Support Vector Machine applied to predict the zoonotic potential of E. coli O157 cattle isolates

Nadejda Lupolova, Timothy Dallman, Louise Matthews, James L Bono, David Gally

Research output: Contribution to journalArticlepeer-review

Abstract

Sequence analyses of pathogen genomes facilitate the tracking of disease outbreaks, allow relationships between strains to be reconstructed and virulence factors to be identified. However, these methods are generally used after an outbreak has happened. Here, we show that support vector machine analysis of bovine E. coli O157 isolate sequences can be applied to predict their zoonotic potential, identifying cattle strains more likely to be a serious threat to human health. Notably, only a minor subset (less than 10 percent) of bovine E. coli O157 isolates analysed in our datasets were predicted to have the potential to cause human disease; this is despite the fact that the majority are within previously defined pathogenic lineages I or I/II and encode key virulence factors. The predictive capacity was retained when tested across datasets. The major differences between human and bovine E. coli O157 isolates were due to the relative abundances of hundreds of predicted prophage proteins. This finding has profound implications for public health management of disease as interventions in cattle, such a vaccination, can be targeted at herds carrying strains of high zoonotic potential. Machine-learning approaches should be applied broadly to further our understanding of pathogen biology.
Original languageEnglish
Pages (from-to)11312-11317
JournalProceedings of the National Academy of Sciences
Volume113
Issue number40
Early online date19 Sep 2016
DOIs
Publication statusPublished - 4 Oct 2016

Keywords

  • machine learning
  • zoonosis
  • Shiga toxin
  • E. coli
  • cattle

Fingerprint

Dive into the research topics of 'Support Vector Machine applied to predict the zoonotic potential of E. coli O157 cattle isolates'. Together they form a unique fingerprint.

Cite this