Discovery of dominant and dormant genes from expression data using a novel generalization of SNR for multi-class problems
2008

Identifying Key Genes in Cancer Using New Methods

Sample size: 63 publication Evidence: high

Author Information

Author(s): Tsai Yu-Shuen, Lin Chin-Teng, Tseng George C, Chung I-Fang, Pal Nikhil Ranjan

Primary Institution: Institute of Biomedical Informatics, National Yang-Ming University, Taipei, Taiwan

Hypothesis

Can new generalizations of the Signal-to-Noise Ratio (SNR) effectively identify dominant and dormant genes in multiclass cancer data?

Conclusion

The study successfully identifies a small set of dominant and dormant biomarkers that can be used for reliable diagnostic prediction systems.

Supporting Evidence

  • The study proposes innovative generalizations of SNR for multiclass cancer discrimination.
  • The new indices can find biologically meaningful genes that act as biomarkers.
  • The dominant genes are usually easy to find, while good dormant genes may require stronger constraints.

Takeaway

Researchers found important genes that can help doctors diagnose different types of cancer more easily.

Methodology

The study used four multiclass cancer datasets and six machine learning tools to evaluate the effectiveness of the new indices for identifying biomarkers.

Limitations

The availability of strong dormant genes may be limited, requiring more dormant genes than dominant genes for effective classification.

Statistical Information

P-Value

0

Digital Object Identifier (DOI)

10.1186/1471-2105-9-425

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication