PREDTAP: A System for Predicting Peptide Binding to TAP
Author Information
Author(s): Zhang Guang Lan, Petrovsky Nikolai, Kwoh Chee Keong, August J Thomas, Brusic Vladimir
Primary Institution: Institute for Infocomm Research
Hypothesis
PREDTAP aims to predict peptide binding to the human transporter associated with antigen processing (TAP) using computational methods.
Conclusion
PREDTAP can enhance the prediction of T-cell epitopes by integrating with other prediction systems for MHC class I binding peptides.
Supporting Evidence
- PREDTAP was validated with extensive testing showing good predictive ability.
- The area under the receiver operating characteristic curve (Aroc) for PREDTAP was greater than 0.85.
- PREDTAP integrates multiple computational methods to improve prediction accuracy.
Takeaway
PREDTAP is a computer program that helps scientists figure out which tiny pieces of proteins can be recognized by the immune system.
Methodology
PREDTAP uses artificial neural networks and hidden Markov models to predict peptide binding.
Potential Biases
The model may be biased towards the training dataset and may not generalize well to all peptides.
Limitations
The predictions may not account for all biological variations and alternative pathways.
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