Abstract
BACKGROUND: Identifying immunogens that induce HIV-1-specific immune responses is a lengthy process that can benefit from computational methods, which predict T-cell epitopes for various HLA types. METHODS: We tested the performance of the NetMHCpan4.0 computational neural network in re-identifying 93 T-cell epitopes that had been previously independently mapped using the whole proteome IFN-γ ELISPOT assays in 6 HLA class I typed Ugandan individuals infected with HIV-1 subtypes A1 and D. To provide a benchmark we compared the predictions for NetMHCpan4.0 to MHCflurry1.2.0 and NetCTL1.2. RESULTS: NetMHCpan4.0 performed best correctly predicting 88 of the 93 experimentally mapped epitopes for a set length of 9-mer and matched HLA class I alleles. Receiver Operator Characteristic (ROC) analysis gave an area under the curve (AUC) of 0.928. Setting NetMHCpan4.0 to predict 11-14mer length did not improve the prediction (37-79 of 93 peptides) with an inverse correlation between the number of predictions and length set. Late time point peptides were significantly stronger binders than early peptides (Wilcoxon signed rank test: p = 0.0000005). MHCflurry1.2.0 similarly predicted all but 2 of the peptides that NetMHCpan4.0 predicted and NetCTL1.2 predicted only 14 of the 93 experimental peptides. CONCLUSION: NetMHCpan4.0 class I epitope predictions covered 95% of the epitope responses identified in six HIV-1 infected individuals, and would have reduced the number of experimental confirmatory tests by > 80%. Algorithmic epitope prediction in conjunction with HLA allele frequency information can cost-effectively assist immunogen design through minimizing the experimental effort.