Critical role of glycosylation in determining the length and structure of T cell epitopes

Abstract

Background: Using a combined in silico approach, we investigated the glycosylation of T cell epitopes and autoantigens. The present systems biology analysis was made possible by currently available databases (representing full proteomes, known human T cell epitopes and autoantigens) as well as glycosylation prediction tools.

Results: We analyzed the probable glycosylation of human T cell epitope sequences extracted from the ImmuneEpitope Database. Our analysis suggests that in contrast to full length SwissProt entries, only a minimal portion of experimentally verified T cell epitopes is potentially N- or O-glycosylated (2.26% and 1.22%, respectively). Bayesian analysis of entries extracted from the Autoantigen Database suggests a correlation between N-glycosylation and autoantigenicity. The analysis of random generated sequences shows that glycosylation probability is also affected by peptide length. Our data suggest that the lack of peptide glycosylation, a feature that probably favors effective recognition by T cells, might have resulted in a selective advantage for short peptides to become T cell epitopes. The length of T cell epitopes is at the intersection of curves determining specificity and glycosylation probability. Thus, the range of length of naturally occurring T cell epitopes may ensure the maximum specificity with the minimal glycosylation probability.

Conclusion: The findings of this bioinformatical approach shed light on fundamental factors that might have shaped adaptive immunity during evolution. Our data suggest that amino acid sequence-based hypo/non-glycosylation of certain segments of proteins might be substantial for determining T cell immunity/autoimmunity.

Figure 1

Average distances of glycosylation sites. The histogram shows frequency distribution of distances between glycosylation sites. It shows a markedly different pattern of N- and O-glycosylation. Most probable O-glycosylation sites are found less than 10 amino acids far from each other. In contrast, distances between probable N-glycosylation sites are highly variable. This indicates that O-glycosylation sites are found in clusters, while conditional N-glycosylation sites are more equally distributed throughout a protein sequence.

Figure 2

The probability of N- and O-glycosylation. Experimentally verified T cell epitopes (filled columns) (found in ImmuneEpitope Database) and randomly selected peptides with identical length from the same protein (gray columns) were analyzed for probable N- and O-glycosylation using Artificial Neural Network-based predictions. Probable glycosylation of ≥ 9 amino acid long peptides is shown in the figure. A peptide was considered to have probable glycosylation if the position of the predicted glycosylation site within the protein coincided with the position of the peptide. Figure 2A shows comparison of the numbers of predicted O-glycosylation sites for each experimentally verified T cell epitope and a randomly selected peptide with identical length from the same protein (Wilcoxon, p = 0.0019). Figure 2B shows comparison of predicted N-glycosylation of randomly selected, length-matched sequences and the functional T cell epitopes (Wilcoxon test, p = 0.00006).

Figure 3

Effect of glycosylation on MHC binding. Binding of peptides derived from SwissProt/UniProtKB entries with SigP to the most common human HLA II alleles was predicted by NetMHCII software. A. HLA alleles showed significant differences in the numbers of predicted binding peptides. B. Proportion of peptides predicted to carry an N-glycosylation site is very different among different MHC II molecules. Most HLA DR alleles are found to be more prone tolerate N-glycosylation, than HLA DP and DQ. C. The frequency of probable O-glycosylation among peptides binding to different HLA alleles is shown on a polar graph.

Figure 4

Number of N-glycosylation sites in autoantigens and non-autoantigenic proteins. Human SwissProt/UniProtKB proteins and known autoantigens (Autoantigen Database) with SigP were examined for the number of probable N-glycosylation sites. For each protein, random control sequences (n = 5) were generated consisting of the same amino acids and of the same length. The mean number of glycosylation sites found in random control sequences was subtracted from the number found in the given protein. The frequency of the difference values is shown for both the autoantigenic and the non-autoantigenic proteins.

Figure 5

Number of bacterial-human exact sequence matches. Human SwissProt/UniProtKB proteins and known autoantigens (Autoantigen Database) containing SigP were scanned for short exact sequence matches with bacterial SwissProt/UniProtKB proteins. The number of these exact sequence matches exponentially decreases as their length grows. Black dots represent data obtained from the analysis of 140 337 bacterial proteins, while empty circles represent estimations based on analysis of 4000 randomly selected bacterial proteins. Data indicate that from ≥ 9 amino acid peptide lengths the number of bacterial-human sequence matches falls below 10⁵.

Figure 6

Autoantigenic sequences with bacterial-human sequence matches. The frequency of proteins that contain a given number of bacterial-human exact sequence matches (min. 9 aa) is shown for autoantigens and non-autoantigenic SwissProt entries. Significantly more autoantigens have at least one bacterial-human exact sequence match than non-autoantigenic human SwissProt entries. Furthermore, autoantigens also bear significantly more matches as compared to non-autoantigenic ones (p < 0.05, Kolmogorov-Smirnov).