Amplification and next generation sequencing of near full-length human enteroviruses for identification and characterisation from clinical samples

Abstract

More than 100 different enterovirus (EV) genotypes infect humans and contribute to substantial morbidity. However, current methods for characterisation of full-length genomes are based on Sanger sequencing of short genomic regions, which are labour-intensive and do not enable comprehensive characterisation of viral populations. Here, we describe a simple and sensitive protocol for the amplification and sequencing of near full-length genomes of human EV species using next generation sequencing. EV genomes were amplified from 89% of samples tested, with C_t values ranging between 15.7 and 39.3. These samples included 7 EV-A genotypes (CVA2, 5-7, 10, 16 and EV71), 19 EV-B genotypes (CVA9, CVB1-6, ECHO3, 4, 6, 7, 9, 11, 16, 18, 25, 29, 30, and EV69), 3 EV-C genotypes (CVA19 and PV2, 3) and 1 EV-D genotype (EV70). We characterised 70 EVs from 58 clinical stool samples and eight reference strains, with a minimum of 100X depth. We found evidence of co-infection in four clinical specimens, each containing two distinct EV genotypes (CVB3/ECHO7, CVB3/ECHO18 and ECHO9/30). Characterisation of the complete genome provided conclusive genotyping of EVs, which can be applied to investigate the intra-host virus evolution of EVs, and allows further identification and investigation of EV outbreaks.

Figure 1

(A) Gel electrophoresis of near full-length genome PCR products produced from four long amplifying DNA polymerases; KlenTaq LA (discontinued), AccuTaq LA, PrimeSTAR GXL and Takara LA Taq (separate gel) per manufacturer’s instructions for samples with high GC/secondary structures. M, HyperLadder 1 kb; 1, CVB3 Nancy; 2, CVB5 Faulkner; 3, H₂O control. (B) Gel electrophoresis of near full-length genome PCR products produced from Takara LA Taq DNA polymerase. M, HyperLadder 1 kb; 1–4, known EV positives from NSW Health Pathology East virology diagnostic lab; 5, CVB3 Nancy; 6, H₂O control. Full-length gels are presented in Supplementary Fig. 1.

Figure 2

(A) Sensitivity of near full-length EV genome PCR tested on VIGR clinical stool samples (n = 65) and reference strains (n = 20) with EV infection detectable within 40 cycles by qPCR. PCR amplification was significantly affected by C_t value, with successful amplification resulting from C_t values ranging between 15.7 and 39.3. (B) Efficiency of near full-length EV genome PCR tested on VIGR clinical stool samples (n = 68) compared to sample age (years from collection to processing), with sequenced (red) and unsequenced samples (black). Mean sample age indicated. Sample age did not significantly affect outcome of amplification, with 6 samples over 10 years old producing a 7–8 kb EV amplicon using gel electrophoresis.

Figure 3

Phylogenetic analysis of the near full-length EV genomes (n = 70) from 58 clinical VIGR stool samples from VIGR children with six previously sequenced prototype strains (CVB1 clone (M16560), CVB3 ATCC Nancy (M33854), CVB4 cultured J.V.B (X05690), CVB5 ATCC Faulkner (AF114383), CVB6 cultured Schmitt (AF039205), ECHO18 cultured Metcalf (AF081331)), a CVB1 lab-cultured strain and an EV71 clinical isolate. The unrooted phylogenetic tree was constructed using the HKY genetic distance model and the Neighbour-Joining method (1000 bootstrap replicates) and displayed as rooted with PV3 outgroup selected, implemented in Geneious software package version 9 (Biomatters). Samples named in the format “sampleID/year of collection (for VIGR isolates)/top BLAST hit”. Scale bar indicates genetic distance (substitutions per nucleotide). Sample clustering into EV species A-C is also depicted. Multiple infections indicated by A and B isolates for samples V13, V35, V38 and V47.

Figure 4

Coverage plot produced from de novo assembly of trimmed short reads produced from VIGR clinical stool sample 13 (V13), resulting in two Contigs over 6.9 kb, implemented in Geneious package version 9 (Biomatters). Both Contig 1 (blue) and Contig 2 (red) are shown, which were identified as ECHO18 and CVB3 respectively using BLAST. V13 displays infection with two viral genotypes at a single time point, with Contig 1 produced from 543048 reads, and Contig 2 produced from 52234 reads, which are stratified by EV genome position.

Figure 5

EV prototype CVB5 strain Faulkner (Accession AF114383.1) annotated with 5′UTR and near full-length genome forward and reverse primer binding sites, including EV probe and inner and outer primer sets. Viral polyprotein coding sequence (CDS) and mature peptide locations are also indicated; implemented in Geneious package version 9 (Biomatters).