6):1682-8 - PubMed
  29. Proc Natl Acad Sci U S A. 2014 Jan 7;111(1):202-7 - PubMed
  30. J Pathol. 2015 Jan;235(1):3-13 - PubMed
  31. Anal Chem. 2015 Apr 21;87(8):4055-62 - PubMed
  32. J Proteome Res. 2016 Mar 4;15(3):683-90 - PubMed
  33. Cell Death Differ. 2016 Jun;23(6):962-78 - PubMed
  34. Nat Rev Clin Oncol. 2017 Jan;14(1):11-31 - PubMed
  35. Proteomics. 2016 Jun;16(11-12):1802-13 - PubMed
  36. Proteomics. 2016 Jun;16(11-12):1814-21 - PubMed
  37. J Proteome Res. 2016 Dec 2;15(12):4265-4276 - PubMed
  38. Proc Natl Acad Sci U S A. 2016 Oct 25;113(43):12244-12249 - PubMed
  39. Clin Exp Immunol. 1998 Jan;111(1):211-8 - PubMed

Publication Types

Grant support