Whole genome sequencing for investigations of meningococcal outbreaks in the United States: a retrospective analysis

Abstract

Although rare in the U.S., outbreaks due to Neisseria meningitidis do occur. Rapid, early outbreak detection is important for timely public health response. In this study, we characterized U.S. meningococcal isolates (N = 201) from 15 epidemiologically defined outbreaks (2009-2015) along with temporally and geographically matched sporadic isolates using multilocus sequence typing, pulsed-field gel electrophoresis (PFGE), and six whole genome sequencing (WGS) based methods. Recombination-corrected maximum likelihood (ML) and Bayesian phylogenies were reconstructed to identify genetically related outbreak isolates. All WGS analysis methods showed high degree of agreement and distinguished isolates with similar or indistinguishable PFGE patterns, or the same strain genotype. Ten outbreaks were caused by a single strain; 5 were due to multiple strains. Five sporadic isolates were phylogenetically related to 2 outbreaks. Analysis of 9 outbreaks using timed phylogenies identified the possible origin and estimated the approximate time that the most recent common ancestor emerged for outbreaks analyzed. U.S. meningococcal outbreaks were caused by single- or multiple-strain introduction, with organizational outbreaks mainly caused by a clonal strain and community outbreaks by divergent strains. WGS can infer linkage of meningococcal cases when epidemiological links are uncertain. Accurate identification of outbreak-associated cases requires both WGS typing and epidemiological data.

Figure 1

Phylogenetic trees generated using different WGS analysis methods for NmB outbreak and sporadic isolates, 2009–2015. (a) SNIPPY Phylogenetic Tree reconstructed from a whole genome core alignment generated based on reference-based short read mapping and corrected for recombination using ClonalFrameML. (b) kSNP Phylogenetic Tree, a maximum likelihood (ML) phylogenetic tree generated using RaXML from the core SNP alignment generated by kSNP. (c) cgMLST Phylogenetic Tree, an ML tree created from the concatenated core gene alignment using RaXML. (d) Parsnp Phylogenetic Tree reconstructed from a whole genome core alignment generated using Parsnp and corrected for recombination using ClonalFrameML. (e) Roary Phylogenetic Tree generated from the concatenated core gene alignment; recombination was corrected using ClonalFrameML. Purple circles represent branch-level bootstrap support out of 100 bootstrap estimates. The circumference of a circle is proportional to the bootstrap support. represented 100% bootstrap support. Bootstrap support was estimated only for kSNP and cgMLST ML phylogenetic trees; the Bayesian recombination-adjusted phylogenies from ClonalFrameML do not estimate bootstrap values. Isolate label contains isolate ID, CC, PFGE pattern, outbreak or sporadic isolates, and year. Geographically matched outbreak and sporadic isolates are indicated by same number following “SP” or “OB” in label. Each colored branch and isolate label represents a different outbreak.

Figure 2

Phylogenetic trees generated using different WGS analysis methods for NmC outbreak and sporadic isolates, 2009–2015. (a) SNIPPY Phylogenetic Tree reconstructed from a whole genome core alignment generated based on reference-based short read mapping and corrected for recombination using ClonalFrameML. (b) kSNP Phylogenetic Tree, an ML phylogenetic tree generated using RaXML from the core SNP alignment generated by kSNP. (c) cgMLST Phylogenetic Tree, an ML tree created from the concatenated core gene alignment. (d) Parsnp Phylogenetic Tree reconstructed from a whole genome core alignment generated using Parsnp and corrected for recombination using ClonalFrameML. (e) Roary Phylogenetic Tree generated from the concatenated core gene alignment; recombination was corrected using ClonalFrameML. Purple circles represent branch-level bootstrap support out of 100 bootstrap estimates. The circumference of a circle is proportional to the bootstrap support. represented 100% bootstrap support. Bootstrap support was estimated only for kSNP and cgMLST ML phylogenetic trees; the Bayesian recombination-adjusted phylogenies from ClonalFrameML do not estimate bootstrap values. Isolate label contains isolate ID, CC, PFGE pattern, outbreak or sporadic isolates, and year. Geographically matched sporadic and outbreak isolates are indicated by the same number following “SP” or “OB” in label. M26263 and M26417 were isolates from the same person. Each colored branch and isolate label represents a different outbreak.

Figure 3

Timed phylogenetic tree of NmB CC32 outbreak and sporadic isolates. A time-dependent phylogenetic reconstruction of the NmB CC32 outbreak and sporadic isolates, inferred by Bayesian inference using BEAST. The NmB CC32 consisted of 24 isolates from 3 outbreaks (OB6, OB11, and OB12), along with the geographically matched sporadic isolates. Geographically matched sporadic and outbreak isolates have the same number following “SP” or “OB” in label. Isolate label contains isolate ID, CC, PFGE pattern, outbreak or sporadic isolates, and year. Each colored branch and isolate label represents a different outbreak.

Figure 4

Timed phylogenetic tree of NmC CC11 outbreak and sporadic isolates. A time-dependent phylogenetic reconstruction of the NmC CC11 outbreak and sporadic isolates, inferred by Bayesian inference using BEAST. The NmB CC11 consisted of 71 isolates from 6 outbreaks (OB7, OB8, OB9, OB14, Chicago (2003), and Toronto (2001)), along with the geographically matched sporadic isolates (SP7, SP8, SP9, and SP14). M26263 and M26417 were isolates from the same person. Each colored branch and isolate label represents a different outbreak.