Spatiotemporal analysis of microbial community dynamics during seasonal stratification events in a freshwater lake (Grand Lake, OK, USA)

Abstract

Many freshwater lakes undergo seasonal stratification, where the formation of phototrophic blooms in the epilimnion and subsequent sedimentation induces hypoxia/anoxia in the thermocline and hypolimnion. This autochthonously produced biomass represents a major seasonal organic input that impacts the entire ecosystem. While the limnological aspects of this process are fairly well documented, relatively little is known regarding the microbial community response to such events, especially in the deeper anoxic layers of the water column. Here, we conducted a spatiotemporal survey of the particle-associated and free-living microbial communities in a warm monomictic freshwater reservoir (Grand Lake O' the Cherokees) in northeastern Oklahoma, USA. Pre-stratification samples (March) harbored a homogeneous community throughout the oxygenated water column dominated by typical oligotrophic aquatic lineages (acl clade within Actinobacteria, and Flavobacterium within the Bacteroidetes). The onset of phototrophic blooming in June induced the progression of this baseline community into two distinct trajectories. Within the oxic epilimnion, samples were characterized by the propagation of phototrophic (Prochlorococcus), and heterotrophic (Planctomycetes, Verrucomicrobia, and Beta-Proteobacteria) lineages. Within the oxygen-deficient thermocline and hypolimnion, the sedimentation of surface biomass induced the development of a highly diverse community, with the enrichment of Chloroflexi, "Latescibacteria", Armatimonadetes, and Delta-Proteobacteria in the particle-associated fraction, and Gemmatimonadetes and "Omnitrophica" in the free-living fraction. Our work documents the development of multiple spatially and temporally distinct niches during lake stratification, and supports the enrichment of multiple yet-uncultured and poorly characterized lineages in the lake's deeper oxygen-deficient layers, an ecologically relevant microbial niche that is often overlooked in lakes diversity surveys.

Fig 1. Geographical location of Grand Lake (right panel).

The sites sampled for this study are shown in the left panel and their coordinates are noted. All three sites lie in the lacustrine area of the lake.

Fig 2. Grand Lake physical and chemical characteristics (X-axis) along depth (in meters) (Y-axis) and season (March, red; June, black; and September, green).

Data are shown for the three sites sampled in this study (site name is shown on top).

Fig 3. Diversity estimates calculated for each of the datasets obtained and shown for the three sites sampled in this study (site name is shown on top).

(A) ACE species richness estimator, (B) the number of observed OTUs _0.03, (C) Shannon diversity index (A-C all normalized to the number of sequences in the smallest dataset), and (D) rarefaction curve ranking (with 1 being the most diverse). Results are grouped first by sampling depth, then by the physical state of the sample (free-living (FL) versus particle-associated (PA)) and shown across the sampling season (March, Black bars; June, White bars; September, Grey bars).

Fig 4. Microbial community structure analysis shown as non-metric multidimensional scaling (NMDS) plots based on Bray Curtis dissimilarity indices (at the species level (0.03)) for pairwise differences between datasets originating from the sites Tree (Circles), P. Dam (Squares), and Dream (Triangles).

The sampling depth is denoted by color; epilimnion (red), thermocline (green), and hypolimnion (blue), the sample physical state is denoted by open (for free-living) and closed (for particle-associated) symbols, and the sampling time is shown by letters inside the symbols; March (M), June (J), and September (S). Sampling time (A) had the greatest effect on community structure where no overlap was observed between samples originating from different months. The same NMDS plot in (A) is shown in panels B and C but truncated to only show samples from a single sampling month (March, June, or September) as indicated in the top left corner of the Fig. To facilitate visualization of the depth (panel B) and the sample physical state (panel C) on community structure, black lines were added to surround all samples from the same depth (panel B) or with the same physical state (panel C). Samples were grouped by the sampling depth (B) in June (middle panel), and September (right panel) but not in March (left panel). Note the accentuation of the sampling depth effect on community structure as time increases from June to September. Finally, the sample physical state (C) affected the community structure in June (middle panel), and to a larger extent in September (right panel), where a clear separation of the PA (closed symbols) and FL (open symbols) communities is starting to form.

Fig 5. Microbial community composition in Grand Lake in March (pre-stratification) samples.

