Blind matrix decomposition techniques to identify marker genes from microarrays

  • Authors:

  • R. Schachtner;D. Lutter;F. J. Theis;E. W. Lang;A. M. Tomé;J. M. Gorriz Saez;C. G. Puntonet

  • Affiliations:

  • Institute of Biophysics, University of Regensburg, Regensburg, Germany;Institute of Biophysics, University of Regensburg, Regensburg, Germany;Institute of Biophysics, University of Regensburg, Regensburg, Germany;Institute of Biophysics, University of Regensburg, Regensburg, Germany;DETI / IEETA, Universidade de Aveiro, Aveiro, Portugal;DATC / ETSI, Universidad de Granada, Granada, Spain;DATC / ETSI, Universidad de Granada, Granada, Spain

  • Venue:
  • ICA'07 Proceedings of the 7th international conference on Independent component analysis and signal separation
  • Year:
  • 2007

Quantified Score

Hi-index 0.00

Visualization

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.