Document Detail


Integration of pathway knowledge into a reweighted recursive feature elimination approach for risk stratification of cancer patients.
MedLine Citation:
PMID:  20591905     Owner:  NLM     Status:  MEDLINE    
Abstract/OtherAbstract:
MOTIVATION: One of the main goals of high-throughput gene-expression studies in cancer research is to identify prognostic gene signatures, which have the potential to predict the clinical outcome. It is common practice to investigate these questions using classification methods. However, standard methods merely rely on gene-expression data and assume the genes to be independent. Including pathway knowledge a priori into the classification process has recently been indicated as a promising way to increase classification accuracy as well as the interpretability and reproducibility of prognostic gene signatures. RESULTS: We propose a new method called Reweighted Recursive Feature Elimination. It is based on the hypothesis that a gene with a low fold-change should have an increased influence on the classifier if it is connected to differentially expressed genes. We used a modified version of Google's PageRank algorithm to alter the ranking criterion of the SVM-RFE algorithm. Evaluations of our method on an integrated breast cancer dataset comprising 788 samples showed an improvement of the area under the receiver operator characteristic curve as well as in the reproducibility and interpretability of selected genes. AVAILABILITY: The R code of the proposed algorithm is given in Supplementary Material.
Authors:
Marc Johannes; Jan C Brase; Holger Fröhlich; Stephan Gade; Mathias Gehrmann; Maria Fälth; Holger Sültmann; Tim Beissbarth
Related Documents :
19618375 - Analysis of the relationship between longitudinal gene expressions and ordered categori...
17570735 - Dgem--a microarray gene expression database for primary human disease tissues.
15013775 - Multi-class cancer subtype classification based on gene expression signatures with reli...
17441605 - New criteria for selecting differentially expressed genes.
3164475 - Effect of in vitro dna methylation on beta-globin gene expression.
20438845 - Overexpression and purification of pwl2d, a mutant of the effector protein pwl2 from ma...
Publication Detail:
Type:  Comparative Study; Journal Article; Research Support, Non-U.S. Gov't     Date:  2010-06-30
Journal Detail:
Title:  Bioinformatics (Oxford, England)     Volume:  26     ISSN:  1367-4811     ISO Abbreviation:  Bioinformatics     Publication Date:  2010 Sep 
Date Detail:
Created Date:  2010-08-18     Completed Date:  2010-09-30     Revised Date:  -    
Medline Journal Info:
Nlm Unique ID:  9808944     Medline TA:  Bioinformatics     Country:  England    
Other Details:
Languages:  eng     Pagination:  2136-44     Citation Subset:  IM    
Affiliation:
German Cancer Research Center, Cancer Genome Research, Im Neuenheimer Feld 280, 69120 Heidelberg. m.johannes@DKFZ-heidelberg.de
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:
Algorithms*
Artificial Intelligence
Breast Neoplasms / diagnosis,  genetics*,  metabolism
Female
Gene Expression Profiling / methods*
Gene Expression Regulation, Neoplastic
Humans
Prognosis
ROC Curve
Receptor, erbB-2 / genetics
Risk Factors
Chemical
Reg. No./Substance:
EC 2.7.10.1/ERBB2 protein, human; EC 2.7.10.1/Receptor, erbB-2

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


Previous Document:  MSMS: a coalescent simulation program including recombination, demographic structure and selection a...
Next Document:  Biological knowledge bases using Wikis: combining the flexibility of Wikis with the structure of dat...