[ad_1] Job Summary This job is an opportunity to join the School of Public Health, Department of Epidemiology and Biostatistics, Imper
[ad_1]
Job Summary
This job is an opportunity to join the School of Public Health, Department of Epidemiology and Biostatistics, Imperial College, and work in the Computational Epidemiology team working on the EU funded EXPANSE project. An exciting and innovative project that combines statistics, machine learning, environmental and social sciences as well as molecular medicine to investigate drivers of cardiometabolic health. Research focuses on integrating Exposome datasets featuring a large number of measurements and/or observations, to better understand the lifestyle, environmental, metabolic, and genetic causes of chronic disease, as well as understanding the features of the exposome that are driving the quality of ageing and individual risk of adverse conditions. This work will be done under the direct supervision of Prof M Chadeau-Hyam, leading the statistical workpackage of the project.
Duties and responsibilities
You will be responsible for the development of advanced machine learning and statistical models to identify biologically imprinted effects of external (blocks of) exposures, their evolution in the life course and the contribution of other compartments of the exposome to these signals. Resulting models should also facilitate the identification of molecular signatures of shared exposome types and their trajectories throughout the life course. The goal is to incorporate in high throughput profiling techniques a longitudinal component to account for full history and for life stages at which individuals may be more susceptible or vulnerable.
Essential requirements
You will be constructing and applying machine learning and statistical models using OMICs data, biochemistry and social factors in the life course in a longitudinal set up and investigating their effect on health and ageing by:
- Preparing bespoke scripts
- Integrating omics and other data in the life course
- Biologically interpreting results
You will have:
- A sound understanding of epidemiological concepts particularly in relation to exposome science
- Experience in longitudinal data/ trajectory modelling
- Familiarity with omics data analyses, including pre-processing algorithms, development of ad-hoc models accounting for technically induced variation (e.g. laboratory artefacts)
- Experience in using classical machine learning approaches including clustering techniques and tree-based algorithms
- Strong programming skills (R, Python) for the preparation of bespoke scripts to analyse and integrate full-resolution omics datasets, including computational skills to optimize and ensure scalability of the resulting models
- Experience in interpreting results from the analysis of OMICs data (e.g. genomics, epigenomics) using relevant software and visualisation tools
- Capacity to develop and implement novel approaches/strategies to investigate how data arising from several platforms interplay and ultimately mediate the effect of external exposures
Further Information
Candidates who have not yet been officially awarded their PhD will be appointed as Research Assistant.
Should you require any further details on the role please contact: Prof. Marc Chadeau-Hyam – m.chadeau@imperial.ac.uk
[ad_2]
Source link
COMMENTS