A New Model for Analyzing Microarray Data
Author Information
Author(s): Ge Huanying, Cheng Chao, Li Lei M
Primary Institution: University of Southern California
Hypothesis
Can a new Probe-Treatment-Reference (PTR) model improve the normalization and summarization of microarray data?
Conclusion
The PTR method effectively reduces variations in non-differentially expressed genes and enhances the detection power of differentially expressed genes.
Supporting Evidence
- The PTR method reduces variations of non-differentially expressed genes.
- The method increases the detection power of differentially expressed genes.
- The study evaluates the PTR method using two Affymetrix spike-in data sets.
Takeaway
This study introduces a new way to analyze gene expression data that helps scientists get more accurate results by using multiple references.
Methodology
The study uses a new PTR model that integrates normalization and summarization by allowing multiple references and employs the Least Absolute Deviations (LAD) approach for parameter estimation.
Potential Biases
Potential bias may arise from the selection of reference arrays.
Limitations
The method's performance may vary with different sample sizes and types of microarray data.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website