Estimating the Binding of Sars-CoV-2 Peptides to HLA Class I in Human Subpopulations Using Artificial Neural Networks

Abstract

Epidemiological studies show that SARS-CoV-2 infection leads to severe symptoms only in a fraction of patients, but the determinants of individual susceptibility to the virus are still unknown. The major histocompatibility complex (MHC) class I exposes viral peptides in all nucleated cells and is involved in the susceptibility to many human diseases. Here, we use artificial neural networks to analyze the binding of SARS-CoV-2 peptides with polymorphic human MHC class I molecules. In this way, we identify two sets of haplotypes present in specific human populations: the first displays weak binding with SARS-CoV-2 peptides, while the second shows strong binding and T cell propensity. Our work offers a useful support to identify the individual susceptibility to COVID-19 and illustrates a mechanism underlying variations in the immune response to SARS-CoV-2. A record of this paper's transparent peer review process is included in the Supplemental Information.

Keywords: HLA; SARS-CoV-2; T cell propensity; artificial neural networks; haplotypes; peptides.

Figure 1

Characterization of the Binding Heterogeneity of SARS-CoV-2 and SARS-CoV Peptides Are Similar and Differs for HCoV-OC43 (A) The number of strongly binding peptides ($I{C}_{50}<\mathrm{1,000}nM$) for SARS-Cov-2, SARS-Cov, and HCOV-OC43 estimated for 79 class I HLA alleles by combining predictions from netMHCpan and MHCflurry. (B) The binding affinities ($I{C}_{50}$) of SARS-Cov-2 peptides are shown in the clustered colormap for 79 class I HLA alleles. Only peptides with at least one binding affinity smaller than 1,000 nM are included.

Figure 2

Response to SARS-CoV-2 across Human Populations (A) Frequencies of haplotypes containing one or two strong alleles, defined as those with highly ranked T cell epitopes. (B) Frequencies of haplotypes containing one, two, and three weakly binding alleles for SARS-CoV-2. Error bars are estimated 95% confidence intervals.