A phylogenetic backbone for Bivalvia: an RNA-seq approach

Abstract

Bivalves are an ancient and ubiquitous group of aquatic invertebrates with an estimated 10 000-20 000 living species. They are economically significant as a human food source, and ecologically important given their biomass and effects on communities. Their phylogenetic relationships have been studied for decades, and their unparalleled fossil record extends from the Cambrian to the Recent. Nevertheless, a robustly supported phylogeny of the deepest nodes, needed to fully exploit the bivalves as a model for testing macroevolutionary theories, is lacking. Here, we present the first phylogenomic approach for this important group of molluscs, including novel transcriptomic data for 31 bivalves obtained through an RNA-seq approach, and analyse these data with published genomes and transcriptomes of other bivalves plus outgroups. Our results provide a well-resolved, robust phylogenetic backbone for Bivalvia with all major lineages delineated, addressing long-standing questions about the monophyly of Protobranchia and Heterodonta, and resolving the position of particular groups such as Palaeoheterodonta, Archiheterodonta and Anomalodesmata. This now fully resolved backbone demonstrates that genomic approaches using hundreds of genes are feasible for resolving phylogenetic questions in bivalves and other animals.

Keywords: bivalves; mollusca; phylogenetics; phylogenomics.

Figure 1.

Schematic of the three supermatrices analysed in this study: supermatrix 1 (white: >37.5% gene occupancy, 1377 genes, 46.1% missing data), supermatrix 2 (blue: >50% gene occupancy, 729 genes, 35.4% missing data), supermatrix 3 (pink: >75% gene occupancy, 173 genes, 16% missing data).

Figure 2.

Phylogenetic hypothesis based on the analysis of supermatrix 1 (>37.5% occupancy; 1377 genes; 231 823 amino acids; 46.6% missing data) under the ML method and PROTGAMMALG model. The main bivalve lineages are illustrated in different colours and all taxonomic names used in the text are indicated at different nodes. Circles in nodes indicate maximum support for all ML and PhyloBayes analyses; otherwise, the bootstrap support values and posterior probabilities are indicated on each node. Circles on tips indicate the number of genes represented for each terminal for the three data matrices analysed. Likelihood scores for the three supermatrices are: >37.5% −lnL = 3 858 777.48; >50% −lnL = 2 099 078.28; >75% −lnL = 517 419.93.

Figure 3.

Supernetwork representation of quartets derived from individual ML gene trees, for three different supermatrices. Phylogenetic conflict is represented by reticulations. Edge lengths correspond to quartet frequencies.