Skip to content

Releases: AIH-SGML/PRiMeR

PRiMeR v0.1

02 Sep 22:31
@AgentDS007 AgentDS007
v0.1
ed3e202
Compare
Choose a tag to compare
PRiMeR v0.1 Latest
Latest

We are excited to announce the first public release of PRiMeR, a tool for Genetics-driven Risk Predictions leveraging the Mendelian Randomization framework. This release includes the following main contributions:

  • Main Model: The core model implemented in the PRiMeR class, which includes methods for training, prediction, and optimization.
  • MR-based Comparison Models: Additional models for Mendelian Randomization, including the UVMRbased and MVMRbased classes.
  • Simulation Script: The generate_data.py script, which simulates the genotypes, risk factors, and outcome summary statistics.
  • Quickstart Notebook: The PRiMeR_quickstart.ipynb notebook that loads the simulated data and runs all models for one seed.

Additionally, if you can bring your data in the form of the simulated data, the notebook can easily be adapted to run on real-world data.

Installation

To get started, follow these steps:

git clone https://github.com/AIH-SGML/PRiMeR.git
cd PRiMeR
conda env create --file ./primer.yml
conda activate primer
pip install -e .

Quickstart Notebook

Check out the examples/README.md for detailed instructions on how to run PRiMeR on your data.

This release has been archived on Zenodo and can be cited using the following DOI:

DOI

Assets 2
Loading