PhD Position in Biomedical Machine Learning
Background
In the machine learning era, the effective integration of data-driven and knowledge-driven approaches is being increasingly recognised as key to improving biotechnological processes and biomarker detection in several diseases. Several “black box” machine learning methods have recently been developed using tumour images and gene/protein expression profiles. However, “black box” approaches based on machine learning suffer from a lack of interpretability, which often prevents the applicability to real case studies.
Methodology
This project aims at developing a “white box” deep learning approach whose predictions are aware of biochemical mechanisms. Specifically, the approach will be a multi-omic and multi-platform biomarker discovery method based on a combination of deep learning and metabolic modelling. The pipeline will combine biological models, computational models, and purpose-built machine learning algorithms. Two applications are planned for the pipeline: (i) breast cancer data from The Cancer Genome Atlas; (ii) bioprocessing data from our ongoing collaboration with FUJIFILM Diosynth Biotechnology.
For the breast cancer case study, we aim to: (i) classify cancer patients into different sub-groups associated with the prediction of poor survival, recurrence, and metastatic status, while highlighting system-level pathway differences; (ii) discover, and mechanistically explain, the role of novel biomarkers of tumour aggressiveness leading to poor survival in breast cancer, suggesting targets for improving treatment and preventing metastasis.
For the biotechnology-related application, we will evaluate the applicability of the pipeline for bacterial cultures. Leveraging data provided by FUJIFILM Diosynth Biotechnology, we will connect bioprocess outcomes to metabolic events underlying the same processes. By integrating a mechanistic model of Escherichia coli with bioprocess data from the FUJIFILM ambr250 system, we will: (i) predict end-stage process performance during production; (ii) identify metabolic drivers underlying process performance; and (iii) determine the metabolic impact of experimental design parameters.
The validation of the proposed pipeline will be achieved through ongoing collaborations with the National Horizon Centre and FUJIFILM. The top-5 biomarkers will be further validated at the protein level, using analytical proteomics and quantitative protein expression measurements with immunohistochemically-stained fixed tissue samples.
This would provide, for the first time, accurate predictions fully based on both transcriptomics and multi-omic activity at the genome scale. Importantly, these predictions will be interpreted mechanistically and transparently (“white box”) through the underlying metabolic model, therefore with significantly higher potential for prognosis and therapeutic interventions compared to traditional black-box machine learning approaches.
Project team
The supervision team will include: (i) two members of the School of Computing, Engineering and Digital Technologies to supervise the development and optimisation of the AI pipeline; (ii) one member of the National Horizon Centre to help validate the pipeline; (iii) two leading staff members at Fujifilm Diosynth Biotechnologies, to provide a case study and datasets on biotherapeutics and biotechnologies.
Dr Claudio Angione (Senior Lecturer in Data Analytics)
Dr Annalisa Occhipinti (Associate Professor in Computer Science)
Dr Panagiota Filippou (Lecturer in Biomedical Sciences, National Horizon Centre)
Dr Chris Lennon (Subject Matter Expert in Molecular & Microbiology at FUJIFILM Diosynth Biotechnologies
Dr Graham McCreath (Senior Director, Data Science at FUJIFILM Diosynth Biotechnologies)
Funding eligibility
The Fees-Paid PhD studentship will cover all tuition fees for the period of a full-time PhD Registration of up to four years. Successful applicants who are eligible will be able to access the UK Doctoral Loan scheme to support with living costs.
The Fully Funded PhD Studentship covers tuition fees for the period of a full-time PhD Registration of up to four years and provide an annual tax-free stipend of £15,000 for three years, subject to satisfactory progress.
Applicants who are employed and their employer is interested in funding a PhD, can apply for a Collaborative Studentship.
Applications are welcome from strong UK, EU and International students.
Entry requirements
Applicants should hold or expect to obtain a good honours degree (2:1 or above) in a relevant discipline. A masters level qualification in a relevant discipline is desirable, but not essential, as well as a demonstrable understanding of the research area. Further details of the expected background may appear in the specific project details. International students will be subject to the standard entry criteria relating to English language ability, ATAS clearance and, when relevant, UK visa requirements and procedures.
How to apply
Please use the Online Application (Funded PHD) application form. When asked to specify funding select “other” and enter ‘RDS’ and the title of the PhD project that you are applying for. You should ensure that you clearly indicate that you are applying for a Funded Studentship and the title of the topic or project on the proposal that you will need to upload when applying. If you would like to apply for more than one project, you will need to complete a further application form and specify the relevant title for each application to a topic or project.
Applications for studentships that do not clearly indicate that the application is for a Funded Studentship and state the title of the project applied for on the proposal may mean that your application may not be considered for the appropriate funding.
Selection process
All applications received by the closing date will be considered. Successful applicants at the application stage will be shortlisted and contacted to arrange an interview. All interviews will be held online. Unsuccessful applicants will be contacted to confirm that the application will not be progressed. After interview, all interviewed applicants will be contacted to inform them of the outcome. Successful applicants progressing to an offer of a place, to commence in either May or October 2022.
About Teesside
We are committed to providing a safe, welcoming and inclusive campus and to supporting all members of our University community to thrive whatever their age, gender, disability, sexual orientation, gender identity, race, marital status, nationality or any other characteristic.
More about our Inclusive campus
As a Teesside University research student, you will join a growing and dynamic research community, allowing you to share your experiences, insight and inspiration with fellow researchers. You will benefit from our academic expertise, and be supported through a strong programme of research training. You will be offered opportunities and support at each stage of your research degree. Our research is designed to have impact, and to influence policy and practice within our region, the UK and beyond. We work with external organisations to anticipate and respond to research needs, and to put our research into practice in sectors as diverse as the arts, engineering, healthcare and computing. PhD students are encouraged to work with their supervisors to explore the potential impact of their work.
