PhD Studentship: Physics-Guided Representation Learning for Drug Discovery

About the role

A four-year, AstraZeneca-funded PhD studentship is offered in the Department of Pure Mathematics and Mathematical Statistics at the University of Cambridge, starting in October 2027. It sits at the interface of statistical machine learning, molecular simulation and drug discovery. The project, titled Physics-Guided Representation Learning from Free Energy Perturbation Data for Affinity Prediction and Candidate Down-Selection, develops machine-learning methods for predicting molecular binding affinities and supporting decisions in drug discovery. The student is jointly supervised by Professor Sergio Bacallado (University of Cambridge) and two AstraZeneca researchers.

Key responsibilities

• Develop and evaluate new statistical and machine-learning methods.
• Investigate how machine-learning models can extract more information from free energy perturbation (FEP) data and experimental measurements, combining physical principles with modern representation-learning techniques.
• Work with public benchmark datasets and collaborate with AstraZeneca researchers on industrial applications of AI in pharmaceutical development.

Required profile

• First-class or upper second-class honours degree (or equivalent), normally after four years of university study.
• Background in Mathematics, Statistics, Machine Learning, Scientific Computing or a closely related discipline.
• Experience with computational chemistry is desirable but not essential.
• Home-fee eligibility; international candidates may be considered if additional funding covers the fee difference.

What we offer

• Funding for four years, covering a maintenance stipend and UK/Home-rate tuition fees.
• Joint academic and industrial supervision and close collaboration with AstraZeneca researchers.

Applications go through the University of Cambridge postgraduate portal, naming the proposed supervisor and the project title, with transcripts, CV, two references and a research summary. The deadline is 6 January 2027; shortlisted candidates are interviewed in January 2027.