Revealing diffuse midline glioma radiotherapy resistance mechanisms with machine learning (23046)

Primary Supervisor:

Dr Jamie Dean
Senior Research Fellow / Junior Group Leader in Computational Radiation Oncology

Introduction:

A 4-year funded PhD studentship is available in the Computational Radiation Biology Lab in the UCL Department of Medical Physics and Biomedical Engineering. Funding will be at least the UCL minimum stipend rate. Details can be found here. 

The successful candidate will join our Research Degree in Medical Physics (application portal here), and benefit from the activities and events organised by the department.

The Computational Radiation Biology Lab seeks to unlock the “fourth dimension” of radiation biology, time, to design superior radiotherapy strategies. While radiotherapy is an effective treatment for numerous cancer patients, for many others it fails to control their tumours. Increasing the rate of treatment success requires understanding and manipulating the temporal evolution of tumours and normal tissues in response to therapy. Through an innovative, multidisciplinary, collaborative approach, integrating mathematical modelling of molecular and cellular radiation response dynamics with longitudinal measurements of the response of cells, mouse models and patients to treatment, the lab is gaining a detailed, quantitative understanding of the dynamic tumour and normal tissue responses to radiotherapy and drug-radiation combination therapies. The lab is then leveraging this knowledge of the “fourth dimension” of radiation biology to design and evaluate superior treatment strategies.

Project Background: 

Diffuse midline glioma (DMG) is a highly lethal brain tumour that most often occurs in young children. The location of these tumours, in highly sensitive areas of the brain, prevents them from being surgically removed. Radiotherapy, using high energy x-rays to damage and kill the cancer cells, is currently the only treatment that is standardly offered to patients as it is the only treatment that has been shown to prolong survival. However, radiotherapy only partially shrinks the tumours or temporarily slows their growth and patients rapidly die of the disease, usually within a year of being diagnosed. There is therefore an urgent need to discover how these tumours are able to survive radiotherapy and use this knowledge to develop more effective treatment approaches.

Recent advances in experimental and computational techniques provide an unprecedented opportunity to advance our knowledge of DMG treatment resistance. Developments in preclinical models, single cell and spatial molecular profiling, and timelapse microscopy, are providing new windows into the complex dynamic response of these tumours to treatment. Innovations in machine learning are enabling the distillation of impactful knowledge from these complex multimodal data. By combining these approaches, we are seeking to reveal and overcome DMG radiotherapy resistance mechanisms.

Research aims: 

We aim to understand the cellular and molecular mechanisms of DMG resistance to radiotherapy. The student will infer which subpopulations of cancer cells survive radiotherapy, whether cells transition between sensitive and resistant states and how this is influenced by treatment, how interactions with other cells in the tumour immune microenvironment contribute to resistance, and the molecular mechanisms underlying these processes. To achieve these aims the student will apply methods from machine learning and dynamical systems theory to multimodal preclinical and clinical data of diffuse midline glioma response to radiotherapy, and codesign experiments with our collaborators to validate their computational inferences.

Person specification & requirements:

• This studentship is only open to Home Fee-paying candidates. More information about fee status criteria can be found here.
• Candidates with backgrounds in computer science, engineering, physical sciences, mathematics or computational biology, or comparable experience in computer programming and machine learning are welcome to apply.
• Hands-on experience in advanced machine learning and its application to complex biomedical data, and interdisciplinary communication of complex concepts will be a plus.
• Candidates should have an interest in neuro-oncology and the application of advanced computational methods to solving high impact problems in biomedicine, and the desire to work collaboratively within a multidisciplinary team.
• Candidates should hold a UK (or international equivalent) first or upper-second Bachelor’s degree.

Funding:

This is a full studentship available to home fee applicants only.

The successful student will receive a stipend starting from at least the UCL minimum (£22,780 in 2025/26) as well as the cost of tuition fees for Home fee students (£6,215 in 2025/26). 

The stipends awarded to PhD students at UCL are tax free and incur no income tax or national insurance contributions. The amount received increases each year over the duration of the studentship. 

UCL’s fee eligibility criteria can be found by following this link.

How to apply:

Please complete the following steps to apply.

• Send an expression of interest and current CV to jamie.dean@ucl.ac.uk and medphys.pgr@ucl.ac.uk, quoting Project Code 23046 in the email subject line.
• Make a formal application via the UCL application portal: Apply | Prospective Students Graduate - UCL – University College London. Please select the programme code ‘Medical Physics RRDMPHSING01’ and enter Project Code 23046 under ‘Name of Award 1’
• If shortlisted, candidates will be invited for an interview.

Application Timeline:

• After the deadline, all applicants that expressed their interests and specified Project 23046 in their Portico application will be considered for interview.
• Candidates will normally be invited for interview within two weeks of the deadline. If you have not been contacted within this time-period, you have unfortunately not been successful in being shortlisted.
• The interview panel will normally consist of the supervision team on the project.
• Note that applications without specifying the project they are applying for and/or making a formal Portico application will be automatically rejected.
• If you are offered and accept a studentship position, a formal UCL Offer of Admission will be sent to you as well as an offer of studentship funding.