Datasets are grouped on the X-axis first by the sampling site, then by the sampling depth (Bot, hypolimnion; Mid, thermocline; and Sur, epilimnion), then by the sample physical state (free-living, FL; particle-associated, PA). (A) The community composition is shown at the phylum level (or class level for Proteobacteria). “Others” denote all phyla with < 1% total abundance, and “unclassified” denote the sequences that could not be classified with accuracy at the phylum level. (B) Sub-class level classification of Actinobacteria. The Y-axis shows percentage within total Actinobacteria sequences identified. (C) Sub-class level classification of Bacteroidetes. The Y-axis shows percentage within total Bacteroidetes sequences identified.

Fig 6. Epilimnion microbial community composition in Grand Lake in June and September when the lake was stratified.

(A) The community composition is shown at the phylum level (or class level for Proteobacteria). “Others” denote all phyla with < 1% total abundance, and “unclassified” denote the percentage abundance of sequences that could not be classified with accuracy at the phylum level. (B-E) Sub-class level classification of (B) Cyanobacteria, (C) Planctomycetes, (D) Verrucomicrobia, and (E) Beta-Proteobacteria. The Y-axis in B-E shows percentage within total Phylum/Class sequences identified. The progressive decrease in Actinobacteria and Bacteroidetes average percentage abundance (across the three sites studied) is shown in (F) for the FL and the PA epilimnion communities. In (A-E) datasets are grouped on the X-axis first by the sampling site, then by the sample physical state (free-living, FL; particle-associated, PA), then by the sampling time (June; and September, Sept). Datasets in (F) are grouped on the X-axis first by the sample physical state (free-living, FL; particle-associated, PA), then by the sampling time (March, June, and September).

Fig 7. Thermocline and hypolimnion microbial community composition in June.

The datasets are grouped on the X-axis first by the sampling site, then by the sample physical state (free-living, FL; particle-associated, PA), then by the sampling depth (Bottom, hypolimnion; Middle, thermocline). (A) The community composition is shown at the phylum level (or class level for Proteobacteria). “Others” denote all phyla with < 1% total abundance, and “unclassified” denote the percentage abundance of sequences that could not be classified with accuracy at the phylum level. (B-G) Sub-class level classification of (B) Bacteroidetes, (C) Gamma-Proteobacteria, (D) Beta-Proteobacteria, and (E) Verrucomicrobia, (F) Planctomycetes, and Alpha-Proteobacteria. The Y-axis in (B-G) shows percentage within total Phylum/Class sequences identified.

Fig 8. Thermocline (Middle) and hypolimnion (Bottom) particle-associated microbial community composition in September.

Shown are the average percentage abundances across the three sites studied. (A) The community composition is shown at the phylum level (or class level for Proteobacteria). “Others” denote all phyla with < 1% total abundance, and “unclassified” denote the percentage abundance of sequences that could not be classified with accuracy at the phylum level. (B-N) Sub-class level classification of (B) Actinobacteria, (C) Beta-Proteobacteria, (D) Verrucomicrobia, (E) Bacteroidetes, (F) Planctomyetes, (G) Alpha-Proteobacteria, (H) Gamma-Proteobacteria, (I) Cyanobacteria, (J) Delta-Proteobacteria, (K) Acidobacteria, (L) Chloroflexi, (M) Armatimonadetes, and (N) WS3. The Y-axis in (B-N) shows percentage within total Phylum/Class sequences identified.

Fig 9. A model depicting the stratification process and the associated changes in dissolved O₂ concentration in Grand Lake from a completely mixed oxic (pink) water column in March (left panel), to the stratification and the development of an oxic epilimnion (pink), a hypoxic thermocline (green), and a completely anoxic hypolimnion (blue) in June (thermocline panel) and September (right panel).

The depth in (m) is shown to the left of the panels. The increase in the particulate concentration that happens with the algal blooming in June in the epilimnion along with the sedimentation of particles to the thermocline and the hypolimnion in June and September is shown as black ovals, the number of which in each layer (epilimnion, thermocline, and hypolimnion) is proportional to the turbidity and BGA cell counts. The size of the ovals is smaller and their number is lower in March to reflect the low turbidity and BGA counts pre-stratification. In June and September panels, the temperature (average temperature across the three sites studied, °C), turbidity (average turbidity across the three sites studied, NTU), and Chlorophyll A (average concentration across the three sites studied, μg/L) are shown (X-axis on top) versus depth (shown in M to the left of the panels). Also depicted is the average microbial community composition at the phylum level (or class level for Proteobacteria) for each of the sampling times and each of the sampling depths shown as % total abundance and grouped by sample physical state as FL or PA (shown on top). The phyla/class color-coding is shown at the hypolimnion. “Others” denote all phyla with < 1% total abundance, including the “unclassified” fraction (sequences that could not be classified with accuracy at the phylum level).