AI-driven prediction of environmental stress sensitivity across insect pollinators

About the Project

• Supervisors:
  Dr Rachel Parkinson (SBBS, Biology) – primary supervisor
  Prof. Chris Bass (University of Exeter)
  Dr Chema Martin-Duran (SBBS, Biology) – co-supervisor
• Studentship Funding:
  Name: SBBS Studentship
  Funder: SBBS

Application Deadline: June 5th

PhD Route: PhD Biological Sciences

Expected Start Date: Sept 2026

Project Overview

Applications are open for a 3-Year funded PhD Studentship in the School of Biological and Behavioural Sciences (SBBS) at Queen Mary University of London.

This project will develop a computational framework to predict how different bee species respond to environmental stressors such as pesticides. Current environmental risk assessment approaches rely heavily on a small number of model species and fail to capture the large variation in sensitivity observed across taxa, limiting our ability to protect biodiversity and design sustainable agricultural systems. The overarching aim is to move beyond species-by-species testing by building generalisable, data-driven models that can predict sensitivity across hundreds of bee species directly from genomic and ecological information.

A central goal of the project is to enable prediction for unseen species and novel stress scenarios, including responses to newly developed pesticide compounds and combinations of multiple stressors encountered in real-world environments. By integrating information across species, the model will provide a scalable approach to forecasting risk where empirical data are lacking, supporting more robust and forward-looking environmental risk assessment.

The student will develop an integrated modelling framework linking genomic features, species traits, and toxicity data extracted from the literature using AI pipelines already developed in the lab. These data will be used to predict species-level sensitivity while explicitly accounting for uncertainty and sparse data. Predictions will be iteratively refined through collaboration with experimental researchers using an automated platform for high-throughput sublethal toxicity testing developed in the lab, providing a direct link between computational prediction and empirical validation.

Keywords:

bee ecotoxicology, environmental risk assessment, pesticide sensitivity, comparative genomics, cross-species prediction, AI-driven modelling

Research Environment

The student will join the Parkinson Lab within SBBS at Queen Mary University of London, an interdisciplinary research group working at the interface of artificial intelligence, ecology, and environmental toxicology. The lab develops computational and experimental tools to understand how environmental stressors affect insect behaviour and fitness, including AI-driven literature mining and automated behavioural phenotyping platforms.

The student will receive training in machine learning for biological data, including representation learning approaches such as protein language models, as well as Bayesian modelling and probabilistic inference. They will gain experience in large-scale data integration, working with genomic, ecological, and literature-derived datasets. There will also be opportunities to collaborate closely with MSc students conducting wet lab and behavioural assays, providing a unique link between computational prediction and experimental validation.

The project benefits from a strong collaborative network, including expertise in insect detoxification biology (co-supervisor Chris Bass, Exeter) and comparative genomics (co-supervisor Chema Martin-Duran, Queen Mary), and access to curated genomic datasets spanning over 200 pollinator species. The student will be supported within a vibrant research environment at QMUL, with access to high-performance computing resources and interdisciplinary training opportunities.

Find out more about the School of Biological and Behavioural Sciences on our website.

Entry Requirements & Criteria

We are looking for candidates to have or be expecting to receive a first or upper-second class honours degree and a Master’s degree in an area relevant to the project. This could include fields such as bioinformatics, computer science, computational biology, statistics, or biology and related disciplines where substantial quantitative or computational experience has been developed.

Candidates should have experience conducting research, ideally involving data analysis or computational work. We particularly welcome applicants from biological backgrounds who have developed strong skills in coding, data wrangling, or quantitative analysis through their research.

Experience working with large or complex datasets is expected. Knowledge of machine learning, statistical modelling, or genomic data analysis would be highly advantageous but is not required.

Applicants should have good programming skills (preferably in Python), and a clear interest in applying computational approaches to biological or environmental problems. Experience with Bayesian methods, large language models, or sequence analysis would be beneficial but is not essential.

Find out more about our entry requirements here.

Applicants from outside of the UK are required to provide evidence of their English language ability. Details can be found on our English Language requirements page.

Funding

The studentship is funded by the SBBS. It will cover home tuition fees, and provide an annual tax-free maintenance allowance for three years rate (£22,618 in 2026/27).

To qualify for Home Fees, this typically means the candidate will be unrestricted in how long they can remain in the UK.

International students will need to cover the difference in fees between the home and overseas basic rate from external sources. Further details can be found on our PhD Tuition Fees page.

Funding and eligibility queries can be sent to the sbbs-pgadmissions@qmul.ac.uk

How to Apply

Formal applications must be submitted through our online form by the stated deadline for consideration.

Applicants are required to submit the following documents:

• Your CV
• A Personal Statement, including:
  • Previous experience relevant to the project
  • Your motivations for pursuing this position
  • Your career aspirations
  • Any further information you think is relevant to the application
• References
• Copies of academic transcripts and degree certificates

Find out more about our application process on our SBBS website.

Informal enquiries about the project can be sent to Dr Rachel Parkinson AT r.parkinson@qmul.ac.uk. Enquiries about eligibility should be directed to the postgraduate research officer at d.seymour@qmul.ac.uk. Applications must be submitted through the online form by the stated deadline.

Admissions-related queries can be sent to sbbs-pgadmissions@qmul.ac.uk.