A Metagenomic Approach to Evaluating Surface Water Quality in Haiti

Abstract

The cholera epidemic that occurred in Haiti post-earthquake in 2010 has resulted in over 9000 deaths during the past eight years. Currently, morbidity and mortality rates for cholera have declined, but cholera cases still occur on a daily basis. One continuing issue is an inability to accurately predict and identify when cholera outbreaks might occur. To explore this surveillance gap, a metagenomic approach employing environmental samples was taken. In this study, surface water samples were collected at two time points from several sites near the original epicenter of the cholera outbreak in the Central Plateau of Haiti. These samples underwent whole genome sequencing and subsequent metagenomic analysis to characterize the microbial community of bacteria, fungi, protists, and viruses, and to identify antibiotic resistance and virulence associated genes. Replicates from sites were analyzed by principle components analysis, and distinct genomic profiles were obtained for each site. Cholera toxin converting phage was detected at one site, and Shiga toxin converting phages at several sites. Members of the Acinetobacter family were frequently detected in samples, including members implicated in waterborne diseases. These results indicate a metagenomic approach to evaluating water samples can be useful for source tracking and the surveillance of pathogens such as Vibrio cholerae over time, as well as for monitoring virulence factors such as cholera toxin.

Keywords: Haiti; bioinformatics; cholera; environmental sampling; metagenomic analysis; principle components analysis; water quality; whole genome sequencing.

Figure 1

Sampling sites in the Central Plateau of Haiti (Mapdata©2018 Google). A blue star denotes the first cluster of cholera cases just south of Mirebalais [23]. Sites labelled 1 through 5a were sampled in triplicate in January 2018. Single samples were taken from sites labelled 6 and 7 in July 2017. Sites 1, 4 and 5b were also sampled in July 2017.

Figure 2

Krona visualization. Total bacterial diversity, representing gamma diversity, among all samples from the January 2018 time point.

Figure 3

Choa1 alpha diversity. All three replicates of each site are represented by a box plot. Raw data used to generate the box plots are presented in Supplemental Table S2.

Figure 4

Principle components analysis (PCA) of relative abundance of bacteria at all sites, including July 2017 samples, which were not replicated (* Site ~1 mile below Lac de Péligre dam).

Figure 5

PCA of relative abundance of bacteria from replicate samples collected in January 2018.