Shotgun pyrosequencing metagenomic analyses of dusts from swine confinement and grain facilities

Abstract

Inhalation of agricultural dusts causes inflammatory reactions and symptoms such as headache, fever, and malaise, which can progress to chronic airway inflammation and associated diseases, e.g. asthma, chronic bronchitis, chronic obstructive pulmonary disease, and hypersensitivity pneumonitis. Although in many agricultural environments feed particles are the major constituent of these dusts, the inflammatory responses that they provoke are likely attributable to particle-associated bacteria, archaebacteria, fungi, and viruses. In this study, we performed shotgun pyrosequencing metagenomic analyses of DNA from dusts from swine confinement facilities or grain elevators, with comparisons to dusts from pet-free households. DNA sequence alignment showed that 19% or 62% of shotgun pyrosequencing metagenomic DNA sequence reads from swine facility or household dusts, respectively, were of swine or human origin, respectively. In contrast only 2% of such reads from grain elevator dust were of mammalian origin. These metagenomic shotgun reads of mammalian origin were excluded from our analyses of agricultural dust microbiota. The ten most prevalent bacterial taxa identified in swine facility compared to grain elevator or household dust were comprised of 75%, 16%, and 42% gram-positive organisms, respectively. Four of the top five swine facility dust genera were assignable (Clostridium, Lactobacillus, Ruminococcus, and Eubacterium, ranging from 4% to 19% relative abundance). The relative abundances of these four genera were lower in dust from grain elevators or pet-free households. These analyses also highlighted the predominance in swine facility dust of Firmicutes (70%) at the phylum level, Clostridia (44%) at the Class level, and Clostridiales at the Order level (41%). In summary, shotgun pyrosequencing metagenomic analyses of agricultural dusts show that they differ qualitatively and quantitatively at the level of microbial taxa present, and that the bioinformatic analyses used for such studies must be carefully designed to avoid the potential contribution of non-microbial DNA, e.g. from resident mammals.

Figure 1. BLASTn screening scheme used for alignment of shotgun metagenomic reads to swine and human genomes.

Post-QC shotgun metagenomic reads from swine facility dust, swine feces, grain elevator dust and household dust without pets were aligned against the swine draft (ssc_ref_Sscrofa10) and human genome (hs_ref_GRCh37.p5) sequence. Reads that aligned against the swine draft and/or the human reference genome sequence with an expect value of less than 10⁻⁵ were subsequently aligned against all finished and draft bacterial genome sequence assemblies currently available at the NCBI FTP site on 11/16/2011. Except were indicated, filtered reads were used in all subsequent bioinformatics analyses. * From the NCBI Sequence Read Archive; E_S/H =  expect values for reads aligned to swine and/or human genomes; E_F =  expect values for reads with poor alignment with swine or human genomes (filtered reads).

Figure 2. DNA yield of dust isolated from swine confinement facilities, grain elevators and households without pets.

Total genomic DNA was isolated by a bead-beating protocol (Mo Bio, Power Clean, Carlsbad, CA) and quantified using a Nanodrop ND-1000 UV spectrophotometer (NanoDrop Technologies, Wilmington, DE). Each bar represents the mean DNA yield (µg/mg dust) ± SEM from two independent dust samples.

Figure 3. Taxonomic classification of metagenomic reads from swine confinement facility dust, grain elevator dust and household dust without pets.

A. Domain level; B. Phylum level. Each pie chart represents relative abundance values expressed as the total number domains (“pre-filtered” dataset) or phyla (“filtered” dataset) from swine confinement facility dust, grain elevator dust and household dust without pets. Other sequences equals reads that align significantly to the M5NR database that are derived from taxa not listed as descendants from one of the domains; Unassigned equal reads that do not align significantly to any M5NR database sequence.

Figure 4. Genus abundance ranking of swine confinement facility dust reads in comparison to grain elevator dust and household dust without pets.

Relative abundance values are expressed on the ordinate as a fraction of the total number of genera identified in swine dust. The 15 most abundant genera identified using the swine facility dust shotgun metagenomic reads and the M5NR database are shown. Relative abundance values were calculated for these same 15 genera for dust collected from grain elevators and households without pets. See Figure S4 for comparisons at the Phylum, Class, Order, and Family taxonomic levels. Black = Swine dust; Gray = House dust; White = Grain dust.

Figure 5. Principal Component Analysis (PCA) of shotgun metagenomic reads from swine facility dust, grain elevator dust, household dust without pets and swine feces: Relative abundance of Genera.

PCA was performed in STAMP using MG-RAST Genus-level organism abundance profiles that were derived from two swine facility dust samples, two grain elevator dust samples, two household dust samples without pets and three swine feces samples. A. The “filtered” reads from the swine confinement facility dust and the household dust datasets were used in the analyses. B. The “filtered” and “swine/human” reads from the swine confinement facility dust and the household dust datasets, respectively, were used in the analyses. Each symbol represents a sample. • Grain elevator dust (green); ▪ Household dust without pets (“filtered”, yellow); ▴ Swine confinement facility dust (“filtered”, red); ♦ Swine feces (blue).

Figure 6. Candidate biomarker analyses based on Genus abundance profiles from dust-derived shotgun metagenomic read datasets.

STAMP Extended Error Graph of the top ranked genera identified in a two-group statistical test comparing MG-RAST Genus abundance profiles generated using the M5NR database for swine facility dust dataset (red) and both household and grain elevator dust datasets (black). Ranking of the genera is based on significance (q) values, which were corrected for multiple testing and show the indicated value for Storey’s false discovery rate. The unclassified genus shown is annotated by MG-RAST as derived from Erysipelotrichaceae.