Development of Bacteroides 16S rRNA gene TaqMan-based real-time PCR assays for estimation of total, human, and bovine fecal pollution in water

Abstract

Bacteroides species are promising indicators for differentiating livestock and human fecal contamination in water because of their high concentration in feces and potential host specificity. In this study, a real-time PCR assay was designed to target Bacteroides species (AllBac) present in human, cattle, and equine feces. Direct PCR amplification (without DNA extraction) using the AllBac assay was tested on feces diluted in water. Fecal concentrations and threshold cycle were linearly correlated, indicating that the AllBac assay can be used to estimate the total amount of fecal contamination in water. Real-time PCR assays were also designed for bovine-associated (BoBac) and human-associated (HuBac) Bacteroides 16S rRNA genes. Assay specificities were tested using human, bovine, swine, canine, and equine fecal samples. The BoBac assay was specific for bovine fecal samples (100% true-positive identification; 0% false-positive identification). The HuBac assay had a 100% true-positive identification, but it also had a 32% false-positive rate with potential for cross-amplification with swine feces. The assays were tested using creek water samples from three different watersheds. Creek water did not inhibit PCR, and results from the AllBac assay were correlated with those from Escherichia coli concentrations (r2= 0.85). The percentage of feces attributable to bovine and human sources was determined for each sample by comparing the values obtained from the BoBac and HuBac assays with that from the AllBac assay. These results suggest that real-time PCR assays without DNA extraction can be used to quantify fecal concentrations and provide preliminary fecal source identification in watersheds.

FIG. 1.

Phylogenetic dendrogram showing the relationship of cloned Bacteroides 16S rRNA gene sequences from different animal fecal sources. For each clone in this study, the first two letters represent the state (TN, Tennessee; PA, Pennsylvania; and TX, Texas), the next two letters represent the animal fecal source (Bo, cattle; Eq, horse; Av, chicken; Ca, dog; Sw, swine; and Hu, human), and the final number indicates the individual clone within the library. Sequences were aligned, and a bootstrap consensus tree was created using Clustal X (version 1.64b). The root was determined using the 16S rRNA gene sequence from Cytophaga fermentans (M58766) as an outgroup. References for cultured and uncultured Bacteroides or 16S rRNA gene sequences indicated on the tree were M58766 and M58762 (17); X83935, X83952, and X83953 (32); AB050110 (Y. Miyamoto, unpublished data) and AB021165 (27); and AF233400 and AF233408 (5). Plasmids containing the shaded sequences were used to determine the effect on sequence mismatches on real-time PCR assays in Fig. 2.

FIG. 2.

The effect of sequence mismatches on PCR amplification in real-time PCR assays. Serial dilutions of six different plasmids were performed to generate standard curves from 2.5 × 10⁷ copies to 25 copies. Real-time PCR assays were performed as follows: top, AllBac assay with 0 sequence mismatches to all plasmids; middle, HuBac assay with 0 to 7 sequence mismatches; and bottom, BoBac assay with 0 to 14 sequence mismatches. Base pair mismatches between each plasmid and the primer and probe used in the real-time PCR assay are in parentheses in the legend boxes. Plasmids having more than seven mismatches to the primers and probe did not amplify.

FIG. 3.

Threshold cycle measurements using the AllBac real time PCR assay in water samples containing bovine feces. Real-time PCR assays were performed on three separate days using triplicate samples for each dilution.

FIG. 4.

Concentration of ribosomal genes in DNA extracts from animal fecal samples determined by the AllBac, HuBac, and BoBac assays. For each sample, the first two letters represent the state (TN, Tennessee; PA, Pennsylvania; and TX, Texas) and the next two letters represent the animal fecal source (Bo, cattle; Eq, horse; Ca, dog; Sw, swine; and Hu, human).

FIG. 5.

Concentration of ribosomal genes in unextracted animal fecal samples determined by the AllBac, HuBac, and BoBac assays. For each sample, the first two letters represent the state (TN, Tennessee; PA, Pennsylvania; and TX, Texas) and the next two letters represent the animal fecal source (Bo, cattle; Eq, horse; Ca, dog; Sw, swine; and Hu, human).

FIG. 6.

Comparison of AllBac and HuBac assays performed on serial dilutions from five individual human fecal samples (top), and the AllBac and BoBac assays run at 57°C on serial dilutions of six individual bovine fecal samples (bottom).