Inter-Laboratory Reproducibility of Inducible HIV-1 Reservoir Quantification by TILDA

Abstract

Substantial efforts to eliminate or reduce latent HIV-1 reservoirs are underway in clinical trials and have created a critical demand for sensitive, accurate, and reproducible tools to evaluate the efficacy of these strategies. Alternative reservoir quantification assays have been developed to circumvent limitations of the quantitative viral outgrowth assay. One such assay is tat/rev induced limiting dilution assay (TILDA), which measures the frequency of CD4+ T cells harboring inducible latent HIV-1 provirus. We modified pre-amplification reagents and conditions (TILDA v2.0) to improve assay execution and first internally validated assay performance using CD4+ T cells obtained from cART-suppressed HIV-1-infected individuals. Detection of tat/rev multiply spliced RNA was not altered by modifying pre-amplification conditions, confirming the robustness of the assay, and supporting the technique's amenability to limited modifications to ensure better implementation for routine use in clinical studies of latent HIV-1 reservoirs. Furthermore, we cross-validated results of TILDA v2.0 and the original assay performed in two separate laboratories using samples from 15 HIV-1-infected individuals. TILDA and TILDA v2.0 showed a strong correlation (Lin's Concordance Correlation Coefficient = 0.86). The low inter-laboratory variability between TILDAs performed at different institutes further supports use of TILDA for reservoir quantitation in multi-center interventional HIV-1 Cure trials.

Keywords: HIV-1 latency; TILDA; assay performance; inducible reservoirs; reservoir quantification.

Figure 1

TILDA analytical and clinical sensitivity. (A) Detection of serial dilutions of a synthetic tat/rev RNA template in the absence of cells using the original TILDA RT-qPCR conditions compared to the TILDA v2.0 RT-qPCR conditions. Three wells per dilution were tested based on cycle threshold (Ct) values. NTC = Negative template control. A multiple paired t-test was used to compare mean Ct values. The error bars represent the SD of the mean of two independent runs. (B) Dilutions of 10–10,000 copies of tat/rev RNA were pre-amplified using different reaction volumes using QIAGEN (25 µL; open circles, and 50 µL; closed circles) or Superscript III Platinum one-step RT kits. Three wells per dilution were tested for positivity. A Pearson’s correlation test between the reference and two test kits is shown. Statistical significance is determined by p < 0.05. (C) Quantification of inducible HIV-1 reservoirs in clinical samples. Frequency of CD4+ T cells expressing tat/rev msRNA after in vitro stimulation with PMA/Ionomycin (N = 32 HIV-1-infected individuals on suppressive cART). Target was not detected for one sample, indicated using an open circle. The median and interquartile range is shown (the median frequency of cells with inducible tat/rev msRNA per million CD4+ T cells = 23.95). The dotted line represents the assay limit of detection (LOD). (D) The inter-assay coefficient of variation (CV) determined from TILDA measurements of four individuals. Mean CV= 24.5%. The other numbers represent the CV for each individual calculated from a minimum of two independent measurements. The error bars represent SD of the mean.

Figure 2

TILDA inter-laboratory reproducibility. (A) The frequency of CD4+ T cells expressing tat/rev msRNA after in vitro stimulation with PMA/Ionomycin in a subset of individuals (N = 15), quantified by TILDA and TILDA v2.0. Each individual is represented by a different colored dot. The open circles are below the LOD. Wilcoxon’s matched-pairs test was used to compare the medians. Statistical significance is determined by p < 0.05. (B) Lin’s Concordance Correlation Coefficient (LCCC) plot. The black dots represent inducible reservoir size quantified by TILDA and TILDA v2.0. The open circle is below the LOD. The grey diagonal line represents the best-fit line. Coefficient of bias (Cb) is a measure of accuracy. (C) Bland–Altman plot using log-transformed inducible reservoir size measurements by the two assays. The open circle is below the LOD. The blue dotted line represents the mean bias, and the red dotted lines represent the 95% limits of agreement.