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

Lead Research Organisation: University of East Anglia
Department Name: Graduate Office

Abstract

Ageing is a significant event in the general population not only due to the increasing proportion of 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.

Publications

10 25 50

Studentship Projects

Project Reference Relationship Related To Start End Student Name
BB/S50743X/1 01/10/2018 31/12/2022
2116392 Studentship BB/S50743X/1 01/10/2018 30/11/2022
 
Title Singalink 3 
Description Signaling networks represent the molecular mechanisms controlling a cell's response to various internal or external stimuli. Most currently available signaling databases contain only a part of the complex network of intertwining pathways, leaving out key interactions or processes. Hence, we have developed SignaLink3 (http://signalink.org/), a value-added knowledge-base that provides manually curated data on signaling pathways and integrated data from several types of databases (interaction, regulation, localisation, disease, etc.) for humans, and three major animal model organisms. SignaLink3 contains over 400 000 newly added human protein-protein interactions resulting in a total of 700 000 interactions for Homo sapiens, making it one of the largest integrated signaling network resources. 
Type Of Technology Webtool/Application 
Year Produced 2021 
Open Source License? Yes  
Impact This webtool provides a quick and easy interface with the large about PPI data which is open access for any users. 
URL http://signalink.org/
 
Title ViralLink 
Description ViralLink is a systems biology workflow which reconstructs and analyses networks representing the effect of viral infection on specific human cell types. 
Type Of Technology Software 
Year Produced 2021 
Open Source License? Yes  
Impact Provides an integrated pipeline to work with viral-host interactions on specific human cell types 
URL https://github.com/korcsmarosgroup/ViralLink
 
Title earlham-sherlock/earlham-sherlock.github.io: First release of the official Sherlock platform 
Description First release. 
Type Of Technology Software 
Year Produced 2021 
Open Source License? Yes  
Impact Sherlock is an open-source data platform to store, analyze and integrate bioinformatics data. Features include: - store all datasets in a redundant, organized cloud storage - convert all datasets to common, optimized file formats - execute analytical queries on top of data files - share datasets among different teams/projects - generate operational datasets for certain services or collaborators 
URL https://zenodo.org/record/4738516
 
Title korcsmarosgroup/iSNP: A systems genomics approach to uncover patient-specific pathogenic pathways and proteins in ulcerative colitis 
Description A novel precision medicine workflow, the integrated single nucleotide polymorphism network platform (iSNP), designed to determine the mechanisms by which SNPs affect cellular regulatory networks, and how SNP co-occurrences contribute to disease pathogenesis in ulcerative colitis (UC) 
Type Of Technology Software 
Year Produced 2022 
Impact Provided an integrated pipeline to preform this systems medicine approach in a reproducible way. 
URL https://zenodo.org/record/6346651
 
Description Blog - 10 things you need to know about getting into machine learning 
Form Of Engagement Activity Engagement focused website, blog or social media channel
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Public/other audiences
Results and Impact A blog for those interested in getting started in Machine Learning in bioinformatics
Year(s) Of Engagement Activity 2019
URL https://www.earlham.ac.uk/articles/10-things-you-need-know-about-getting-machine-learning
 
Description Blog - A PhD, is it worth it? Just ask our students 
Form Of Engagement Activity Engagement focused website, blog or social media channel
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Undergraduate students
Results and Impact Blog answering questions and describing the first year of a PhD student and giving recommendations of what we wish we knew before we started. it was published on the Earlham Institutes website.
Year(s) Of Engagement Activity 2020
URL https://www.earlham.ac.uk/articles/phd-it-worth-it-just-ask-our-students
 
Description How AI will help us to explore our microbiome 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach Regional
Primary Audience Schools
Results and Impact Public engagement about how we can use AI to help us to explore our microbiome. This was short talk ~15 minutes
Year(s) Of Engagement Activity 2019
 
Description Inside EI - Open Day 
Form Of Engagement Activity Participation in an open day or visit at my research institution
Part Of Official Scheme? No
Geographic Reach Regional
Primary Audience Schools
Results and Impact Open day for the general public and schools to visit a research institute and ask questions to researchers.
Year(s) Of Engagement Activity 2019
URL https://www.earlham.ac.uk/open-day-2019