Paper No: 32
Blind Matrix Decomposition Techniques to Identify Marker Genes From Microarrays
Author(s): Reinhard
Schachtner, Dominik Lutter, Fabian J. Theis, Elmar W. Lang, Ana
Maria Tomé, Juan Manuel Gorriz Saez, Carlos G. Puntonet
Abstract
Exploratory matrix factorization methods like PCA, ICA
and sparseNMF are applied to identify marker genes and classify gene
expression data sets into different categories for diagnostic purposes or
group genes into functional categories for further investigation of related
regulatory pathways. Gene expression levels of either human breast cancer (HBC)
cell lines [6] or the famous leucemia data set [10] are considered. |
