Document Detail

Combining gene expression and interaction network data to improve kidney lesion score prediction.
MedLine Citation:
PMID:  22450270     Owner:  NLM     Status:  In-Data-Review    
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.
Davoud Moulavi; Mohsen Hajiloo; Jorg Sander; Philip F Halloran; Russell Greiner
Publication Detail:
Type:  Journal Article    
Journal Detail:
Title:  International journal of bioinformatics research and applications     Volume:  8     ISSN:  1744-5485     ISO Abbreviation:  Int J Bioinform Res Appl     Publication Date:  2012  
Date Detail:
Created Date:  2012-03-27     Completed Date:  -     Revised Date:  -    
Medline Journal Info:
Nlm Unique ID:  101253758     Medline TA:  Int J Bioinform Res Appl     Country:  Switzerland    
Other Details:
Languages:  eng     Pagination:  54-66     Citation Subset:  IM    
Department of Computing Science, University of Alberta, Edmonton, Alberta T6G 2E8, Canada.
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine

Previous Document:  Large margin classifiers and Random Forests for integrated biological prediction.
Next Document:  Detecting molecular selection on single amino acid replacements.