Triplet-Based Codon Organization Optimizes the Impact of Synonymous Mutation on Nucleic Acid Molecular Dynamics

Abstract

Since the elucidation of the genetic code almost 50 years ago, many nonrandom aspects of its codon organization remain only partly resolved. Here, we investigate the recent hypothesis of 'dual-use' codons which proposes that in addition to allowing adjustment of codon optimization to tRNA abundance, the degeneracy in the triplet-based genetic code also multiplexes information regarding DNA's helical shape and protein-binding dynamics while avoiding interference with other protein-level characteristics determined by amino acid properties. How such structural optimization of the code within eukaryotic chromatin could have arisen from an RNA world is a mystery, but would imply some preadaptation in an RNA context. We analyzed synonymous (protein-silent) and nonsynonymous (protein-altering) mutational impacts on molecular dynamics in 13823 identically degenerate alternative codon reorganizations, defined by codon transitions in 7680 GPU-accelerated molecular dynamic simulations of implicitly and explicitly solvated double-stranded aRNA and bDNA structures. When compared to all possible alternative codon assignments, the standard genetic code minimized the impact of synonymous mutations on the random atomic fluctuations and correlations of carbon backbone vector trajectories while facilitating the specific movements that contribute to DNA polymer flexibility. This trend was notably stronger in the context of RNA supporting the idea that dual-use codon optimization and informational multiplexing in DNA resulted from the preadaptation of the RNA duplex to resist changes to thermostability. The nonrandom and divergent molecular dynamics of synonymous mutations also imply that the triplet-based code may have resulted from adaptive functional expansion enabling a primordial doublet code to multiplex gene regulatory information via the shape and charge of the minor groove.

Keywords: Codon organization; Dual-use codon; Genetic code; Molecular dynamics; RNA world.

Fig. 1

A general overview (a) of our pipeline for calculating the level of MD optimization within the context of nucleic acid structures (i.e., dsRNA and bDNA). Generalized Born MD simulations (Amber 14) were run on 50 sets of all 64 codons centered on implicitly solvated G-capped 23 bp DNA fragments. Explicitly solvated systems were tested as well with equilibration times reduced to 0.2 µs. Alternative coding schemes defining the synonymous/nonsynonymous categorizations were generated by combinatoric base exchanges at all three codon positions, thus maintaining the same level of degeneracy in all alternative code combinations. Mutational impacts for all changes within the genetic code were defined using atomic fluctuations and correlations (i.e., cpptraj) and then summed over all synonymous sites (blue line) and all nonsynonymous sites (yellow line) and then compared to histograms of respective synonymous or nonsynonymous impacts in all the alternative codes (histograms). Mutational impacts were defined two ways, first as (b) absolute differences in correlation of vector trajectories (i.e., yellow arrows) along backbone carbons, and second as (c) absolute differences in atomic fluctuations or rapid harmonic vibrations (i.e., blue circles). (Color figure online)

Fig. 1

A general overview (a) of our pipeline for calculating the level of MD optimization within the context of nucleic acid structures (i.e., dsRNA and bDNA). Generalized Born MD simulations (Amber 14) were run on 50 sets of all 64 codons centered on implicitly solvated G-capped 23 bp DNA fragments. Explicitly solvated systems were tested as well with equilibration times reduced to 0.2 µs. Alternative coding schemes defining the synonymous/nonsynonymous categorizations were generated by combinatoric base exchanges at all three codon positions, thus maintaining the same level of degeneracy in all alternative code combinations. Mutational impacts for all changes within the genetic code were defined using atomic fluctuations and correlations (i.e., cpptraj) and then summed over all synonymous sites (blue line) and all nonsynonymous sites (yellow line) and then compared to histograms of respective synonymous or nonsynonymous impacts in all the alternative codes (histograms). Mutational impacts were defined two ways, first as (b) absolute differences in correlation of vector trajectories (i.e., yellow arrows) along backbone carbons, and second as (c) absolute differences in atomic fluctuations or rapid harmonic vibrations (i.e., blue circles). (Color figure online)

Fig. 2

Sum totals of relative impacts of synonymous and nonsynonymous mutation on a the MD of double-stranded aRNA, b the MD of double-stranded bDNA, and c the predicted DNA flexibility when comparing the canonical genetic code (dashed line) to all possible 13,823 alternative codes (histogram). Mutational impacts are defined according to mutational shifts in both correlation of atomic vector trajectories (dCORR—top) and atomic fluctuations (dFLUX—bottom) collected on all backbone carbons within a 5 bp mask centered on the mutation site. The calculations were conducted with cpptraj software (Ambertools16) in plots (a) and (b) and the TRX score of (Heddi et al. 2010) in plot (c)

Fig. 3

Sum totals of relative impacts of strand-specific mutation on the MD of a double-stranded aRNA and b bDNA comparing the canonical genetic code (dashed line) to all possible 13,823 alternative codes (histogram). Mutational impacts are defined as in Fig. 2 but were collected according to whether mutation types were symmetric (e.g., nonsynonymous on both leading and lagging strand) or asymmetric (i.e., synonymous on one strand but nonsynonymous on the other)

Fig. 4

Atom specific heatmaps showing the average dCORR and dFLUX on a double-stranded aRNA and b bDNA as a function of mutation type (N nonsynonymous, S synonymous, NN nonsynonymous on both strands, SS synonymous on both strands, SN synonymous on only one strand)