We are currently advertising National Productivity Investment Fund Industrial CASE studentships with a deadline of the 16th July 2018.

27 / 06 / 2018

How bugs in the gut affect ageing - using machine learning and networks to increase healthy lifespan (KORCSMAROS_E18ICASENF)

how to apply

Ageing is a significant event in the general population not only due to the increasing proportion of the elderly but also the prevalence of various age-associated disorders. Hence, it is essential to understand the mechanisms which either drive or slow down the ageing process. From a prognostic perspective, there exist very few tools which could predict beforehand the onset of ageing. Alterations in the gut microbiome have been observed in aged individuals compared to those displaying no ageing onset.

Machine Learning is a novel area of Artificial Intelligence wherein computers are allowed to learn rapidly from large datasets to discover the underlying complex patterns and signatures with minimal human interference. By combining systems biology approaches which capture the effects of the gut microbiota on host processes, the project aims to discover mechanistic explanations from the underlying hidden patterns identified by machine learning in metagenomic datasets from aged and healthy subjects.

The studentship will provide the prospective candidate with an excellent opportunity to carry out cross-disciplinary research by virtue of a collaboration between the Earlham Institute, a world-leader in bioinformatics, the Quadram Institute, a pioneer in gut health and microbiota research and the industry partner BenevolentAI which has a big footprint in heralding AI/ML approaches in translational medicine. The goal of the project will be to create a Machine Learning based Systems Biology pipeline to understand the mechanisms mediated by the underlying changes in the gut microbiome on ageing and related processes. The developed pipeline will be standardized thus making it scalable, reproducible and amenable to other microbiome-related datasets.