Bluetongue virus spread in Europe is a consequence of climatic, landscape and vertebrate host factors as revealed by phylogeographic inference

Abstract

Spatio-temporal patterns of the spread of infectious diseases are commonly driven by environmental and ecological factors. This is particularly true for vector-borne diseases because vector populations can be strongly affected by host distribution as well as by climatic and landscape variables. Here, we aim to identify environmental drivers for bluetongue virus (BTV), the causative agent of a major vector-borne disease of ruminants that has emerged multiple times in Europe in recent decades. In order to determine the importance of climatic, landscape and host-related factors affecting BTV diffusion across Europe, we fitted different phylogeographic models to a dataset of 113 time-stamped and geo-referenced BTV genomes, representing multiple strains and serotypes. Diffusion models using continuous space revealed that terrestrial habitat below 300 m altitude, wind direction and higher livestock densities were associated with faster BTV movement. Results of discrete phylogeographic analysis involving generalized linear models broadly supported these findings, but varied considerably with the level of spatial partitioning. Contrary to common perception, we found no evidence for average temperature having a positive effect on BTV diffusion, though both methodological and biological reasons could be responsible for this result. Our study provides important insights into the drivers of BTV transmission at the landscape scale that could inform predictive models of viral spread and have implications for designing control strategies.

Keywords: bluetongue; environmental drivers; phylogeography; predictor testing; vector-borne pathogen; viral diffusion.

Figure 1.

Spatial distribution of samples and discretizations. (a) Spatial distribution of the 113 samples used to reconstruct the phylogeographic history of BTV in continuous space and discretizations of these samples in (b) arbitrary locations (balanced), (c) individual countries or (d) geographical zones as described in Materials and methods section. Dots were placed at centroids and their sizes are proportional to the sample size.

Figure 2.

Conceptual diagrams. Graphs show expected relationships for correct specification of a predictor. If a predictor facilitates BTV diffusion, a negative relationship is expected between the predictor when treated as a conductor and computed resistances. If a predictor is acting as a barrier of BTV diffusion, a positive relationship is expected between the predictor when treated as a resistor and computed resistances. For both conductors and resistors, the computed resistances are expected to be positively correlated with the viral travel time (phylogeography in continuous space) and negatively with the transition rates between locations (phylogeography in discrete space).

Figure 3.

Support and contribution for a subset of predictors of BTV movement between locations for three different spatial discretizations. For each potential predictor, support is represented by an inclusion probability and a relative contribution indicated for log scale GLM coefficients conditional on the predictor being included in the model (posterior mean and 95% Bayesian CI). Darker dots indicate conditional effect sizes supported by Bayes factors greater than 3. For rasterized variables, resistance distances were obtained with raster treated as a conductance factor.