Refining intra-protein contact prediction by graph analysis
2007
Improving Protein Contact Prediction with Graph Analysis
Sample size: 57
publication
Evidence: moderate
Author Information
Author(s): Milana Frenkel-Morgenstern, Rachel Magid, Eran Eyal, Shmuel Pietrokovski
Primary Institution: Weizmann Institute of Science
Hypothesis
Can graph analysis improve the accuracy of intra-protein contact predictions?
Conclusion
The GARP method significantly enhances the accuracy of basic contact prediction methods.
Supporting Evidence
- The GARP method improved accuracy from 12% to 18% for whole proteins.
- Core region accuracy increased from 24% to 26% using GARP.
- The method is simple to implement and can be applied to various prediction methods.
Takeaway
This study shows a new way to predict how parts of proteins interact, making it easier to understand their structure.
Methodology
The study used graph analysis to refine predictions of intra-protein contacts based on a weighted graph created from predicted contact scores.
Limitations
The improvement in accuracy for core regions was smaller, possibly due to fewer edges available for prediction.
Statistical Information
Statistical Significance
p<0.05
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website