quollr: An R Package for Visualizing 2-D Models from Nonlinear Dimension Reductions in High-Dimensional Space

TL;DR

quollr is an R package that helps visualize and evaluate the accuracy of 2-D representations of high-dimensional data obtained through nonlinear dimension reduction methods, aiding in method and hyper-parameter selection.

Contribution

The paper introduces quollr, a novel R package that visualizes and assesses the quality of nonlinear dimension reduction outputs, addressing challenges in method comparison and structure preservation.

Findings

quollr effectively identifies the most accurate dimension reduction method.

The package demonstrates usability with scRNA-seq data.

Provides a visual tool for hyper-parameter tuning in nonlinear reductions.

Abstract

Nonlinear dimension reduction methods provide a low-dimensional representation of high-dimensional data by applying a Nonlinear transformation. However, the complexity of the transformations and data structures can create wildly different representations depending on the method and hyper-parameter choices. It is difficult to determine whether any of these representations are accurate, which one is the best, or whether they have missed important structures. The R package quollr has been developed as a new visual tool to determine which method and which hyper-parameter choices provide the most accurate representation of high-dimensional data. The scurve data from the package is used to illustrate the algorithm. Single-cell RNA sequencing (scRNA-seq) data from mouse limb muscles are used to demonstrate the usability of the package.