MRC DiMeN Doctoral Training Partnership: The Biting-Edge of AI – Predicting Mosquito Vector Competence for Viruses

Description

Mosquito-borne viruses (arboviruses) pose major global threats to animal and human health, and food security. They are disproportionately prominent in global emerging infectious diseases, currently threaten the UK (e.g., West Nile and Usutu viruses), and will likely continue to increase in their global importance.

While current research primarily focuses on the climatic suitability of established mosquito vectors, many local species have proven to be competent for arbovirus transmission. Viruses such as Zika, West Nile, chikungunya, and Usutu have expanded their global reach, largely due to previously unexposed mosquito species becoming viable new vectors.

The ability to computationally predict whether a local mosquito species is able transmit an arbovirus before incursion is paramount for enhancing risk assessment, preparedness, and outbreak mitigation.

This project aims to develop an AI-framework to predict vector-competence. This framework can estimate transmission risk in new regions; and prioritise the otherwise unfeasible number of virus-mosquito combinations that would be required for a before-the-incursion testing regimen. Importantly, this framework can improve its predictive performance by directing wet-lab based experiments to target its blind-spots.

The supervisors have consolidated current arbovirus mosquito-competence literature, into a unified repository. Utilising those data, you will be able to address the following questions:

1. Which virus and mosquito traits correlate with arbovirus competence?

Given the complexity of competence drivers, the student will develop an array of features, encompassing virus genomic traits, mosquito phylogeny, and ecological characteristics. These features need not directly cause vector competence; any correlating with competence could be predictive of it. You will further expand AI-frameworks developed by Blagrove and Wardeh (supervisors 1 and 2) to uncover such correlations.

2. How can we identify and overcome the predictive blind spots?

Collaborating closely with Wardeh, you will integrate Active Learning (AL) into the AI- frameworks. AL is a machine-learning technique which can identify the most informative and testable novel arbovirus-mosquito combinations.

Finally, depending on your interests and aspirations, you could perform laboratory testing in Blagrove’s (supervisor 1) arbovirus infection suite, gaining a broad range of laboratory and virus handling skills (to be trained by Blagrove’s group of approx. 10 people). Or continue to computationally refine the framework and become a leader in AI development (working more closely with Wardeh). This flexibility is intended to allow you to pursue your interests and skills as they develop, rather than fix you down a specific path. Further insight, development and alternative routes are also available with supervisor 3 (Baylis), an epidemiologist.

Benefits of being in the DiMeN DTP:

This project is part of the Discovery Medicine North Doctoral Training Partnership (DiMeN DTP), a diverse community of PhD students across the North of England researching the major health problems facing the world today. Our partner institutions (Universities of Leeds, Liverpool, Newcastle, York and Sheffield) are internationally recognised as centres of research excellence and can offer you access to state-of-the-art facilities to deliver high impact research.

We are very proud of our student-centred ethos and committed to supporting you throughout your PhD. As part of the DTP, we offer bespoke training in key skills sought after in early career researchers, as well as opportunities to broaden your career horizons in a range of non-academic sectors.

Being funded by the MRC means you can access additional funding for research placements, training opportunities or internships in science policy, science communication and beyond. Further information on the programme and how to apply can be found on our website:

https://www.dimen.org.uk/