Imperial College London Featured PhD Programmes
Imperial College London Featured PhD Programmes
University of Kent Featured PhD Programmes
Norwich Research Park Featured PhD Programmes
Cardiff University Featured PhD Programmes

Machine Learning and Integrative Approaches in Immunology: Developing machine-learning and mathematical models to understand heterogeneity of response to personalised cancer immunotherapy

This project is no longer listed on and may not be available.

Click here to search for PhD studentship opportunities
  • Full or part time
    Dr H Koohy
    Prof V Cerundolo
    Prof T Dong
    Prof A Simmons
  • Application Deadline
    No more applications being accepted
  • Self-Funded PhD Students Only
    Self-Funded PhD Students Only

Project Description

Cancer immunology is an area of cancer research that is gaining tremendous momentum. However, responses to immunotherapy are heterogeneous and patient care could be substantially improved by better understanding of how and why responses to immunotherapeutic approaches vary in different patients. Research interests in the Koohy group are focused on the development of machine-learning and computational approaches to help us further understand mechanisms underlying the heterogeneity of response to personalised cancer immunotherapy in which the patients’ immune system is modulated to find and kill cancer cells.

Cancer is usually characterized by accumulation of genetic alterations. Tumour-specific somatic mutations may generate small mutated proteins known as neoantigens that are presented on the surface of cancer cell as ‘cancerous flags’, in association with HLA class I and II molecules. Neoantigens can be recognized by autologous T cells as foreign and therefore are considered as targets for improved cancer vaccines and adaptive T cell therapies. However, cancer cells rapidly develop various mechanisms to escape immune response that further adds to the complexity of predicting the effectiveness of the treatment.

Multiple factors have been reported affecting an immune response to the treatment including mutation burden rate, cytotoxic T cell infiltration, antigen processing and presentation defects, mutation-driven clonal signature and the composition of intestinal microbiota. Owing to advances in high throughput sequencing technologies, in particular recent single cell advancements, these features can now be measured from patients’ samples at single cell level at multiple time points including before, during and after the treatment. Readouts of these experiments in the form of high throughput sequencing data including genomics, transcriptomics, T cell receptor repertoire, and epigenomics data form inputs for mathematical and machine learning models to study the mechanisms underlying heterogeneity of the response.

Due to limited data, many of these potentially predictive features have not been incorporated into current mathematical and computational approaches. The community is therefore in need of more sophisticated approaches capable of modelling more confounding features by leveraging more information from patient’s data.

In our group, we work on developing the next generations of mathematical and computational models capable of formulating as many as the above-mentioned factors.

Since the interrogation of the adaptive immune repertoire is of high relevance for understanding the adaptive immune response in diseases such as cancer, we are also keen in utilising/developing models to reveal the high dimensional complexity of the immune receptor sequence landscape. Of particular interest for us is to systematically cluster groups of TCR sequences according to their likely antigen specificity in the cancer context.

We closely work with world-class cancer immunologists including Prof. Vincenzo Cerundolo’ group to study antigen processing and loading and single cell approaches in TCR profiling, Prof. Tao Dong’s to study virus associated cancer specific T cells at single cell level and Prof. Alison Simmons to study the heterogeneity and composition of intestinal microbiome in cancer patients with cutting edge single cell technologies.

These projects require a very solid understanding of T cell and cancer immunology, the cutting-edge advances in single cell technologies, their applications in immunology as well as their specific computational challenges. Working with us will also require a good understanding of mathematical and machine-learning approaches in immunology. Training for both underlying immunology and modelling will be provided in the unit or within the Oxford University teaching and training schemes.

Projects in our group all have multidisciplinary nature and therefore require solid understanding in cutting-edge advancements in a number of subdisciplines. This include A) General Cell biology and commonly used high throughput sequencing assays (bulk and single cell), B) T cell and cancer immunology and immune-repertoire assays, C) Advances in single cell technologies and D) Mathematical machine-learning approaches in particular deep neural networks. Training for all of these will be provided by experts mainly in the unit, but also from some other Oxford affiliated institutes such as Big Data Institute.

As well as the specific training detailed above, students will have access to high-quality training in scientific and generic skills, as well as access to a wide-range of seminars and training opportunities through the many research institutes and centres based in Oxford.

All MRC WIMM graduate students are encouraged to participate in the successful mentoring scheme of the Radcliffe Department of Medicine, which is the host department of the MRC WIMM. This mentoring scheme provides an additional possible channel for personal and professional development outside the regular supervisory framework.

Funding Notes

Our main deadline for applications for funded places has now passed. Supervisors may still be able to consider applications from students who have alternative means of funding (for example, charitable funding, clinical fellows or applicants with funding from a foreign government or equivalent). Prospective applicants are strongly advised to contact their prospective supervisor in advance of making an application.

Please note that any applications received after the main funding deadline will not be assessed until all applications that were received by the deadline have been processed. This may affect supervisor availability.


Genome organization and chromatin analysis identify transcriptional downregulation of insulin-like growth factor signaling as a hallmark of aging in developing B cells. Koohy H, Bolland DJ, Matheson LS, Schoenfelder S, Stellato C, Dimond A, Várnai C, Chovanec P, Chessa T, Denizot J, Manzano Garcia R, Wingett SW, Freire-Pritchett P, Nagano T, Hawkins P, Stephens L, Elderkin S, Spivakov M, Fraser P, Corcoran AE, Varga-Weisz PD. Genome Biol. 2018 Sep 5;19(1):126.

Local Chromatin Features Including PU.1 and IKAROS Binding and H3K4 Methylation Shape the Repertoire of Immunoglobulin Kappa Genes Chosen for V(D)J Recombination. Matheson LS, Bolland DJ, Chovanec P, Krueger F, Andrews S, Koohy H, Corcoran AE. Front Immunol. 2017 Nov 17;8:1550.

Two Mutually Exclusive Local Chromatin States Drive Efficient V(D)J Recombination. Bolland DJ, Koohy H, Wood AL, Matheson LS, Krueger F, Stubbington MJ, Baizan-Edge A, Chovanec P, Stubbs BA, Tabbada K, Andrews SR, Spivakov M, Corcoran AE. Cell Rep. 2016 Jun 14;15(11):2475-87.

Clonal analysis of Salmonella-specific effector T cells reveals serovar-specific and cross-reactive T cell responses. Napolitani G, Kurupati P, Teng KWW, Gibani MM, Rei M, Aulicino A, Preciado-Llanes L, Wong MT, Becht E, Howson L, de Haas P, Salio M, Blohmke CJ, Olsen LR, Pinto DMS, Scifo L, Jones C, Dobinson H, Campbell D, Juel HB, Thomaides-Brears H, Pickard D, Bumann D, Baker S, Dougan G, Simmons A, Gordon MA, Newell EW, Pollard AJ, Cerundolo V. Nat Immunol. 2018 Jun 20. doi: 10.1038/s41590-018-0133-z.

Structural Remodelling of the Human Colonic Mesenchyme in Inflammatory Bowel Disease. James Kinchen, Hannah H Chen, Kaushal Parikh, Francosis Gervais, Hashem Koohy, Alison Simmons. Cells, 2018, September 27, DOI:

How good is research at University of Oxford in Clinical Medicine?

FTE Category A staff submitted: 238.51

Research output data provided by the Research Excellence Framework (REF)

Click here to see the results for all UK universities

FindAPhD. Copyright 2005-2019
All rights reserved.