Fancy a gene? A surprisingly complex evolutionary history of peroxiredoxins

Abstract

While the phylum Apicomplexa includes "only" several thousand described species of obligatory parasites of animals, it may in fact be the most specious group of parasitic protists with over a million species 1. The best known representatives are Plasmodium spp., Toxoplasma gondii and Cryptosporidium spp., which belong to the most important and widespread human parasites exacting an enormous disease burden. On the other hand, dinoflagellates and colpodellids, which are monophyletic with the apicomplexans, are ecologically highly significant, as they belong to the most abundant marine protists 2. As the common ancestor of these groups was most likely a free-living photosynthesizing protist, one wonders, which evolutionary forces contributed to the dramatic transition of some of its descendants into the arguably most successful intracellular parasites? Although a range of various processes and mechanisms contributed to this transition, most likely it also involved an acquisition of genes via horizontal gene transfer (HGT), which might have provided typical characteristics of a parasitic cell, such as immune escape, nutritional dependence and the capacity to invade other cells.

Keywords: Apicomplexa; Chromera; Plasmodium; endosymbiont; horizontal gene transfer; oxidative stress; peroxiredoxin.

Figure 1. FIGURE 1: Bayesian phylogenetic tree as inferred from Prx5 amino acid sequences.

The original dataset used by Djuika et al. was extended by the addition of relevant sequences from the chromerid algae Chromera velia and Vitrella brassicaformis, and the early-branching apicomplexan Gregarina niphandroides. Sequences were aligned using MAFFT, edited by Gblocs (both implemented in SeaView), and the alignment was analyzed by Bayesian inference and maximum likelihood (ML) method. MrBayes 3.2 was used to assess Bayesian topologies and posterior probabilities (PP) using WAG model. Two independent Monte-Carlo Markov chains were run under the default settings for 3 million generations; we used 500,000 generations as a burn-in and omitted them from topology reconstruction and PP calculation. ML bootstrap support is shown for selected nodes in the tree; ML tree was computed by RAxML , using γ corrected WAG model with bootstrap analysis being inferred from 1,000 replicates. Putative intracellular localizations of the Prx5 proteins were predicted using the TargetP and SignalP programs, respectively .