What is the extent of prokaryotic diversity?

Abstract

The extent of microbial diversity is an intrinsically fascinating subject of profound practical importance. The term 'diversity' may allude to the number of taxa or species richness as well as their relative abundance. There is uncertainty about both, primarily because sample sizes are too small. Non-parametric diversity estimators make gross underestimates if used with small sample sizes on unevenly distributed communities. One can make richness estimates over many scales using small samples by assuming a species/taxa-abundance distribution. However, no one knows what the underlying taxa-abundance distributions are for bacterial communities. Latterly, diversity has been estimated by fitting data from gene clone libraries and extrapolating from this to taxa-abundance curves to estimate richness. However, since sample sizes are small, we cannot be sure that such samples are representative of the community from which they were drawn. It is however possible to formulate, and calibrate, models that predict the diversity of local communities and of samples drawn from that local community. The calibration of such models suggests that migration rates are small and decrease as the community gets larger. The preliminary predictions of the model are qualitatively consistent with the patterns seen in clone libraries in 'real life'. The validation of this model is also confounded by small sample sizes. However, if such models were properly validated, they could form invaluable tools for the prediction of microbial diversity and a basis for the systematic exploration of microbial diversity on the planet.

Figure 1

Non-parametric methods must be used with caution when sample sizes are small. The sample sizes required to correctly characterize a sample with a diversity (i.e. richness) of 5000, undertaking a complete census, a 95% census or using non-parametric methods (Chao 1 and ACE). Note that if the diversity is uniform, non-parametric estimators are very efficient. However, if the diversity is lognormally distributed, then a very large sample is required to obtain the correct answer. The simulations are described in more detail elsewhere (Schloss & Handelsman in press).

Figure 2

A ‘quick and dirty’ way to estimate diversity by assuming a distribution. (a) The total number of taxa in a community with a lognormal species abundance curve is simply the area under that curve (called the species curve). The individuals curve is the number of species at each abundance (the species curve) multiplied by their abundance (the x-axis). There is therefore a mathematical relationship between the area under a species area curve, the number of individuals N_T (the area under the individuals curve), and the maximum and the minimum abundance (N_max and N_min). (b) The relationship, over 30 orders of magnitude in population size, for various ratios of N_T/N_max by assuming that N_min is equal to one (Curtis et al. 2002). As a rule of thumb, soil has a ratio of 10 and seas and lakes have a ratio of 4. There are about 10³⁰ bacteria in the world (Whitman et al. 1998).

Figure 3

Different distributions are observed in the same environment. Clone libraries of different groups of organisms (Archaea and Bacteria) in the same environment can appear to have radically different distributions. Hypothetical geometric (Archaea) and lognormal (Bacteria) distributions are shown. In this example, the bacterial and archaeal 16S rRNA gene sequences amplified from the same anaerobic digester exhibit very different distributions. Thus, the distribution of species is not likely to be a simple function of the suitability of the environment (data from Godon et al. 1997).

Figure 4

Small samples can be very misleading. To demonstrate the unreliability of small sample sizes, four radically different distributions (on the left) were sampled (200 individuals selected randomly) and the resulting distributions (shown on the right) plotted (Sloan et al. in press). Note that all the sample distributions are superficially alike.

Figure 5

A schematic of the model used to estimate diversity. When an individual dies in the local community, it is replaced from outside the community with a probability m, or from within the community with a probability 1−m (after Hubbell 2001; Sloan et al. 2006, in press).

Figure 6

Predictions of the Sloan et al. (2006, in press) model. Probability density functions, ϕ_i for the local abundance of a species that makes up 20% of the source community. m=1 means the space vacated by every death is filled by an immigrant and the source and local communities are highly coupled. Therefore, ϕ_i forms a tight bell-shaped distribution with mean relative abundance 20%. As m drops, the local community becomes increasingly more isolated and the internal neutral dynamics act to increase the skew and variance of the distributions, making low abundances more probable, but increasing the uncertainty or variability. As m continues to drop, the mode of the distribution becomes zero (m<0.04) and the likelihood of the species being absent increases.

