Towards a Virtual Cell: Agentic AI for Sample-Specific Signalling Networks

Project Overview

Every cell tells its own story, but the tools we use to read it often do not. When researchers interpret gene and protein expression data, they usually turn to databases of known molecular interactions. Yet these interaction networks offer, at best, an “average” picture of biological systems. The phenomena that matter most, such as disease, drug response and cellular adaptation, arise precisely when those networks are perturbed.

This entirely computational PhD offers you the chance to change how expression studies are understood. You will pursue a new approach that uses sample-specific phosphoproteomics data to automatically refine canonical interaction networks, producing models that capture what is genuinely happening in each sample. These tailored networks provide a more rigorous foundation for interpreting experimental results and open the door to real mechanistic insight.

You will design, build and evaluate an agentic AI system, combining phosphoproteomics analysis, prior knowledge retrieval, network refinement and automated hypothesis generation. The result will be a step towards the “virtual cell”: an interpretable, sample-specific model of signalling that can be interrogated and used to generate testable predictions. Applications of this approach include target discovery, drug response prediction, and mechanistic understanding of fundamental biological phenomena. More broadly, the project contributes to the emerging field of automated scientific discovery, in which AI systems not only analyse data but also propose the next questions to ask.

 

Research Environment 

This project will be based in Prof Conrad Bessant’s lab within the Digital Environment Research Institute (DERI) at Queen Mary University of London. It builds on the lab’s track record in proteomics, network science and AI. Prof Bessant is Academic Lead of the UKRI-BBSRC AI for Drug Discovery Collaborative Training Partnership (AIDD-CTP), and the lab has strong links with the pharmaceutical and AI industries. You will join an international research environment and publish your work in leading journals, building the skills and profile for a career in academia or industry.

School of Biological and Behavioural Sciences

 

Entry Requirements 

We are looking for candidates to have or expecting to receive a first or upper-second class honours degree and a Master’s degree in an area relevant to the project such as bioinformatics, computational biology, computer science or a related quantitative discipline.

Fluency in Python is essential, with experience of R, AI and network science desirable. No laboratory experience is required, but enthusiasm for answering biological questions is essential and an understanding of how biological data are generated would be useful.

You must meet the IELTS requirements for your course and upload evidence before CSC’s application deadline, ideally by 17^th March 2027. You are therefore strongly advised to sit an approved English Language test as soon as possible, where your IELTS test must still be valid when you enrol for the programme.

Find out more about our entry requirements here.

 

How to Apply

Formal applications must be submitted through our online form by 27th January 2027 for consideration. Please identify yourself as a ‘CSC Scholar’ in the funding section of the application. 

Applicants are required to submit the following documents: 

• Your CV 

• Personal Statement 

• Evidence of English Language e.g.) IELTS Certificate 

• Copies of academic transcripts and degree certificates  

• References 

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

 

Informal enquiries about the project can be sent to Conrad Bessant at c.bessant@qmul.ac.uk. Admissions-related queries can be sent to sbbs-phd-admissions@qmul.ac.uk

Shortlisted applicants will be invited for a formal interview by the supervisor. If you are successful in your QMUL application, then you will be issued an QMUL Offer Letter, conditional on securing a CSC scholarship along with academic conditions still required to meet our entry requirements.  

Once applicants have obtained their QMUL Offer Letter, they should then apply to CSC for the scholarship with the support of the supervisor.  

For further information, please go to the QMUL China Scholarship Council webpage. 

 

Apply Online

 

References

1. Hijazi, M., Smith, R., Rajeeve, V., Bessant, C. & Cutillas, P. R. (2020). Reconstructing kinase network topologies from phosphoproteomics data reveals cancer-associated rewiring. Nature Biotechnology, 38, 493–502. https://doi.org/10.1038/s41587-019-0391-9

 

2. Garrido-Rodriguez, M., Potel, C., Burtscher, M. L. et al. (2026). Benchmarking EGF signaling pathway inference using phosphoproteomics and kinase-substrate interactions. Nature Communications, 17, 2071. https://doi.org/10.1038/s41467-026-69332-0

 

3. Ghareeb, A. E., Chang, B., Mitchener, L. et al. (2026). A multi-agent system for automating scientific discovery. Nature, 655, 497–505. https://doi.org/10.1038/s41586-026-10652-y

 

See Also

• Entry Requirements
• Fees and Funding
• Application Process