Rapid geographical source attribution of Salmonella enterica serovar Enteritidis genomes using hierarchical machine learning
- University of Bristol, United Kingdom
- University of Bath, United Kingdom
- UK Health Security Agency, United Kingdom
- Utrecht University, Netherlands
Abstract
Salmonella enterica serovar Enteritidis is one of the most frequent causes of Salmonellosis globally and is commonly transmitted from animals to humans by the consumption of contaminated foodstuffs. In the UK and many other countries in the Global North, a significant proportion of cases are caused by consumption of imported food products or contracted during foreign travel, therefore making the rapid identification of the geographical source of new infections a requirement for robust public health outbreak investigations. Herein, we detail the development and application of a hierarchical machine learning model to rapidly identify and trace the geographical source of S. Enteritidis infections from whole genome sequencing data. 2,313 S. Enteritidis genomes, collected by the UKHSA between 2014-2019, were used to train a 'local classifier per node' hierarchical classifier to attribute isolates to 4 continents, 11 sub-regions and 38 countries (53 classes). The highest classification accuracy was achieved at the continental level followed by the sub-regional and country levels (macro F1: 0.954, 0.718, 0.661 respectively). A number of countries commonly visited by UK travellers were predicted with high accuracy (hF1: >0.9). Longitudinal analysis and validation with publicly accessible international samples indicated that predictions were robust to prospective external datasets. The hierarchical machine learning framework provided granular geographical source prediction directly from sequencing reads in <4 minutes per sample, facilitating rapid outbreak resolution and real-time genomic epidemiology. The results suggest additional application to a broader range of pathogens and other geographically structured problems, such as antimicrobial resistance prediction, is warranted.
Data availability
The final optimised hierarchical model as well as a pipeline for pre-processing raw read data to unitigs/patterns for input and paper data is available from https://github.com/SionBayliss/HierarchicalML with a short description and tutorial for ease of use. This end-to-end process, from FASTQ to prediction, is open access and available to users under GNU GPL licence . This depository also includes the preprocessed unitig datasets and resulting predictions. Short read sequencing data is available from the Sequence Read Archive (Bioproject: PRJNA248792). Please not that the sequence data has been previously deposited/published in the Sequence Read Archive by PHE/UKHSA and was not generated for this project.
-
Public Health England - SalmonellaNCBI SRA: PRJNA248792.
Article and author information
Author details
Funding
Academy of Medical Sciences (SBF005\1089)
- Lauren A Cowley
The funders had no role in study design, data collection and interpretation, or the decision to submit the work for publication.
Copyright
© 2023, Bayliss et al.
This article is distributed under the terms of the Creative Commons Attribution License permitting unrestricted use and redistribution provided that the original author and source are credited.
Metrics
-
- 1,609
- views
-
- 194
- downloads
-
- 8
- citations
Views, downloads and citations are aggregated across all versions of this paper published by eLife.
Download links
A two-part list of links to download the article, or parts of the article, in various formats.
Downloads (link to download the article as PDF)
Open citations (links to open the citations from this article in various online reference manager services)
Cite this article (links to download the citations from this article in formats compatible with various reference manager tools)
Rapid geographical source attribution of Salmonella enterica serovar Enteritidis genomes using hierarchical machine learning
eLife 12:e84167.
https://doi.org/10.7554/eLife.84167
Further reading
-
- Epidemiology and Global Health
- Microbiology and Infectious Disease
Several areas of the world suffer a notably high incidence of Shiga toxin-producing Escherichia coli. To assess the impact of persistent cross-species transmission systems on the epidemiology of E. coli O157:H7 in Alberta, Canada, we sequenced and assembled E. coli O157:H7 isolates originating from collocated cattle and human populations, 2007–2015. We constructed a timed phylogeny using BEAST2 using a structured coalescent model. We then extended the tree with human isolates through 2019 to assess the long-term disease impact of locally persistent lineages. During 2007–2015, we estimated that 88.5% of human lineages arose from cattle lineages. We identified 11 persistent lineages local to Alberta, which were associated with 38.0% (95% CI 29.3%, 47.3%) of human isolates. During the later period, six locally persistent lineages continued to be associated with human illness, including 74.7% (95% CI 68.3%, 80.3%) of reported cases in 2018 and 2019. Our study identified multiple locally evolving lineages transmitted between cattle and humans persistently associated with E. coli O157:H7 illnesses for up to 13 y. Locally persistent lineages may be a principal cause of the high incidence of E. coli O157:H7 in locations such as Alberta and provide opportunities for focused control efforts.
-
- Epidemiology and Global Health
Given the rapid cross-country spread of SARS-CoV-2 and the resulting difficulty in tracking lineage spread, we investigated the potential of combining mobile service data and fine-granular metadata (such as postal codes and genomic data) to advance integrated genomic surveillance of the pandemic in the federal state of Thuringia, Germany. We sequenced over 6500 SARS-CoV-2 Alpha genomes (B.1.1.7) across 7 months within Thuringia while collecting patients’ isolation dates and postal codes. Our dataset is complemented by over 66,000 publicly available German Alpha genomes and mobile service data for Thuringia. We identified the existence and spread of nine persistent mutation variants within the Alpha lineage, seven of which formed separate phylogenetic clusters with different spreading patterns in Thuringia. The remaining two are subclusters. Mobile service data can indicate these clusters’ spread and highlight a potential sampling bias, especially of low-prevalence variants. Thereby, mobile service data can be used either retrospectively to assess surveillance coverage and efficiency from already collected data or to actively guide part of a surveillance sampling process to districts where these variants are expected to emerge. The latter concept was successfully implemented as a proof-of-concept for a mobility-guided sampling strategy in response to the surveillance of Omicron sublineage BQ.1.1. The combination of mobile service data and SARS-CoV-2 surveillance by genome sequencing is a valuable tool for more targeted and responsive surveillance.
