Variational Inference of Polygenic Risk Scores (VIPRS)

This site contains documentation, tutorials, and examples for using the viprs package for the purposes of inferring polygenic risk scores (PRS) from GWAS summary statistics. The viprs package is a python package that uses variational inference to estimate the posterior distribution of variant effect sizes conditional on the GWAS summary statistics. The package is designed to be fast and accurate, and to provide a variety of options for the user to customize the inference process.

The details of the method and algorithms are described in detail in the following paper(s):

Zabad, S., Gravel, S., & Li, Y. (2023). Fast and accurate Bayesian polygenic risk modeling with variational inference. The American Journal of Human Genetics, 110(5), 741–761. https://doi.org/10.1016/j.ajhg.2023.03.009

Helpful links

• API Reference
• Installation
• Getting Started
• Command Line Scripts
• Download Reference LD matrices
• Project homepage on GitHub
• Sister package magenpy

Software contributions

The latest version of the viprs package was developed in collaboration between research scientists at McGill University and Intel Labs.

• Contributors from McGill University:
  • Shadi Zabad
  • Yue Li
  • Simon Gravel
• Contributors from Intel Labs:
  • Chirayu Anant Haryan
  • Sanchit Misra

Contact

If you have any questions or issues, please feel free to open an issue on the GitHub repository or contact us directly at:

• Shadi Zabad
• Yue Li
• Simon Gravel