plmmr: an R package to fit penalized linear mixed models for genome-wide association data with complex correlation structure

TL;DR

The plmmr R package helps analyze genome-wide data by accounting for complex correlations, improving predictions using penalized linear mixed models.

Contribution

plmmr introduces a novel R package for penalized linear mixed models with memory mapping to handle genome-scale data efficiently.

Findings

plmmr estimates and uses observation correlations to improve prediction accuracy in high-dimensional data.

The package supports genome-scale analysis on ordinary machines using memory-mapped files.

Real-world examples demonstrate plmmr's effectiveness in genome-wide association studies.

Abstract

Correlation among the observations in high-dimensional regression modeling can be a major source of confounding. We present a new open-source package, plmmr, to implement penalized linear mixed models in R. This R package estimates correlation among observations in high-dimensional data and uses those estimates to improve prediction with the best linear unbiased predictor. The package uses memory mapping so that genome-scale data can be analyzed on ordinary machines even if the size of data exceeds random-access memory. We present here the methods, workflow, and file-backing approach upon which plmmr is built, and we demonstrate its computational capabilities with two examples from real genome-wide association studies data.

Figures