Extensive parallelism in protein evolution

Abstract

Background: Independently evolving lineages mostly accumulate different changes, which leads to their gradual divergence. However, parallel accumulation of identical changes is also common, especially in traits with only a small number of possible states.

Results: We characterize parallelism in evolution of coding sequences in three four-species sets of genomes of mammals, Drosophila, and yeasts. Each such set contains two independent evolutionary paths, which we call paths I and II. An amino acid replacement which occurred along path I also occurs along path II with the probability 50-80% of that expected under selective neutrality. Thus, the per site rate of parallel evolution of proteins is several times higher than their average rate of evolution, but still lower than the rate of evolution of neutral sequences. This deficit may be caused by changes in the fitness landscape, leading to a replacement being possible along path I but not along path II. However, constant, weak selection assumed by the nearly neutral model of evolution appears to be a more likely explanation. Then, the average coefficient of selection associated with an amino acid replacement, in the units of the effective population size, must exceed approximately 0.4, and the fraction of effectively neutral replacements must be below approximately 30%. At a majority of evolvable amino acid sites, only a relatively small number of different amino acids is permitted.

Conclusion: High, but below-neutral, rates of parallel amino acid replacements suggest that a majority of amino acid replacements that occur in evolution are subject to weak, but non-trivial, selection, as predicted by Ohta's nearly-neutral theory.

Figure 1

Phylogenetic trees used in our analysis, drawn to scale. For each edge, the average per site divergence at nonsynonymous (red) and synonymous (blue) sites is shown. Green lines show paths I, which are used to identify evolvable sites, and magenta lines show paths II, which are used to measure rates of evolution at these sites.

Figure 2

Rate of evolution and frequency of the inferior allele as functions of 4N_es. Rate of evolution v is in the units of rate of neutral evolution M [13].

Figure 3

Distributions of selection coefficients with extremal properties. Distributions p(s) that correspond to the minimal average selection coefficient (blue line) and to the maximal fraction of selectively neutral sites (red lines), as long as the average rate of parallel evolution P constitutes 0.7 of the rate of neutral evolution. Vertical lines denote delta functions.