Identifying Disease-Causing Genes Using Microarray Data
Author Information
Author(s): Mohammadi Azadeh, Saraee Mohammad H, Salehi Mansoor
Primary Institution: Isfahan University of Technology
Hypothesis
Can a novel framework combining Fisher method and SVMRFE improve gene selection for cancer diagnosis?
Conclusion
The proposed method predicts marker genes for colon, DLBCL, and prostate cancer with high accuracy.
Supporting Evidence
- The proposed method improved classification performance in terms of accuracy, sensitivity, and specificity.
- The study utilized Gene Ontology to enhance gene selection accuracy.
- The method was tested on colon, DLBCL, and prostate cancer datasets.
Takeaway
This study created a new way to find important genes that cause cancer by using special data analysis techniques.
Methodology
The study combined Fisher method and SVMRFE for gene selection, incorporating Gene Ontology information.
Potential Biases
Selection bias may occur if feature selection is not properly validated during cross-validation.
Limitations
The method's performance may be affected by the small sample size and potential noise in microarray data.
Participant Demographics
The study analyzed datasets from colon cancer, DLBCL, and prostate cancer patients.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website