Using SVM and ECOC to Identify and Classify Transcription Factors
Author Information
Author(s): Zheng Guangyong, Qian Ziliang, Yang Qing, Wei Chaochun, Xie Lu, Zhu Yangyong, Li Yixue
Primary Institution: Fudan University
Hypothesis
Can the combination of SVM and ECOC improve the identification and classification accuracy of transcription factors?
Conclusion
The combination of SVM and ECOC significantly improves the accuracy of transcription factor classification.
Supporting Evidence
- The SVM method achieved an identification success rate of 88.22%.
- The ECOC algorithm improved classification accuracy significantly compared to one-against-all methods.
- The study constructed a web server for easy access to the developed tools.
Takeaway
This study created a tool that helps scientists find and sort proteins that control gene activity, making it easier to understand how genes work.
Methodology
The study used support vector machine (SVM) for identifying transcription factors and error-correcting output coding (ECOC) for classifying them into four classes.
Limitations
The tools cannot predict proteins without any annotated protein domains or functional sites.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website