Phylogenetic conservatism of functional traits in microorganisms

Abstract

A central question in biology is how biodiversity influences ecosystem functioning. Underlying this is the relationship between organismal phylogeny and the presence of specific functional traits. The relationship is complicated by gene loss and convergent evolution, resulting in the polyphyletic distribution of many traits. In microorganisms, lateral gene transfer can further distort the linkage between phylogeny and the presence of specific functional traits. To identify the phylogenetic conservation of specific traits in microorganisms, we developed a new phylogenetic metric-consenTRAIT-to estimate the clade depth where organisms share a trait. We then analyzed the distribution of 89 functional traits across a broad range of Bacteria and Archaea using genotypic and phenotypic data. A total of 93% of the traits were significantly non-randomly distributed, which suggested that vertical inheritance was generally important for the phylogenetic dispersion of functional traits in microorganisms. Further, traits in microbes were associated with a continuum of trait depths (τD), ranging from a few deep to many shallow clades (average τD: 0.101-0.0011 rRNA sequence dissimilarity). Next, we demonstrated that the dispersion and the depth of clades that contain a trait is correlated with the trait's complexity. Specifically, complex traits encoded by many genes like photosynthesis and methanogenesis were found in a few deep clusters, whereas the ability to use simple carbon substrates was highly phylogenetically dispersed. On the basis of these results, we propose a framework for predicting the phylogenetic conservatism of functional traits depending on the complexity of the trait. This framework enables predicting how variation in microbial composition may affect microbially-mediated ecosystem processes as well as linking phylogenetic and trait-based patterns of biogeography.

Figure 1

Hypothetical phylogenetic distribution of functional traits present in i clades including a trait A with a high τ_D, three clades with trait B with a low τ_D, and five randomly distributed lineages with trait C. R_i denotes the root node for each clade i with a given trait and the τ_D is the average 16S rRNA distance between the root node and the strains in each clade sharing a trait.

Figure 2

τ_D of functional traits. τ_D is estimated using consenTRAIT as the average 16S rRNA sequence distance between members of a clade where at least 90% of the strains carry a trait and the root node of this clade. (a) Traits identified based on genomic subsystems. (b) Phenotypic traits identified based on the ability to used specific organic carbon substrates. Black dots denote non-random phylogenetic distribution based on either consenTRAIT τ_D (P<0.05) or the phylogenetic dispersion test for discrete traits D, (P(D)_random<0.5) (Fritz and Purvis, 2010). The box plot represents the values from 100 bootstrap trees, where the box includes values from the 25–75 percentile, the bars includes the 5–95 percentile and the line represents the median.

Figure 3

Phylogenetic distribution of functional traits (red lines) in Prokaryotes. (a) Phylogenetic distribution of the traits oxygenic photosynthesis, nitrogen fixation and utilization of melibiose based on annotated genomic subsystems in the SEED database. (b) Phylogenetic distribution of the traits raffinose, citrate, and serine utilization based on observed growth in Biolog substrate utilization plates. The phylogenetic trees are based on a 16S rRNA alignment from the Silva database and estimated in Phylip using a distance based matrix (F84 correction), neighbor-joining, and 100 bootstraps (Felsenstein, 2006).

Figure 4

Role of complexity on phylogenetic dispersion and τ_D. (a) Relationship between the number of genes underlying traits and phylogenetic dispersal (Fritz and Purvis, 2010). (b) Relationship between number of genes underlying traits and τ_D. The correlation coefficients were based on Spearman correlation, but Pearson correlations were also significant (P<0.05).