PCAtools: PCAtools: Everything Principal Components Analysis

biplot

R Documentation

Draw a bi-plot, comparing 2 selected principal components / eigenvectors.

Description

Draw a bi-plot, comparing 2 selected principal components / eigenvectors.

Usage

biplot(
  pcaobj,
  x = "PC1",
  y = "PC2",
  showLoadings = FALSE,
  ntopLoadings = 5,
  showLoadingsNames = if (showLoadings) TRUE else FALSE,
  colLoadingsNames = "black",
  sizeLoadingsNames = 3,
  boxedLoadingsNames = TRUE,
  fillBoxedLoadings = alpha("white", 1/4),
  drawConnectorsLoadings = TRUE,
  widthConnectorsLoadings = 0.5,
  colConnectorsLoadings = "grey50",
  lengthLoadingsArrowsFactor = 1.5,
  colLoadingsArrows = "black",
  widthLoadingsArrows = 0.5,
  alphaLoadingsArrow = 1,
  colby = NULL,
  colkey = NULL,
  colLegendTitle = if (!is.null(colby)) colby else NULL,
  singlecol = NULL,
  shape = NULL,
  shapekey = NULL,
  shapeLegendTitle = if (!is.null(shape)) shape else NULL,
  pointSize = 3,
  legendPosition = "none",
  legendLabSize = 12,
  legendTitleSize = 14,
  legendIconSize = 5,
  encircle = FALSE,
  encircleFill = TRUE,
  encircleFillKey = NULL,
  encircleAlpha = 1/4,
  encircleLineSize = 0.25,
  encircleLineCol = NULL,
  ellipse = FALSE,
  ellipseType = "t",
  ellipseLevel = 0.95,
  ellipseSegments = 51,
  ellipseFill = TRUE,
  ellipseFillKey = NULL,
  ellipseAlpha = 1/4,
  ellipseLineSize = 0.25,
  ellipseLineCol = NULL,
  xlim = if (showLoadings || ellipse) c(min(pcaobj$rotated[, x]) -
    abs((min(pcaobj$rotated[, x])/100) * 35), max(pcaobj$rotated[, x]) +
    abs((min(pcaobj$rotated[, x])/100) * 35)) else c(min(pcaobj$rotated[, x]) -
    abs((min(pcaobj$rotated[, x])/100) * 10), max(pcaobj$rotated[, x]) +
    abs((min(pcaobj$rotated[, x])/100) * 10)),
  ylim = if (showLoadings || ellipse) c(min(pcaobj$rotated[, y]) -
    abs((min(pcaobj$rotated[, y])/100) * 35), max(pcaobj$rotated[, y]) +
    abs((min(pcaobj$rotated[, y])/100) * 35)) else c(min(pcaobj$rotated[, y]) -
    abs((min(pcaobj$rotated[, y])/100) * 10), max(pcaobj$rotated[, y]) +
    abs((min(pcaobj$rotated[, y])/100) * 10)),
  lab = rownames(pcaobj$metadata),
  labSize = 3,
  boxedLabels = FALSE,
  selectLab = NULL,
  drawConnectors = TRUE,
  widthConnectors = 0.5,
  colConnectors = "grey50",
  max.overlaps = 15,
  maxoverlapsConnectors = NULL,
  min.segment.length = 0,
  directionConnectors = "both",
  xlab = paste0(x, ", ", round(pcaobj$variance[x], digits = 2), "% variation"),
  xlabAngle = 0,
  xlabhjust = 0.5,
  xlabvjust = 0.5,
  ylab = paste0(y, ", ", round(pcaobj$variance[y], digits = 2), "% variation"),
  ylabAngle = 0,
  ylabhjust = 0.5,
  ylabvjust = 0.5,
  axisLabSize = 16,
  title = "",
  subtitle = "",
  caption = "",
  titleLabSize = 16,
  subtitleLabSize = 12,
  captionLabSize = 12,
  hline = NULL,
  hlineType = "longdash",
  hlineCol = "black",
  hlineWidth = 0.4,
  vline = NULL,
  vlineType = "longdash",
  vlineCol = "black",
  vlineWidth = 0.4,
  gridlines.major = TRUE,
  gridlines.minor = TRUE,
  borderWidth = 0.8,
  borderColour = "black",
  returnPlot = TRUE
)

