Constant mean viral copy number per infected cell in tissues regardless of high, low, or undetectable plasma HIV RNA

Abstract

Quantitative analysis of the relationship between virus expression and disease outcome has been critical for understanding HIV-1 pathogenesis. Yet the amount of viral RNA contained within an HIV-expressing cell and the relationship between the number of virus-producing cells and plasma virus load has not been established or reflected in models of viral dynamics. We report here a novel strategy for the coordinated analysis of virus expression in lymph node specimens. The results obtained for patients with a broad range of plasma viral loads before and after antiretroviral therapy reveal a constant mean viral (v)RNA copy number (3.6 log10 copies) per infected cell, regardless of plasma virus load or treatment status. In addition, there was a significant but nonlinear direct correlation between the frequency of vRNA+ lymph node cells and plasma vRNA. As predicted from this relationship, residual cells expressing this same mean copy number are detectable (frequency <2/10(6) cells) in tissues of treated patients who have plasma vRNA levels below the current detectable threshold (<50 copies/ml). These data suggest that fully replication-active cells are responsible for sustaining viremia after initiation of potent antiretroviral therapy and that plasma virus titers correlate, albeit in a nonlinear fashion, with the number of virus-expressing cells in lymphoid tissue.

Figure 3

Representative photomicrographs of ISH for HIV RNA. (A) Suspension of normal PBMC infected with HIV-1 in vitro. (B) HIV RNA⁺ cell identified in lymph node frozen tissue section. (C) Lymph node section of patient HADE showing HIV RNA in germinal center of lymph node scored as 1+ and two individual positive single cells. (D) Lymph node section of patient TRRA showing HIV RNA in germinal center of lymph node scored as 3+ and two individual positive single cells.

Figure 1

Plasma samples from HIV-infected patients were obtained and immediately separated into 1-ml aliquots, which were analyzed by each of two methods with blinded results. In addition, a standard preparation of HIV RNA was obtained from the National Institute of Allergy and Infectious Diseases AIDS Research and Reference Reagent Program and analyzed by the UAB QC-RT-PCR procedure. Roche Monitor^® assay was performed as per manufacturer's instructions. Specimens with viral loads >5 × 10⁵/ml were analyzed after appropriate dilution. The UAB QC-RT-PCR procedure was performed as described in Materials and Methods.

Figure 2

Analysis of HIV RNA⁺ cells by LDA and single-cell UAB QC-RT-PCR. (A) LDA for the frequency of HIV vRNA–expressing cells on five untreated patients described in Table I. After dilution of lymph node cells in 96-well microtiter plates, each well was harvested and QC-RT-PCR performed. For the graph in A, wells were scored positive or negative for HIV vRNA only. The number of lymph node cells diluted per well is plotted along the x-axis, and the percent negative wells by QC-RT-PCR is plotted along the y-axis. The frequency of HIV vRNA–expressing cells per 10⁶ lymph node cells was calculated by Poisson statistics. (B) Frequency histograms for four of the LDAs graphed in A for quantification of copies per well. The range of copies per well for each bar on the x-axis represents 0.3 log₁₀ multiples of copies of HIV vRNA. Only positive wells (>1,000 copies) were used for the calculation of mean HIV vRNA copies per well. See Table I for summary of other patient data and calculations of HIV vRNA quantity in different pools.

Figure 2

Analysis of HIV RNA⁺ cells by LDA and single-cell UAB QC-RT-PCR. (A) LDA for the frequency of HIV vRNA–expressing cells on five untreated patients described in Table I. After dilution of lymph node cells in 96-well microtiter plates, each well was harvested and QC-RT-PCR performed. For the graph in A, wells were scored positive or negative for HIV vRNA only. The number of lymph node cells diluted per well is plotted along the x-axis, and the percent negative wells by QC-RT-PCR is plotted along the y-axis. The frequency of HIV vRNA–expressing cells per 10⁶ lymph node cells was calculated by Poisson statistics. (B) Frequency histograms for four of the LDAs graphed in A for quantification of copies per well. The range of copies per well for each bar on the x-axis represents 0.3 log₁₀ multiples of copies of HIV vRNA. Only positive wells (>1,000 copies) were used for the calculation of mean HIV vRNA copies per well. See Table I for summary of other patient data and calculations of HIV vRNA quantity in different pools.

Figure 4

Relationship of plasma viral load to HIV vRNA–expressing cells in lymph node tissue. Each point represents a separate biopsy specimen paired with the plasma viral load at time of biopsy. HIV vRNA⁺ cells were measured by ISH, and plasma viral loads were determined by the Roche Monitor^® ultra-sensitive assay. The lines connecting points with the same symbols represent the same patient before and after HAART, as shown in Table I. Overall regression line (using the log-transformed data) of these data: slope = 1.6; r =  0.95 (P < 10⁻⁸).