Figure 7

How the value of N_Tm and m can be determined. (a) For a given mean source community abundance, the frequency with which an organism is observed is related to N_Tm, the total number of individuals multiplied by the immigration parameter. At high N_Tm values, the local distribution is tightly clustered around the mean meta-community distribution (in this case 0.2). As the N_Tm values drop, the distribution widens and eventually the mode of the curve falls below the detection limit and the organism is no longer observed. There is therefore a relationship between the mean source community abundance N_Tm and the frequency with which an organism is observed. (b) The expected frequency–relative abundance relationships observed in a local community for differing N_Tm values. Thus, for a given dataset, the N_Tm values can be found by fitting a line to these data; where the value of N_T is known, m can be easily inferred.

Figure 8

Data and theory compared. The theoretical (solid line) and observed (squares or triangles) relationship between the mean relative abundance of taxa and the frequency with which they appear in a population of fixed size. Each of the points represents a different taxon. (a) Clone libraries of different ammonia monooxygenase (AMO) genes at 13 different domestic sewage works, N_Tm=1.41 (Wagner & Loy 2002). The triangles represent putative salt tolerant taxa. (b) Clone libraries of 16S rRNA genes from different AOB at six sites from the Humber Estuary, N_Tm=14. (c) Clone libraries of 16S rRNA genes from five experimental aquatic microcosms, N_Tm=10.3 (Horner-Devine et al. 2003). (d) 16S RNA sequences for 16 different bacterial taxa that are considered to be specific to freshwater environments sampled from 96 different lakes (Zwart et al. 2003), N_Tm=1.36. It is interesting to note that though both panels (c) and (d) pertain to lakes, the fit is much better in the larger dataset. This might be for two reasons: first, a larger dataset from larger systems will give a better indication of p_i but also because prior to the analysis of (d) we removed data that represented three cyanobacterial lineages, leaving only data from one functional group of putative heterotrophs whereas (c) contains all the bacterial sequences. Other examples and a full description are given in Sloan et al. (2006, in press).

Figure 9

The scaling of immigration with N_T. From left to right are shown a single cell, through a clone library to a FISH study and a DGGE gel. The solid line is the scaling predicted within a system from the clone library data. The data is shown at (a) a local scale and (b) a global scale, there being approximately 10³⁰ bacteria in the world. It is apparent that a plausible extrapolation of the observed data could bring the rate of immigration below a plausible rate of speciation. This would permit speciation in an open system.

Figure 10

Model predictions are qualitatively consistent with the patterns seen in ‘real life’. A sample of 50 ammonia-oxidizing bacteria (AOB) clones and 500 bacterial clones in one of the wastewater treatment plants featured in figure 9 found taxa diversities of 7 and 202, respectively, in the two samples. Here, we examine the ability of the Sloan et al. model to qualitatively reproduce that finding. We used known N_T values and, hypothetical source diversities of 200 (for the low source diversity group corresponding with the AOB) and 100 000 (for the high source diversity corresponding with the general bacterial population); immigration parameters were estimated using the extrapolation procedure mentioned in this paper (10⁻¹² for the AOB and 1.5×10⁻¹⁶ for the general bacterial population). (a) Represents the AOB, the diversity is similar to that found in the samples. (b) Represents the high source diversity group, the most abundant members of which are shown in (c) for greater clarity. The clone and local diversity are obviously distinct. Slightly less diversity was found in the model than observed in practice, suggesting some small errors in the source term or the immigration parameter. This is neither proof nor disproof of the model, but an encouraging indication that a more formal validation may be worthwhile undertaking.

Figure 11

The validation of the model is impossible with small sample sizes. Using the neutral model to simulate the effect of migration and source community diversity in a microbial community of 10¹⁸ individuals (e.g. a wastewater treatment plant) on (a) the number of taxa in a library of 500 clones and (b) the true local richness in a community of 10¹⁸. The number of taxa in the sample soon plateaus, which means we can infer relatively little about the local or source diversity except that both probably exceed 10³ and 10⁴, respectively. Note how the clone library species richness actually dips slightly at higher diversities, probably owing to a change in evenness in the underlying local community.