The unbearable uncertainty of panarthropod relationships

Abstract

Panarthropoda, the clade comprising the phyla Onychophora, Tardigrada and Euarthropoda, encompasses the largest majority of animal biodiversity. The relationships among the phyla are contested and resolution is key to understanding the evolutionary assembly of panarthropod bodyplans. Molecular phylogenetic analyses generally support monophyly of Onychophora and Euarthropoda to the exclusion of Tardigrada (Lobopodia hypothesis), which is also supported by some analyses of morphological data. However, analyses of morphological data have also been interpreted to support monophyly of Tardigrada and Euarthropoda to the exclusion of Onychophora (Tactopoda hypothesis). Support has also been found for a clade of Onychophora and Tardigrada that excludes Euarthropoda (Protarthropoda hypothesis). Here we show, using a diversity of phylogenetic inference methods, that morphological datasets cannot discriminate statistically between the Lobopodia, Tactopoda and Protarthropoda hypotheses. Since the relationships among the living clades of panarthropod phyla cannot be discriminated based on morphological data, we call into question the accuracy of morphology-based phylogenies of Panarthropoda that include fossil species and the evolutionary hypotheses based upon them.

Unveiling the Hidden Viromes Across the Animal Tree of Life: Insights from a Taxonomic Classification Pipeline Applied to Invertebrates of 31 Metazoan Phyla

“…Viromes of Arthropoda only appear to be closely similar to those of Onychophora, which also shares a rather pronounced centroid homology with Annelida, all three being phyla dominated by terrestrial species. In the case of Arthropoda and Onychophora, both belong to the clade of Panarthropoda, alongside Tardigrada (Wu et al, 2023 and Figure 1C), which could explain the remarkable degree of similarity observed between their virome compositions. Unfortunately, Tardigrada could not be included in this part of the analysis to test this hypothesis further because of its low sample count.…”

“…However, in order to include the full set of 31 phyla considered for this study, other works that specifically addressed the placement of certain phyla were taken into account, which was the case for Kinorhyncha, Loricifera and Nematomorpha (Yamasaki et al, 2015) and for Dicyemida and Orthonectida (Lu et al, 2017). Certain nodes that are proposed only in new studies, supported by relatively low bootstrap values or that are in contradiction between different analyses in the literature were highlighted as still disputed/problematic (Schultz et al, 2023;Marlétaz et al, 2019;Juravel et al, 2023;Laumer et al, 2018;Herranz et al, 2022;Wu et al, 2023), since this tree is presented for guidance only.…”

Statistical evaluation of character support reveals the instability of higher-level dinosaur phylogeny

“…When alternative ways of resolving a given branch are of interest, as in the controversy surrounding early dinosaur phylogeny, we encourage the community to move beyond the mere reporting of a phylogenetic point estimate toward explicitly testing it against the next best alternative. Following recent practice (Wu et al, 2023), we used a variety of likelihood ratio tests (LRTs) to this end (Shimodaira and Hasegawa, 1999; Shimodaira, 2002; Strimmer and Rambaut, 2002), but other approaches are possible. Bayesian inference differs from maximum likelihood in its treatment of nuisance parameters such as branch lengths or the parameters of the substitution and rate heterogeneity models, which are jointly optimized with the parameter of interest (topology) in maximum likelihood but marginalized over in Bayesian methods (Huelsenbeck et al, 2002).…”

Statistical evaluation of character support reveals the instability of higher-level dinosaur phylogeny

“…When alternative ways of resolving a given branch are of interest, as in the controversy surrounding early dinosaur phylogeny, we encourage the community to move beyond the mere reporting of a phylogenetic point estimate toward explicitly testing it against the next best alternative. Following recent practice 87 , we used a variety of likelihood ratio tests (LRTs) to this end 63 – 65 , but other approaches are possible. Bayesian inference differs from maximum likelihood in its treatment of nuisance parameters such as branch lengths or the parameters of the substitution and rate heterogeneity models, which are jointly optimized with the parameter of interest (topology) in maximum likelihood but marginalized over in Bayesian methods 88 .…”