TransferGWAS of Brain MRI Data from UK Biobank
Author Information
Author(s): Alexander Rakowski, Remo Monti, Christoph Lippert
Primary Institution: Hasso Plattner Institute for Digital Engineering, University of Potsdam, Germany
Hypothesis
Can deep neural networks uncover novel genetic associations in brain MRI data?
Conclusion
The study identified 289 genetic loci associated with brain MRI features, including 11 novel associations.
Supporting Evidence
- Identified 289 independent loci associated with various traits.
- 11 regions had no previously reported associations.
- Improved predictions of bone mineral density using polygenic scores.
Takeaway
Researchers used advanced computer models to find new links between genes and brain images, helping us understand how our genes might affect brain health.
Methodology
The study used deep neural networks to extract features from brain MRI scans and performed a genome-wide association study on these features.
Potential Biases
Potential bias due to the reliance on a single ancestry group for the GWAS.
Limitations
The study primarily focused on a white British population, which may limit the generalizability of the findings to other ancestries.
Participant Demographics
Participants were self-identified as white British.
Statistical Information
P-Value
p<0.0001
Statistical Significance
p<0.05
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website