Enabling genomic island prediction and comparison in multiple genomes to investigate bacterial evolution and outbreaks

Abstract

Outbreaks of virulent and/or drug-resistant bacteria have a significant impact on human health and major economic consequences. Genomic islands (GIs; defined as clusters of genes of probable horizontal origin) are of high interest because they disproportionately encode virulence factors, some antimicrobial-resistance (AMR) genes, and other adaptations of medical or environmental interest. While microbial genome sequencing has become rapid and inexpensive, current computational methods for GI analysis are not amenable for rapid, accurate, user-friendly and scalable comparative analysis of sets of related genomes. To help fill this gap, we have developed IslandCompare, an open-source computational pipeline for GI prediction and comparison across several to hundreds of bacterial genomes. A dynamic and interactive visualization strategy displays a bacterial core-genome phylogeny, with bacterial genomes linearly displayed at the phylogenetic tree leaves. Genomes are overlaid with GI predictions and AMR determinants from the Comprehensive Antibiotic Resistance Database (CARD), and regions of similarity between the genomes are also displayed. GI predictions are performed using Sigi-HMM and IslandPath-DIMOB, the two most precise GI prediction tools based on nucleotide composition biases, as well as a novel blast-based consistency step to improve cross-genome prediction consistency. GIs across genomes sharing sequence similarity are grouped into clusters, further aiding comparative analysis and visualization of acquisition and loss of mobile GIs in specific sub-clades. IslandCompare is an open-source software that is containerized for local use, plus available via a user-friendly, web-based interface to allow direct use by bioinformaticians, biologists and clinicians (at https://islandcompare.ca).

Keywords: antimicrobial resistance; comparative genomics; genomic islands; interactive visualization; web server.

Fig. 1.

The IslandCompare workflow. IslandCompare integrates three parallel workflows for the prediction and comparison of GIs, the phyletic visualization of genomes, and the annotation and highlighting of genes with potentially interesting functions such as AMR genes. All results are stored in a standard gff3 format that is used either for interactive visualization in the IslandCompare user-friendly web interface, with images available for download, or for the export of data to conduct further GI analyses.

Fig. 2.

Comparative visualization of four P. aeruginosa genomes highlighting GIs and AMR determinants. (a) A phylogeny (left) indicates the relationship between the isolates in the analysis, with zoom-in functionality available. (a – right, b) GIs are represented as coloured blocks placed on a linear representation of the genome (linear white bars indicate genomes, with alignments between genomes shown in grey), with GIs coloured by (a) cluster or (b) prediction method. (c) The cluster view allows users to explore gene content within a given GI.

Fig. 3.

Counts of predicted GIs for each cluster and proportion predicted by the blast-based consistency module for a dataset of 166 L . monocytogenes genomes. Only clusters with more than one GI sequence predicted in the dataset are represented here (see Fig. S4a, b for all clusters).

Fig. 4.

GI prediction metrics across 86 genomes with known positive and negative GI regions. Predictions were made on the same set of genomes annotated by either NCBI or Prokka. All analyses were run for the GI results both with and without the blast-based consistency module results included.

Fig. 5.

Evaluation of a range of parameters for GI clustering in IslandCompare for datasets of (a) 166 L . monocytogenes genomes and (b) 40 P . aeruginosa genomes. Based on this analysis, a k-mer size of 16 and inflation value of 5.0 were selected for the Mash and MCL steps in the IslandCompare clustering pipeline, respectively.