Mining Housekeeping Genes with a Naive Bayes Classifier
Author Information
Author(s): De Ferrari Luna, Aitken Stuart
Primary Institution: School of Informatics, the University of Edinburgh
Hypothesis
Can a Naive Bayes classifier effectively identify housekeeping genes based on physical and functional characteristics?
Conclusion
The classifier successfully identified housekeeping and tissue-specific genes, showing promise for future improvements.
Supporting Evidence
- The classifier achieved a 97% success rate for human housekeeping genes.
- It also showed a 93% success rate for mouse and 90% for fruit fly.
- The method uses existing gene data without the need for costly lab tests.
Takeaway
This study created a computer program that can tell if a gene is a housekeeping gene by looking at its features, without needing to test it in a lab.
Methodology
A Naive Bayes classifier was used to analyze physical characteristics of genes to classify them as housekeeping or tissue-specific.
Potential Biases
Potential biases in the data sources and the classification method could affect the results.
Limitations
The study's findings may not apply universally across all species, and the method relies on existing database information.
Statistical Information
P-Value
p<0.05
Statistical Significance
p<0.05
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website