Inferring Protein Function Using Native Disorder
Author Information
Author(s): Anna Lobley, Mark B. Swindells, Christine A. Orengo, David T. Jones
Primary Institution: University College London
Hypothesis
The study investigates the contribution of protein disorder in predicting protein function using Gene Ontology categories.
Conclusion
The study demonstrates that incorporating protein disorder information significantly improves the accuracy of predicting protein functions.
Supporting Evidence
- Disordered regions are essential for the function of many proteins.
- The study found that 31 Molecular Function categories and 33 Biological Process categories were significantly enriched in disordered proteins.
- The inclusion of disorder features improved prediction accuracies for many function categories.
Takeaway
This study shows that parts of proteins that are not structured can help scientists guess what those proteins do.
Methodology
The study used Support Vector Machine classifiers to analyze the contribution of disordered regions in predicting protein functions based on Gene Ontology categories.
Limitations
The predictions of disordered residues were not experimentally confirmed, which may affect the accuracy of the results.
Statistical Information
P-Value
<0.001
Statistical Significance
p<0.001
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website