Alloimmunity to Class 2 Human Leucocyte Antigens May Reduce HIV-1 Acquisition - A Nested Case-Control Study in HIV-1 Serodiscordant Couples

Abstract

Enveloped viruses, including the Human Immunodeficiency Virus-1 (HIV), incorporate host proteins such as human leucocyte antigens (HLA) into their envelope. Pre-existing antibodies against HLA, termed HLA antibodies, may bind to these surface proteins and reduce viral infectivity. Related evidence includes macaque studies which suggest that xenoimmunization with HLA antigens may protect against simian immunodeficiency virus infection. Since HIV gp120 shows homology with class 2 HLA, including shared affinity for binding to CD4, class 2 HLA antibodies may influence HIV acquisition via binding to gp120 on the viral envelope. We conducted a nested case-control study on HIV serodiscordant couples, comparing the frequency of HLA antibodies among highly exposed persistently seronegative controls with those who went on to acquire HIV (HIV-seroconverters). We first performed low resolution HLA typing on 143 individuals who were HIV-infected at enrollment (index partners) and their corresponding sexual partners (115 highly exposed persistently seronegative individuals and 28 HIV-seroconverters). We then measured HLA class 1 and 2 antibodies in the highly exposed persistently seronegative individuals and HIV-seroconverters at early and late timepoints. We analyzed whether such antibodies were directed at HLA specificities of their HIV-infected index partners, and whether autoantibodies or complement-fixing class 2 HLA antibodies were present. Seventy-nine percent of highly exposed persistently seronegative individuals had HLA antibodies; 56% against class 1 and 50% against class 2 alleles. Half of the group of highly exposed persistently seronegative individuals, prior to seroconversion, expressed class 2 HLA antibodies, compared with only 29% of controls (p=0.05). HIV infection was a sensitizing event leading to de novo development of antibodies against HLA-A and HLA-B loci, but not against class 2 loci. HLA autoantibodies were present in 27% of highly exposed persistently seronegative individuals. Complement-fixing class 2 HLA antibodies did not differ significantly between highly exposed persistently seronegative individuals and seroconverters. In multivariable regression, presence of class 2 HLA antibodies at early timepoints was associated with reduced odds of HIV acquisition (odds ratio 0.330, confidence interval 0.112-0.976, p=0.045). These epidemiological data suggest that pre-existing class 2 HLA antibodies were associated with reduced odds of HIV acquisition.

Keywords: HLA; MHC; antibody; heterologous; highly exposed persistently seronegative; non-specific.

Figure 1

Class 2 HLA antibodies in HIV-seroconverters compared with highly exposed persistently seronegative controls, at the first and second timepoints. Upper panel shows comparison of highly expos ed persistently seronegative controls with all HIV-seroconverter couples. Lower panel shows comparison of highly exposed persistently seronegative controls with only linked HIV-seroconverter couples. At the first timepoint, a significantly higher proportion of highly exposed persistently seronegative controls than individuals who went on to acquire HIV expressed class 2 HLA antibodies.

Figure 2

Class 1 HLA antibodies in HIV-seroconverters compared with highly exposed persistently seronegative controls, at the first and second timepoint. Upper panel shows comparison of highly exposed persistently seronegative controls with all HIV-seroconverter couples. Lower panel shows comparison of highly exposed persistently seronegative controls with only linked seroconverters. At the second timepoint, significantly more HIV-seroconverters (all seroconverters or linked seroconverters) than highly exposed persistently seronegative controls expressed class 1 HLA antibodies.

Figure 3

Matching class 2 HLA antibodies in HIV-seroconverters compared with highly exposed persistently seronegative controls, at the first and second timepoints. Upper panel shows comparison of highly exposed persistently seronegative controls with all HIV-seroconverter couples. Lower panel shows comparison of highly exposed persistently seronegative controls with only linked HIV-seroconverter couples. At the first timepoint there was a trend to more matching class 2 HLA antibodies in highly exposed persistently seronegative controls than in those who went on to acquire HIV.

Figure 4

Matching class 1 HLA antibodies in HIV-seroconverters compared with highly exposed persistently seronegative controls, at the first and second timepoints. Upper panel shows comparison of highly exposed persistently seronegative controls with all seroconverter couples. Lower panel shows comparison of highly exposed persistently seronegative controls with only linked HIV-seroconverters. At the second timepoint, a significantly higher proportion of HIV-seroconverters, following HIV seroconversion, than highly exposed persistently seronegative controls expressed matching class 1 HLA antibodies.

Figure 5

Number of HLA antibody specificities per individual, at the first and second timepoints. The left hand graphs show HLA-A, HLA-B and HLA-C antibody specificities. The right hand graphs show HLA-DRB1 and HLA-DRB3,4,5 antibody specificities. At the second timepoint, HIV-seroconverters had a median of two antibody specificities per person compared with highly exposed persistently seronegative controls who had a median of one antibody specificity per person. There was no other significant difference noted.