Supporting Evidence-Based Interventions (SEBI)

Menu

PHD opportunity: Artificial Intelligence and Machine Learning to improve predictive modelling of Anti Microbial Resistance

The project will use data-driven approaches to model antimicrobial use and resistance in human-livestock interactions in low-and middle-income countries.

PHD opportunity: Artificial Intelligence and Machine Learning to improve predictive modelling of Anti Microbial Resistance
Composite image credit: AI screen by wcn247 ; Fulani cattle pic by SEBI

Supervisors:  Dominic Moran, Andy Peters, Adrian Muwonge, Jasmina Lazic

Closing Date:  6th January 2021

Antimicrobial resistance (AMR) and the falling efficacy of medically important drugs is a global medical emergency.  AMR is the quintessential One Health problem, affecting the health of people, their animals, and the environment.  As a One Health problem, addressing AMR demands collaborations across multiple sectors, a diversity of disciplines, and public and private institutions.  Worldwide, many antibiotics used in human medicine are also used in food-animal production, not only for treating sick animals but also for disease prevention, treatment of in-contacts (metaphylaxis) and growth promotion.  There is general agreement that this often poorly regulated use is a significant driver/pressure of AMR and there is a need to develop a clearer macro to micro picture of how this resistance develops in specific locations.  

In the developing world, the majority of antimicrobial resistance (AMR) arises in the community setting where the livestock-human interface is particularly important.  But there are significant gaps in our knowledge linking antimicrobial use (AMU) and AMR.  This project aims to develop a data framework for understating the links between observed data on animal health, known disease prevalence and treatments and drug availability and the frequently unobserved processes that lead to the emergence of AMR and disease resistance hotspots.  AMR is a biological phenomenon that can emerge from the interplay of human, animal and environmental drivers and conditioners.  The project will seek to estimate community-generated antibiotic resistance (CGR) by exploiting relatively cheap information from antibiotic sources, distribution networks, household decision making and the known biological processes that drive antimicrobial susceptibility (to resistance) In seeking to bridge significant data gaps and uncertainties, the project will draw on Artificial Intelligence and Machine Learning to improve predictive modelling of AMR, the rational and legal use of antimicrobials and antibiotic combinations, as well as future research directions.

The project will build on expertise and data curated under the  Supporting Evidence Based Interventions (SEBI)SEBI mobilises and applies data and evidence to help the livestock community make better investments that improve livelihoods for smallholders in low and middle-income countries.  The project has collected systematic data on disease prevalence including those normally treated with antimicrobials e.g. mastitis.  The project would initially focus on prevalence data for Ethiopia and will use this to construct predictive capabilities with Nigerian data, using automation tools that will be developed and trialled as part of this project.  The student will develop an end-to-end understanding of the human and biological processes that explain AMR including expertise in antimicrobial sensitivity testing (AST) and the other is whole-genome sequencing for antimicrobial sensitivity testing.  They will also develop a variety of research, professional and project management skills through interaction with the SEBI team, Roslin and GAAFS researchers plus a period of internship with the CASE partners.

Funding information and application procedures

This 4 year PhD project is part of a competition funded by EASTBIO BBSRC Doctoral Training Partnership (DTP) http://www.eastscotbiodtp.ac.uk/how-apply-0 .

This opportunity is open to UK and international students and provides funding to cover stipend and UK level tuition fees.  The University of Edinburgh will cover the difference between home and international fees meaning that the EASTBIO DTP will offer fully-funded studentships to all appointees.  However there is a cap on the number of international students the DTP can recruit.  It is therefore important for us to know from the outset which fees status category applicants will fall under when formally applying for entry to our university.

Please refer to UKRI website and Annex B of the UKRI Training Grant Terms and Conditions for full eligibility criteria.

EASTBIO Application and Reference Forms can be downloaded via   http://www.eastscotbiodtp.ac.uk/how-apply-0

Please send your completed EASTBIO Application Form along with a copy of your academic transcripts to RDSVS.PGR.Admin@ed.ac.uk

You should also ensure that two references have been send to RDSVS.PGR.Admin@ed.ac.uk  by the deadline using the EASTBIO Reference Form.