Environmental DNA from multiple pathogens is elevated near active Atlantic salmon farms

Abstract

The spread of infection from reservoir host populations is a key mechanism for disease emergence and extinction risk and is a management concern for salmon aquaculture and fisheries. Using a quantitative environmental DNA methodology, we assessed pathogen environmental DNA in relation to salmon farms in coastal British Columbia, Canada, by testing for 39 species of salmon pathogens (viral, bacterial, and eukaryotic) in 134 marine environmental samples at 58 salmon farm sites (both active and inactive) over 3 years. Environmental DNA from 22 pathogen species was detected 496 times and species varied in their occurrence among years and sites, likely reflecting variation in environmental factors, other native host species, and strength of association with domesticated Atlantic salmon. Overall, we found that the probability of detecting pathogen environmental DNA (eDNA) was 2.72 (95% CI: 1.48, 5.02) times higher at active versus inactive salmon farm sites and 1.76 (95% CI: 1.28, 2.42) times higher per standard deviation increase in domesticated Atlantic salmon eDNA concentration at a site. If the distribution of pathogen eDNA accurately reflects the distribution of viable pathogens, our findings suggest that salmon farms serve as a potential reservoir for a number of infectious agents; thereby elevating the risk of exposure for wild salmon and other fish species that share the marine environment.

Keywords: aquaculture; disease spillover; infectious disease; microparasites; wild salmon.

Figure 1.

A map depicting (a) all farm tenure sites included in this study as well as individual maps for each sampling year, depicting (b) 2016, (c) 2017, and (d) 2018 sampling sites. Label colours in b, c, and d indicate which sites contained active salmon farms (red) and those that were inactive (black) at the time of sampling. Numbers correspond to site numbers in electronic supplementary material, table S1, which contains information on site status for each sampling year. (Online version in colour.)

Figure 2.

Raw qPCR detections of pathogen eDNA separated by phylum (a) and subdivided by species (b) at active and inactive sites across all three sampling years (2016–2018). Coloured boxes next to pathogen species indicate the phylum (eukaryotes and bacteria) or Baltimore class (viruses) classification group that each pathogen belongs to. The colour of pathogen species' cells (b) indicates the number of detections of each species by site status and sampling year. Cells with a pattern fill indicate pathogen species that were not tested in that sampling year. Numbers above stacked bars (a) indicate the number of active and inactive sites sampled in each year. (Online version in colour.)

Figure 3.

Pathogen eDNA detection odds ratios in relation to active salmon farms and relative Atlantic salmon eDNA concentration. Pathogen-specific odds ratios were generated by adding species-specific random effect estimates to the fixed effect predictor (i.e. farm status or Atlantic salmon eDNA) from multi-year GLMMs. Error bars depict pathogen-specific odds ratios ± fixed effect (farm status or Atlantic salmon eDNA) confidence intervals. Odds ratios for farm status and Atlantic salmon eDNA were generated from multi-year model estimates. Species estimates could not be estimated for pathogens that were represented by a single eDNA detection (I. hoferi, PRV, SPAV-2). Odds ratios from Atlantic salmon eDNA model results depict the change in probability of pathogen eDNA detection associated with a single standard deviation change in Atlantic salmon eDNA concentration.