Assessing intra-lab precision and inter-lab repeatability of outgrowth assays of HIV-1 latent reservoir size

Abstract

Quantitative viral outgrowth assays (QVOA) use limiting dilutions of CD4+ T cells to measure the size of the latent HIV-1 reservoir, a major obstacle to curing HIV-1. Efforts to reduce the reservoir require assays that can reliably quantify its size in blood and tissues. Although QVOA is regarded as a \"gold standard\" for reservoir measurement, little is known about its accuracy and precision or about how cell storage conditions or laboratory-specific practices affect results. Owing to this lack of knowledge, confidence intervals around reservoir size estimates - as well as judgments of the ability of therapeutic interventions to alter the size of the replication-competent but transcriptionally inactive latent reservoir - rely on theoretical statistical assumptions about dilution assays. To address this gap, we have carried out a Bayesian statistical analysis of QVOA reliability on 75 split samples of peripheral blood mononuclear cells (PBMC) from 5 antiretroviral therapy (ART)-suppressed participants, measured using four different QVOAs at separate labs, estimating assay precision and the effect of frozen cell storage on estimated reservoir size. We found that typical assay results are expected to differ from the true value by a factor of 1.6 to 1.9 up or down. Systematic assay differences comprised a 24-fold range between the assays with highest and lowest scales, likely reflecting differences in viral outgrowth readout and input cell stimulation protocols. We also found that controlled-rate freezing and storage of samples did not cause substantial differences in QVOA compared to use of fresh cells (95% probability of < 2-fold change), supporting continued use of frozen storage to allow transport and batched analysis of samples. Finally, we simulated an early-phase clinical trial to demonstrate that batched analysis of pre- and post-therapy samples may increase power to detect a three-fold reservoir reduction by 15 to 24 percentage points.\n\nAuthor summaryThe latent reservoir of resting CD4+ T cells is a major, if not the primary, obstacle to curing HIV. Quantitative viral outgrowth assays (QVOAs) are used to measure the latent reservoir in ART-suppressed HIV-infected people. Using QVOA is difficult, however, as the fraction of cells constituting the latent reservoir is typically about one in one million, far lower than other infectious disease biomarkers. To study reliability of these assays, we distributed 75 PBMC samples from five ART-suppressed HIV-infected participants among four labs, each conducting QVOA and following prespecified sample batching procedures. Using a Bayesian statistical method, we analyzed detailed assay output to understand how results varied within batches, between batches, and between labs. We found that, if batch variation can be controlled (i.e., a lab assays all samples in one batch), typical assay results are expected to differ from the true value by a factor of 1.6 to 1.9 up or down. We also found that freezing, storing, and thawing samples for later analysis caused no more than a 2-fold change in results. These outcomes, and the statistical methods developed to obtain them, should lead towards more precise and powerful assessments of HIV cure strategies.