Video | Business Headlines | Internet | Science | Scientific Ethics | Technology | Search

 

New tool to classify severity of Salmonella

Otago scientist involved in new tool to classify severity of Salmonella

Wednesday 9 May 2018

A University of Otago expert is part of an international collaboration that has created a new machine learning tool that can detect whether emerging strains of the bacterium Salmonella are more likely to cause life-threatening bloodstream infections rather than only food poisoning.

The software tool, created by a scientist at the Wellcome Sanger Institute in the United Kingdom, the University of Otago, and the Helmholtz Institute for RNA-based Infection Research in Germany, greatly speeds up the process for identifying the genetic changes underlying new invasive types of Salmonella that are a greater concern to public health.

A study published in PLOS Genetics today, details how the machine learning tool could be useful for flagging dangerous bacteria before they cause an outbreak, from hospital wards to a global scale.

The group of bacteria known as Salmonella includes many different types that vary in the severity of the disease they cause. Some types cause food poisoning, known as Gastrointestinal Salmonella, whereas others cause severe disease by spreading beyond the gut, for example Salmonella Typhi, which causes typhoid fever.

Dr Paul Gardner of the University of Otago’s Department of Biochemistry says the method correctly classifies which Salmonella types are going to be invasive and which ones are not, by analysing genome sequences.

“Essentially we can answer the question of: Do we need to worry about this as it could cause quite a lot of people to become sick, or is this not going to trouble the community too much,” Dr Gardner says.

To understand the genetic changes that determine whether an emerging strain of Salmonella will cause food poisoning versus a more severe infection, researchers built the machine learning model that analyses which mutations play an important role.

The team trained the model using old lineages of salmonella that are evolutionarily distinct, including six Salmonella bacteria that caused invasive infections, and seven gastrointestinal strains of the bacteria. The machine learning model identified almost 200 genes involved in determining whether the bacterium will cause food poisoning or is better adapted to causing invasive infection.

The study was co-lead by Dr Nicole Wheeler of the Wellcome Sanger Institute.

“Using this tool, we can tackle massive data sets and get results in seconds. Ultimately, this work will have a big impact on the surveillance of dangerous bacteria in a way we haven’t been able to before, not only in hospital wards, but at a global scale,” Dr Wheeler says.

Developers say the machine learning tool, which produces an invasiveness index based on a “Random Forest” model, is not limited to Salmonella and could be used to study other factors such as emerging antibiotic resistance in any bacterium, and could be used in real time to identify a dangerous strain of bacteria before it spreads to cause an outbreak.


ends

© Scoop Media

 
 
 
Business Headlines | Sci-Tech Headlines

 

You'd Hope: Employers Told To Pay Minimum Wage

Advertisers offering jobs to backpackers are being told they must pay the minimum wage or risk prosecution. Last week, RNZ revealed a job website - Backpackerboard - was advertising roles below the $16.50 per hour minimum wage. More>>

ALSO:

Still Gaining: More Migrants Head Back Overseas

Annual net migration is down 4,800 from a high point a year ago, largely because more non-New Zealand citizens are leaving the country, Stats NZ said today. More>>

Christchurch: Red Zone Used To Boost Endangered Bee Population

“May 20 has been declared World Bee Day by the United Nations, and I am pleased to announce today that we have been able to use the red zone to protect and grow our native bee stocks,” says Minister Megan Woods. More>>

Trips, Support, Conferences For Agents: Insurers Spend $34 Million On Soft Commissions

“We are concerned that insurers are designing and offering incentives that potentially set advisers up to fail in complying with their obligations.” More>>

ALSO:

Privacy Commissioner: Facial Recognition Tech Not Reliable

The Privacy Commissioner says businesses should take great care when using facial recognition technology because there is a high risk of misidentification. More>>

Compliance Costs: Cheesemakers "Have A Reason To Smile"

Delighted to be a guest at The Great Eketahuna Cheese Festival today, Mr O’Connor launched the Food Safety Template for Cheesemakers – a tool to help cheesemakers producing cheese for New Zealand and Australia to meet food safety requirements. More>>