Weighted analysis of general microarray experiments
2007

Improved Method for Analyzing Microarray Data

Sample size: 40 publication 10 minutes Evidence: high

Author Information

Author(s): Anders Sjögren, Erik Kristiansson, Mats Rudemo, Olle Nerman

Primary Institution: Chalmers University of Technology

Hypothesis

Can the WAME method be generalized to handle both one- and two-channel microarray datasets?

Conclusion

The WAME procedure is generalized to handle unpaired designs and is shown to produce more accurate p-values compared to traditional methods.

Supporting Evidence

  • WAME detects unequal variances and correlations in microarray data.
  • WAME produces more accurate p-values than traditional methods.
  • The method is available as an R-package for wider use.
  • Two public datasets were analyzed to validate the method's effectiveness.

Takeaway

This study created a new way to analyze gene data that works better when the samples aren't paired, helping scientists get more accurate results.

Methodology

The study extended the WAME method to analyze one-channel datasets by estimating variances and covariances for each sample.

Potential Biases

Potential bias due to the assumption of no regulated genes in the estimation process.

Limitations

The method may produce conservative p-values when many genes are differentially expressed.

Participant Demographics

Included biopsies from 20 human hearts with normal sinus rhythm and 10 hearts with permanent atrial fibrillation, as well as lung tissue from smokers with varying emphysema severity.

Statistical Information

P-Value

p<0.05

Statistical Significance

p<0.05

Digital Object Identifier (DOI)

10.1186/1471-2105-8-387

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication