Skip to Content

Deep Learning for Precision Oncology

School of Medicine, Dentistry and Biomedical Sciences | PHD
Funding
Funded
Reference Number
SMED-2251-1033
Application Deadline
14 April 2025
Start Date
1 October 2025

Overview

This project is a 4-year PhD project with enhanced training and 3+ month placement, which is funded by UKRI BBSRC through the NI Landscape Partnership in AI for Bioscience (NILAB) Programme, delivered by Queen’s University Belfast and Ulster University. Details of the enhanced training will be available later at qub.ac.uk/nilab/. NILAB aims to bridge the gap between biology and artificial intelligence to accelerate bioscience discovery and foster effective collaboration between academia, industrial partners, and government bodies. NILAB’s mission is to train the next generation of researchers to develop and use AI to uncover the rules of life, addressing challenges in human health, animal welfare, and sustainable food systems.

All cancer types can potentially resist therapy, either through innate mechanisms or acquired in response to treatment. Patients with resistant tumours have poor prognosis and around 460 people die of cancer every day in the UK alone. Accordingly, better and more effective therapies are urgently needed, including: novel molecular targets, new drug indications, companion diagnostic biomarkers and approaches to enable selective immune targeting. Promising approaches towards these precision oncology tools seek to identify molecular ‘weak points’ in cancer and to understand the mechanisms that drive resistance to therapy. Indeed, rich genome-scale multimodal data are available for cancer cells and patients, with matched readouts of sensitivity to potential therapeutic inhibition of protein targets. These data are ripe for interrogation by cutting-edge AI methods, which will be applied to enable integrative drug discovery at scale. This project aims to overcome drug resistance in multiple cancers, towards longer remission times and increased likelihood of a complete pathological response (tumour clearance). Discovery of biomarkers would ultimately enable more effective prescribing across a range of clinical pathways and could lead to earlier diagnosis of drug-resistant cancers.

The successful candidate will be based in the Overton group (www.overton-lab.uk) and co-supervised by Dr Son Mai, benefiting from an industry placement and guidance from Mevox Ltd. The student will be furnished with skills and knowledge necessary to succeed as an independent research scientist, including training in: cancer biology, deep learning, polyomics data integration, cluster computing, network biology, structural bioinformatics and transferable skills (scientific method, disseminating results, computer programming etc.). Student development will be guided by assessment of specific needs.

All types of cancer are potentially able to resist therapy, either through innate mechanisms or acquired in response to treatment. Patients with resistant tumours have poor prognosis and around 460 people die of cancer every day in the UK alone. Accordingly, better and more effective therapies are urgently needed for these patients; including novel molecular targets, new drug indications, companion diagnostic biomarkers and approaches to enable selective killing of tumour cells by the immune system. Promising approaches towards these precision oncology tools seek to identify molecular weak points in cancer and to understand the mechanisms that drive resistance to therapy. Indeed, rich genome-scale multimodal data are available for cancer cells and patients, including matched readouts of sensitivity to potential therapeutic inhibition of protein targets. These data are ripe for interrogation by cutting-edge AI methods, applied to enable integrative drug discovery at scale. Therapies discovered in this project could overcome drug resistance in multiple cancers, potentially producing longer remission times and possibly increasing the likelihood of complete pathological response (full tumour clearance). An associated aim to discover biomarkers would ultimately enable more effective prescribing across a range of clinical pathways and could help with earlier diagnosis of drug-resistant cancers.

The successful candidate will be primarily based in the Overton group (www.overton-lab.uk) at the Patrick G Johnston Centre for Cancer Research. Research work will examine publicly available data, including from the Cancer Dependency Map and patient datasets with drug sensitive and drug resistant samples. Initial steps will involve quality control and data characterisation, followed by training generative AI models to capture the relationship between gene status, including neoantigens and cancer progression. These models will enable identification of protein targets for cancer therapy development, combination therapies with existing frontline treatments and new indications for existing compounds, including drug repurposing. Therefore, results are expected to lead to fundamental insights into the molecular biology of cancer; with proposed strategies that exploit vulnerabilities to produce cell death through loss of gene function or targeting by the immune system. This project also investigates candidate RNA-based or DNA-based biomarkers for the efficacy of therapies identified with the above approaches. These candidate biomarkers are hoped to enable earlier diagnosis of therapy resistance and inform clinical treatment pathways.

The student will benefit from co-supervision by Dr Son Mai who has extensive experience in high performance machine learning (including deep learning) and mining complex data. Partnership with Mevox Ltd (https://mevoxltd.com/) will provide further guidance and exposure to an industry environment.

Funding Information

This project is open to both home and international applicants on a competitive basis. Top ranked students will be offered their choice of projects to which they apply. Funding is available for both domestic and international students with 30% of the funding allocated for international students.

Fees: Queen’s standard
Stipend: £20,780 (2025/2026)

Project Summary
Supervisor

Dr Ian Overton

More Information

askmhls@qub.ac.uk

Research Profile

Mode of Study

Full-time: 4 Years

Funding Body
UKRI BBSRC through the NILAB Programme
Apply now Register your interest