Paenibacillus larvae is a Gram-positive, spore-forming bacterium that causes American foulbrood disease (AFB) in honeybee larvae [1,2]. AFB is lethal and highly infectious to individual larvae. It can also be fatal to colonies and can easily be spread between apiaries unless proper control measures are carried out. AFB is highly contagious and the spread depends largely on apiculture; transportation and trading of bee material, hive equipment and honey both locally and globally [3]. In Sweden and many other countries, AFB is a notifiable disease and control measures like burning infected colonies and hive material or shaking the bees onto new wax foundations is required. The disease is widely distributed across the world causing great economic losses in apiculture [4] and is also widespread in most parts of southern and central Sweden; in northern Sweden it occurs only locally. The incidence of AFB in Sweden has decreased drastically during the second half of the 1900s, coinciding with the introduction of a strict control program aimed at preventing epidemic spread. However, it still causes local problems in parts of the country.[5]

Little is known about the genetic variation and population structure of P. larvae, information that could shed light on the observed patterns of disease. Molecular characterization, or sub-typing techniques with various discriminatory powers have been used to differentiate between strains and genotypes of P. larvae and helped unravel the epidemiology of AFB [6–8]. One major sub-typing technique is based on repetitive elements within bacterial genomes (rep-PCR) using enterobacterial repetitive intergenic consensus (ERIC) primers [7]. Four distinct genotypes (ERIC I-IV) have been identified for P. larvae using rep-PCR. These have further been shown to form two clusters when using pulsed-field gel electrophoresis (PFGE) [1]. PFGE has a higher resolution than regular gel electrophoresis and therefore adds discriminatory power to epidemiological studies of AFB [6]. Another typing scheme developed recently for P. larvae is multilocus sequence typing (MLST), which was used to determine the distribution and biogeography of P. larvae strains from 6 continents [8]. Although the main aim of the study was not epidemiological, a sub-set of data from an AFB outbreak in Jersey (an island in the English Channel) included in the study demonstrated the potential power of MLST in studies of disease transmission [8].

MLST has been somewhat of a typing gold standard for several pathogens, e.g. the Bacillus cereus-group [9] and Campylobacter spp. [10]. However, a traditional MLST based on 7 genes does not have enough resolution to enable source tracing of bacterial pathogens through an epidemic. Seven MLST-genes do not mutate fast enough to generate the variation required to distinguish alternative transmission scenarios [11,12]. Traditional MLST is a technique best suited for studying population structure of bacteria.

Since their emergence about 15 years ago, Next Generation Sequencing (NGS) technologies have radically changed infectious disease research. NGS has a broad range of applications including research, clinical diagnostics and epidemiology. Outbreak investigations and surveillance of communicable diseases have greatly improved by the higher resolution of NGS compared to other typing methods [13–15]. High-resolution epidemiological studies using Whole Genome Sequencing (WGS) can be conducted using either a single nucleotide polymorphism (SNP) approach or a gene-by-gene approach. The latter is essentially an MLST-type analysis, but extended to the whole genome [11,16]. New genomes are queried using an online reference database; any new alleles will get unique identifiers and the database will cover more and more of the allelic diversity of the organism. This way the allele nomenclature is standardized and new genomes can be compared to all previously analyzed and deposited genomes [11]. At the time writing, the publicly accessible online reference database for P. larvae MLST typing (PubMLST, http://pubmlst.org/plarvae/) covered only the seven standard MLST-genes.

WGS has been successfully used for epidemiological investigations of highly clonal and invariant bacterial species, e.g. Bacillus anthracis [14] and Mycobacterium tuberculosis [17], due to the ability of WGS to identify even minor variation. WGS technology is also valuable in retrospective studies for elucidating the start, progress and end of a disease outbreak, information which is useful for mitigating future outbreaks. WGS can also be used in real-time, to help monitor and control an ongoing outbreak [18].

Here we report the first use of WGS on P. larvae for an epidemiological application. Since AFB is mainly spread through beekeeping activities such as moving contaminated hive material, WGS could be a useful tool to determine when and from where the pathogen was introduced in a geographical area, a beekeeping operation or an apiary.

