Combining gene expression and interaction network data to improve kidney lesion score prediction

  • Authors:
  • Davoud Moulavi;Mohsen Hajiloo;Jorg Sander;Philip F. Halloran;Russell Greiner

  • Affiliations:
  • Department of Computing Science, University of Alberta, Edmonton, Alberta T6G 2E8, Canada.;Alberta Innovates Center for Machine Learning, Department of Computing Science, University of Alberta, Edmonton, Alberta T6G 2E8, Canada.;Department of Computing Science, University of Alberta, Edmonton, Alberta T6G 2E8, Canada.;Alberta Transplant Applied Genomics Center, 250, Heritage Medical Research Centre, University of Alberta, Edmonton, Alberta T6G 2S2, Canada.;Alberta Innovates Center for Machine Learning, Department of Computing Science, University of Alberta, Edmonton, Alberta T6G 2E8, Canada

  • Venue:
  • International Journal of Bioinformatics Research and Applications
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

Current method of diagnosing kidney rejection based on histopathology of renal biopsies in form of lesion scores is error-prone. Researchers use gene expression microarrays in combination of machine learning to build better kidney rejection predictors. However the high dimensionality of data makes this task challenging and compels application of feature selection methods. We present a method for predicting lesions using combination of statistical and biological feature selection methods along with an ensemble learning technique. Results show that combining highly interacting genes (Hub Genes) from protein-protein interaction network with genes selected by squared t-test method brings the most accurate kidney lesion score predictor.