The European livestock resistome

Abstract

Metagenomic sequencing has proven to be a powerful tool in the monitoring of antimicrobial resistance (AMR). Here, we provide a comparative analysis of the resistome from pigs, poultry, veal calves, turkey, and rainbow trout, for a total of 538 herds across nine European countries. We calculated the effects of per-farm management practices and antimicrobial usage (AMU) on the resistome in pigs, broilers, and veal calves. We also provide an in-depth study of the associations between bacterial diversity, resistome diversity, and AMR abundances as well as co-occurrence analysis of bacterial taxa and antimicrobial resistance genes (ARGs) and the universality of the latter. The resistomes of veal calves and pigs clustered together, as did those of avian origin, while the rainbow trout resistome was different. Moreover, we identified clear core resistomes for each specific food-producing animal species. We identified positive associations between bacterial alpha diversity and both resistome alpha diversity and abundance. Network analyses revealed very few taxa-ARG associations in pigs but a large number for the avian species. Using updated reference databases and optimized bioinformatics, previously reported significant associations between AMU, biosecurity, and AMR in pig and poultry farms were validated. AMU is an important driver for AMR; however, our integrated analyses suggest that factors contributing to increased bacterial diversity might also be associated with higher AMR load. We also found that dispersal limitations of ARGs are shaping livestock resistomes, and future efforts to fight AMR should continue to emphasize biosecurity measures.IMPORTANCEUnderstanding the occurrence, diversity, and drivers for antimicrobial resistance (AMR) is important to focus future control efforts. So far, almost all attempts to limit AMR in livestock have addressed antimicrobial consumption. We here performed an integrated analysis of the resistomes of five important farmed animal populations across Europe finding that the resistome and AMR levels are also shaped by factors related to bacterial diversity, as well as dispersal limitations. Thus, future studies and interventions aimed at reducing AMR should not only address antimicrobial usage but also consider other epidemiological and ecological factors.

Keywords: antimicrobial resistance; diversity; livestock; metagenomics; resistome.

Fig 1

AMR in different livestock cohorts. (a) Summed abundance of AMR genes across the livestock species (log2). Horizontal box lines represent the first quartile, the median, and the third quartile. Whiskers extend to the smallest and largest data points within the interval (first quartile − 1.5 × interquartile range [IQR], third quartile + 1.5 × IQR). Data points outside this interval are plotted as circles. (b) Class-level AMR composition. Samples are grouped into panels by host species and country; each sample is represented by a stacked vertical bar. Colors indicate the relative number of gene counts corresponding to each AMR class. (c and d) AMR gene-level biplot, based on mean IQLR values obtained with ALDEx2 and Euclidean distances in the resulting simplex space. Low-quality fish samples are excluded (44 excluded out of 58 total). (c) Projection of livestock samples onto the first two principal components. Ellipses show the 95% confidence interval for each host species (multivariate t-distribution). (d) Corresponding projection of AMR genes onto the (same) first two principal components. The 15 genes with the highest variance in IQLR space are shown and colored according to their AMR class.

Fig 2

Animal host effect on AMR genes. Color shades represent relatively high (red) and low (blue) gene abundances in herds of the corresponding host species. Text labels indicate the number and direction of pairwise differential abundance tests flagged as “substantial” (ALDEx2: absolute effect size >1 and overlap <0.05) for this gene and host species. Only AMR genes with at least one substantial pairwise result are shown.

Fig 3

Country effect on AMR genes within different host species. Color shades represent relatively high (red) and low (blue) gene abundances in herds from the corresponding country. Text labels indicate the number and direction of pairwise differential abundance tests flagged as “substantial” (ALDEx2: absolute effect size >1 and overlap <0.05) for this gene and country. Only AMR genes with at least one substantial pairwise result are shown (no such result was detected in veal calf herds).

Fig 4

Alpha diversity of livestock microbiomes. (a) Estimated richness (Chao1) of AMR genes, separated by host species and country of origin. (b) Estimated species richness (Chao1) of bacterial species, separated by host species and country of origin. (c) Association between bacterial and AMR estimated richness from previous plots. (d) Association between bacterial species and AMR gene diversity, calculated as effective number of species exp(Shannon). (e) Association between AMR diversity and total AMR load. (c–e) Local regression lines (loess) are drawn separately for each animal species and mark extrema on the x-axis. See panel a for the meaning of the color.

Fig 5

Co-occurrence correlation networks of bacteria and ARGs within terrestrial livestock. Fruchterman Reingold network representation of Spearman’s rank correlations (rho > 0.8, and Benjamini–Hochberg-corrected P < 0.01) between bacterial (genera) and ARG (ARGs clustered on 90% sequence identity) as well as within ARG taxa. Nodes represent bacterial (green) and ARG (pink) taxa (node sizes reflect the degree of connectivity). Edges represent either positive (red) or negative (blue) Spearman’s correlations between taxa. (a) Co-occurrence networks for broilers (a), pigs (b), turkey (c) and veal calves (d) can be seen.

Fig 6

Universality dynamics of ARGs in terrestrial livestock. (a–d) Scatter plots and local trend lines for associations between resistome overlap (x) and dissimilarity (y) in farm sample pairs, stratified by same (a, c) and differing (b, d) countries (columns) and same (a, b) and differing (c, d) livestock species status (rows). (e) Model coefficients for log⁡dissimilarity ~ log⁡1-overlap*Category where category encodes whether covariates are shared. On the x-axis, shifting further to the right suggests a more universal or stronger effect on the negativity of the dissimilarity–overlap curve.