Nationwide molecular surveillance of pandemic H1N1 influenza A virus genomes: Canada, 2009

Abstract

Background: In April 2009, a novel triple-reassortant swine influenza A H1N1 virus ("A/H1N1pdm"; also known as SOIV) was detected and spread globally as the first influenza pandemic of the 21(st) century. Sequencing has since been conducted at an unprecedented rate globally in order to monitor the diversification of this emergent virus and to track mutations that may affect virus behavior.

Methodology/principal findings: By Sanger sequencing, we determined consensus whole-genome sequences for A/H1N1pdm viruses sampled nationwide in Canada over 33 weeks during the 2009 first and second pandemic waves. A total of 235 virus genomes sampled from unique subjects were analyzed, providing insight into the temporal and spatial trajectory of A/H1N1pdm lineages within Canada. Three clades (2, 3, and 7) were identifiable within the first two weeks of A/H1N1pdm appearance, with clades 5 and 6 appearing thereafter; further diversification was not apparent. Only two viral sites displayed evidence of adaptive evolution, located in hemagglutinin (HA) corresponding to D222 in the HA receptor-binding site, and to E374 at HA2-subunit position 47. Among the Canadian sampled viruses, we observed notable genetic diversity (1.47 x 10⁻³ amino acid substitutions per site) in the gene encoding PB1, particularly within the viral genomic RNA (vRNA)-binding domain (residues 493-757). This genome data set supports the conclusion that A/H1N1pdm is evolving but not excessively relative to other H1N1 influenza A viruses. Entropy analysis was used to investigate whether any mutated A/H1N1pdm protein residues were associated with infection severity; however no virus genotypes were observed to trend with infection severity. One virus that harboured heterozygote coding mutations, including PB2 D567D/G, was attributed to a severe and potentially mixed infection; yet the functional significance of this PB2 mutation remains unknown.

Conclusions/significance: These findings contribute to enhanced understanding of Influenza A/H1N1pdm viral dynamics.

Figure 1. Geographical and clade distributions for A/H1N1pdm viruses sampled in Canada.

Phylogenetic analysis was performed with two hundred thirty five viruses sampled in Canada and linked to their corresponding clades, as shown in Figure 2.

Figure 2. Spatial patterning of Canadian A/H1N1pdm viruses.

Phylogenetic trees were inferred using the neighbour-joining distance method, with genetic distances calculated by maximum likelihood using Kimura's two-parameter model (K2P) in MEGA 4.0. The resultant consensus tree was generated using the Summarization of Split Support on Phylogenetic Trees (SumTrees) program ver. 1.02. Lineages are colour-coded according to the region of virus collection.

Figure 3. Phylogenetic relationships for A/H1N1pdm viruses sampled from Canada and globally.

Phylogenetic tree inferred for two hundred thirty five virus whole genomes sampled from Canada and representative global reference genomes using the Neighbour-joining (NJ) method. Scale bar indicates the number of nucleotide substitutions per site. Colour-coding: clade 1 (not shown); clade 2 (orange); clade 3 (teal); clade 4 (yellow); clade 5 (green); clade 6 (blue), and clade 7 (pink).

Figure 4. Temporal patterning of Canadian A/H1N1pdm viruses.

Phylogenetic trees were inferred using the neighbour-joining distance method, with genetic distances calculated by maximum likelihood using Kimura's two-parameter model (K2P) in MEGA 4.0. The resultant consensus tree was generated using the Summarization of Split Support on Phylogenetic Trees (SumTrees) program ver. 1.02. Clade distributions are colour-coded according to 1, 3 or 5 week time periods corresponding to virus collection dates.