Investigating Effects of Tulathromycin Metaphylaxis on the Fecal Resistome and Microbiome of Commercial Feedlot Cattle Early in the Feeding Period

Abstract

The objective was to examine effects of treating commercial beef feedlot cattle with therapeutic doses of tulathromycin, a macrolide antimicrobial drug, on changes in the fecal resistome and microbiome using shotgun metagenomic sequencing. Two pens of cattle were used, with all cattle in one pen receiving metaphylaxis treatment (800 mg subcutaneous tulathromycin) at arrival to the feedlot, and all cattle in the other pen remaining unexposed to parenteral antibiotics throughout the study period. Fecal samples were collected from 15 selected cattle in each group just prior to treatment (Day 1), and again 11 days later (Day 11). Shotgun sequencing was performed on isolated metagenomic DNA, and reads were aligned to a resistance and a taxonomic database to identify alignments to antimicrobial resistance (AMR) gene accessions and microbiome content. Overall, we identified AMR genes accessions encompassing 9 classes of AMR drugs and encoding 24 unique AMR mechanisms. Statistical analysis was used to identify differences in the resistome and microbiome between the untreated and treated groups at both timepoints, as well as over time. Based on composition and ordination analyses, the resistome and microbiome were not significantly different between the two groups on Day 1 or on Day 11. However, both the resistome and microbiome changed significantly between these two sampling dates. These results indicate that the transition into the feedlot-and associated changes in diet, geography, conspecific exposure, and environment-may exert a greater influence over the fecal resistome and microbiome of feedlot cattle than common metaphylactic antimicrobial drug treatment.

Keywords: feedlot; metagenomics; metaphylaxis; microbiome; resistome; tulathromycin.

Figure 1

Total AMR gene abundance determined by shotgun metagenomic sequencing and normalized using 16S rRNA abundance, by drug class, among treated and untreated cattle in samples obtained at Day 1 and again at Day 11. Values are formulated from the number of reads that aligned to AMR genes and normalized to bacterial abundance characterized by alignments to 16S gene sequences from the Greengenes database.

Figure 2

Ordination comparing resistome composition at the AMR drug class and resistance mechanism, using non-metric multidimensional scaling (NMDS), for the two study groups at Day 1 and Day 11. Separation of resistomes from treated and untreated cattle was not statistically significant at either Day 1 or Day 11 (Day 1 vs. Day 11; ANOSIM P > 0.05). However, the resistomes of the treated and untreated groups were significantly separated over time (Day 1 vs. Day 11; ANOSIM P < 0.05).

Figure 3

Log-fold change in abundance to AMR mechanisms for the treated (red bars) and untreated (gray bars) over time from Day 1 to day11. Bars to the right of the 0-line signify an increase in abundance, the size of the bars represent the average expression of the AMR mechanism and bars are labeled with adjusted p-values < 0.05.

Figure 4

Boxplot of resistome richness and Shannon's diversity at the AMR class and mechanism levels of the two study groups at Day 1 and Day 11. The horizontal line is the median value, the middle box indicates the inter-quantile range, whiskers represent values within 1.5 IQR of the lower and upper quartiles, and individual points show outlier values.

Figure 5

Average relative abundance of CSS normalized counts of shotgun metagenomic reads aligning to bacterial, archaeal and viral genomes at the phylum level for both study groups at Day 1 and Day 11. Phyla comprising <3% of each sample group were combined into the category “Low abundance phyla”.

Figure 6

Ordination comparing microbiome composition at the phylum, class, and order levels, using non-metric multidimensional scaling (NMDS), for treated and untreated groups of cattle at Day 1 and Day 11. Separation of microbiomes from treated and untreated cattle was not statistically significant at either Day 1 or Day 11 (treated vs. untreated; ANOSIM P > 0.05). However, microbiomes for the study groups differed significantly over time (Day 1 vs. Day 11; ANOSIM P < 0.05).

Figure 7

Boxplot of microbiome richness and Shannon's diversity at the phylum, class and order levels of the two study groups at Day 1 and Day 11. The horizontal line is the median value, the middle box indicates the inter-quantile range, whiskers represent values within 1.5 IQR of the lower and upper quartiles, and individual points show outlier values.