The HIV-1 subtype C epidemic in South America is linked to the United Kingdom

Abstract

Background: The global spread of HIV-1 has been accompanied by the emergence of genetically distinct viral strains. Over the past two decades subtype C viruses, which predominate in Southern and Eastern Africa, have spread rapidly throughout parts of South America. Phylogenetic studies indicate that subtype C viruses were introduced to South America through a single founder event that occurred in Southern Brazil. However, the external route via which subtype C viruses spread to the South American continent has remained unclear.

Methodology/principal findings: We used automated genotyping to screen 8,309 HIV-1 subtype C pol gene sequences sampled within the UK for isolates genetically linked to the subtype C epidemic in South America. Maximum likelihood and Bayesian approaches were used to explore the phylogenetic relationships between 54 sequences identified in this screen, and a set of globally sampled subtype C reference sequences. Phylogenetic trees disclosed a robustly supported relationship between sequences from Brazil, the UK and East Africa. A monophyletic cluster comprised exclusively of sequences from the UK and Brazil was identified and dated to approximately the early 1980s using a Bayesian coalescent-based method. A sub-cluster of 27 sequences isolated from homosexual men of UK origin was also identified and dated to the early 1990s.

Conclusions: Phylogenetic, demographic and temporal data support the conclusion that the UK was a crucial staging post in the spread of subtype C from East Africa to South America. This unexpected finding demonstrates the role of diffuse international networks in the global spread of HIV-1 infection, and the utility of globally sampled viral sequence data in revealing these networks. Additionally, we show that subtype C viruses are spreading within the UK amongst men who have sex with men.

Figure 1. Bayesian tree of HIV-1 subtype C pol sequences.

Evolutionary relationships between 54 United Kingdom, 87 Brazilian and 120 non-Brazilian subtype C pol sequences, estimated using Bayesian phylogenetic analysis, are shown. Colors on terminal branches and terminal nodes indicate the geographic location of sampling, as shown in the key (bottom right). Asterisks indicate nodes with posterior probability values of 0.95 or higher. Brackets indicate clades comprised of sequences sampled from a specific geographic region, and with posterior probability values above 0.95. The mean dates of the most recent common ancestors to the ‘UK and Brazil’ and ‘UK-MSM’ clades are indicated alongside the corresponding internal nodes (white circles). Note that the majority (n = 8,266, >99%) of the UK subtype C sequences examined in this report grouped within the ‘Africa and Asia’ clade in preliminary analysis and are not shown here.