This R package provides functionality for pre-processing of paired and unpaired data in preparation for the application machine learning algorithms. The analysis pipeline carefully documents steps so that the end data product is fully reproducible. This package was designed to seamlessly handle single or multiple data types with an ultimate end goal of integrated and flexible machine learning and feature selection over fundamentally different data sources.

devtools::install_github("pmartR/peppuR")

Get started by following along with the intro vignette:

vignette("single-source-pipeline", package = "peppuR")