Computational identification of ubiquitylation sites from protein sequences
2008

Predicting Ubiquitylation Sites in Proteins

Sample size: 157 publication 10 minutes Evidence: moderate

Author Information

Author(s): Tung Chun-Wei, Ho Shinn-Ying

Primary Institution: National Chiao Tung University

Hypothesis

This study aims to develop an accurate sequence-based prediction method to identify promising ubiquitylation sites.

Conclusion

The UbiPred system can effectively predict ubiquitylation sites with improved accuracy, helping biologists identify promising sites for experimental verification.

Supporting Evidence

  • The UbiPred system achieved a prediction accuracy of 84.44%.
  • The study identified 23 promising ubiquitylation sites from an independent dataset.
  • The algorithm IPMA improved prediction accuracy from 72.19% to 84.44%.

Takeaway

Scientists created a computer program that helps find important spots on proteins where a small tag called ubiquitin can attach, which is important for many cell functions.

Methodology

The study used a dataset of 157 ubiquitylation sites and 3676 non-ubiquitylation sites, applying support vector machine classifiers and evaluating various features.

Potential Biases

Potential biases may arise from the dataset selection and the reliance on computational methods without extensive experimental validation.

Limitations

The study may not account for all possible ubiquitylation sites, and the prediction accuracy could be affected by the dataset's characteristics.

Statistical Information

P-Value

p<0.05

Statistical Significance

p<0.05

Digital Object Identifier (DOI)

10.1186/1471-2105-9-310

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication