Funded PhD Opportunity How to optimally identify patient strata: tools and technologies for managing data sets so as to yield patient classification systems.
This opportunity is now closed.
Subject: Biomedical Sciences
Biomedical science is moving towards an era of personalised and stratified medicine in which the treatment that a patient receives is informed either by the patient’s individual traits (personalized medicine) or by the strata of traits to which they belong (stratified medicine). Critical to this development is the use of patient data to create and refine diagnostics that identify a patient’s disease risk and that identify optimal therapeutic strategies. At the present time there are few examples of software that specifically support the development of personalised and stratified medicine diagnostics. More fundamentally, there are currently no software libraries available that have been developed to support personalised and stratified medicine and that can simplify the development of such software.
In recent work, we have undertaken a number of analyses of large cohort patient data, combining regression techniques, computational optimisation and data discretisation in order to develop predictive diagnostics tools. In this studentship we would seek to expand on this work developing a library of functions to support diagnostics development for patient stratification that would be sufficiently general to be useable across a broad range of data types and interoperable with a broad range of programming languages.
Aims This project will develop a library of functions composed using the R scripting language to be distributed as both source code and compiled binaries to maximise compatibility across languages and platforms. The tools developed will
*support brute-force approaches, undertaking a global analysis of all permutations of subclassifications of patient data to identify the optimal subclassification. The functions will be developed to support single and multi-thread calculations and to optionally exploit parallel architectures in particular GPU architectures.
*support numerical convergent approaches that will yield approximations to optimal subclassifications in much shorter time. These functions will be developed to support single and multi-thread calculations and to optionally exploit parallel architectures in particular GPU architectures.
We will also undertake an informatics analysis of the structure of patient cohort data, using measures such as information entropy, to determine what data should be incorporated into future patient cohort studies and how it should be best exploited in order to maximise efficient identification of diagnostics.
We anticipate that the software library developed here will stimulate wide interest amongst the personalised and stratified medicine research community. It will streamline future research, improving the efficiency of diagnostic discovery. Although the software outputs will have high utility, the software library itself can stimulate incremental expansion into the future, becoming a platform for future ‘tools and resources’ research activity. Software libraries can serve as excellent promotional tools for authors and institutes into the future.
- Upper Second Class Honours (2:1) Degree from a UK institution (or overseas award deemed equivalent via UK NARIC)
- Sound understanding of subject area as evidenced by a comprehensive research proposal
- A comprehensive and articulate personal statement
If the University receives a large number of applicants for the project, the following desirable criteria may be applied to shortlist applicants for interview.
- First Class Honours (1st) Degree
- Completion of Masters at a level equivalent to commendation or distinction at Ulster
- Research project completion within taught Masters degree or MRES
- Experience using research methods or other approaches relevant to the subject domain
- Work experience relevant to the proposed project
- Publications - peer-reviewed
- Experience of presentation of research findings
Vice Chancellors Research Scholarships (VCRS)
The scholarships will cover tuition fees and a maintenance award of £14,777 per annum for three years (subject to satisfactory academic performance). Applications are invited from UK, European Union and overseas students.
The scholarship will cover tuition fees at the Home rate and a maintenance allowance of £ 14,777 per annum for three years. EU applicants will only be eligible for the fees component of the studentship (no maintenance award is provided). For Non EU nationals the candidate must be "settled" in the UK.
The Doctoral College at Ulster University
Launch of the Doctoral College
Current PhD researchers and an alumnus shared their experiences, career development and the social impact of their work at the launch of the Doctoral College at Ulster University.Watch Video