Safety, pharmacokinetics and antiviral activity of PGT121, a broadly neutralizing monoclonal antibody against HIV-1: a randomized, placebo-controlled, phase 1 clinical trial

Abstract

Human immunodeficiency virus (HIV)-1-specific broadly neutralizing monoclonal antibodies are currently under development to treat and prevent HIV-1 infection. We performed a single-center, randomized, double-blind, dose-escalation, placebo-controlled trial of a single administration of the HIV-1 V3-glycan-specific antibody PGT121 at 3, 10 and 30 mg kg^-1 in HIV-uninfected adults and HIV-infected adults on antiretroviral therapy (ART), as well as a multicenter, open-label trial of one infusion of PGT121 at 30 mg kg^-1 in viremic HIV-infected adults not on ART (no. NCT02960581). The primary endpoints were safety and tolerability, pharmacokinetics (PK) and antiviral activity in viremic HIV-infected adults not on ART. The secondary endpoints were changes in anti-PGT121 antibody titers and CD4⁺ T-cell count, and development of HIV-1 sequence variations associated with PGT121 resistance. Among 48 participants enrolled, no treatment-related serious adverse events, potential immune-mediated diseases or Grade 3 or higher adverse events were reported. The most common reactions among PGT121 recipients were intravenous/injection site tenderness, pain and headache. Absolute and relative CD4⁺ T-cell counts did not change following PGT121 infusion in HIV-infected participants. Neutralizing anti-drug antibodies were not elicited. PGT121 reduced plasma HIV RNA levels by a median of 1.77 log in viremic participants, with a viral load nadir at a median of 8.5 days. Two individuals with low baseline viral loads experienced ART-free viral suppression for ≥168 days following antibody infusion, and rebound viruses in these individuals demonstrated full or partial PGT121 sensitivity. The trial met the prespecified endpoints. These data suggest that further investigation of the potential of antibody-based therapeutic strategies for long-term suppression of HIV is warranted, including in individuals off ART and with low viral load.

Fig. 1. Trial profile.

Participant recruitment, randomization, and follow up are depicted. Participants were enrolled concurrently at BIDMC (Beth Israel Deaconess Medical Center), OIC (Orlando Immunology Center), and HART (Houston AIDS Research Team, McGovern Medical School at The University of Texas Health Science Center).

Fig. 2. PGT121 PK.

a–c, The PK profile of serum PGT121 is shown for HIV-uninfected participants (a), HIV-infected participants on antiretroviral therapy (b) and HIV-infected viremic participants (c).

Fig. 3. HIV-1 RNA viral load and sensitivity to PGT121 before and after PGT121 infusion.

a, Plasma HIV-1 RNA levels are shown following PGT121 infusion in HIV-infected viremic participants not on ART. The arrow indicates the day of PGT121 infusion, the gray line equals median value and the dotted line indicates the lower limit of quantification for HIV-1 RNA levels (40 copies (cp) ml^–1). Asterisks indicate the time point at which ART was started, and dots indicate when samples were collected for sequencing. b, IC₅₀ neutralization scores (µg ml^–1), indicating sensitivity or resistance to PGT121 among isolated viruses, are shown for each participant, before and after PGT121 administration. c, HIV-1 viral load and PGT121 serum levels are shown for participants 6113 and 1536 following PGT121 infusion. Open circles indicate that either HIV-1 RNA (black) or PGT121 level (red) was below the limit of detection.

Fig. 4. Immunologic responses following PGT121 infusion in two long-term suppressors.

a, The percentages of Env-, Gag- and Pol-specific CD8⁺ T cells secreting IFN-γ and TNF-α Env are shown for participants 6113 and 1536 at day 0 (D0) and day 84 (D84). b, The magnitude of Gag- and Pol-specific IFN-γ-secreting cellular immune responses (spot-forming units (SFU) 10^–6 PBMCs) is plotted by peptide subpool for participants 6113 and 1536 at D0 and D84.

Extended Data Fig. 1. Correlation between PGT121 neutralizing and binding antibody concentrations.

Concordance between PGT121 concentrations measured by binding and neutralizing antibody assays using pseudovirus strains CNE30 (a) and X2088_c9 (b). The dotted line is the identity line. Solid line is the trend line. Data are colored by participant. Lin’s concordance correlation coefficient is a measurement of accuracy and precision which is used to assess agreement between two sets of measurements.

