In my talk, I will give an overview about modern machine learning techniques for analysing the huge number of features in metabolite data. I will introduce Independent Component Analysis (ICA) as a useful alternative to classical Principal Component Analysis. I will show in which cases a Support Vector Machine (SVM) can be appropriate for biomarker detection. And I will talk about time course analysis and how to analysis and visualize the nonlinear data structure. This will be completed by showing some examples in Matlab.
|Citation:||Scholz, M. (2012). Visualization of metabolomics data. In: 2nd Workshop on Holistic Analytical Methods for Systems Biology Studies, Athens, Greece, November 11-12, 2012: 16. handle: http://hdl.handle.net/10449/22017|
|Organization unit:||Computational Biology # CRI_2011-JAN2016|
|Title:||Visualization of metabolomics data|
|Nature of content:||Abstract in Atti di convegno/Conference abstract|
|Appears in Collections:||03 - Conference object|