Mass spectrometry of human leukocyte antigen class I peptidomes reveals strong effects of protein abundance and turnover on antigen presentation

Abstract

HLA class I molecules reflect the health state of cells to cytotoxic T cells by presenting a repertoire of endogenously derived peptides. However, the extent to which the proteome shapes the peptidome is still largely unknown. Here we present a high-throughput mass-spectrometry-based workflow that allows stringent and accurate identification of thousands of such peptides and direct determination of binding motifs. Applying the workflow to seven cancer cell lines and primary cells, yielded more than 22,000 unique HLA peptides across different allelic binding specificities. By computing a score representing the HLA-I sampling density, we show a strong link between protein abundance and HLA-presentation (p < 0.0001). When analyzing overpresented proteins - those with at least fivefold higher density score than expected for their abundance - we noticed that they are degraded almost 3 h faster than similar but nonpresented proteins (top 20% abundance class; median half-life 20.8h versus 23.6h, p < 0.0001). This validates protein degradation as an important factor for HLA presentation. Ribosomal, mitochondrial respiratory chain, and nucleosomal proteins are particularly well presented. Taking a set of proteins associated with cancer, we compared the predicted immunogenicity of previously validated T-cell epitopes with other peptides from these proteins in our data set. The validated epitopes indeed tend to have higher immunogenic scores than the other detected HLA peptides. Remarkably, we identified five mutated peptides from a human colon cancer cell line, which have very recently been predicted to be HLA-I binders. Altogether, we demonstrate the usefulness of combining MS-analysis with immunogenesis prediction for identifying, ranking, and selecting peptides for therapeutic use.

Fig. 1.

Schematic overview of HLA-I peptidomics. A, Sample preparation. HLA-I complexes were immunoaffinity purified from cells lysates using anti-HLA-I (W6–32) antibody cross-linked to Protein-A Sepharose beads. HLA-I peptides were purified from the heavy chain based on their hydrophobicity using a C-18 column. B, Liquid chromatography and mass spectrometry. The enriched mixtures of HLA-I peptides were measured on a quadrupole Orbitrap mass spectrometer (Q Exactive), resulting in high resolution and high mass accuracy at the MS and MS/MS levels. C, Identification of HLA-I peptides. HLA-I peptides were analyzed with MaxQuant software, using an unspecific search, allowing the identification of peptides with one, two, and three charge states. In total, 22,244 unique HLA-I peptides were identified with a median identification score of 123 using a threshold of 1% FDR at the peptide level. D, HLA-I consensus binding motifs. Using the GibbsCluster tool the consensus binding motifs were defined from the identified peptides sequences.

Fig. 2.

Properties of the HLA-I peptidomes data set obtained from seven cell lines. A, Number of HLA-I peptides identified in each peptidome sample. B, Length distribution of HLA-I peptides. C, Intensities of HLA peptides span over four orders of magnitudes. D, Identification score distribution of HLA-I peptides for each of the charge states. E, Number of HLA-I peptides that were identified with the different charge states.

Fig. 3.

HLA-I peptidomes are highly reproducible. A, Cells expressing similar alleles shared more peptide sequences than cells expressing different set of alleles. Very low quantitative reproducibility of peptidomes isolated from cells expressing different set of alleles. B, Quantitative reproducibility of the peptidomes isolated from SupB15WT and SupB15RT. The reproducibility of the peptidomes was excellent (R² = 0.83 –0.91) between biological replicates and very good (R² = 0.71 – 0.76) between the two isogenic lines.

Fig. 4.

High confident identification of purified HLA-I peptides. A, Defining motifs directly from the mixture of identified peptides. Gibbs clustering analysis was performed for the purified 9-mer HLA-I peptides from the different cell lines. The motifs of the isogenic cell lines SupB15WT and SupB15RT cells were identical; therefore the results are shown only for SupB15WT. For each initial number of clusters the information content of the alignment is shown as a bar plot, where the size of each block within a bar is proportional to the size of a given cluster. The blue star marks the number of clusters that were selected based on the optimal fitness (higher KLD values) and minimum outliers, and their sequence logo plots are shown with the number of HLA-I peptides in each cluster and the assigned HLA-I alleles that fit each cluster. Binding motifs were calculated for each cluster from the frequency of the amino acids (AA) in positions P1 to P9 in the peptides sequences (see Supplemental Data). Frequency of more than 30% was classified as a dominant anchor motif (bold), more than 20% as a strong motif (underline), and more that 10% as a weak motif. B, Confirming the accurate identification of the observed peptides by predicting their affinity to the expressed alleles. We predicted using NetMHCcon (39) the binding affinity (maximal predicted binding affinity; HLA-A*02:01 and HLA-B*07:02) of the peptidome data set of 9-mer peptides from JY cells, and estimated the performance of the predictor using the expressed proteins as the set of input sequences. We compared the default affinity score <500 nm to include weak binders and the high affinity score of <50 nm to restrict to strong binders only. C, The computed Receiver Operating Characteristic (ROC) curve for the binding affinity to the HLA-I based on the predicted 9-mer epitopes from JY cells. The AUC (area under the curve) value is 0.975. D, Evaluating the deterioration in the ROC analysis when introducing noise of randomly selected 9-mer sequences from the expressed proteins. 9-mer peptides were added from 0 to100%, in steps of 5%, to the list of observed 9-mer peptides from JY cells. E, AUC values calculated from ten iterations of noise introduction.

Fig. 5.

HLA-I sampling for presentation correlates with proteins length, abundance, and half-life. A, HLA-I peptides in proteins as a function of proteins length. The plot represents the comparison between the number of presented peptides and the length of the source proteins as detected in proteomic analysis of total cell lysates. The blue line is a running average calculation of the data points. B, HLA-I peptides in proteins as a function of proteins abundance. The plot represents the comparison between the number of presented peptides and protein abundance, in Log₂(intensity) of their source proteins as detected in proteomic analysis of total cell lysates. Every protein that was detected in the proteomics analysis in each of the cell lines is presented in the plot according to the number of resulting detected HLA-I. Therefore, the same protein can be represented in the plot several times in case that it was detected in different intensities and gave rise to different number of epitopes in each of the cell lines. The blue line is a running average calculation of the data points. C, HLA-I sampling density (D) correlates with protein abundance. Using a running average, HLA-I sampling density is significantly correlated with the abundance of the source proteins (p < 0.0001). The data was fitted with a trend line (solid line) for each cell line. D, Fold HLA-I sampling density over the expected sampling (D′). For each protein the ratio D/D′ is represented as a function of protein abundance. The criteria for the selection of overpresented proteins was set to D>5 times larger than the expected HLA-I sampling density (D′). E, Unbiased selection of overpresented proteins. An explanatory plot showing how without correcting for the bias that originates from preferential presentation of highly expressed proteins the selection of overpresented proteins will result in selecting mainly the abundant proteins. The histogram represents protein abundance. The emphasized black histogram (5 x trend) shows the protein abundance for the subset of proteins with D>5 times larger than the expected HLA-I sampling density (D′), and it has the same shape as the proteome (in gray). The red histogram (biased) illustrates what would happen if D′ was a constant (D′ = 0.012), resulting in a biased selection toward highly expressed but not overpresented proteins. F, Presentation efficiency (D/D′) in relation to proteins half-life. Regardless of expression levels, turnover rates measures as half-life values, statistically significant correlate with presentation, in all cell lines (p < 0.001).

Fig. 6.

Characterization of overpresented proteins. A, Protein degradation and HLA-I presentation. Hidden proteins, with the same length and same abundance level, are longer lived than overpresented but also in general longer lived than other highly abundant proteins. From the top 20% abundant proteins we compared 154 proteins, which were overpresented proteins (D/D′>5) to balanced set of similar size of hidden proteins (D′ = 0) with matched expression and protein length. B, Predicting immunogenicity of HLA-I peptides from cancer antigens and from overpresented proteins. The 229 epitopes from the set of validated cancer antigens are significantly more immunogenic than the 82 HLA-I peptides from the same proteins which we identified in our peptidomics data set. Overpresented proteins (D/D′>5) are not more immunogenic than the rest of the presented peptidome (0<D<5) both in primary and cancer cell lines.