Signature Evaluation Tool (SET): A Tool for Evaluating Gene Expression Signatures
Author Information
Author(s): Jen Chih-Hung, Yang Tsun-Po, Tung Chien-Yi, Su Shu-Han, Lin Chi-Hung, Hsu Ming-Ta, Wang Hsei-Wei
Primary Institution: National Yang-Ming University
Hypothesis
A tool to evaluate the discrimination power of candidate genes is in high demand by clinical researchers.
Conclusion
SET is a valuable tool for rapidly narrowing down candidate diagnostic markers from numerous signature genes.
Supporting Evidence
- SET can reduce the number of genes needed for accurate cancer diagnosis.
- The tool allows for the visualization of prediction strength for gene signatures.
- SET has been validated with multiple datasets showing consistent results.
Takeaway
SET helps scientists find important genes that can tell different types of cancer apart, making it easier to choose the right treatment.
Methodology
SET uses a weighted voting algorithm and cross-validation to evaluate gene signatures.
Limitations
SET is a tool for signature evaluation rather than a machine learning tool for building an optimized prediction rule.
Participant Demographics
The study involved 295 breast cancer samples and 179 colon cancer samples.
Statistical Information
P-Value
<0.001
Statistical Significance
p<0.001
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website