FREE PhD study and funding virtual fair REGISTER NOW FREE PhD study and funding virtual fair REGISTER NOW

Predicting healthy outcomes using machine learning of longitudinal data

   Department of Computer Science

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

Click here to search for PhD studentship opportunities
  Dr D Wang, Dr Mauricio Alvarez  No more applications being accepted  Funded PhD Project (UK Students Only)

About the Project

Since the advent of high-throughput genomics, proteomics and metabolomics, it has become common practice to collect and process longitudinal biological samples to follow the evolution of a disease or condition using molecular markers. These molecular markers are usually high-dimensional in nature, requiring sophisticated statistical processing. While our ability to measure high-dimensional markers has been steadily increasing, the ability to analyse these data effectively has not kept pace. In longitudinal studies in particular, dependence of measurements between times within samples is of great importance. Longitudinal statistical methods typically deal with this serial dependence, but assume, explicitly or implicitly, that each sample at each time provides only one, or at most a few, measured outcomes. This project will bridge the gap between traditional longitudinal population studies and the high dimensional world of molecular measurements, by developing new approaches for study design, modelling and inference that fully exploit both the cross-sectional (between dimensions) and longitudinal (between times) dependence structures of the data collected in these studies. The current absence of a coherent general methodological framework for longitudinal population studies with high dimensional outcomes confines the analysis objectives to univariate longitudinal or multivariate cross sectional properties of the system under study, limiting the insights gained. Also, one-dimension-at-a-time study designs are inherently inefficient, resulting in the need for larger sample sizes than would otherwise be sufficient. In order to overcome this limitation, decrease the number of participants and effort needed for longitudinal population studies and increase the amount of information gained, we propose to develop a methodological framework for high-dimensional longitudinal data that will be tested on real-world data from birth cohorts in Singapore

Dr Dennis Wang and Dr Mauricio Alvarez at The University of Sheffield (Sheffield) will be co-supervising a PhD candidate with Prof Michael Meaney (neuro-development), Dr Jonathan Huang (biostatistics) at the Singapore Institute for Clinical Sciences (SICS) to develop data analytics toolkits for longitudinal molecular data from birth cohorts.

 The theoretical basis and prototyping for the methodology will be developed in Sheffield. The candidate will test the methodology on real-world datasets from the S-PRESTO and GUSTO studies, and enable the open-source methodology to be used as a software toolkit for future studies in Singapore. This work is outlined in four work packages:

 1. Application of the longitudinal modelling method to describe repeated measures of DNA methylation in the Growing Up in Singapore Towards Healthy Outcomes (GUSTO);

 2. Application of the longitudinal modelling method to repeated measures of metabolite profiles during preconception and course of pregnancy from the Singapore Preconception Study of Long-Term Maternal and Child Outcomes (S-PRESTO) study.

 3. Critical comparison of population results obtained using existing and proposed methodology from GUSTO and S-PRESTO;

 4. Implementation of the new methodology as open-source software for future studies.

Required Qualifications: Undergraduate degree in a quantitative discipline (physics, computer science, statistics, etc.) or a biomedical sciences degree with scientific programming experience.

Award details:

  • Student must have UK/Settled status to be eligible for UK Home tuition fees.
  • For each student admitted to the 4-year programme, A*Star will provide the following financial support, whilst the student is in Singapore:
  • Living allowance: A monthly stipend of two thousand, seven hundred Singapore Dollars (~£1,400) whilst in Singapore.
  • A one-off "settling-in allowance" of one thousand Singapore dollars (~£530).
  • A one-time airfare allowance of one thousand five hundred Singapore dollars (~£800).
  • One-time IT allowance of eight hundred Singapore dollars (~£425)
  • Consumables and Bench Fees incurred by students when based at A*Star in Singapore.
  • Cost of medical insurance while the student is based at A*Star.
  • Medical insurance, Housing subsidy, Conference allowance.
  • Whilst in Sheffield, students receive primary fees (£4,500 in 21/22) and stipend at the UKRI rate (£15,609 in 2021/22). In addition, students may be able to claim up to £500 from Sheffield towards the costs of an airfare back to the UK whilst they are in Singapore in order to make a home visit. This will normally only be available for students who meet the normal expectations of spending approximately half of the programme (2 years) in Singapore.

For interested applicants, please email Dr Dennis Wang, [Email Address Removed], in the first instance.

To apply for the studentship, applicants need to apply directly to the University of Sheffield using the online application system. Please name Dr Dennis Wang and Dr Mauricio Alvarez as your proposed supervisors.

Complete an application for admission to the standard Computer Science PhD programme

Applications should include a research proposal, CV, transcripts and two references.

The research proposal (up to 4 A4 pages, including references) should outline your reasons for applying for this scholarship and how you would approach the researching, including details of your skills and experience.

Funding Notes

Award details:
• For each student admitted to the 4-year programme, A*Star will provide funding whilst the student is in Singapore and Sheffield outlined in the project description section
Search Suggestions
Search suggestions

Based on your current searches we recommend the following search filters.

PhD saved successfully
View saved PhDs