Precision Medicine DTP - Augmenting clinical risk predictors through multi-omics

Background

Risk prediction to prevent or delay the onset of disease is a major goal for health research. Currently, the gold standard predictors for cardiovascular disease (ASSIGN score), heart attack or stroke (QRISK), and Alzheimer’s dementia (CAIDE) use a mix of self-report and clinical variables. However, it is highly likely that we can improve on this by the integration of omics data. This includes the incorporation of polygenic risk scores (which account for germline differences between individuals), genome-wide DNA methylation and ultra-high-throughput mass spectrometry proteomics.

We have already established that DNA methylation signatures of lifestyle, cholesterol, and inflammation augment associations between their self-reported or clinical analogs and health/disease. Here, we will extend this work in an extremely large sample with novel proteomics data and health outcomes measured from data linkage.

The current project utilizes the largest genome-wide DNA methylation and proteomics resource in the world (n=20,000 with both, in addition to genotype data). Furthermore, there is extant data linkage to electronic health records (prescriptions, hospital and GP), enabling the ascertainment of incident disease outcomes over a 10-15 year baseline post blood-draw for the omics data. This project is therefore at the cutting edge of omics and eHealth research and offers an opportunity for clinically meaningful precision medicine applications.

Aims

The aims of the project are 6-fold:

1. To characterize clinically applied predictors of common disease outcomes in 20,000 individuals in the Generation Scotland cohort.
2. To use prescription, GP, and hospital records to identify incident and prevalent cases of the common disease outcomes in (1).
3. To relate the clinical predictors in (1) to the disease data in (2) using survival models.
4. Apply statistical machine learning pipelines to generate DNA methylation (800,000 features) and protein (4,000 features) based proxies for the component parts of the clinical predictors, as well as conducting direct prediction of the disease outcomes. Generate polygenic risk scores for the clinical predictor variables and disease outcomes.
5. Use multivariate mixed effects survival models to compare and contrast the clinical and omics predictors of disease.
6. Provide recommendations on how to improve current clinical prediction models.

Training Outcomes

1. Understand current clinical predictors and diagnosis of disease and future disease risk

2. Data science skills for the manipulation/analysis of big datasets

3. Gain expertise in the epidemiology of ageing and an understanding of electronic health records.

4. Apply a host of statistical and machine learning approaches for prediction.

This project would suit a motivated student with statistics, data science, machine learning, bioinformatics, epidemiology or related backgrounds. In this cross-disciplinary project, the student will develop, implement and apply statistical/machine learning methodologies that can efficiently combine multiple layers of molecular genetic data, in addition to lifestyle factors, in order to predict disease outcomes. This is a unique opportunity in which data science research will be translated into signatures for potential clinical use. As such, the student will be trained as a biomedical data scientist, developing analytical and computational skills that are in high demand both in academia and in industry.

This MRC programme is joint between the Universities of Edinburgh and Glasgow. You will be registered at the host institution of the primary supervisor detailed in your project selection.

All applications should be made via the University of Edinburgh, irrespective of project location. For those applying to a University of Glasgow project, your application along with any supporting documents will be shared with University of Glasgow.

http://www.ed.ac.uk/studying/postgraduate/degrees/index.php?r=site/view&id=919

Please note, you must apply to one of the projects and you must contact the primary supervisor prior to making your application. Additional information on the application process is available from the link above.

For more information about Precision Medicine visit:
http://www.ed.ac.uk/usher/precision-medicine