TransferGWAS of T1-weighted Brain MRI Data from UK Biobank
2024

TransferGWAS of Brain MRI Data from UK Biobank

Sample size: 36311 publication 10 minutes Evidence: moderate

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)

10.1371/journal.pgen.1011332

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication