Genetic variability among complete human respiratory syncytial virus subgroup A genomes: bridging molecular evolutionary dynamics and epidemiology

Abstract

Human respiratory syncytial virus (RSV) is an important cause of severe lower respiratory tract infections in infants and the elderly. In the vast majority of cases, however, RSV infections run mild and symptoms resemble those of a common cold. The immunological, clinical, and epidemiological profile of severe RSV infections suggests a disease caused by a virus with typical seasonal transmission behavior, lacking clear-cut virulence factors, but instead causing disease by modifying the host's immune response in a way that stimulates pathogenesis. Yet, the interplay between RSV-evoked immune responses and epidemic behavior, and how this affects the genomic evolutionary dynamics of the virus, remains poorly understood. Here, we present a comprehensive collection of 33 novel RSV subgroup A genomes from strains sampled over the last decade, and provide the first measurement of RSV-A genomic diversity through time in a phylodynamic framework. In addition, we map amino acid substitutions per protein to determine mutational hotspots in specific domains. Using Bayesian genealogical inference, we estimated the genomic evolutionary rate to be 6.47 × 10(-4) (credible interval: 5.56 × 10(-4), 7.38 × 10(-4)) substitutions/site/year, considerably slower than previous estimates based on G gene sequences only. The G gene is however marked by elevated substitution rates compared to other RSV genes, which can be attributed to relaxed selective constraints. In line with this, site-specific selection analyses identify the G gene as the major target of diversifying selection. Importantly, statistical analysis demonstrates that the immune driven positive selection does not leave a measurable imprint on the genome phylogeny, implying that RSV lineage replacement mainly follows nonselective epidemiological processes. The roughly 50 years of RSV-A genomic evolution are characterized by a constant population size through time and general co-circulation of lineages over many epidemic seasons - a conclusion that might be taken into account when developing future therapeutic and preventive strategies.

Figure 1. Sequence variability in RSV proteins.

The number of substitutions per site (black bars) and the sequence variability (%) in each RSV protein calculated per strain relative to the consensus.

Figure 2. Amino acid substitutions in specific domains of the RSV G protein.

Indicated are the transmembrane domain (TM), heparin binding domain (HBD), N-terminal cytosolic domain, C-terminal ectodomain, the immunogenic internal domain and the region showing partial homology with the fourth subdomain of the 55 kDa TNFr. Dashed lines represent the mucin-like regions. N-glycosylation sites are indicated by black dots, conserved substitutions by black bars and non-conserved substitutions by red bars. Positively selected sites are marked by asterisks.

Figure 3. Amino acid substitutions in specific domains of the RSV F protein.

A) Indicated are the signal peptide (S), fusion peptide (F), transmembrane domain (TM), F1 and F2 domains, antigenic sites I, II and IV (black triangles), and N-glycosylation sites (black dots). B) Substitutions marked in the 3D structure of the trimeric fusion protein. Amino acid class changes are indicated in red, orange indicating similar class.

Figure 4. Phylogeny based on whole genomic sequences.

Distribution of Dutch-Belgian strains (blue) and Milwaukee strains (green). A color gradient (blue = slow, black = average, red = fast) reflects the variation in evolutionary rates among branches; node bars depict the credibility intervals for nodes showing a posterior probability support >95% (blue bar) or <95% (yellow bar). Recombinant partitions are indicated with arrows and asterisks.

Figure 5. Evolutionary rate estimates for the different genes and for the non-coding partition.

Distributed (blue square) and removed (red triangle) data sets.