Genomic Epidemiology Reconstructs the Introduction and Spread of Zika Virus in Central America and Mexico

Abstract

The Zika virus (ZIKV) epidemic in the Americas established ZIKV as a major public health threat and uncovered its association with severe diseases, including microcephaly. However, genetic epidemiology in some at-risk regions, particularly Central America and Mexico, remains limited. We report 61 ZIKV genomes from this region, generated using metagenomic sequencing with ZIKV-specific enrichment, and combine phylogenetic, epidemiological, and environmental data to reconstruct ZIKV transmission. These analyses revealed multiple independent ZIKV introductions to Central America and Mexico. One introduction, likely from Brazil via Honduras, led to most infections and the undetected spread of ZIKV through the region from late 2014. Multiple lines of evidence indicate biannual peaks of ZIKV transmission in the region, likely driven by varying local environmental conditions for mosquito vectors and herd immunity. The spatial and temporal heterogeneity of ZIKV transmission in Central America and Mexico challenges arbovirus surveillance and disease control measures.

Keywords: Central America; Mexico; Zika virus; bait capture enrichment; effective reproductive number; genomics; metagenomic sequencing; phylodynamics; transmission; “spiked” primer enrichment.

Graphical abstract

Figure 1

Zika Virus Sampling and Sequencing in Central America and Mexico (A) Map of Central America and Mexico. Colored circles indicate the sampling locations of Zika virus sequences generated in this study, and the locations of publicly available sequences from Central America and Mexico. (B) The temporal and geographic distribution of Zika virus qRT-PCR-positive samples tested in this study. Samples are colored according to their sampling location. (C) Consensus genome coverage of the Zika virus sequences generated in this study. Sequences are colored according to their sampling location and the Zika virus genome structure is shown above the plot.

Figure 2

Genomic Epidemiology of Zika Virus in Central America and Mexico (A) A maximum clade credibility phylogeny estimated from complete and partial Zika virus sequences from the Americas (see STAR Methods for details). For visual clarity, basal Asian and Pacific lineages are not displayed, and two large clades (corresponding to groups of sequences in South America and the Caribbean) have been collapsed and their positions indicated by purple and brown squares, respectively. Violin plots show the posterior distributions of the estimated dates of nodes A and B (see main text). Branch colors indicate the most probable ancestral lineage locations of isolates from the Central America and Mexico region. Circles at internal nodes denote clade posterior probabilities >0.75. For selected nodes, colored numbers show the posterior probabilities of inferred ancestral locations, while black numbers are the clade posterior probabilities. (B) Earliest inferred dates of Zika virus introduction to and within Central America and Mexico. Each box-and-whisker plot corresponds to the earliest movement between a pair of locations with well-supported virus lineage migration (left color, source location; right color, destination location). Letters indicate federal states of Mexico (C, Chiapas; O, Oaxaca; G, Guerrero). (C) Effective reproductive number (R_e) through time, estimated using a birth-death skyline approach. The black line, darker shading, and lighter shading represent, respectively, the median posterior estimate of R_e, and its 50% and 95% highest posterior density credible intervals. Circled numbers indicate the four periods of epidemic dynamics mentioned in the main text.

Figure 3

Geographic and Temporal Distribution of Zika Virus Cases in Central America and Mexico Each panel corresponds to a country within the Central America and Mexico region. In each panel, the bar plots show notified Zika virus cases per week until May 2017 (plots adapted from PAHO); dashed lines indicate the estimated climatic vector suitability score, averaged across the country (see STAR Methods for details); and a small colored arrowhead indicates the date of earliest confirmation of autochthonous Zika virus cases in that country.

Figure 4

Spatial and Temporal Heterogeneity of Zika Virus Transmission in Honduras (A) Maps of Central America centered on Honduras showing population density (left panel) and elevation (right panel). In the bottom panel, the bar plots show notified Zika virus cases per week for the two main cities of Honduras highlighted on the population density map. For each bar plot, dashed lines indicate the estimated climatic vector suitability score for the two cities. (B) Maps of estimated Aedes aegypti climatic suitability scores. Monthly averages for January and June are shown.