Dr Nicole Wheeler
18 July 2018
11:00am
QIB Lecture Theatre
Machine learning identifies signatures of host adaptation in the bacterial pathogen Salmonella enterica
Speaker: Dr Nicole Wheeler, Wellcome Sanger Institute, will present a seminar entitled: Machine learning identifies signatures of host adaptation in the bacterial pathogen Salmonella enterica
Host: John Wain
Abstract:
Thanks to the dropping cost of whole genome sequencing technologies, and coordinated global surveillance efforts, we now have access to vast collections of genomic data from bacteria circulating in human populations. However, our ability to draw insights about why some of these bacteria cause severe disease, and which lineages might be problematic in the future is still limited. New methods are urgently required to effectively utilize these large resources of genomic data to provide functional insights into established and emerging pathogens.
In this work, we have measured the burden of atypical mutations in protein coding genes across independently evolved Salmonella enterica lineages, and used these as input to train a machine learning algorithm to identify strains associated with extraintestinal disease. Members of the species fall along a continuum, from pathovars which cause gastrointestinal infection and low mortality, associated with a broad host-range, to those that cause invasive infection and high mortality, associated with a narrowed host range. Our machine learning algorithm was able to perfectly discriminate long-established gastrointestinal and invasive serovars of Salmonella. Additionally, it was able to identify recently emerged Salmonella Enteritidis and Typhimurium lineages associated with invasive disease in immunocompromised populations in sub-Saharan Africa, and within-host adaptation to invasive infection.
We have dissected the architecture of the model to identify the genes that were most informative of phenotype, revealing a common theme of degradation of metabolic pathways in extraintestinal lineages. This approach identifies patterns of gene degradation and diversifying selection specific to invasive serovars that have been captured by more labour-intensive investigations, but can be readily scaled to larger analyses.
All staff from organisations on the Norwich Research Park are welcome to attend.