The successful candidate will join an international team of bioinformaticians, molecular biologists, computer scientists and clinicians working on developing machine learning models for predicting long-term health conditions. The successful candidate will aggregate and manage molecular data from several large patient cohorts collected from the UK, Singapore and other international sites. The aim is to organise and link the datasets to create larger training sets for machine learning and identify test cases where predictive models can be used to define multiple long-term conditions or multimorbidities.
Duties and responsibilities
Design and implement relational databases or file structures to organise collated molecular and data.
Access and retrieve health datasets from academic and healthcare data repositories
Develop detailed quality control and data processing procedures to standardise extracted datasets.
Contribute to high quality publications by describing the collection and curation of machine-readable datasets for AI algorithms.
Mentor and supervise junior informaticians (MSc/PhD students) on best practices for data management.
Participate in leading international efforts aimed at establishing best practices and standards for data sharing in health research.
Research Associate: Hold a PhD (or equivalent) in Epidemiology, Computer Science, Bioinformatics, medical statistics or a closely related discipline.
Research Assistant: Near completion of a PhD (or equivalent) in Epidemiology, Computer Science, Bioinformatics, medical statistics or a closely related discipline
Expertise processing and conducting quality control of data from biomedical studies
Experience generating summary statistics in experimental or clinical studies
Experience in data manipulation, feature engineering, visualisation and modelling
Scripting / programming ability in at least one of Python, R or Matlab
To apply, visit www.imperial.ac.uk/jobs and search by the job reference MED03534.