Global genomic similarity and core genome sequence diversity of the Streptococcus genus as a toolkit to identify closely related bacterial species in complex environments

Background: The Streptococcus genus is relevant to both public health and food safety because of its ability to cause pathogenic infections. It is well-represented (>100 genomes) in publicly available databases. Streptococci are ubiquitous, with multiple sources of isolation, from human pathogens to dairy products. The Streptococcus genus has traditionally been classified by morphology, serum types, the 16S ribosomal RNA (rRNA) gene, and multi-locus sequence types subject to in-depth comparative genomic analysis. Methods: Core and pan-genomes described the genomic diversity of 108 strains belonging to 16 Streptococcus species. The core genome nucleotide diversity was calculated and compared to phylogenomic distances within the genus Streptococcus. The core genome was also used as a resource to recruit metagenomic fragment reads from streptococci dominated environments. A conventional 16S rRNA gene phylogeny reconstruction was used as a reference to compare the resulting dendrograms of average nucleotide identity (ANI) and genome similarity score (GSS) dendrograms. Results: The core genome, in this work, consists of 404 proteins that are shared by all 108 Streptococcus. The average identity of the pairwise compared core proteins decreases proportionally to GSS lower scores, across species. The GSS dendrogram recovers most of the clades in the 16S rRNA gene phylogeny while distinguishing between 16S polytomies (unresolved nodes). The GSS is a distance metric that can reflect evolutionary history comparing orthologous proteins. Additionally, GSS resulted in the most useful metric for genus and species comparisons, where ANI metrics failed due to false positives when comparing different species. Discussion: Understanding of genomic variability and species relatedness is the goal of tools like GSS, which makes use of the maximum pairwise shared orthologous sequences for its calculation. It allows for long evolutionary distances (above species) to be included because of the use of amino acid alignment scores, rather than nucleotides, and normalizing by positive matches. Newly sequenced species and strains could be easily placed into GSS dendrograms to infer overall genomic relatedness. The GSS is not restricted to ubiquitous conservancy of gene features; thus, it reflects the mosaic-structure and dynamism of gene acquisition and loss in bacterial genomes.