HIV-1 latent reservoir size and diversity are stable following brief treatment interruption

Abstract

Background: The effect of a brief analytical treatment interruption (ATI) on the HIV-1 latent reservoir of individuals who initiate antiretroviral therapy (ART) during chronic infection is unknown.

Methods: We evaluated the impact of transient viremia on the latent reservoir in participants who underwent an ATI and at least 6 months of subsequent viral suppression in a clinical trial testing the effect of passive infusion of the broadly neutralizing Ab VRC01 during ATI.

Results: Measures of total HIV-1 DNA, cell-associated RNA, and infectious units per million cells (IUPM) (measured by quantitative viral outgrowth assay [QVOA]) were not statistically different before or after ATI. Phylogenetic analyses of HIV-1 env sequences from QVOA and proviral DNA demonstrated little change in the composition of the virus populations comprising the pre- and post-ATI reservoir. Expanded clones were common in both QVOA and proviral DNA sequences. The frequency of clonal populations differed significantly between QVOA viruses, proviral DNA sequences, and the viruses that reactivated in vivo.

Conclusions: The results indicate that transient viremia from ATI does not substantially alter measures of the latent reservoir, that clonal expansion is prevalent within the latent reservoir, and that characterization of latent viruses that can reactivate in vivo remains challenging.

Trial registration: ClinicalTrials.gov NCT02463227FUNDING. Funding was provided by the NIH.

Keywords: AIDS/HIV; Clinical Trials; T cells.

Figure 1. Study schema.

The A5340 clinical trial schema is shown at the top, with the type and timing of clinical specimens obtained for the present study shown in the center, and the assays performed shown at the bottom.

Figure 2. Quantitative measures of reservoir change.

Pre-ATI and post-ATI values (obtained at study entry and more than 6 months after viral suppression following ART reinitiation, respectively) of total HIV-1 DNA in CD4⁺ T cells (A), cell-associated HIV-1 RNA (caRNA) in CD4⁺ T cells (B), and the frequency of resting CD4⁺ T cells bearing replication-competent virus (IUPM) (C) are shown for each A5340 participant. Total DNA is not shown for participant A06, because the values were below detectable levels at both time points. P values shown in A–C indicate the significance of the within-participant changes and were determined by Wilcoxon signed-rank test.

Figure 3. ML phylogenetic trees of SGS-derived gp160 env sequences from pre-ART plasma, rebound plasma, and replication-competent latent viruses for participants A01, A02, and A05–A07.

Env sequences from pre-ART plasma are shown as black circles, sequences from rebound plasma from the first and second weeks of detectable viremia after ATI are shown as red and orange triangles, respectively, and sequences from virus supernatant from individual pre- and post-ATI p24⁺ QVOA culture supernatants are shown as solid blue or open blue squares. Genetic distance is shown by the scale bar, indicating 5 nucleotides (or ~0.2% difference). Bootstrap values above 70 are indicated by asterisks. Envs tested for neutralization sensitivity (Neut tested) in participants A01, A02, and A06 are indicated with an inverted v (^). Populations of identical QVOA sequences are seen in participants A01, A02, and A06, including a single dominant clone in participant A01 representing 95% of all QVOA sequences. Rebound sequences are generally distinct from QVOA sequences, except in participant A06, in which limited genetic diversity challenged distinction and in A07, in which the single QVOA sequence aligned with a rebound lineage.

Figure 4. ML phylogenetic trees of SGS-derived gp160 env sequences from pre-ART plasma, rebound plasma, and replication-competent latent viruses for participants A08, A09, and A13.

Genetic distance is shown by the scale bar, indicating 5 nucleotides (or ~0.2% difference) for participants A08 and A13, and 20 nucleotides (~0.8% difference) for participant A09. Bootstrap values above 70 are indicated by asterisks. Envs tested for neutralization sensitivity in participants A09 are indicated with an inverted v (^). Populations of identical QVOA sequences are seen in participants A08, A09, and A13. Viral rebound sequences are distinct from QVOA sequences in participants A09 and A13; in participant A08, some pre- and post-ATI QVOA sequences are identical or nearly identical to rebound lineages.

Figure 5. Neutralization sensitivity to VRC01 and autologous plasma at the time of viral rebound.

Representative Envs from 4 participants were cloned and tested as pseudoviruses in infectivity assays for sensitivity to VRC01 and autologous plasma. Representative infectivity curves for the rebound and QVOA Envs for participant A01 are shown against VRC01 (A) and autologous plasma (B). All assays were performed in triplicate, and the mean infectivity ± SEM for each dilution is shown. The mean IC₈₀ for virus inhibition against VRC01 (C) and autologous plasma (D) is shown for 4 participants. Pre-ATI viruses are shown in black, QVOA viruses in blue, and rebound viruses in red.

Figure 6. ML phylogenetic trees of SGS-derived gp160 env sequences from pre-ART plasma, rebound plasma, replication-competent latent viruses, and genetically intact proviral DNA for participants A01, A02, and A05–A07.

Env sequences from pre-ART plasma are shown as black circles, sequences from rebound plasma from the first and second weeks of detectable viremia after ATI are shown as red and orange triangles, respectively, sequences from virus supernatant from pre- and post-ATI individual p24⁺ QVOA culture well supernatants are shown as solid blue or open blue squares, and sequences from pre- and post-ATI proviral DNA (pDNA) are shown as solid purple or open purple diamonds. For clearer visualization, identical sequences are aligned horizontally in rows of 5. Genetic distance is shown by the scale bar, indicating 5 nucleotides (or ~0.2% difference) in all trees. Bootstrap values above 70 are indicated by asterisks. Populations of identical proviral DNA sequences are seen in all participants, including a large clonal population in participant A02 comprising 61% of total proviral DNA sequences. In general, the larger clonal populations of proviral DNA sequences show limited or no overlap with the larger QVOA clones.

Figure 7. ML phylogenetic trees of SGS-derived gp160 env sequences from pre-ART plasma, rebound plasma, replication-competent latent viruses, and genetically intact proviral DNA for participants A08, A09, and A13.

Populations of identical proviral DNA sequences are found in all participants, including a single clone comprising 78% of the proviral DNA sequences for participant A13, which was not sampled in the QVOA sequences. Bootstrap values above 70 are indicated by asterisks.