Corallimorpharians are not "naked corals": insights into relationships between Scleractinia and Corallimorpharia from phylogenomic analyses

Abstract

Calcification is one of the most distinctive traits of scleractinian corals. Their hard skeletons form the substratum of reef ecosystems and confer on corals their remarkable diversity of shapes. Corallimorpharians are non-calcifying, close relatives of scleractinian corals, and the evolutionary relationship between these two groups is key to understanding the evolution of calcification in the coral lineage. One pivotal question is whether scleractinians are a monophyletic group, paraphyly being an alternative possibility if corallimorpharians are corals that have lost their ability to calcify, as is implied by the "naked-coral" hypothesis. Despite major efforts, relationships between scleractinians and corallimorpharians remain equivocal and controversial. Although the complete mitochondrial genomes of a range of scleractinians and corallimorpharians have been obtained, heterogeneity in composition and evolutionary rates means that mitochondrial sequences are insufficient to understand the relationship between these two groups. To overcome these limitations, transcriptome data were generated for three representative corallimorpharians. These were used in combination with sequences available for a representative range of scleractinians to identify 291 orthologous single copy protein-coding nuclear markers. Unlike the mitochondrial sequences, these nuclear markers do not display any distinct compositional bias in their nucleotide or amino-acid sequences. A range of phylogenomic approaches congruently reveal a topology consistent with scleractinian monophyly and corallimorpharians as the sister clade of scleractinians.

Keywords: Anthozoa; Corallimorpharia; Corals; Phylogenomics; Scleractinia.

Figure 1. Relationship between Scleractinia and Corallimorpharia.

(A) The two competing hypotheses regarding the relationship between Corallimorpharia and Scleractinia: scleractinian monophyly and the “naked coral” topology. Scleractinian monophyly implies that the ability to calcify was acquired in the ancestor of Scleractinia, whilst the naked coral hypothesis requires secondary loss of this trait in the ancestor of Corallimorpharia. (B) Maximum likelihood phylogenetic tree based on the amino acid sequences of 291 nuclear genes from 15 anthozoans with the JTT + GAMMA + I model. The critical nodes (1, 2, 3 and 4) are fully supported, as reported in Table 1. The same topology was obtained for all the other analyses with equally strong support (see Table 1).

Figure 2

(A) Numbers of trees based on individual genes supporting scleractinian monophyly, naked coral or other topologies for maximum likelihood (ml) and Bayesian inference (bi) for amino-acid (aa) and nucleotide alignments (nt). The majority of trees are consistent with scleractinian monophyly, whereas few support the naked corals scenario. (B) Summary of the concordance of phylogenetic inference for each gene. Each line represents a gene. The main pattern (black lines) represents genes that are fully consistent with scleractinian monophyly, whilst only a small proportion of genes consistently agree with the naked coral hypothesis (white lines). The checkered lines correspond to genes producing topologies that are not consistent across the different types of inference. The patterns are sorted from most abundant at the top of the figure to least abundant at the bottom. (C) Distribution of sequence lengths for genes consistent with scleractinian monophyly (S, black lines in B) and the naked coral hypothesis (N, white lines B). The sequences of the genes consistent with scleractinian monophyly are significantly longer (Mann Whitney U test p = 0.0004).