Classifying Transcription Factor Targets in Yeast
Author Information
Author(s): Dustin T Holloway, Kon Mark, Charles DeLisi
Primary Institution: Boston University
Hypothesis
Can a supervised-learning approach improve the identification of transcription factor targets and reveal biological features contributing to regulation?
Conclusion
The study successfully predicts new transcription factor targets and provides insights into their regulatory functions.
Supporting Evidence
- The method predicted targets for 163 transcription factors, revealing new insights into their regulatory roles.
- Predictions were made available on a web server for further analysis.
- Statistical enrichment was observed in biological processes related to carbon metabolism and energy generation.
Takeaway
The researchers figured out how to find new targets for proteins that control gene activity in yeast, helping us understand how genes work together.
Methodology
The study used a supervised learning approach with support vector machines to classify transcription factor targets based on various genomic datasets.
Potential Biases
The choice of negative training sets may introduce bias, as it is difficult to determine which genes are truly not bound by transcription factors.
Limitations
The predictions may contain false positives, and the biological significance of some predicted interactions needs further validation.
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