MDSViewer: Visualization of SPADE cluster or sample similarities using...

In tchitchek-lab/SPADEVizR: SPADEVizR: an R package for Visualization, Analysis and Integration of SPADE results

Visualization of SPADE cluster or sample similarities using MDS

Description

Multidimensional Scaling (MDS) methods aim to represent the similarities and differences among high-dimensional objects into a space of a lower number of dimensions, generally in two or three dimensions for visualization purposes. In MDS representations, the Kruskal Stress (KS) indicates the percentage of information lost during the dimensionality reduction process.

The MDS Viewer aims to visualize the similarities between samples or clusters based on their abundances. In such representation, each dot represents a sample or a cluster and the distances between the dots are proportional to the Euclidean distance between these objects.

The representation space can be specified using the 'space' parameter ("samples" or "clusters").

Usage

MDSViewer(Results, space = "clusters", samples = NULL,
  clusters = NULL, use.percentages = TRUE, dist.method = "euclidean",
  show.on_device = TRUE)

Arguments

Results	a 'Results' object
space	a character specifying the space ("clusters" or "samples", "cluster" by default)
samples	a character vector providing the sample names to used (all samples by default)
clusters	a character vector containing the clusters names to be visualized (by default all clusters will be displayed)
use.percentages	a logical specifying if the visualization should be performed on percentage
dist.method	a character string containing the name of the distance measure to use
show.on_device	a logical specifying if the representation will be displayed on device

Details

In the case of "samples" space, biological conditions information can be assigned to the samples (provided by the slot 'assignments' in the 'Results' object). This parameter must be a dataframe with sample names in row names and 2 other columns specifying the biological conditions and individuals.

Value

a 'ggplot' object

tchitchek-lab/SPADEVizR documentation built on Jan. 27, 2024, 8:58 p.m.