| Title: | Multi-omic biomarkers of common chronic disease incidence and progression |
| Lead Institution: | University of Bristol |
| Principal investigator: |
Application 236527
WARNING: the interactive features of this website use CSS3, which your browser does not support. To use the full features of this website, please update your browser.
About
This research project aims to use the wealth of biomedical data from the UK Biobank project to discover ways to predict disease risk and progression. A major challenge is the difficulty of identifying large numbers of individuals with specific diseases but early enough in the disease process when disease detection and outcome prediction would be clinically useful. We aim to address this challenge by developing precise molecular scores of well-known disease risk factors including smoking behaviour, alcohol consumption, diet, physical activity, inflammation and genetics in large numbers of healthy individuals. We hope that these molecular scores can then be combined in smaller disease-specific studies to obtain accurate molecular predictors of disease risk and progression. Molecular markers and marker integration will be obtained and evaluated using a range of complementary statistical approaches that have been developed in machine learning, artificial intelligence and economics. We hope that these markers will be useful clinically for cheaply identifying subpopulations at high risk of disease who could most benefit from health interventions or to choose the most effective course of treatment.1 Publication
| Pub ID | Title | Author(s) | Year | Journal |
|---|---|---|---|---|
| 20200 | Leveraging population-scale proteomic data with deep learning for head and neck cancer detection in saliva | Anza Shakeel (+6) | 2026 | npj Digital Medicine |
Enabling scientific discoveries that improve human health