Machine learning for Real-time Detection of Airborne Fungi

Scientific background:

The air we breathe is teaming with microorganisms and other biogenic particulates (collectively referred to as bioaerosols). Many of these have negative effects on human and plant health. For example, Aspergillus emitted from composting can cause asthma, and respiratory infections; crop pathogens such as Phytophthora and Alternaria threaten global food security. Climate change is driving range expansion and seasonality of these taxa, but we lack real-time monitoring data to assess the risk. A major development towards this are optical measurement systems that characterise individual bioaerosols, but their use for fungi remains underdeveloped. We have optimised methods for collecting/characterising bioaerosols from different environments for molecular analysis1,2. This project aims to apply novel methods to develop classification algorithms for real-time bioaerosols monitoring to assess exposure and health impacts. 

Research methodology:

The project will utilise state-of-the-art computational and molecular techniques. Machine leaning will be used to develop novel classification algorithms for key fungal taxa by aerosolizing fungi into a SwisensPoleno air-flow-cytometer in ambient air, compositing sites, and crop systems. For comparison, high-throughput sequencing will be used to characterise airborne fungal communities. Additional data from a SwisensPoleno Jupiter and multi-vial-cyclone sampler will be provided by the UKHSA Chilton’s monitoring station. These data will be used to develop better forecasting tools and assess how bioaerosol exposure will be effected by a changing climate.   

Training:

The individual will receive training in novel air sampling techniques, molecular microbial, bioinformatic and fieldwork skills. Additionally, they will receive training in data analysis and machine leaning at Swisens. The individual will be encouraged to present at conferences and will gain experience in policy development (UKHSA/Environment Agency). The candidate will also be invited to join the UKHSA’s and Environment Agency’s Chief Scientist’s Group PhD network.   

Person specification:

This is an exciting opportunity for a highly motivated individual with a background in Computer Science, Bioinformatics, Biological/Environmental Sciences, Molecular Biology, Microbiology who is keen to undertake both lab and fieldwork, engage with regulators and end users. The successful applicant will join a multi-disciplinary team at Essex with time spent at the collaborative partners UKHSA, EA. 

To apply, email a covering letter and CV to ariesapp@essex.ac.uk

For more information, please see: https://www.aries-dtp.ac.uk/studentships/ferguson/

ARIES is awaiting confirmation of funding under the BBSRC-NERC DLA award scheme, which is expected shortly. Funding for this studentship is subject to this confirmation and UKRI terms and conditions. Successful candidates who meet UKRI’s eligibility criteria will be awarded a fully-funded ARIES studentship of fees, maintenance stipend (£19,237 p.a. for 2024/25) and research costs.

A limited number of ARIES studentships are available to International applicants. Please note however that ARIES funding does not cover additional costs associated with relocation to, and living in, the UK.

ARIES is committed to equality, diversity, widening participation and inclusion in all areas of its operation. We encourage applications from all sections of the community regardless of gender, ethnicity, disability, age, sexual orientation, and transgender status. Projects have been developed with consideration of a safe, inclusive, and appropriate research and fieldwork environment. Academic qualifications are considered alongside non-academic experience, with equal weighting given to experience and potential.

For further information, please visit www.aries-dtp.ac.uk