Extended Data Fig. 2. Anti-drug antibody responses.

(a) Binding anti-drug antibodies at day 0 and day 168 by participant (each black bar represents a separate participant). The red dotted line indicates the run-specific floating cut-point. (b) Binding anti-drug antibodies in the setting of PGT121 or no PGT121 competition in participants 7945 and 2305. (c) Anti-PGT121 neutralizing activity (ID50 titers) at days 0 and 168 for participants 7945 and 2305.

Extended Data Fig. 3. Viral sensitivity to PGT121 and other bNAbs before and after PGT121 infusion.

IC₅₀ neutralization scores (in µg/ml) are shown for each participant: PGT121 is shown on the left, followed by 10–1074 that also targets the V3 glycan, then a V2 apex bNAb (PGDM1400), then a CD4bs bNAb (3BNC117). Baseline and post PGT121 treatment values are shown, followed by the amino acid sequence of the GDIR motif (HXB2 positions 324–327) and the N-linked glycosylation motif (positions 332–334). Blue amino acids indicate sensitivity signatures for PGT121, while black and red amino acids indicate resistance signatures.

Extended Data Fig. 4. Correlation between PGT121 neutralization and viral load kinetics.

(a) Correlation between maximum viral load drop and PGT121 geometric mean IC80 titers for baseline viruses. Open symbols indicate participants whose minimum viral load was below the lower limit of quantitation (40 copies/ml). Grey lines indicate range of individual baseline virus IC₈₀ titers. Black line is the linear regression trend line. (b) Same as (A), but using predicted average instantaneous inhibitory potential (IIP) for baseline viruses (see Methods). (c) Correlation between initial viral load decline rate and geometric mean PGT121 IC₈₀ titers for baseline viruses. Grey lines indicate range of IC₈₀ titers, black line the trend. See methods for initial viral load decline rate calculations. (d) Same as (C) but using average IIP as in (B). (e) Correlation between days to rebound and average maximum percent inhibition (MPI) of rebound viruses by PGT121. Because most rebound viruses had IC80 above threshold (50 µg/ml), we used MPI defined as the observed percent neutralization of each virus at 50 µg/ml. Time to rebound was calculated as the first timepoint when the viral load post infusion returns to 0.5 Log10 copies/ml below the baseline or higher. (f) Same as (E), but using average IIP for rebound viruses. In each panel, statistics using Pearson moment correlation and Kendall Tau rank test are shown. One sided p-values are reported.

Extended Data Fig. 5. Maximum likelihood phylogenetic tree of HIV-1 Env sequences isolated from participants pre- and post-PGT121 treatment.

The branch colors indicate sequences sampled at baseline (blue) versus post-PGT121 treatment (red). The colored box at every leaf indicates PGT121 sensitivity as an IC₅₀ score in a TZM.bl assay; black is undetectable, blue and green are relatively resistant, and yellow-through-red increasingly sensitive. The likely amino acids that confer PGT121 resistance mutation are indicated to the right of the branches. If a four-letter motif is indicated, it represents positions 324–327 (HXB2 numbering), a conserved part PGT121 epitope; GDIR is the common consensus form and is associated with antibody sensitivity. If a three-letter motif is indicated, it refers to positions 332–334; most commonly this is a glycosylation site (NIS), and an N-linked glycan is generally critical for V3 bNAb sensitivity. Blue letters indicate PGT121 sensitive signature amino acids, red indicate resistant. The glycosylation motif can be lost by either the loss of the Asn (N) at N332, or the loss of a Thr (T) or Ser (S) at S334. D325 is the most variable position in the highly conserved GDIR motif. D325N does not always confer resistances (for example participant 6775), but is generally associated with resistance (for example participants 6292 and 2990).

Extended Data Fig. 6. V3 glycan signatures.

