About this position
PhD studentship: Discovery of rational therapeutic biomarkers in breast cancer by systems pathology and deep learning
Supervisor: Dr Hamid Raza Ali
Department/location: Cancer Research UK Cambridge Institute
Deadline for application: 16th October 2026
Course start date: 1st October 2027
Overview
The Ali Lab wishes to recruit a student to work on the project entitled: "Discovery of rational therapeutic biomarkers in breast cancer by systems pathology and deep learning".
For further information about the research group, including their most recent publications, please visit their website at www.ali-lab.co.uk/
Project details
The therapeutic landscape for breast cancer patients is rapidly evolving with novel therapies regularly receiving regulatory approval. Yet directing these treatments to patients likely to benefit while sparing those unlikely to respond from their toxicities remains a major challenge. Many modern therapies, like immunotherapy and ADCs, rely on tissue architecture to be effective.
Intercellular relationships in breast cancer tissues also determine cellular activation states and expression profiles, rendering some cells susceptible and others resistant to new treatments.
The aim of this project is to use modern multiomic spatial methods (in which our group has extensive expertise14) together with deep learning (for efficient representation and cross-modal learning) to discover the potential therapeutic landscape for novel therapies in breast cancer, and to propose rational multidimensional biomarkers for combinatorial therapy. We are generating multimodal spatial datasets in cohorts of breast cancer patients (the largest of their kind; making extensive use of imaging mass cytometry and spatial transcriptomics) that span observational studies and clinical trials. We must precisely define the landscape of novel target expression, quantify its heterogeneity, and the contribution of tissue architecture as a determinant of expression profiles.
This project will involve large scale data processing and analysis in a setting with ample expertise and infrastructure. This is a rare opportunity to develop expertise in quantitative pathology in the burgeoning field of spatial cancer biology.
Ours is a diverse and collaborative group that spans clinicians, pathologists, computational and cancer biologists. You will receive extensive training in cancer pathology, highly multiplexed imaging, and predictive modelling.
References/further reading
- Wang, X. Q. et al. Spatial predictors of immunotherapy response in triple-negative breast cancer. Nature 621, 868-876 (2023).
- Danenberg, E. et al. Breast tumor microenvironment structures are associated with genomic features and clinical outcome. Nat Genet 54, 660-669 (2022).
- Ali, H. R. et al. Imaging mass cytometry and multiplatform genomics define the phenogenomic landscape of breast cancer. Nat Cancer 1, 163-175 (2020).
- Gupta, P. et al. Single-cell spatial atlas of the aging human breast. Nat Aging https://doi.org/10.1038/s43587-026-01104-3 (2026) doi:10.1038/s43587-026-01104-3.
Preferred skills/knowledge
Applications are invited from graduates in quantitative disciplines such as computer science, AI, and mathematics, but we also encourage applications from biologists and clinicians already experienced in computational methods.
How to apply
Please apply via the University Applicant Portal. For further information about the course and to access the Applicant Portal, click the 'Apply' button above.
You should select to commence study in October 2027.
References
We would appreciate it if you could ask your referees to submit their references as soon as possible upon request, despite the longer University deadline for references. They will receive a request once you have completed the References section of your application.
How to apply
- Read the full advert on the source site — it carries the authoritative terms.
- Prepare your SOP, CV, transcripts and referees before the deadline.
- Apply through the university's own portal. Never pay a fee to a third party.