plotBubble: Basic plot of binned vectors.

In metagenomeSeq: Statistical analysis for sparse high-throughput sequencing

Description

This function plots takes two vectors, calculates the contingency table and plots circles sized by the contingency table value. Optional significance vectors of the values significant will shade the circles by proportion of significance.

Usage

plotBubble(
  yvector,
  xvector,
  sigvector = NULL,
  nbreaks = 10,
  ybreak = quantile(yvector, p = seq(0, 1, length.out = nbreaks)),
  xbreak = quantile(xvector, p = seq(0, 1, length.out = nbreaks)),
  scale = 1,
  local = FALSE,
  ...
)

Arguments

yvector	A vector of values represented along y-axis.
xvector	A vector of values represented along x-axis.
sigvector	A vector of the names of significant features (names should match x/yvector).
nbreaks	Number of bins to break yvector and xvector into.
ybreak	The values to break the yvector at.
xbreak	The values to break the xvector at.
scale	Scaling of circle bin sizes.
local	Boolean to shade by signficant bin numbers (TRUE) or overall proportion (FALSE).
...	Additional plot arguments.

Value

A matrix of features along rows, and the group membership along columns.

See Also

plotMRheatmap

Examples

data(mouseData)
mouseData = mouseData[which(rowSums(mouseData)>139),]
sparsity = rowMeans(MRcounts(mouseData)==0)
lor = log(fitPA(mouseData,cl=pData(mouseData)[,3])$oddsRatio)
plotBubble(lor,sparsity,main="lor ~ sparsity")
# Example 2
x = runif(100000)
y = runif(100000)
plotBubble(y,x)

metagenomeSeq documentation built on Nov. 8, 2020, 5:34 p.m.