Recursive Cluster Elimination (RCE) for classification and feature selection from gene expression data
2007

Recursive Cluster Elimination for Gene Classification

Sample size: 72 publication 10 minutes Evidence: high

Author Information

Author(s): Yousef Malik, Jung Segun, Showe Louise C, Showe Michael K

Primary Institution: The Wistar Institute

Hypothesis

Can recursive cluster elimination improve gene selection and classification accuracy in gene expression studies?

Conclusion

SVM-RCE provides improved classification accuracy with complex microarray datasets compared to traditional methods.

Supporting Evidence

  • SVM-RCE showed improved accuracy over SVM-RFE and PDA-RFE in multiple datasets.
  • The method effectively identifies clusters of correlated genes that enhance classification performance.
  • SVM-RCE allows for the removal of less informative gene clusters, improving overall classification accuracy.

Takeaway

This study shows a new way to group genes together to help classify diseases better, which is like putting similar toys in the same box to find them easily.

Methodology

The study used a novel method called SVM-RCE that combines K-means clustering and Support Vector Machines for gene classification.

Potential Biases

The study may be influenced by the selection of datasets and the inherent biases in gene expression data.

Limitations

The method's performance may vary based on the choice of initial clusters and the datasets used.

Participant Demographics

The study involved datasets from patients with leukemia, prostate cancer, and CTCL, among others.

Statistical Information

P-Value

p<0.05

Confidence Interval

null

Statistical Significance

p<0.05

Digital Object Identifier (DOI)

10.1186/1471-2105-8-144

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication