Molecular and phylogeographic analysis of human immuno-deficiency virus type 1 strains infecting treatment-naive patients from Kigali, Rwanda

Abstract

This study aimed at describing the genetic subtype distribution of HIV-1 strains circulating in Kigali and their epidemiological link with the HIV-1 strains from the five countries surrounding Rwanda. One hundred and thirty eight pol (RT and PR) sequences from 116 chronically- and 22 recently-infected antiretroviral therapy (ART)-naïve patients from Kigali were generated and subjected to HIV drug resistance (HIV-DR), phylogenetic and recombinant analyses in connection with 366 reference pol sequences from Rwanda, Burundi, Kenya, Democratic Republic of Congo, Tanzania and Uganda (Los Alamos database). Among the Rwandan samples, subtype A1 predominated (71.7%), followed by A1/C recombinants (18.1%), subtype C (5.8%), subtype D (2.9%), one A1/D recombinant (0.7%) and one unknown subtype (0.7%). Thirteen unique and three multiple A1/C recombinant forms were identified. No evidence for direct transmission events was found within the Rwandan strains. Molecular characteristics of HIV-1 were similar between chronically and recently-infected individuals and were not significantly associated with demographic or social factors. Our report suggests that the HIV-1 epidemic in Kigali is characterized by the emergence of A1/C recombinants and is not phylogenetically connected with the HIV-1 epidemic in the five neighboring countries. The relatively low level of transmitted HIV-DR mutations (2.9%) reported here indicates the good performance of the ART programme in Rwanda. However, the importance of promoting couples' counseling, testing and disclosure during HIV prevention strategies is highlighted.

Figure 1. Selection of recently and chronically infected participants.

Left: chronically-infected patient were selected from two sources: ·118 of 218 HIV patients eligible for ART and identified through VCT, were selected for HIVDR genotyping based on the completeness of the month 12 follow up visit, the viral load data and the availability of plasma. For seven samples, a pol sequence could not be generated during HIV-DR genotyping. ·from the cross sectional survey, five of 121 female participants classified as long-term infections had plasma available for HIVDR genotyping. In total, 116 HIV sequences of chronically infected participants were available for the analysis. Right: out of the patients participating in the cross sectional survey, 13 recent infections based on concordant negative results of the BED/Ax-AI assays were identified and had enough plasma available for HIVDR genotyping. Nine seroconverters were identified from the subsequent longitudinal incidence study and tested for HIVDR genotyping. In total, 22 pol sequences could be generated from recently infected individuals.

Figure 2. Bootscan analysis of RT and PR sequences of A/C recombinants from Rwanda.

Bootscan analyses of representative multiple (left side: A, B, C) and unique (right side: D, E, F) A1/C recombinant forms. The analysis was performed using SimPlot 3.5.1 configured with 1000 bootstrap replicates, 200 basepair (bp) window and a step size of 20 bp. The x-axis shows aligned nucleotides of the sequences analyzed and the y-axis shows the percentage of permuted tree, i.e. the bootstrap value. The reference strains that were used in the analysis are indicated in color. Parental reference sequences, subtype B, D, G, and F1, were selected from the Los Alamos database and parental subtype A1 (729HENN) and C (H0513) sequences were taken from this study. The breakpoint position(s) and the subtype designation is shown schematically at the bottom of each bootscan, with the number of sequences harboring a similar recombination pattern indicated in bold (e.g, figure A, N = 8). 414HENN is an example of a group of 8 similar recombinants (A). 716KC & 427HENN (B) and 480HENN & 754HENN (C) shared similar bootscan patterns. Graphs C to F show results for observed unique recombinant variants.

Figure 3. HIV-1 subtype distribution in Rwanda.

a) The pie chart on the left shows the HIV-1 subtype distribution of 92 gag and env sequences isolated between 1988 and 2006 in Rwanda and available from the Los Alamos database. The classification of subtype A into the A1 sub-subtype was not routinely done before 2006. The pie chart on the right shows the HIV-1 subtype distribution of 138 pol sequences from the chronically and recently infected study participants enrolled between 2007 and 2010. The HIV-1 subtype distribution before 2006 and in our cohort was significantly different as calculated by the Pearson Chi square (p<0.002). b) Subtype distribution in chronically infected study participants (on the left) and recently (on the right) infected participants enrolled in our study between 2007 and 2010. No statistically significant differences in the subtype distribution were found.

Figure 4. Phylogenetic tree for subtype A1 and C.

HIV-1 A1 (N = 94) and C (N = 8) pol sequences obtained from the Rwandan study participants were analyzed in connection to reference sequences from the Los Alamos database originating from Rwanda (N = 4) and the five surrounding countries collected between 1992 and 2009 (272 A1 and 212 C). The four subtype D (analysis 2, data not shown) and the 25 A1/C recombinant sequences were further examined in two separate analyses including 376 subtype D reference sequences and 6 A1/C reference sequences, respectively (analysis 3 data not shown). Country of origin of each sequence is color coded, with Rwanda in grey. The bootstrap values >85% are indicated in red. Related sequences found within subtype A1 (bootstrap value 100) are shown in detail in the three rectangular phylogenetic tree zoomed inserts.