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.
Scholz, M.U. (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
Visualization of metabolomics data
Scholz, Matthias Uwe
2012-01-01
Abstract
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.File | Dimensione | Formato | |
---|---|---|---|
2012 scholz.pdf
accesso aperto
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
54.26 kB
Formato
Adobe PDF
|
54.26 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.