Reduced evolutionary rates in HIV-1 reveal extensive latency periods among replicating lineages

Abstract

Background: HIV-1 can persist for the duration of a patient's life due in part to its ability to hide from the immune system, and from antiretroviral drugs, in long-lived latent reservoirs. Latent forms of HIV-1 may also be disproportionally involved in transmission. Thus, it is important to detect and quantify latency in the HIV-1 life cycle.

Results: We developed a novel molecular clock-based phylogenetic tool to investigate the prevalence of HIV-1 lineages that have experienced latency. The method removes alternative sources that may affect evolutionary rates, such as hypermutation, recombination, and selection, to reveal the contribution of generation-time effects caused by latency. Our method was able to recover latent lineages with high specificity and sensitivity, and low false discovery rates, even on relatively short branches on simulated phylogenies. Applying the tool to HIV-1 sequences from 26 patients, we show that the majority of phylogenetic lineages have been affected by generation-time effects in every patient type, whether untreated, elite controller, or under effective or failing treatment. Furthermore, we discovered extensive effects of latency in sequence data (gag, pol, and env) from reservoirs as well as in the replicating plasma population. To better understand our phylogenetic findings, we developed a dynamic model of virus-host interactions to investigate the proportion of lineages in the actively replicating population that have ever been latent. Assuming neutral evolution, our dynamic modeling showed that under most parameter conditions, it is possible for a few activated latent viruses to propagate so that in time, most HIV-1 lineages will have been latent at some time in their past.

Conclusions: These results suggest that cycling in and out of latency plays a major role in the evolution of HIV-1. Thus, no aspect of HIV-1 evolution can be fully understood without considering latency - including treatment, drug resistance, immune evasion, transmission, and pathogenesis.

Figure 1

Success of phylogenetic latency detection in critical simulation scenarios. Detection of latency-affected lineages was done by pair-wise comparisons of all taxa, testing whether the shorter lineage was significantly shorter according to a Poisson test. (A) Sensitivity results from simulations with 100 taxa and one random branch affected by latency at f _latent = 0.1–0.9 of the corresponding original non-latent genetic distance. Lines show moving average for general trends (f _latent = 0.9–0.1, left to right). Individual simulation results are shown in the Supplement (Additional file 1: Figure S2). (B) The minimum latency fraction on an affected branch to achieve 95% sensitivity as a function of the mean height of non-latent taxa from the MRCA of all taxa. The height is in log10-units to facilitate reading short tree height performance. (C) Specificity as a function of the mean height of non-latent taxa from the MRCA of all taxa. Panels B and C have loess curves fitted to show general trends.

Figure 2

The false discovery rate (FDR) of our phylogenetic latency detection method. Because our latency detection method performs many tests, the risk of false positives increases. This figure shows the FDR as a function of the total number of positives detected (TP + FP). The FDR depended strongly on the number of latency periods (panels), and on the number of taxa compared (lines); cyan = 10 taxa, green = 20 taxa, blue = 30 taxa, purple = 40 taxa, magenta = 50 taxa, and red = 60 taxa. Each line shows the mean of 50,000 simulated random phylogenies at f _latent = 0.5–0.9. Means were calculated when ≥50 observations occurred at any TP + FP level. The hairline shows FDR = 0.05.

Figure 3

Latency detection in HIV-1 phylogenies. To avoid effects of selection, only 3^rd codon DNA positions were used for phylogenetic reconstruction and latency detection. Latency was detected in an untreated patient (K-G), an elite suppressor (O-9), a successfully treated patient (B-139), and in a patient with failed treatment (M-105). These are representative patients of each group in Table 1. All 26 patient trees are shown in the online supplementary materials (Additional file 1: Figure S1). Taxa are labeled P for plasma-derived virus and R for resting CD4+ T cell pro-virus. Filled symbols indicate significant reduction in genetic distance (circles p < 0.05; squares p < 0.01; triangles p < 0.001). Crossed circles indicate potential recombinants, omitted from latency detection. Unlabelled ingroup taxa indicate additional sequences from neither plasma nor resting cells. Color indicates time since 1^st sample of patient. Patient K-G was rooted at 1^st sample close to PHI (unlabeled taxa), and the other patients were rooted by an outgroup (HIV-1 HXB2, unlabelled). The circled numbers are observations of interest discussed in the text.

Figure 4

Dynamic modeling of ever-latent HIV-1 lineages. (A) Assuming neutral evolution most parameter regimes suggest that the vast majority of all HIV-1 lineages have been latent during their evolution. The heat map scale, blue to red, shows fraction of ever-latent (0.0-1.0) in an untreated patient after 10 years of infection within previously described parameter ranges for the fraction of HIV-1 that become deposited into the latent pool, the half-life of the latent pool, and the activation rate of latent HIV-1 back into the replicating population. (B) Assuming differential fitness costs for ever-latents and never latents, the fraction ever-latents surviving is reduced compared to a neutral model. The fitness plots were generated assuming a half-life of 10 months.