Glycan signatures are displayed for participants with (a) high viral load and sensitive viruses at baseline, (b) high viral load and resistant viruses at baseline, and (c) low viral load at baseline. LOGO plots are shown representing the sensitivity and resistance mutations for all V3 glycan signatures. The height of the letter indicates the frequences the sample, for the baseline on the top, and the post PGT121 treatment directly underneath. The putative resistance conferring mutations are boxed in black. Red letters indicate resistance, blue sensitivity, green depended on the antibody, and black indicate amino acids not supported statistically as either a sensistivity or resistance signature. The signatures outside of the binding region are more likely to modulate levels of sensitivity, and are seldom perturbed.

Extended Data Fig. 7. Complex recombination patterns among two participants.

The role of recombination in carrying forward resistant form is shown for study participants 6292 (top) and 2990 (bottom). Left panels show the phylogenetic trees with leaves labeled according to the sensitive/resistant form they are carrying; in the middle panels the corresponding sequences (in the same order as the trees on the left) are each represented by a line, and recombinants display regions where recombination breakpoints likely occurred as rectangles (solid rectangles indicate statistically significant recombination breakpoints); corresponding neutralization data (IC50 and IC80) is shown on the right. In both study participants recombination has no impact at baseline as all forms are PGT121 sensitive. However, complex forms of resistance emerge at visit 7. In 6292, these involve D325 alone, N332 alone, and a combination of both. At visit 7, in 2 out of 2 recombination events between a sensitive and a resistant parental form, the resistant form is found in the recombinant, yet all visit 7 viruses are resistant. Either these mutations are occurring de novo on recombinant backbones, or they are resulting from recombination of parental forms that carry the mutation but have not been sampled. In 2990, recombination carries forward PGT121 resistant forms in 3 out of 3 events where the parental strains carry a sensitive and resistant form each. Of note, D325N does not confer 10–1074 resistance in 2990, neither does D325E in 6292. However, D325K, found in 6292, gives rise to resistance to both 10–1074 and PGT121.

Extended Data Fig. 8. Modeling the effects of PGT121 on plasma viral load.

Best fit of viral dynamic model (light blue line) to measured viral load data (blue asterisks) for 6 participants. PGT121 serum concentration is shown in solid red. Horizontal dotted line indicates the viral load limit of detection. Participants 2990,6292 and 2305 shown in the top row belong to the high viral load group, with the remaining patients belonging to the low viral load group. The model follows two populations of virus, PGT121 sensitive and PGT121 resistant, denoted by the purple and orange dashed lines, respectively, while the total viral load is a solid light blue line. The level of resistance is allowed to vary among participants. For 2305, 2936, 2990, 6292 and 6113 the resistant population is predicted to pre-exist at the indicated levels. For the long-term controller 6113 the pre-existing resistant virus is predicted to be partially sensitive to the antibody and after PGT121 administration its level quickly decreases below the x-axis and does not reappear until after day 100. For the other long-term controller 1536, the resistant population may pre-exist at a baseline level of 10^–3 copies/ml or lower or may arise by mutation. Loss of control in both 1536 and 6113 is predicted to occur due to a resurgence of resistant virus. For the periods of observation indicated, the resistant population is predicted to persist (2305, 2936 and 2990) or to be replaced by drug sensitive virus as the antibody concentration wanes in 6292 and the long-term controllers 1536 and 6113.

Extended Data Fig. 9. Immunologic responses following PGT121 infusion in HIV-infected participants on ART.

The number of IFN-γ secreting CD4 + and CD8 + T cells (A and B, respectively), IL-2 secreting CD4 + and CD8 + T cells (C and D, respectively) and TNF-a secreting CD4 + and CD8 + T cells (E and F, respectively) recognizing peptide subpools across the Gag, Pol and Env protein were measured by flow cytometry in all group 2 A, B and C participants (PGT121 and placebo recipients, N = 15) at baseline (pre-mAb) and at day 28 (post-mAb). For panels A-F, data are presented as median values + /− 95% CI; n = 4 (active) and n = 1 (placebo) for each subgroup. Frequencies of activated CD38 and Ki67 expressing IFN-γ secreting CD4 + and CD8 + T cells (G and H, respectively), and frequencies of PD-1 expressing IFN-γ secreting CD4 + and CD8 + T cells (I and J, respectively) at baseline (pre-mAb) and at day 28 (post-mAb) were assessed by flow cytometry. Boxplots display minimum, maximum, median and interquartile range; n = 4 (active) and n = 1 (placebo) for each subgroup.