47Glioblastoma gene expression profile diagnostics by the artificial neural networks

  • Authors:

  • A. A. Mekler;I. Knyazeva;D. R. Schwartz;Y. A. Kuperin;V. V. Dmitrenko;V. I. Rymar;V. M. Kavsan

  • Affiliations:

  • Institute of Human Brain, Russian Acad. Sci., Saint Petersburg, Russia;Central Astronomical Observatory at Pulkovo, Russian Acad. Sci., Saint Petersburg, Russia;Saint Petersburg State Polytechnical University, Saint-Petersburg, Russia;Saint Petersburg State University, Saint Petersburg, Russia;Institute of Molecular Biology and Genetics of NASU, Kiev, Ukraine;Institute of Molecular Biology and Genetics of NASU, Kiev, Ukraine;Institute of Molecular Biology and Genetics of NASU, Kiev, Ukraine

  • Venue:
  • Optical Memory and Neural Networks
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

Two artificial neural networks of different types were applied to gene expression profiles in glioblastoma, the most aggressive human brain tumor, and in normal brain tissue. The results of gene expression profiles classification are presented. First method, self organizing maps, gave good discrimination of profiles on the trained map. Another ANN, perceptron, showed a good result of classificatio -- more then 95% of the test data set were successfully classified. Due to high correlations between some gene expression values one can suppose, that number of genes necessary for successful classification may be reduced.