AstraZeneca-Funded Non-Clinical PhD Studentship (Fixed Term): Physics-Guided Representation Learning for Drug Discovery

University of Cambridge; Cambridge; On-site; GBP 19,000 - 20,000; Full time

Benefits offered by this job

Stipend provided

Tuition fees at UK/Home rate

International candidates eligible with

AstraZeneca collaboration

Job summary

The University of Cambridge invites applications for a four-year AstraZeneca-funded PhD studentship in the Department of Pure Mathematics and Mathematical Statistics, starting October 2027. The successful candidate will be jointly supervised by Prof Sergio Bacallado, Dr Dino Oglic and Dr Jon Paul Janet.

The project, Physics-Guided Representation Learning from Free Energy Perturbation Data for Affinity Prediction and Candidate Down-Selection, will develop ML methods to predict molecular binding

Qualifications

• A first-class or upper second-class honours degree (or equivalent) in Mathematics, Statistics, ML, or Scientific Computing.
• Strong mathematical and statistical background with ML experience.
• Interest in applying expertise to drug discovery and computational chemistry is desirable.

Responsibilities

• Develop ML methods for representing FEP data and predicting molecular binding affinities.
• Collaborate with academia and AstraZeneca researchers on project-related studies.
• Prepare research summaries, results, and contribute to publications.

Skills

Mathematics

Statistics

Machine Learning

Scientific Computing

Computational Chemistry (desirable)

Education

Honours degree in Mathematics/Statistics/ML/Scientific Computing

Job description

Applications are invited for a four-year, AstraZeneca-funded PhD studentship in the Department of Pure Mathematics and Mathematical Statistics, commencing in October 2027.The successful candidate will be jointly supervised by Prof Sergio Bacallado (University of Cambridge), Dr Dino Oglic (AstraZeneca), and Dr Jon Paul Janet (AstraZeneca). The studentship offers an opportunity to conduct cutting-edge research at the interface of statistical machine learning, molecular simulation and drug discovery.Project descriptionThe project, entitled Physics-Guided Representation Learning from Free Energy Perturbation Data for Affinity Prediction and Candidate Down-Selection, aims to develop novel machine-learning methods for predicting molecular binding affinities and supporting decision-making in drug discovery.Free energy perturbation (FEP) calculations provide valuable information about how strongly candidate drug molecules bind to their biological targets, but these calculations are computationally expensive. This project will investigate how machine-learning models can extract richer information from FEP data and experimental measurements, combining physical principles with modern representation-learning techniques.The research will involve developing and evaluating new statistical and machine-learning methods, with access to both public benchmark datasets and AstraZeneca's industrial drug-discovery expertise and data.Candidate requirementsApplicants should have, or expect to obtain, a first-class or upper second-class honours degree (or equivalent), normally following four years of university study. We welcome applicants with backgrounds in Mathematics, Statistics, Machine Learning, Scientific Computing, or any closely related discipline.Experience with computational chemistry would be desirable but is not essential. We particularly welcome applications from candidates with strong mathematical or machine-learning backgrounds who are interested in applying their expertise to problems in drug discovery.FundingThe studentship provides funding for four years, covering a maintenance stipend and University tuition fees at the UK/Home rate.The studentship is open to candidates eligible for Home-fee status. International candidates may also be considered, provided that additional funding can be secured through scholarships or other approved funding schemes to cover the difference between Home and international tuition fees. This difference cannot be covered through student self-funding.Training and supervisionThe student will benefit from joint academic and industrial supervision, participating in the research activities of the Department of Pure Mathematics and Mathematical Statistics and collaborating closely with AstraZeneca researchers to gain exposure to industrial applications of artificial intelligence in pharmaceutical development.How to applyApplications must be submitted through the University of Cambridge Postgraduate Applicant Portal, selecting the course PhD in Pure Mathematics and Mathematical Statistics:https://www.postgraduate.study.cam.ac.uk/courses/directory/mapmpdpms/applyApplicants should indicate Dr Sergio Bacallado as their proposed supervisor and use the following project title:Physics-Guided Representation Learning from Free Energy Perturbation Data for Affinity Prediction and Candidate Down-Selection.Applications should include the supporting documentation required by the University, including academic transcripts, a CV, two references, and the relevant research summary and reasons for applying.The deadline for applications is 6 January 2027 (23:59 UK time).Shortlisted candidates will be invited to interview in January 2027.Informal enquiries about the project are welcome and may be addressed to Dr Sergio Bacallado at [e-mail] University actively supports equality, diversity and inclusion and encourages applications from all sections of society.