Back

SAIGE-BRUSH: an efficient, user-friendly and low cost cloud implementation for genome-wide association studies

Brunetti, T. M.; Pozdeyev, N.; Daya, M.; Barnes, K. C.; Rafaels, N.; Gignoux, C.

2021-05-09 bioinformatics
10.1101/2021.05.07.443171 bioRxiv
Show abstract

SAIGE-Biobank Re-Usable SAIGE Helper (SAIGE-BRUSH) allows users with little computational expertise to utilize SAIGE for GWAS with parallelization and data collection on biobank data sets. This implementation requires no installation and has additional features not programmed within the original SAIGE framework, such as concurrency, reproducibility, reusability, scalability, association analysis results filtering and output plots. This is all achieved without writing any code from the user. This implementation is currently being utilized by the Biobank at the Colorado Center for Personalized Medicine (CCPM) on Google Cloud but is flexible for a number of architectures available to genetic analysts. Availability: This open source implementation is freely available at https://github.com/tbrunetti/SAIGE-BRUSH and is licensed under the MIT License. Contact: Chris Gignoux at chris.gignoux@cuanschutz.edu & Nick Rafaels at nicholas.rafaels@cuanschutz.edu Supplemental Material: For detailed user documentation, please visit https://saige-brush.readthedocs.io/en/latest/

Matching journals

The top 1 journal accounts for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.