| Title: | Deep-learning-based genetic analysis and phenotype prediction using variants of any frequency based on UK Biobank sequencing datasets |
| Lead Institution: | German Cancer Research Center (DKFZ) |
| Principal investigator: | Dr Oliver Stegle |
Application 81358
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
A key challenge in medicine is to understand how genetic variations, arising from mutations and inheritance patterns, determine medically relevant traits - such as cholesterol level - and predisposition to diseases such as cancer within populations. While the contributions of common genetic variants to different human traits have been extensively studied and characterized, there is still a lack of understanding of the impact of rare genetic variants. However, recent studies have shown that rare genetic variants strongly contribute to a variety of traits. Our aim is to develop and apply novel computational methods that allow for identifying and quantifying the contribution of rare genetic variants in humans. The ultimate goal of this work is to integrate the effect of rare variants into models that can predict human disease traits. The scale and diversity of the UK Biobank dataset offers the possibility to develop and build the proposed trait/disease prediction models, using advanced techniques of machine learning and artificial intelligence. The resulting models will be made publicly available for download and use by the scientific community. Moreover, the output of these models will yield new insights into the specific genes that are involved in different traits and diseases, including predisposition to severe COVID-19. Collectively, this project will contribute to an improved understanding of the genetic basis of human disease traits, which will ultimately enable improved diagnosis and new treatment strategies.1 Publication
| Pub ID | Title | Author(s) | Year | Journal |
|---|---|---|---|---|
| 13441 | Integration of variant annotations using deep set networks boosts rare variant association testing | Brian Clarke (+12) | 2024 | Nature Genetics |
Enabling scientific discoveries that improve human health