Deep learning and 3D-DESI imaging reveal the hidden metabolic heterogeneity of cancer
Royal Society of Chemistry
MetadataShow full item record
Inglese, P., McKenzie, J., Mroz, A., Kinross, J., Veselkov, K., Holmes, E., Takats, Z., et al. (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
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.
We would like to acknowledge funding from the Department of Health, National Institute for Health Research, Bowel and Cancer Research, the European Research Council, the Wellcome Trust and the Imperial National Institute of Health Biomedical Research Centre for funding DESI research. Mr Inglese is supported by the Imperial College Stratified Medicine Graduate Training Programme in Systems Medicine and Spectroscopic Profiling (STRATiGRAD). We would like to acknowledge Prof Robert Goldin and Dr Abigail Speller for the manual annotation of the H&E stained images. This work used the computing resources of the UK MEDical BIOinformatics partnership - aggregation, integration, visualisation and analysis of large, complex data (UK MED-BIO) which is supported by the Medical Research Council [grant number MR/L01632X/1].
External DOI: https://doi.org/10.1039/C6SC03738K
This record's URL: https://www.repository.cam.ac.uk/handle/1810/263248
Attribution-NonCommercial 4.0 International