Computational MHC-I epitope predictor identifies 95% of experimentally mapped HIV-1 clade A and D epitopes in a Ugandan cohort

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.

Keywords: Artificial neural network; Epitope mapping; HIV-1; In-silico; MHCflurry1.2.0 and NetCTL1.2; NetMHCpan4.0.; T-cell.

Fig. 1

ELISPOT peptide consort; the experimental peptide mapping data was generated by culture ELISPOT of multiple peptide pools tested in duplicate wells per time point, followed by ex-vivo ELISPOT of potential candidate epitopes. To experimentally map a single time point required at least 541 assay wells

Fig. 2

NetMHCpan Binder Predictions. a Using our experimental peptide sequences as inputs into NetMHCpan4.0 to predict epitopes for 22 HLA types represented in the 6 HIV-1 Infected people, a heatmap showing absolute counts of computationally predicted 9-mer binders against HIV-1 genes was constructed. The dendrogram shows the nearest similarity for the number of predicted counts across HLA types; b the length of the HIV-1 protein sequence plotted against the absolute number of NetMHCpan4.0 predicted 9mer binders showing a positive correlation (Spearman’s correlation coefficient, r_s = 0.88). The number of distinct predictions is dependent on the length of the HIV-1 sequence; c comparison of HIV-1 clade A and D absolute number of NetMHCpan4.0 predicted 9mer binders per HIV-1 gene for the wet experiment test peptide sequences. The algorithm predicted more binders for clade D than clade A

Fig. 3

Computational epitope prediction. NetMHCpan4.0 set length plotted against the number of predicted binders per HLA type shows that the number of predictions reduces as the input set length increases. The dotted line is the trend line, whereas the solid line is the line of best fit. The core 9mer epitope sequence was similar across 9mer through 14mer set length except for one 14-mer peptide (hit 72 in Table 2)

Fig. 4

Early versus Late Peptides. Experimentally mapped peptides at baseline (n = 34) and at least 12 months later (n = 34) were compared using the 9-mer computational NetMHCpan4.0 scores of the hits. The lower the computational score the stronger the predicted binding. Late peptides were significantly stronger binders than early peptides (Wilcoxon signed rank test, p = 0.0000005)

Fig. 5

ROC plot. False versus true positive rate for all 9-mer and a single 14-mer test peptides across the 22 test HLA class I types. The diagonal line shows the random guess whereas the red curve shows the observed experimentally mapped epitopes versus the NetMHCpan4.0 expected predictions