Phylogenetic Networks and Parameters Inferred from HIV Nucleotide Sequences of High-Risk and General Population Groups in Uganda: Implications for Epidemic Control

Abstract

Phylogenetic inference is useful in characterising HIV transmission networks and assessing where prevention is likely to have the greatest impact. However, estimating parameters that influence the network structure is still scarce, but important in evaluating determinants of HIV spread. We analyzed 2017 HIV pol sequences (728 Lake Victoria fisherfolk communities (FFCs), 592 female sex workers (FSWs) and 697 general population (GP)) to identify transmission networks on Maximum Likelihood (ML) phylogenetic trees and refined them using time-resolved phylogenies. Network generative models were fitted to the observed degree distributions and network parameters, and corrected Akaike Information Criteria and Bayesian Information Criteria values were estimated. 347 (17.2%) HIV sequences were linked on ML trees (maximum genetic distance ≤4.5%, ≥95% bootstrap support) and, of these, 303 (86.7%) that consisted of pure A1 (n = 168) and D (n = 135) subtypes were analyzed in BEAST v1.8.4. The majority of networks (at least 40%) were found at a time depth of ≤5 years. The waring and yule models fitted best networks of FFCs and FSWs respectively while the negative binomial model fitted best networks in the GP. The network structure in the HIV-hyperendemic FFCs is likely to be scale-free and shaped by preferential attachment, in contrast to the GP. The findings support the targeting of interventions for FFCs in a timely manner for effective epidemic control. Interventions ought to be tailored according to the dynamics of the HIV epidemic in the target population and understanding the network structure is critical in ensuring the success of HIV prevention programs.

Keywords: HIV; epidemic control; model; parameters; phylodynamic; phylogenetic; populations; prevention; transmission network.

Figure 1

An example of a Maximum Clade Credibility (MCC) time-resolved phylogeny for HIV-1 sequences linked at a maximum genetic distance of 4.5%. Tips (without labels) on the tree represent sampled sequences that are linked (nodes supported by a high posterior probability of 1) with the branches colored according to the population (green, fisherfolk communities; red, female sex workers; blue, general population; purple, historical Ugandan samples collected during the early years (1980s) of the epidemic). The black colored branches are reference sequences that were downloaded from the Los Alamos HIV sequence database. Time scale at the bottom is in calendar years.

Figure 2

A graph showing the bootstrap resampling of parameter estimates. Panels show the cumulative mean and standard deviation (SD) of $\gamma$ and $k_{min}$, respectively. In both panels, the vertical scale represents the parameter estimates and the horizontal scale represents the number of bootstrap iterations while the black and the red lines represent the mean and 95% CI intervals, respectively.

Figure 3

Model fit statistics. Five models that included the discrete Pareto, Yule, Waring, Negative Binomial and Poisson lognormal were fitted to the observed network degree distributions inferred from HIV sequence datasets of fisherfolk communities (FFCs), female sex workers (FSWs) and the general population (GP). (A) shows the corrected Akaike Information Criteria scores for the model fit while (B) shows the Bayesian Information Criteria (BIC) scores. The model with the lowest AICc and BIC scores was considered as the best-fitting model.