Whole genome sequencing and de novo assembly identifies Sydney-like variant noroviruses and recombinants during the winter 2012/2013 outbreak in England

Abstract

Background: Norovirus is the commonest cause of epidemic gastroenteritis among people of all ages. Outbreaks frequently occur in hospitals and the community, costing the UK an estimated £110 m per annum. An evolutionary explanation for periodic increases in norovirus cases, despite some host-specific post immunity is currently limited to the identification of obvious recombinants. Our understanding could be significantly enhanced by full length genome sequences for large numbers of intensively sampled viruses, which would also assist control and vaccine design. Our objective is to develop rapid, high-throughput, end-to-end methods yielding complete norovirus genome sequences. We apply these methods to recent English outbreaks, placing them in the wider context of the international norovirus epidemic of winter 2012.

Method: Norovirus sequences were generated from 28 unique clinical samples by Illumina RNA sequencing (RNA-Seq) of total faecal RNA. A range of de novo sequence assemblers were attempted. The best assembler was identified by validation against three replicate samples and two norovirus qPCR negative samples, together with an additional 20 sequences determined by PCR and fractional capillary sequencing. Phylogenetic methods were used to reconstruct evolutionary relationships from the whole genome sequences.

Results: Full length norovirus genomes were generated from 23/28 samples. 5/28 partial norovirus genomes were associated with low viral copy numbers. The de novo assembled sequences differed from sequences determined by capillary sequencing by <0.003%. Intra-host nucleotide sequence diversity was rare, but detectable by mapping short sequence reads onto its de novo assembled consensus. Genomes similar to the Sydney 2012 strain caused 78% (18/23) of cases, consistent with its previously documented association with the winter 2012 global outbreak. Interestingly, phylogenetic analysis and recombination detection analysis of the consensus sequences identified two related viruses as recombinants, containing sequences in prior circulation to Sydney 2012 in open reading frame (ORF) 2.

Conclusion: Our approach facilitates the rapid determination of complete norovirus genomes. This method provides high resolution of full norovirus genomes which, when coupled with detailed epidemiology, may improve the understanding of evolution and control of this important healthcare-associated pathogen.

Figure 1

Norovirus epidemiology and sampling frame. Locations from which samples were obtained with England and Jersey (map courtesy of Google map).

Figure 2

Assembly performance. (A) The estimated coverage of the contigs produced and (B) the number of contigs produced by four assemblers, on a 32 sample test dataset. One dot signifies the result for one sample. Box and whiskers plots indicating median (thick grey line), 25th and 75th centiles (edges of box) and 5th and 95th centile (ends of whiskers) are shown. Mann–Whitney U test are shown comparing each assembler with Vicuna (p values given at the top of each figure).

Figure 3

Intra-sample variation. Bar plot displaying the frequency of samples and the number of intra-sample variants.

Figure 4

Graphical SNV matrix. Graph matrix depicting all 803 single nucleotide variants between New Orleans 2009 and Sydney 2012. Conserved sites within the genome have been removed in this depiction. Nucleotides identical to the Sydney 2012 variant are shown in blue, whilst nucleotides identical to New Orleans 2009 are depicted in yellow. Turquoise areas depict variants that are neither Sydney 2012 nor New Orleans 2009 like. Grey areas depict non assembled information.

Figure 5

Norovirus phylogenies for ORF1 and ORF2/3. Maximum likelihood trees for ORF1 and ORF2/ORF3 regions based on an alignment of 23 norovirus sequences from England and Jersey isolated during winter 2012/13 and two GII.4 reference genomes: New Orleans 2009 and Sydney 2012 (represented with yellow and blue filled circles, respectively). Trees were constructed in PhyML (27) under an HKY85 model of nucleotide substitution, midpoint rooted and bootstrapped with 100 replicates. The bootstrap support is provided for each node (in bold). Clades are coloured according to the reference strain with which they appear to cluster. The dashed line highlights phylogenetic incongruity between ORF1 and ORF2/ORF3, proposed to have arisen by recombination.