Identification of a small optimal subset of CpG sites as bio-markers from high-throughput DNA methylation profiles
2008

Identifying DNA Methylation Biomarkers for Lung Cancer

Sample size: 46 publication 10 minutes Evidence: moderate

Author Information

Author(s): Meng Hailong, Murrelle Edward L, Li Guoya

Primary Institution: ClearPoint Resources Inc.

Hypothesis

Can a small number of signature CpG sites be sufficient to classify lung cancer and normal tissue samples?

Conclusion

The study demonstrates that a small number of signature CpG sites can effectively classify lung cancer tissue from normal lung tissue.

Supporting Evidence

  • A small number of signature CpG sites can classify lung cancer and normal tissue samples.
  • The FW_SVM method achieved high predictive accuracy with a compact feature size.
  • Two specific CpG sites were identified as effective biomarkers for lung cancer.

Takeaway

Scientists found that just a few specific DNA markers can help tell the difference between lung cancer and normal lung tissue.

Methodology

A two-stage feature selection method combining filter and wrapper approaches was used to identify signature CpG sites from high-throughput DNA methylation data.

Potential Biases

Potential bias due to the small sample size and the complexity of disease mechanisms.

Limitations

The findings are based on a relatively small dataset, and further validation in larger datasets is needed.

Participant Demographics

The study included 19 male and 25 female cell lines, 37 human embryonic stem cells, and 23 lung adenocarcinoma samples.

Statistical Information

P-Value

0.005

Statistical Significance

p<0.005

Digital Object Identifier (DOI)

10.1186/1471-2105-9-457

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication