Solving the riddle of codon usage preferences: a test for translational selection

Abstract

Translational selection is responsible for the unequal usage of synonymous codons in protein coding genes in a wide variety of organisms. It is one of the most subtle and pervasive forces of molecular evolution, yet, establishing the underlying causes for its idiosyncratic behaviour across living kingdoms has proven elusive to researchers over the past 20 years. In this study, a statistical model for measuring translational selection in any given genome is developed, and the test is applied to 126 fully sequenced genomes, ranging from archaea to eukaryotes. It is shown that tRNA gene redundancy and genome size are interacting forces that ultimately determine the action of translational selection, and that an optimal genome size exists for which this kind of selection is maximal. Accordingly, genome size also presents upper and lower boundaries beyond which selection on codon usage is not possible. We propose a model where the coevolution of genome size and tRNA genes explains the observed patterns in translational selection in all living organisms. This model finally unifies our understanding of codon usage across prokaryotes and eukaryotes. Helicobacter pylori, Saccharomyces cerevisiae and Homo sapiens are codon usage paradigms that can be better understood under the proposed model.

Figure 1

Genetic code and general codon–anticodon recognition rules for tRNA genes. This table simply summarizes all the theoretically possible interactions between the coding codons and the extant tRNA sequences in the organisms analysed in this work. The interested reader is advised to refer to the literature (47,46) for a detailed description of codon–anticodon pairings.

Figure 2

Nc-plot for yeast and simulated E.coli K12 genes. Grey points, simulated E.coli K12 genes; red points, actual yeast genes; dashed line, Wright's proposed function (Equation 5); bold line, the function proposed herein (Equation 8) with optimized parameters.

Figure 3

tAI versus f₁(x)–Nc for five organisms for which codon usage has been well studied.

Figure 4

Action of natural selection on codon usage in the genomic landscape. (a) Fitted regression surface of S-values to tRNA gene number and genome size. Pink dots, predicted S-values for every organism; red dots, organisms with S-values higher than predicted by the model; blue, organisms with S-values lower than predicted. Vertical lines join each observed data point to its predicted value. (b) Thermal image (contour plot) of the same regression surface. The hottest (highest) S-values are shown in white, while the cooler (lowest) values are in red. E, Eukaryota; B, Eubacteria; and A, Archaea. The contour lines reflect the estimated S-value for a particular region. (c) Estimated probability density function for the presence of a maximum in the regression analysis. (d) Hypothetical evolution of codon usage optimization. A small genome sized ancestor (0), suffered a series of genome expansions (1–4). During this evolutionary process, the phylogeny would move into, and then out of the selective hot-spot. The process can be reverted at any time if selection for genome size or tRNA set reduction is present, such as in non-free living organisms e.g. H.pylori (5) or P.falciparum (6).