Rapid geographical source attribution of Salmonella enterica serovar Enteritidis genomes using hierarchical machine learning

  1. Sion C Bayliss  Is a corresponding author
  2. Rebecca K Locke
  3. Claire Jenkins
  4. Marie Anne Chattaway
  5. Timothy J Dallman
  6. Lauren A Cowley
  1. University of Bristol, United Kingdom
  2. University of Bath, United Kingdom
  3. UK Health Security Agency, United Kingdom
  4. 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.

The following previously published data sets were used

Article and author information

Author details

  1. Sion C Bayliss

    Bristol Veterinary School, University of Bristol, Bristol, United Kingdom
    For correspondence
    s.bayliss@bristol.ac.uk
    Competing interests
    The authors declare that no competing interests exist.
    ORCID icon "This ORCID iD identifies the author of this article:" 0000-0002-5997-2002
  2. Rebecca K Locke

    Life Sciences Department, University of Bath, Bath, United Kingdom
    Competing interests
    The authors declare that no competing interests exist.
  3. Claire Jenkins

    Gastrointestinal Reference Services, UK Health Security Agency, London, United Kingdom
    Competing interests
    The authors declare that no competing interests exist.
  4. Marie Anne Chattaway

    Gastrointestinal Reference Services, UK Health Security Agency, London, United Kingdom
    Competing interests
    The authors declare that no competing interests exist.
  5. Timothy J Dallman

    Institute for Risk Assessment Sciences, Utrecht University, Utrecht, Netherlands
    Competing interests
    The authors declare that no competing interests exist.
  6. Lauren A Cowley

    Life Sciences Department, University of Bath, Bath, United Kingdom
    Competing interests
    The authors declare that no competing interests exist.

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

  • 1,348
    views
  • 168
    downloads
  • 7
    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)

  1. Sion C Bayliss
  2. Rebecca K Locke
  3. Claire Jenkins
  4. Marie Anne Chattaway
  5. Timothy J Dallman
  6. Lauren A Cowley
(2023)
Rapid geographical source attribution of Salmonella enterica serovar Enteritidis genomes using hierarchical machine learning
eLife 12:e84167.
https://doi.org/10.7554/eLife.84167

Share this article

https://doi.org/10.7554/eLife.84167

Further reading

    1. Epidemiology and Global Health
    2. Evolutionary Biology
    Renan Maestri, Benoît Perez-Lamarque ... Hélène Morlon
    Research Article

    Several coronaviruses infect humans, with three, including the SARS-CoV2, causing diseases. While coronaviruses are especially prone to induce pandemics, we know little about their evolutionary history, host-to-host transmissions, and biogeography. One of the difficulties lies in dating the origination of the family, a particularly challenging task for RNA viruses in general. Previous cophylogenetic tests of virus-host associations, including in the Coronaviridae family, have suggested a virus-host codiversification history stretching many millions of years. Here, we establish a framework for robustly testing scenarios of ancient origination and codiversification versus recent origination and diversification by host switches. Applied to coronaviruses and their mammalian hosts, our results support a scenario of recent origination of coronaviruses in bats and diversification by host switches, with preferential host switches within mammalian orders. Hotspots of coronavirus diversity, concentrated in East Asia and Europe, are consistent with this scenario of relatively recent origination and localized host switches. Spillovers from bats to other species are rare, but have the highest probability to be towards humans than to any other mammal species, implicating humans as the evolutionary intermediate host. The high host-switching rates within orders, as well as between humans, domesticated mammals, and non-flying wild mammals, indicates the potential for rapid additional spreading of coronaviruses across the world. Our results suggest that the evolutionary history of extant mammalian coronaviruses is recent, and that cases of long-term virus–host codiversification have been largely over-estimated.

    1. Cancer Biology
    2. Epidemiology and Global Health
    Chelsea L Hansen, Cécile Viboud, Lone Simonsen
    Research Article

    Cancer is considered a risk factor for COVID-19 mortality, yet several countries have reported that deaths with a primary code of cancer remained within historic levels during the COVID-19 pandemic. Here, we further elucidate the relationship between cancer mortality and COVID-19 on a population level in the US. We compared pandemic-related mortality patterns from underlying and multiple cause (MC) death data for six types of cancer, diabetes, and Alzheimer’s. Any pandemic-related changes in coding practices should be eliminated by study of MC data. Nationally in 2020, MC cancer mortality rose by only 3% over a pre-pandemic baseline, corresponding to ~13,600 excess deaths. Mortality elevation was measurably higher for less deadly cancers (breast, colorectal, and hematological, 2–7%) than cancers with a poor survival rate (lung and pancreatic, 0–1%). In comparison, there was substantial elevation in MC deaths from diabetes (37%) and Alzheimer’s (19%). To understand these differences, we simulated the expected excess mortality for each condition using COVID-19 attack rates, life expectancy, population size, and mean age of individuals living with each condition. We find that the observed mortality differences are primarily explained by differences in life expectancy, with the risk of death from deadly cancers outcompeting the risk of death from COVID-19.