The combination approach of SVM and ECOC for powerful identification and classification of transcription factor
2008

Using SVM and ECOC to Identify and Classify Transcription Factors

Sample size: 450 publication Evidence: high

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)

10.1186/1471-2105-9-282

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication