A peptide filtering relation quantifies MHC class I peptide optimization

Abstract

Major Histocompatibility Complex (MHC) class I molecules enable cytotoxic T lymphocytes to destroy virus-infected or cancerous cells, thereby preventing disease progression. MHC class I molecules provide a snapshot of the contents of a cell by binding to protein fragments arising from intracellular protein turnover and presenting these fragments at the cell surface. Competing fragments (peptides) are selected for cell-surface presentation on the basis of their ability to form a stable complex with MHC class I, by a process known as peptide optimization. A better understanding of the optimization process is important for our understanding of immunodominance, the predominance of some T lymphocyte specificities over others, which can determine the efficacy of an immune response, the danger of immune evasion, and the success of vaccination strategies. In this paper we present a dynamical systems model of peptide optimization by MHC class I. We incorporate the chaperone molecule tapasin, which has been shown to enhance peptide optimization to different extents for different MHC class I alleles. Using a combination of published and novel experimental data to parameterize the model, we arrive at a relation of peptide filtering, which quantifies peptide optimization as a function of peptide supply and peptide unbinding rates. From this relation, we find that tapasin enhances peptide unbinding to improve peptide optimization without significantly delaying the transit of MHC to the cell surface, and differences in peptide optimization across MHC class I alleles can be explained by allele-specific differences in peptide binding. Importantly, our filtering relation may be used to dynamically predict the cell surface abundance of any number of competing peptides by MHC class I alleles, providing a quantitative basis to investigate viral infection or disease at the cellular level. We exemplify this by simulating optimization of the distribution of peptides derived from Human Immunodeficiency Virus Gag-Pol polyprotein.

Figure 1. Basic process of MHC class I antigen presentation.

Degradation of cytosolic and nuclear proteins, predominantly by the proteasome, generates peptides that are actively transported into the lumen of the endoplasmic reticulum (ER). Loading and editing of peptide cargo on MHC class I is achieved in the peptide loading complex, resulting in loaded MHC class I being released into the Golgi and transported to the cell surface, where the MHC class I peptide complex is presented to the immune system via the T-cell receptor. Known constituents of the peptide loading complex such as the transporter for antigen processing (TAP), tapasin, ERp57, calreticulin and MHC heavy-chain together with are shown explicitly.

Figure 2. Indexed reactions for a dynamical systems model of MHC class I peptide optimization.

Each shape in the model represents a molecular species and each box represents a reaction, where inbound edges represent reactants and outbound edges represent products. Boxes are labeled with corresponding reaction rates, where a single rate denotes an irreversible reaction and two rates denote a reversible reaction, with the rate of the forward reaction indicated on top. The subset of reactions taking place at the cell surface is given by (see Methods for the full reaction set).

Figure 3. Selection of HLA–B allele parameters.

The horizontal axis indicates the set of parameters that were allowed to vary between alleles. The vertical axis quantifies the Bayesian information criterion (BIC) of the best parameter values for a given set of allele parameters. BIC penalizes deviations of the model simulation from the experimental data, whilst also penalizing models with more variable parameters, implying that low BIC values correspond to more representative models. The best parameter values for a given set of allele parameters were inferred using the Filzbach MCMC software (see Methods).

Figure 4. Simulation of time-dependent peptide optimization by HLA–B.

The peptide optimization model of Fig. 2 was used to simulate a labeled cohort of peptide-MHC complexes by switching from generation of an unlabeled MHC population to a labeled population for 5 min (yellow blocks). The plots represent the concentration of total labeled MHC (blue), labeled MHC with medium or high affinity peptide (green) and labeled MHC with high affinity peptide only (red), at each time point. Simulations were performed in the absence (A) and presence (B) of tapasin. Corresponding experimental results are also reported (circles). Simulations were conducted for representative low, medium and high affinity peptides with a separate dissociation rate and generation rate for each peptide , and a separate peptide binding rate for each HLA–B allele (Table S1 in Text S1; Protocol S1).

Figure 5. Filtering relation of MHC class I peptide optimization.

(A) Consider a population of MHC complexes containing peptides with off-rate . denotes the expected number of MHC complexes that will egress before the peptide can escape. denotes the expected proportion of egressed MHC complexes that will contain peptides with off-rate . This defines a measure of peptide optimization. We plot and as functions of for three peptides with different off-rates and the same initial populations. Maximal optimization is achieved when , with (dashed lines). (B) Consider a population of tapasin-MHC complexes containing peptides with off-rate . denotes the expected number of MHC complexes that will unbind from tapasin and egress before the peptide can escape, where . is defined as in A. We plot and as functions of with (black line in A). Maximal optimization is achieved when , with .

Figure 6. Peptide optimization and trafficking for H2−K.

The model of Fig. 2 was calibrated for H2− by varying the rates of peptide binding, MHC degradation at the cell surface, and egress (Table S2 in Text S1; Protocol S2). Each simulation computes the steady state of the model with three types of peptide: two background peptides and and one of the four SIINFEKL peptide variants ( estimated from data in panel A). (A) Release of peptides from MHC following treatment with brefeldin A (BFA) measured with 25.D1 (symbols), fitted to single exponential decays (solid lines). (B) Dissociation of endogenous peptides from cells treated with BFA. (C) Steady-state presentation of specific peptide-MHC complexes at the cell surface, comparing simulation with measurements of 25.D1 from . (D) Total steady-state peptide-MHC complexes (cell surface), comparing simulation with measurements of Y3 from . Simulated values were scaled by a proportionality factor for optimally overlapping the 25.D1 data (with SIINFEKM removed) and the Y3 data (all points) (Text S1). (B–D) The x-axis shows the relative affinity of peptides given by the inverse of the off-rate. Steady state concentrations were obtained by equating the right hand sides of the ODEs to zero. Steady state concentrations in tapasin-deficient cells were simulated by setting . (E–G) For quantifying egression of peptide-MHC complexes, .220. (E) and .220..Tpn (F) were pulsed for 10 min with -Met/Cys and chased for the indicated times (min). Y3 immunoprecipitates were digested with endoglycosidase-H (EndoH) and SDS-PAGE and autoradiography were performed. Arrows indicate heavy chain resistant (R) and sensitive (S) to EndoH digestion. EndoH analysis of H2− was performed as described previously . (B–D, G) The solid lines indicate model simulations and triangles indicate measured data-points. The experimental data for (A,B,E–F) is novel, while the experimental data for (C,D) is from .

Figure 7. Simulation of cell surface presentation of HIV virus peptides by HLA–B2705.

The sequence of the HIV-1 polyprotein Gag-Pol was obtained from the UniProt online resource (accession P03367). All peptides between 8 and 10 amino acids in length were then derived from the sequence and assessed for their off-rates using the BIMAS prediction algorithm (http://www-bimas.cit.nih.gov/molbio/hla_bind [28]). The peptides were then simulated by assuming that they are all supplied into the ER via TAP at an equal rate, such that the total supply rate is equal to the total supply rate estimated for Fig. 4. As the algorithm predicted many peptides to have the same off-rate, peptides were clustered for ease of computation. (A) The number of peptides with a given peptide off-rate, as calculated by BIMAS. (B) Steady-state cell surface presentation of peptide-MHC complexes as a function of peptide off-rate. Peptide supply was assumed to be constant for each individual peptide. Therefore, the supply rate associated with a particular off-rate is simply scaled by the number of peptides with that off-rate, as quantified in A. The lowest off-rate (highest affinity) peptides for B2705 (KRWIILGLNK) and B4403 (AETQCETAY) are indicated. Simulations were performed for the presence and absence of tapasin, as indicated in the key. (C) Enhancement of cell surface presentation by tapasin was computed by dividing simulated tapasin-sufficient presentation by simulated tapasin-deficient presentation for each peptide. The results of the HIV simulations illustrate the extent to which tapasin can affect a downstream immune response. Theoretically, tapasin can enhance presentation by up to a factor , where is the off-rate of the peptide from MHC (Fig. 5). However, the characteristics of the MHC allele, such as the allele-specific peptide on-rate, can significantly alter the effect of tapasin on the presentation of a given peptide. Our model allows differences in presentation levels to be quantified by taking into account peptide supply and peptide off-rate, together with the effects of tapasin and the binding properties of the MHC class I allele under consideration. In particular, our analysis of the HIV-1 Gag-Pol polyprotein provides a specific quantitative prediction for the cell surface presentation of the immunodominant KRWIILGLNK by HLA–B2705. By simulating the range of peptides derived from Gag-Pol, representing a range of off-rates, we observe that the enhancement by tapasin is independent of peptide supply, instead being wholly determined by the peptide off- and on-rates (Fig. 7 C).