Funckenstein: A New Method for Predicting Gene Function
Author Information
Author(s): Tian Weidong, Zhang Lan V, Taşan Murat, Gibbons Francis D, King Oliver D, Park Julie, Wunderlich Zeba, Cherry J Michael, Roth Frederick P
Primary Institution: Harvard Medical School
Hypothesis
Can combining guilt-by-profiling and guilt-by-association improve predictions of gene function in Saccharomyces cerevisiae?
Conclusion
Funckenstein outperforms previous strategies in predicting gene functions, especially for specific functions.
Supporting Evidence
- Funckenstein was compared with a previous method and showed improved performance.
- The method was applied to 2,455 Gene Ontology terms.
- Cross-validation demonstrated high precision in predictions.
- Funckenstein achieved a higher area under the precision-recall curve than previous methods.
Takeaway
Funckenstein is a smart tool that helps scientists guess what genes do by looking at how they relate to each other and their characteristics.
Methodology
The study used a combination of guilt-by-profiling and guilt-by-association methods to predict gene functions based on large datasets.
Potential Biases
Potential overfitting due to the use of similar evidence types in both classifiers.
Limitations
The predictions may not be accurate for dubious genes due to lack of experimental data.
Participant Demographics
The study focused on protein-coding genes in Saccharomyces cerevisiae.
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