Javascript is not activated in your browser. This website needs javascript activated to work properly.
You are here

Classification and diagnostic prediction of cancers using gene expression profiling and artificial neural networks

  • J Khan
  • JS Wei
  • Markus Ringnér
  • Lao Saal
  • M Ladanyi
  • F Westermann
  • F Berthold
  • M Schwab
  • CR Antonescu
  • Carsten Peterson
  • PS Meltzer
Publishing year: 2001
Language: English
Pages: 673-679
Publication/Series: Nature Medicine
Volume: 7
Issue: 6
Document type: Journal article
Publisher: Nature Publishing Group

Abstract english

The purpose of this study was to develop a method of classifying cancers to specific diagnosticcategories based on their gene expression signatures using artificial neural networks (ANNs).We trained the ANNs using the small, round blue-cell tumors (SRBCTs) as a model. These cancersbelong to four distinct diagnostic categories and often present diagnostic dilemmas in clinicalpractice. The ANNs correctly classified all samples and identified the genes most relevant to theclassification. Expression of several of these genes has been reported in SRBCTs, but most havenot been associated with these cancers. To test the ability of the trained ANN models to recognizeSRBCTs, we analyzed additional blinded samples that were not previously used for the trainingprocedure, and correctly classified them in all cases. This study demonstrates the potentialapplications of these methods for tumor diagnosis and the identification of candidate targets fortherapy.


  • Biophysics


  • ISSN: 1546-170X
Markus Ringnér
E-mail: markus [dot] ringner [at] biol [dot] lu [dot] se

Research engineer

Molecular Cell Biology


Sölvegatan 35, Lund