Serum alpha-mannosidase as an additional barrier to eliciting oligomannose-specific HIV-1-neutralizing antibodies

Abstract

Oligomannose-type glycans on HIV-1 gp120 form a patch that is targeted by several broadly neutralizing antibodies (bnAbs) and that therefore is of interest to vaccine design. However, attempts to elicit similar oligomannose-specific bnAbs by immunizing with oligomannosidic glycoconjugates have only been modestly successful so far. A common assumption is that eliciting oligomannose-specific bnAbs is hindered by B cell tolerance, resulting from the presented oligomannosides being sensed as self molecules. Here, we present data, along with existing scientific evidence, supporting an additional, or perhaps alternate, explanation: serum mannosidase trimming of the presented oligomannosides in vivo. Mannosidase trimming lessens the likelihood of eliciting antibodies with capacity to bind full-sized oligomannose, which typifies the binding mode of existing bnAbs to the oligomannose patch. The rapidity of the observed trimming suggests the need for immunization strategies and/or synthetic glycosides that readily avoid or resist mannosidase trimming upon immunization and can overcome possible tolerance restrictions.

Figure 1

PGT128 and related bnAbs bind the CRM₁₉₇-conjugated mimetic (NIT211) with similar or greater avidity as the BSA-conjugated version (NIT82B). The NIT211 derivative (NIT211_3) used here is loaded at 3.5 glycosides per CRM₁₉₇. NIT82B is loaded at 4.4 glycosides per BSA. The conjugates (63–73 kDa) were coated as solid-phase antigen onto microtiter-plate wells at 5 µg/ml and assayed for recognition by PGT125, 126, 128, and 130. All antibodies were tested as IgGs.

Figure 2

Serum mannosidase trims protein-conjugated oligomannose mimetic in vitro. Shown is PGT128 binding to the BSA-conjugated (a) or the CRM₁₉₇-conjugated glycoside (b) (5 µg/ml) after in situ overnight incubation of glycoconjugate-coated ELISA plates with buffer, mammalian serum, serum supplemented with kifunensine (Kif) or serum supplemented with EDTA. All experiments for a given serum were performed on a single assay plate to avoid potential plate-to-plate variability. Shown are representative results from two independent experiments.

Figure 3

Sera from Trianni mice immunized with the adjuvanted CRM₁₉₇-conjugated version of our oligomannose mimetic bind preferentially to the serum mannosidase-trimmed glycoconjugate. Trianni mice (n = 5) were immunized three times (days 0, 21, 42) with GLA-SE adjuvanted CRM₁₉₇-oligomannoside conjugate NIT211 (pre-made mixture of NIT211_4 (5.9 ligands/CRM₁₉₇) and NIT211_5 (6.5 ligands/CRM₁₉₇). Sera collected on day 49 were assayed for binding to heterologous BSA glycoconjugate (NIT82B)-coated ELISA plates after overnight (24 h) incubation of the glycoconjugate-coated wells with buffer or human serum. Graphs depict geometric mean values for the five serum samples, each assayed in duplicate, with error bars denoting the standard deviation from the mean.

Figure 4

SOSIP trimers are refractory to serum mannosidase trimming. Binding of a murine (IgG2a) version of antibody PGT128 to HIS-tagged SOSIP trimers ZM197M and C.ZA97 absorbed onto Ni²⁺-coated plates (5 µg/ml) was determined following in situ overnight incubation with buffer or human serum. Results are from a single experiment.