U-CIE [/juː 'siː/]: Color encoding of high-dimensional data.

ABSTRACT: Data visualization is essential to discover patterns and anomalies in large high-dimensional datasets. New dimensionality reduction techniques have thus been developed for visualizing omics data, in particular from single-cell studies. However, jointly showing several types of data, for example, single-cell expression and gene networks, remains a challenge. Here, we present 'U-CIE, a visualization method that encodes arbitrary high-dimensional data as colors using a combination of dimensionality reduction and the CIELAB color space to retain the original structure to the extent possible. U-CIE first uses UMAP to reduce high-dimensional data to three dimensions, partially preserving distances between entities. Next, it embeds the resulting three-dimensional representation within the CIELAB

SUBMITTER: Koutrouli M 

PROVIDER: S-EPMC9387205 | biostudies-literature | 2022 Sep

REPOSITORIES: biostudies-literature