Network Inference and Machine Learning: Identification of Diseases-gene Regulation
Eligibility: UK/EU/International graduates with the required entry requirements
Funding details: Bursary plus tuition fees (UK/EU/International)
Duration: Full-Time – for a mazimum of four years
Application deadline: 31 January 2020
Interview dates: Will be confirmed to shortlisted candidates
Start date: May or September 2020
For more details contact Dr Fe He.
This research project is a collaboration between Coventry University and Singapore’s Agency for Science, Technology and Research (A*STAR). The successful candidate will have the opportunity to conduct their research project both at Coventry University, UK and for up to 2 years at the A*STAR Institute for Infocomm Research in Singapore.
About the project
A complex disease like cancer is normally the consequence of alteration or dysfunction of pathways – constituting genes that are actively interacting with each other – rather than individual genes. It is therefore crucial to develop network-based (e.g. gene regulatory networks (GRNs), protein-protein interactions (PPIs), drug-target interactions (DTIs)) biomarkers for diagnostic, predictive or prognostic purposes during the process of drug design or the development of personalised medicine. Inferring the structure of such networks from gene expression data has therefore become a central goal of much recent systems biology research.
There is a rich and growing literature on gene (or protein) network reconstruction or inference, ranging from data-driven methods to probabilistic model- and mechanistic model-based methods. Recent studies including ours, demonstrate the pivotal role of utilising dynamic information from the data to improve the accuracy of network inference, since most data-driven methods purely study either the linear interactions or ignore the dynamic information.
In this PhD project, we will investigate how to reduce the computational cost of a dynamic/mechanistic model-based approach with the assist of non-parametric Bayesian method and other data-driven methods; and to address related issues of identifiable models, noise/stochastic effects and limited model assumptions. This is based on our recently published work on parametric and non-parametric gradient matching inference techniques for GRNs reconstruction; as well as matrix factorisation models for PPIs and DTIs prediction.
The studentship is fully funded and will include:
- full tuition fees
- a stipend for up to 4 years (£15009/year) subject to satisfactory progress
- a one-time airfare to and from Singapore
- a one-time settling-in allowance in Singapore
- medical insurance for the period in Singapore
- conference allowances.
The successful candidate will receive comprehensive research training including technical, personal and professional skills at the Doctoral College and Centre for Research Capability and Development at Coventry University.
- A minimum of a 2:1 undergraduate degree in Mathematics/Statistics, Computer Science, Engineering, or a related discipline with a minimum 60% mark in the project element or equivalent with a minimum 60% overall module average.
- In the event of a undergraduate degree classification of less than 2:1, a Master’s Degree in a relevant subject area as mentioned above will be considered as an equivalent.
- The Masters must have been attained with minimum overall marks at merit level (60%). In addition, the dissertation or equivalent element in the Masters must also have been attained with a minimum mark of merit level (60%).
- Competent programming skills (in Matlab, Python, R or Julia) and experienced in mathematics/statistics and numerical analysis.
- Interest in machine learning, mathematical modelling or statistical inference, and enthusiastic to work on an inter-disciplinary research project.
- The potential to engage in innovative research and to complete the PhD within 4 years.
- Minimum English language proficiency of IELTS Academic 7.0 with a minimum of 6.5 in each component, if you are an EU (non UK) or overseas national.