Population structure and evolution of Rhinoviruses

Abstract

Rhinoviruses, formerly known as Human rhinoviruses, are the most common cause of air-borne upper respiratory tract infections in humans. Rhinoviruses belong to the family Picornaviridae and are divided into three species namely, Rhinovirus A, -B and -C, which are antigenically diverse. Genetic recombination is found to be one of the important causes for diversification of Rhinovirus species. Although emerging lineages within Rhinoviruses have been reported, their population structure has not been studied yet. The availability of complete genome sequences facilitates study of population structure, genetic diversity and underlying evolutionary forces, such as mutation, recombination and selection pressure. Analysis of complete genomes of Rhinoviruses using a model-based population genetics approach provided a strong evidence for existence of seven genetically distinct subpopulations. As a result of diversification, Rhinovirus A and -C populations are divided into four and two subpopulations, respectively. Genetically, the Rhinovirus B population was found to be homogeneous. Intra-species recombination was observed to be prominent in Rhinovirus A and -C species. Significant evidence of episodic positive selection was obtained for several sites within coding sequences of structural and non-structural proteins. This corroborates well with known phenotypic properties such as antigenicity of structural proteins. Episodic positive selection appears to be responsible for emergence of new lineages especially in Rhinovirus A. In summary, the Rhinovirus population is an ensemble of seven distinct lineages. In case of Rhinovirus A, intra-species recombination and episodic positive selection contribute to its further diversification. In case of Rhinovirus C, intra- and inter-species recombinations are responsible for observed diversity. Population genetics approach was further useful to analyze phylogenetic tree topologies pertaining to recombinant strains, especially when trees are derived using complete genomes. Understanding of population structure serves as a foundation for designing new vaccines and drugs as well as to explain emergence of drug resistance amongst subpopulations.

Figure 1. Determination of K_opt using the plot of K vs. ΔK.

ΔK represents the rate of change of posterior probability given the number of clusters (K). ΔK is plotted against K to determine optimum number of clusters (K_opt) within Rhinovirus population (comprising of HRV-A, -B and -C). The peak at K = 7, represents that K_opt is 7 and thus indicate that Rhinovirus population is subdivided into seven genetically distinct subpopulations.

Figure 2. Population structure of Rhinoviruses obtained by Bayesian-based clustering approach using admixture model at K = 7.

HRV-A comprises of four subpopulations viz. -A (blue), -A1 (yellow), -A2 (red), -A3 (green). HRV-B members form a single cluster (magenta) with no further subdivision. HRV-C comprises of two subpopulations viz. C1 (orange) and C2 (cyan). The A1, A2, A3, C1 and C2 subpopulations show presence of several admixed strains. Admixed strains are color coded based on the proportion of membership scores to belong to the respective subpopulations.

Figure 3. Sublevel clustering of HRV-A: The plot of K vs. ΔK obtained for HRV-A strains.

ΔK represents the rate of change of posterior probability given the number of clusters (K). ΔK is plotted against K to determine optimum number of clusters (K_opt) within Rhinovirus A population. A major peak at K = 2 and a minor peak at K = 13 is observed. It suggests that Rhinovirus A population primarily divides into two major groups. The minor peak at K = 13 indicates that Rhinovirus A population is further subdivided into 13 minor subpopulations.

Figure 4. Sublevel clustering of HRV-C: The plot of K vs. ΔK obtained for HRV-C strains.

ΔK represents the rate of change of posterior probability given the number of clusters (K). ΔK is plotted against K to determine optimum number of clusters (K_opt) within Rhinovirus C population. A major peak at K = 2 and two minor peaks at 4 and 9 are observed. The major peak at K = 2 suggests that Rhinovirus C population primarily divided into two major groups (which correspond to the C1 and C2 subpopulations as mentioned in the text). The peak at K = 9, represents optimum number of minor subpopulations within HRV-C based on significant F _ST value of 0.47.

Figure 5. Phylogenetic tree of Rhinoviruses obtained using Neighbor-joining method in MEGA 5.05.

Complete genome sequence data with 1000 bootstrap replicates was used. The operational taxonomic unit (OTU) label consists of two parts divided by pipe (‘|’) character. The first part (before ‘|’) indicates species-serotype and second part constitute GenBank accession number of the associated entry. The branches in the tree are color coded as per the seven subpopulations obtained using STRUCTURE program [Subpopulation A: blue, A1: yellow, A2: red, A3: green, B: magenta, C1: orange, C2: cyan].