The aim of the study was to i) evaluate the use of core genome MLST to differentiate isolates of P. larvae and ii) to investigate in detail the epidemiology of an isolated AFB outbreak on the Baltic Isle of Gotland, Sweden.

No specific permissions were required for these locations/activities. The honeybee samples were collected by bee inspectors authorized by the local County Boards and the Swedish Board of Agriculture and sent to the National Reference Laboratory for Bee Health at the Swedish University of Agricultural Sciences. The field studies did not involve endangered or protected species, only managed honeybees (Apis mellifera).

In the summer of 2014, symptoms of AFB were observed in a honeybee colony in a previously disease-free area on the island Gotland in the Baltic Sea. The colony was burned in accordance with Swedish legislation and the remaining colonies in the infected apiary and in other apiaries within a 3 km radius were inspected. No other diseased colonies were found upon visual inspection. However, since the owner of the infected apiary (Beekeeper 1) had other apiaries scattered throughout the island and had sold bee material (nukes) to other beekeepers, an additional 42 apiaries that were either owned by or contained bees sold by the affected beekeeper were investigated for the presence of P. larvae, using culture-based microbiological assays on extracts of adult bee samples [19,24].

Clinical symptoms of AFB were observed by visual inspection in 7 colonies in 4 of the 42 investigated apiaries on Gotland. In the bee samples collected in connection with the Gotland outbreak (G), high levels (>6,000 spores per bee) of P. larvae were detected in 24 colonies in 10 apiaries. Paenibacillus larvae was not detected by culture-based assays in any of the other sampled apiaries (n = 38) on the island. A total of 24 P. larvae isolates from the Gotland outbreak were recovered from diseased honeybee brood or adult bees (beekeepers 1–3, Table 1). The additional 28 P. larvae isolates from the county Uppland on the mainland (U) were isolated from adult bee samples from 28 colonies in 16 apiaries in 2 beekeeping operations the season after observed clinical disease (in 2014 and 2012 respectively, Table 1).

P. larvae from colonies owned by three beekeepers (1–3) from the AFB outbreak on Gotland and two beekeepers (4–5) on mainland Sweden were characterized using established ERIC typing methods. The P. larvae isolates from the apiaries of beekeeper 1, the owner of the first infected apiary, represented both ERIC I and ERIC II genotypes, whereas bacterial isolates from beekeeper 2 and 3 each represented one single genotype, ERIC II and ERIC I, respectively. The P. larvae isolates from beekeepers 4 and 5, from earlier, unrelated AFB disease incidences in Uppland on mainland Sweden, were all of ERIC I-type (Table 1).

This study presents the use of WGS and core genome MLST for separating P. larvae isolates with high resolution and the application of these techniques to trace the progress of two separate American foulbrood epidemics in Sweden. The study clearly separates the P. larvae isolates from the 2014 outbreak of AFB on the island Gotland into four different clones. The high degree of similarity between the clones strongly support that they were directly related through transmission.

When using a cut-off value of CT (Cluster Threshold), ≤ 10 the Gotland ERIC II isolates divide into two separate clusters but when setting a cut-off value of CT ≤ 30, the same isolates represent one clone or cluster. Since we demonstrated that the natural diversity of isolates within a large beekeeping practice was 16 allele differences at the most, it is likely that the more accurate cut-off value for what represents an outbreak clone or cluster is closer to 10 than 30. However, there is no consensus on how similar or closely related two bacterial isolates must be to establish that they originate from the same outbreak. The number of allele differences may vary with the lifecycle of the bacterium, the time-frame of sampling (longer infection time possibly leads to more allele variants), the mutation frequency of the bacterium and even which individual bacterial colony was chosen and picked from the agar plate. The high number of variables makes setting cut-off values difficult but studies on other bacteria have attempted to do this by investigating confirmed outbreak isolates. A study using cgMLST on confirmed outbreaks of Listeria monocytogenes set the threshold for the isolates to be part of the same cluster, the so-called to ≤ 10 allelic differences [26]. Another study of methicillin-resistant Staphylococcus aureus (MRSA) outbreaks selected a cutoff of ≤ 30 SNP differences to indicate a putative transmission event [27].

