Decreases in average bacterial community rRNA operon copy number during succession

Abstract

Trait-based studies can help clarify the mechanisms driving patterns of microbial community assembly and coexistence. Here, we use a trait-based approach to explore the importance of rRNA operon copy number in microbial succession, building on prior evidence that organisms with higher copy numbers respond more rapidly to nutrient inputs. We set flasks of heterotrophic media into the environment and examined bacterial community assembly at seven time points. Communities were arrayed along a geographic gradient to introduce stochasticity via dispersal processes and were analyzed using 16 S rRNA gene pyrosequencing, and rRNA operon copy number was modeled using ancestral trait reconstruction. We found that taxonomic composition was similar between communities at the beginning of the experiment and then diverged through time; as well, phylogenetic clustering within communities decreased over time. The average rRNA operon copy number decreased over the experiment, and variance in rRNA operon copy number was lowest both early and late in succession. We then analyzed bacterial community data from other soil and sediment primary and secondary successional sequences from three markedly different ecosystem types. Our results demonstrate that decreases in average copy number are a consistent feature of communities across various drivers of ecological succession. Importantly, our work supports the scaling of the copy number trait over multiple levels of biological organization, ranging from cells to populations and communities, with implications for both microbial ecology and evolution.

Figure 1

(a) NMDS plot showing an increase in beta diversity over successional time. Different colors represent different microcosms from distinct geographic distances (see Supplementary Figure 1); hatched lines of the same color represent replicate microcosms. Points are joined to show successional trajectories over the course of the experiment; terminal arrows show the community composition in the microcosms at the end of the experiment. The scale represents relative Bray–Curtis dissimilarity values. (b) Boxplot showing an increase in beta diversity through successional time. The plot displays Bray–Curtis dissimilarity of each replicate to the centroid (a measure of beta diversity) for each time point. PERMDISP analysis demonstrates significant increases in beta diversity (measured as multivariate dispersion), with samples after 43 h being significantly more dispersed than earlier time points (PERMDISP, P=0.001).

Figure 2

Scatterplot showing a decrease in the mean weighted rRNA copy number over successional time as well as lower variance in copy number in both early and late communities. Copy number was estimated using PICRUSt (Langille et al., 2013) and weighted values were obtained by multiplying copy numbers by relative abundance for each OTU and taking the summation of these values for each community. Bars represent s.d.

Figure 3

Frequency-abundance plots over successional time that show an increase in the relative importance of taxa with lower rRNA copy numbers. The plots at both 19 and 23 h were similar so only the 23-h plot is shown. Each point represents a unique OTU and we have plotted its average relative abundance within a community against its frequency (distribution across samples) among communities. Points are colored by the rRNA copy number as estimated using PICRUSt (Langille et al., 2013).

Figure 4

(a) Net Relatedness Index and (b) Nearest Taxon Index over successional time. Both indices show a significant decrease in phylogenetic clustering as communities assemble. For these analyses we used the Greengenes gg_13_5 tree that was trimmed in QIIME to contain only OTUs observed in this study. Bars represent s.d.

Figure 5

Boxplots and scatterplot showing a decrease in the mean weighted rRNA copy number over successional time for the three additional communities examined: a burned forest soil (a) (Ferrenberg et al., 2013); a salt marsh sediment chronosequence (b) (Dini-Andreote et al., 2015); and a glacier forefield chronosequence (c), which included linear regression analysis (multiple R²=0.4949, P<0.0001). Copy number was estimated using PICRUSt (Langille et al., 2013) and weighted values were obtained by multiplying rRNA copy numbers by relative abundance for a given OTU, and summing weighted averages across a given sample.