You are invited to apply for the position of a postdoctoral researcher to work within a new EPSRC funded project: “Transfer learning of pharmacogenomic information across disease types and preclinical models for drug sensitivity prediction”. This post is available for 36 months.
This EPSRC-funded project will be based within the Machine Learning (ML) Research Group at the Department of Computer Science. You will develop transfer learning principles in ML for the prediction of drug response using high-dimensional molecular measurements. This interdisciplinary project brings together experts from different fields to develop AI tools for drug development research by leveraging advances in both transfer learning (a branch of machine learning) and pharmacogenomics (an important
component of personalised medicine). We integrate these two multi-disciplinary themes through three research objectives:
1) Develop machine learning models that can effectively transfer knowledge in the "large p small n" context of pharmacogenomic data to predict drug sensitivity.
2) Develop a machine learning toolkit (software and training data) for improving prediction of drug response for disease types with limited data (eg. bladder cancer, motor neurones, animal models).
3) Identify dose-dependent biomarkers of drug response in new disease types to enable repurposing of drugs to new disease types.
You will be jointly supervised by Dr Dennis Wang from the Department of Neuroscience, Dr Mauricio Alvarez from the Department of Computer Science, and Dr Mark Dunning from the Sheffield Bioinformatics Core. The project will also involve Dr Laura Ferraiuolo from University of Sheffield and collaborators in Princess Margaret Cancer Centre (Toronto), Cerevel Therapeutics (Boston), University of Southampton, and Helmholtz Zentrum Munchen (Munich).
You will be able to demonstrate knowledge of a wide range of machine learning techniques (in particular probabilistic modelling) and practical experience handling genomics data. You will hold a PhD in quantitative discipline with a solid background in mathematics/statistics.
Please apply online by clicking the Apply -> Apply