A computational method based on support vector machines with a weighted string kernel to predict peptide immunogenicity and identify important recognition positions. POPISK yields a mean 10-fold cross-validation accuracy of 68% in predicting T-cell reactivity of HLA-A2-binding peptides. POPISK is capable of predicting immunogenicity with scores that can also correctly predict the change in T-cell reactivity related to point mutations in epitopes reported in previous studies using crystal structures.
School of Pharmacy, Kaohsiung Medical University, Kaohsiung, Taiwan; Institute of Bioinformatics and Systems Biology, National Chiao Tung University, Hsinchu, Taiwan; Center for Bioinformatics Tübingen, Eberhard Karls University Tübingen, Tübingen, Germany; Department of Biological Science and Technology, National Chiao Tung University, Hsinchu, Taiwan
POPISK funding source(s)
This work was supported by the National Science Council of Taiwan (NSC 100-2627-B-009-004) and Deutsche Forschungsgemeinschaft (SFB 685/B1).