Predicting Peptide Binding Affinities to MHC Molecules Using a Modified Semi-Empirical Scoring Function
2011

Predicting Peptide Binding to MHC Molecules

Sample size: 20 publication Evidence: moderate

Author Information

Author(s): Liao Webber W., Arthur Jonathan W.

Primary Institution: Sydney Medical School, University of Sydney

Hypothesis

Can a modified semi-empirical scoring function improve the prediction of peptide-MHC binding affinities?

Conclusion

The modified scoring function shows improved predictive capability for some MHC class I alleles but struggles with class II alleles like HLA-DR15.

Supporting Evidence

  • The modified scoring function outperformed the original implementation for class I alleles.
  • The study identified that using multiple reference structures improves prediction accuracy.
  • The method struggled to predict binding affinities for the HLA-DR15 allele.

Takeaway

The study tries to predict how well certain proteins can stick to immune system molecules, which is important for understanding diseases like multiple sclerosis.

Methodology

The study used a modified Fresno semi-empirical scoring function and open-source software to predict peptide binding affinities to MHC molecules.

Limitations

The predictive capacity of the method remains poor for class II MHC molecules despite using a large set of binding data.

Digital Object Identifier (DOI)

10.1371/journal.pone.0025055

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication