Comparative evaluation of gene-set analysis methods
2007

Comparative Evaluation of Gene-Set Analysis Methods

Sample size: 10 publication Evidence: moderate

Author Information

Author(s): Liu Qi, Dinu Irina, Adewale Adeniyi J, Potter John D, Yasui Yutaka

Primary Institution: University of Alberta

Hypothesis

How do the statistical performances of Global Test, ANCOVA Global Test, and SAM-GS compare in gene-set analysis?

Conclusion

Standardization improves the performance of all three methods, with SAM-GS showing slightly higher power.

Supporting Evidence

  • Global Test and ANCOVA Global Test require standardization for proper performance.
  • SAM-GS showed slightly higher power in detecting significant gene sets.
  • Permutation-based inference is recommended for accurate p-value calculation.
  • Standardization led to similar results across all three methods.

Takeaway

This study looks at different ways to analyze gene data to see how well they work, especially when we make sure the data is standardized.

Methodology

The study compared three gene-set analysis methods using simulation experiments and real-world microarray datasets.

Limitations

The study primarily focused on binary phenotypes and did not explore other types of phenotypes extensively.

Statistical Information

P-Value

<0.001

Statistical Significance

p<0.001

Digital Object Identifier (DOI)

10.1186/1471-2105-8-431

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication