Phylodynamics of major CRF01_AE epidemic clusters circulating in mainland of China

Abstract

As the most dominant HIV-1 strain in China, CRF01_AE needs to have its evolutionary and demographic history documented. In this study, we provide phylogenetic analysis of all CRF01_AE pol sequences identified in mainland China. CRF01_AE sequences were collected from the Los Alamos HIV Sequence Database and the local Chinese provincial centers of disease control and prevention. Phylogenetic trees were constructed to identify major epidemic clusters. Bayesian coalescent-based method was used to reconstruct the time scale and demographic history. There were 2965 CRF01_AE sequences from 24 Chinese provinces that were collected, and 5 major epidemic clusters containing 85% of the total CRF01_AE sequences were identified. Every cluster contains sequences from more than 10 provinces with 1 or 2 dominant transmission routes. One cluster arose in the 1990s and 4 clusters arose in the 2000s. Cluster I is in the decline stage, while the other clusters are in the stable stage. Obvious lineage can be observed among sequences from the same transmission route but not the same area. Two large clusters in high-level prevalence were found in MSM (Men who have sex with men), which highlighted that more emphasis should be placed on MSM for HIV control in mainland China.

Figure 1

Geographical and transmission route compositions of CRF01_AE sequences enrolled in the study. Map of China with prefecture names and the number of sequences listed on the left side. Transmission routes of sequences were collected and are depicted as a pie chart. Maps were generated with R software 3.3.1 (https://www.r-project.org/).

Figure 2

Epidemic clusters labeled in ML tree and MCC tree. (a) Maximum likelihood phylogenetic analysis of CRF01_AE pol sequences from mainland China. The dataset included 2965 CRF01_AE sequences from 24 Chinese provinces. The tree was rooted using 3 subtype A1 sequences as the outgroup. Five significantly supported monophyletic clusters (numbers inside the monophyletic clades correspond to approximate likelihood ratio test SH-like values) were identified and are colored differently. Branches are scaled in nucleotide substitutions per site according to the bar at the bottom of the figure. (b) Maximum clade credibility trees of the CRF01_AE sequences from China based on the partial pol gene. There were 939 sequences that were finally selected in the dataset. All of the sequences are labeled in color as in the ML tree. The data of MRCA and posterior probability are labeled next to each node.

Figure 3

Distribution of Chinese CRF01_AE sequences from different clusters. The number of sequences from different clusters is listed below the cluster name. The provinces containing sequences from different clusters are colored as in the ML and MCC trees. The transmission routes of sequences from each cluster are also depicted below. Maps were generated with R software 3.3.1 (https://www.r-project.org/).

Figure 4

Demographic history of major CRF01_AE epidemic clusters in mainland China. (a–e) Median estimates of the effective number of infections using Bayesian skyline (solid line) are shown in each graphic together with 95% highest probability density intervals of the Bayesian skyline estimates (blue area). The vertical axes represent the estimated effective number of infections on a logarithmic scale. Time scale is in calendar years. (f) tMRCA and 95 CI of each cluster are listed.