Real-time plasmid transmission detection pipeline

Abstract

The spread of antimicrobial resistance among bacteria by horizontal plasmid transmissions poses a major challenge for clinical microbiology. Here, we evaluate a new real-time plasmid transmission detection pipeline implemented in the SeqSphere⁺ (Ridom GmbH, Münster, Germany) software. Within the pipeline, a local Mash plasmid database is created, and Mash searches with a distance threshold of 0.001 are used to trigger plasmid transmission early warning alerts (EWAs). Clonal transmissions are detected using core-genome multi-locus sequence typing allelic differences. The tools MOB-suite, NCBI AMRFinderPlus, CGE MobileElementFinder, pyGenomeViz, and MUMmer, integrated in SeqSphere+, are used to characterize plasmids and for visual pairwise plasmid comparisons, respectively. We evaluated the pipeline using published hybrid assemblies (Oxford Nanopore Technology/Illumina) of a surveillance and outbreak data set with plasmid transmissions. To emulate prospective usage, samples were imported in chronological order of sampling date. Different combinations of the user-adjustable parameters sketch size (1,000 vs 10,000) and plasmid size correction were tested, and discrepancies between resulting clusters were analyzed with Quast. When using a sketch size of 1,000 with size correction turned on, the SeqSphere⁺ pipeline agreed with the published data and produced the same clonal and carbapenemase-carrying plasmid clusters. EWAs were in the correct chronological order. In summary, the developed pipeline presented here is suitable for integration into clinical microbiology settings with limited bioinformatics knowledge due to its automated analyses and alert system, which are combined with the GUI-based SeqSphere⁺ platform. Thus, with its integrated sample database, (near) real-time plasmid transmission detection is within reach in bacterial routine-diagnostic settings when long-read sequencing is employed.

Importance: Plasmid-mediated spread of antimicrobial resistance is a major challenge for clinical microbiology, and monitoring of potential plasmid transmissions is essential to combat further dissemination. Whole-genome sequencing is often used to surveil nosocomial transmissions but usually limited to the detection of clonal transmissions (based on chromosomal markers). Recent advances in long-read sequencing technologies enable full reconstruction of plasmids and the detection of very similar plasmids, but so far, easy-to-use bioinformatic tools for this purpose have been missing. Here, we present an evaluation of an innovative real-time plasmid transmission detection pipeline. It is integrated into the GUI-based SeqSphere⁺ software, which already offers core-genome multi-locus sequence typing-based pathogen outbreak detection. It requires very limited bioinformatics knowledge, and its database, automated analyses, and alert system make it well suited for prospective clinical application.

Keywords: antimicrobial resistance; horizontal gene transfer; long-read sequencing; plasmid; transmission; whole-genome sequencing.

Fig 1

Overview of plasmid transmission detection pipeline.

Fig 2

Plasmid population snapshot based on Mash distances between 71 carbapenemase-carrying plasmids. Each circle represents one plasmid, and plasmids with a Mash distance of 0 are lumped together in single circles with a larger size. Connection lines are drawn for plasmids with a Mash distance <0.06. Fill color represents the species of the respective isolates, and colored, dotted circles mark clonal clusters among these isolates. Plasmid clusters (Mash distance threshold <0.001) are illustrated by gray shaded areas around the circles. Clonal (in color) and plasmid (in gray) cluster names are stated next to the clusters.

Fig 3

Visualization of a combination of clonal and horizontal plasmid transmissions. Direction of transmission is assumed based on temporal order of isolation. ST = MLST sequence type.