High-throughput monitoring of wild bee diversity and abundance via mitogenomics

Abstract

Bee populations and other pollinators face multiple, synergistically acting threats, which have led to population declines, loss of local species richness and pollination services, and extinctions. However, our understanding of the degree, distribution and causes of declines is patchy, in part due to inadequate monitoring systems, with the challenge of taxonomic identification posing a major logistical barrier. Pollinator conservation would benefit from a high-throughput identification pipeline.We show that the metagenomic mining and resequencing of mitochondrial genomes (mitogenomics) can be applied successfully to bulk samples of wild bees. We assembled the mitogenomes of 48 UK bee species and then shotgun-sequenced total DNA extracted from 204 whole bees that had been collected in 10 pan-trap samples from farms in England and been identified morphologically to 33 species. Each sample data set was mapped against the 48 reference mitogenomes.The morphological and mitogenomic data sets were highly congruent. Out of 63 total species detections in the morphological data set, the mitogenomic data set made 59 correct detections (93·7% detection rate) and detected six more species (putative false positives). Direct inspection and an analysis with species-specific primers suggested that these putative false positives were most likely due to incorrect morphological IDs. Read frequency significantly predicted species biomass frequency (R² = 24·9%). Species lists, biomass frequencies, extrapolated species richness and community structure were recovered with less error than in a metabarcoding pipeline.Mitogenomics automates the onerous task of taxonomic identification, even for cryptic species, allowing the tracking of changes in species richness and distributions. A mitogenomic pipeline should thus be able to contain costs, maintain consistently high-quality data over long time series, incorporate retrospective taxonomic revisions and provide an auditable evidence trail. Mitogenomic data sets also provide estimates of species counts within samples and thus have potential for tracking population trajectories.

Keywords: Hymenoptera; agri‐environment schemes; biodiversity and ecosystem services; farmland biodiversity; genome skimming; metabarcoding; metagenomics; mitogenomes; neonicotinoids; pollination.

Figure 1

Mitogenomic resequencing pipeline. (1) Reference mitogenomes were assembled from 48 bee species. (2). The 204 bee individuals in 10 bulk samples were morphologically identified to 33 bee species. (3) Total DNA from the same 10 samples was shotgun‐sequenced (the ‘resequencing’ step), and the reads were bioinformatically mapped to the reference mitogenomes, generating Table 1. Note that the vast majority of the output in step 3 was nuclear genome reads, which were discarded.

Figure 2

Frequency histograms of read coverages from the true‐negative and true‐positive detections in the mitogenomics pipeline. The dashed line at 10% is the threshold used to calculate species‐detection statistics. Inset: A map of read coverages on the 48 mitogenomes from sample HD_CG_1, showing the 6 true positives (Bombus pascuorum, B. terrestris, Lasioglossum calceatum, L. leucopus, L. leucozonium and L. malachurum) plus Bombus lucorum, a putative false positive that was confirmed by species‐specific PCR (Fig. S6).

Figure 3

Scatterplot of biomasses versus read numbers. Each data point is one bee species in one sample (samples indicated by colours). The biomass and read numbers were z‐transformed to correct for different sample sizes. The dashed line is the 1:1 line. If all points were on this line, there would be no error in converting from reads to biomass, and thus from biomass to counts (given a species‐typical biomass). The thick solid line is the generalised least squares (GLS) regression (read_freqs ~ 0·0137 + 0·5840*biomass_freqs), and the thin solid line is the linear regression. Both regressions are highly significant (P = 0·0001), and the linear regression returns an R² of 24·9%. Conducting the same regression analysis but using metabarcode‐read frequency produced a non‐significant GLS regression (P = 0·237, Fig. S4).

Figure 4

Community analyses. Lines connect samples from the same farm. In the left hand column are the results using the morphological data set (Bee biomass frequencies). In the right‐hand column are the results using the mitogenomic data set (Read frequencies). The top row uses presence/absence. The bottom row uses biomass and read frequencies (quantitative). In general, the morphological and mitogenomic data sets (comparing left with right) organise the samples highly similarly (procrustes r _{presence/absence} = 0·981, P = 0·001; r _quantitative = 0·966, P = 0·001; 9999 permutations). Samples from the same farm and locations tend to cluster together. CN = Chilterns North; CS = Chilterns South, HD = Hampshire Downs, and LW = Low Weald. CG = Conservation Grade farm; OELS = Organic+Entry‐Level‐Stewardship farm; ELS = Entry‐Level‐Stewardship farm. See Fig. S5 for the metabarcoding result.