Cancer cells undergo metabolic changes that contribute to tumorigenesis, which can be determined using metabolomics data produced by techniques such as nuclear magnetic resonance and mass spectroscopy, and analyzed through statistical and machine learning methods. Since these data represent well the metabolic phenotype of these cells, they are very relevant in cancer research, to better understand tumour cells metabolism and help in efforts of biomarker and drug target discovery. This mini-review focuses on data analysis methods that are commonly used to extract knowledge from cancer metabolomics data, such as univariate analysis and supervised and unsupervised multivariate data analysis, including clustering and machine learning.
CITATION STYLE
Cardoso, S., Baptista, D., Santos, R., & Rocha, M. (2019). A review on metabolomics data analysis for cancer applications. In Advances in Intelligent Systems and Computing (Vol. 803, pp. 157–165). Springer Verlag. https://doi.org/10.1007/978-3-319-98702-6_19
Mendeley helps you to discover research relevant for your work.