Large-scale validation of methods for cytotoxic T-lymphocyte epitope prediction
2007

Validation of CTL Epitope Prediction Methods

Sample size: 216 publication Evidence: moderate

Author Information

Author(s): Mette V. Larsen, Claus Lundegaard, Kasper Lamberth, Soren Buus, Ole Lund, Morten Nielsen

Primary Institution: Technical University of Denmark

Hypothesis

How does the predictive performance of NetCTL-1.2 compare to other CTL epitope prediction methods?

Conclusion

NetCTL-1.2 shows higher predictive performance than EpiJen, MAPPP, MHC-pathway, and WAPP, although some comparisons are not statistically significant.

Supporting Evidence

  • NetCTL-1.2 has a higher predictive performance than EpiJen, MAPPP, MHC-pathway, and WAPP on all performance measures.
  • The higher performance of NetCTL-1.2 compared to EpiJen and MHC-pathway is not statistically significant on all measures.
  • NetCTL-1.2 achieved a sensitivity among the 5% top-scoring peptides above 0.72.

Takeaway

This study tested different methods to predict immune responses to viruses, finding that one method, NetCTL-1.2, works better than others.

Methodology

The study compared the performance of five CTL epitope prediction methods using two evaluation datasets of known HIV CTL epitopes.

Limitations

The performance measures may not be applicable to all methods due to differences in output formats.

Statistical Information

P-Value

0.02

Statistical Significance

p<0.05

Digital Object Identifier (DOI)

10.1186/1471-2105-8-424

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication