Gene and pathway identification with Lp penalized Bayesian logistic regression
2008

Identifying Genes and Pathways Related to Cancer Using Bayesian Logistic Regression

Sample size: 98 publication 10 minutes Evidence: moderate

Author Information

Author(s): Liu Zhenqiu, Gartenhaus Ronald B, Tan Ming, Jiang Feng, Jiao Xiaoli

Primary Institution: University of Maryland Greenebaum Cancer Center

Hypothesis

Can a Bayesian approach improve the identification of cancer-related genes and pathways compared to traditional methods?

Conclusion

The proposed methods can effectively identify important genes and pathways related to cancer and build a parsimonious model for future patient predictions.

Supporting Evidence

  • The proposed algorithm (BLpLog) is significantly faster than traditional methods.
  • The study identified 11 genes with high differentiation in patients with and without metastases.
  • The integrated algorithm effectively identified cancer-related pathways using DAVID.

Takeaway

This study created a new way to find important genes for cancer by looking at how genes work together, even if their individual changes are small.

Methodology

The study used a Bayesian logistic regression model to identify cancer-related genes and pathways from gene expression data.

Potential Biases

The methods may favor genes with larger expression changes, potentially overlooking important regulatory genes.

Limitations

The study's findings may be limited by the small sample size and the potential for missing data in gene expression levels.

Participant Demographics

The study included 98 primary breast cancer patients, aged under 55, with varying disease outcomes.

Statistical Information

P-Value

0.976

Statistical Significance

p<0.05

Digital Object Identifier (DOI)

10.1186/1471-2105-9-412

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication