Unequal evolutionary rates in the human immunodeficiency virus type 1 (HIV-1) pandemic: the evolutionary rate of HIV-1 slows down when the epidemic rate increases

Abstract

HIV-1 sequences in intravenous drug user (IDU) networks are highly homogenous even after several years, while this is not observed in most sexual epidemics. To address this disparity, we examined the human immunodeficiency virus type 1 (HIV-1) evolutionary rate on the population level for IDU and heterosexual transmissions. All available HIV-1 env V3 sequences from IDU outbreaks and heterosexual epidemics with known sampling dates were collected from the Los Alamos HIV sequence database. Evolutionary rates were calculated using phylogenetic trees with a t test root optimization of dated samples. The evolutionary rate of HIV-1 subtype A1 was found to be 8.4 times lower in fast spread among IDUs in the former Soviet Union (FSU) than in slow spread among heterosexual individuals in Africa. Mixed epidemics (IDU and heterosexual) showed intermediate evolutionary rates, indicating a combination of fast- and slow-spread patterns. Hence, if transmissions occur repeatedly during the initial stage of host infection, before selective pressures of the immune system have much impact, the rate of HIV-1 evolution on the population level will decrease. Conversely, in slow spread, where HIV-1 evolves under the pressure of the immune system before a donor infects a recipient, the virus evolution at the population level will increase. Epidemiological modeling confirmed that the evolutionary rate of HIV-1 depends on the rate of spread and predicted that the HIV-1 evolutionary rate in a fast-spreading epidemic, e.g., for IDUs in the FSU, will increase as the population becomes saturated with infections and the virus starts to spread to other risk groups.

FIG. 1.

Root and rate optimization. The distance (Δd) between two groups of sequences is optimized by a t test finding the best rooting point in a phylogenetic tree. Δd is calculated by d₂ − d₁, where d₂ is the average distance of group 2, and d₁ is the average distance of group 1, from the rooting point of the tree. The sequences are separated by a Δt.

FIG. 2.

Accuracy of the root-and-rate-optimization method in estimating Δd. The graph shows observed Δd against Δd_exp based on tree simulations. White circles represent data for when the fraction of the tree containing Δd is 0.8, black triangles represent a fraction of 0.5, and stars represent a fraction of 0.2. subst., substitution.

FIG. 3.

Fast (FSU) and slow (Africa) HIV-1 subtype A1 epidemics. Delta distances (Δd) (a) and evolutionary rates (R) (b) are plotted against time between sampling dates (Δt). Black dots represent FSU data, and white dots represent African data. Δd values were calculated using a t test root optimization on maximum-likelihood reconstructed phylogenetic trees (Fig. 1). Each data point represents the Δd and R from an individual maximum likelihood tree optimization. The lines indicate the estimated Poisson-corrected evolutionary rate (R̂) in each epidemic (solid line, FSU; dashed line, Africa). subst., substitution.

FIG. 4.

Viral divergence during an epidemic. The average divergence of the virus over time is shown both (a) when all the population is sampled and (b) when only recently infected people are sampled. In both cases, we see that the average divergence is less for an epidemic among a cohort of drug users (thick line) than for one among heterosexual cohorts. For the latter, we simulated both a small, susceptible population with the same size as that of the drug user epidemic (normal line) and a 10-fold-larger initial susceptible population (dashed line).

FIG. 5.

Schematic drawing of the impact of immune selection on the evolutionary rate of HIV-1. Timeline A represents the first stage of infection, where the immune system is not yet activated. Timeline B represents the second stage of infection, where immune selection has started. The dotted line (no selection) is representative of the evolutionary rate of virus spreading rapidly among IDUs, transmitted from person to person during stage A, therefore experiencing no diversifying selection pressure and hence very little divergence. The normal line is representative of the evolutionary rate of virus spreading from person to person during infection stage B, i.e., in a slow heterosexual spread.