Another factor affecting cut-off values is the number of loci used for analysis. A cgMLST-analysis of 1,000 loci could therefore have 1/3 of the cut off value for an analysis of 3,000 loci. In the current analysis however, most of the target genes were part of the shared genomes.

The low allelic differences in this study between outbreak isolates within the same cluster clearly show their strong relatedness. Such low diversity estimates among outbreak isolates have been observed during disease outbreaks of other bacterial species [27,28] and also when multiple bacterial isolates from one individual animal that died from anthrax, a disease caused by another spore-forming bacterium Bacillus anthracis [14], were compared. By these criteria, approximately 10 allelic differences between isolates should be enough to define a cluster of a single bacterial clone.

The results presented here are based on a genome-wide, gene-by-gene approach, similar in concept to the traditional 7-gene MLST but extended to the whole genome. A full SNP analysis would increase the resolution even more since SNPs are analyzed individually rather than used to define the allelic status of whole genes and SNPs that lie outside the coding regions can be included. However, it is not clear that such additional resolution would significantly improve the accuracy of the tracing or contribute more noise to the data and analyses. One advantage of cgMLST over SNP-based analyses is that new isolates can be added progressively without requiring a re-calibration of the database, making it easier to compare and mix different studies. SNP-based analyses can always be performed on the same genomic data if additional resolution is required.

When creating a cgMLST target set, it is advantageous to have access to a complete genome. The only complete, fully annotated P. larvae genome available at the time this study started was DSM 25430 (NCBI accession NC_023134), which is an ERIC II-genome. However, the ERIC I genome (DSM 25719, NCBI WGS accession ADFW) is considerably larger than the ERIC II genome (4.5 Mb vs 4.0 Mb) [25]. This means that additional allelic differences are potentially available among the ERIC I genomes when the target set is defined from an ERIC II-genome. One possible way to remedy this would be to create an ERIC I-gene target set from the large amount of sequence data produced. However, later the ERIC I-genome of ATCC 9545 (NZ_CP019687) was published and the full ERIC I genome could be used by a gene target set created from this genome. The difference between analyzing our ERIC I-genomes using the ERIC I reference instead of the ERIC II reference was however minor (data not shown) and did not change any of the conclusions drawn from this study.

The cgMLST method is based on a ‘shared genome’ concept [29] where the allelic differences between isolates are distilled into a reduced set of alleles that all isolates have in common. The disadvantage is that with increasing divergence among all isolates fewer common alleles are identified for priming the analyses. The size of the shared genome is also affected by technical factors such as sequencing coverage, assembly quality and genetic deletions. For example, the original 3,373 gene targets, available from the ERIC II reference genome, was reduced to 3,309 for the analyses of the ERIC II isolates in this study. This level of resolution was more than sufficient to cluster the isolates accurately by both their ERIC and ST classifications with further significant clusters identified with each of these and was a significant improvement on ERIC typing or 7-gene MLST.

The results presented in Fig 1 suggest, but do not conclusively determine, that beekeeper 1 is the source of the outbreak. Instead of being the source, beekeeper 1 could theoretically have received three to four different clones of P. larvae from beekeepers 2 and 3. Fig 1 indicates that the isolates were strongly connected but the direction of the transmissions needed confirmation (the same as for other typing techniques) by more epidemiological links and background information. However, in combination with the information that there had been a transfer of bees from beekeeper 1 to beekeepers 2 and 3, the genomic results in this study supported the conclusions on the origin of the outbreak. The bacterial isolates from earlier AFB outbreaks on mainland Sweden unrelated to the Gotland outbreak served as a reference to determine the diversity of clones and spread within beekeeping operations managing several apiaries.

As increasing numbers of whole genomes of P. larvae become available, a standardized public cgMLST database capturing the diversity of P. larvae will facilitate future analyses of AFB epidemics.

We have used WGS to look at the spread of American foulbrood during outbreaks in Sweden. This is, to our knowledge, the first time WGS of P. larvae has been used for an epidemiological investigation. We found that this method showed higher discriminatory power than previously described methods used for AFB epidemiological studies and it had the necessary resolution to draw conclusions on the origin of a disease outbreak and shows great promise to be a future standard for epidemiological studies on this devastating disease.