Arguments

`pcaobj`	Object of class 'pca' created by pca().
`x`	A principal component to plot on x-axis. All principal component names are stored in pcaobj$label.
`y`	A principal component to plot on y-axis. All principal component names are stored in pcaobj$label.
`showLoadings`	Logical, indicating whether or not to overlay variable loadings.
`ntopLoadings`	If showLoadings == TRUE, select this many variables based on absolute ordered variable loading for each PC in the biplot. As a result of looking across 2 PCs, it can occur whereby greater than this number are actually displayed.
`showLoadingsNames`	Logical, indicating to show variable loadings names or not.
`colLoadingsNames`	If 'showLoadings == TRUE', colour of text labels.
`sizeLoadingsNames`	If 'showLoadings == TRUE', size of text labels.
`boxedLoadingsNames`	Logical, if 'showLoadings == TRUE', draw text labels in boxes.
`fillBoxedLoadings`	When 'boxedLoadingsNames == TRUE', this controls the background fill of the boxes. To control both the fill and transparency, user can specify a value of the form 'alpha(<colour>, <alpha>)'.
`drawConnectorsLoadings`	If 'showLoadings == TRUE', draw line connectors to the variable loadings arrows in order to fit more labels in the plot space.
`widthConnectorsLoadings`	If 'showLoadings == TRUE', width of the line connectors drawn to the variable loadings arrows.
`colConnectorsLoadings`	If 'showLoadings == TRUE', colour of the line connectors drawn to the variable loadings arrows.
`lengthLoadingsArrowsFactor`	If 'showLoadings == TRUE', multiply the internally-determined length of the variable loadings arrows by this factor.
`colLoadingsArrows`	If showLoadings == TRUE, colour of the variable loadings arrows.
`widthLoadingsArrows`	If showLoadings == TRUE, width of the variable loadings arrows.
`alphaLoadingsArrow`	If showLoadings == TRUE, colour transparency of the variable loadings arrows.
`colby`	If NULL, all points will be coloured differently. If not NULL, value is assumed to be a column name in pcaobj$metadata relating to some grouping/categorical variable.
`colkey`	Vector of name-value pairs relating to value passed to 'col', e.g., c(A='forestgreen', B='gold').
`colLegendTitle`	Title of the legend for the variable specified by 'colby'.
`singlecol`	If specified, all points will be shaded by this colour. Overrides 'col'.
`shape`	If NULL, all points will be have the same shape. If not NULL, value is assumed to be a column name in pcaobj$metadata relating to some grouping/categorical variable.
`shapekey`	Vector of name-value pairs relating to value passed to 'shape', e.g., c(A=10, B=21).
`shapeLegendTitle`	Title of the legend for the variable specified by 'shape'.
`pointSize`	Size of plotted points.
`legendPosition`	Position of legend ('top', 'bottom', 'left', 'right', 'none').
`legendLabSize`	Size of plot legend text.
`legendTitleSize`	Size of plot legend title text.
`legendIconSize`	Size of plot legend icons / symbols.
`encircle`	Logical, indicating whether to draw a polygon around the groups specified by 'colby'.
`encircleFill`	Logical, if 'encircle == TRUE', this determines whether to fill the encircled region or not.
`encircleFillKey`	Vector of name-value pairs relating to value passed to 'encircleFill', e.g., c(A='forestgreen', B='gold'). If NULL, the fill is controlled by whatever has already been used for 'colby' / 'colkey'.
`encircleAlpha`	Alpha for purposes of controlling colour transparency of the encircled region. Used when 'encircle == TRUE'.
`encircleLineSize`	Line width of the encircled line when 'encircle == TRUE'.
`encircleLineCol`	Colour of the encircled line when 'encircle == TRUE'.
`ellipse`	Logical, indicating whether to draw a data ellipse around the groups specified by 'colby'.
`ellipseType`	[paraphrased from https://ggplot2.tidyverse.org/reference/stat_ellipse.html] The type of ellipse. "t" assumes a multivariate t-distribution, while "norm" assumes a multivariate normal distribution. "euclid" draws a circle with the radius equal to level, representing the euclidean distance from the center. This ellipse probably won't appear circular unless coord_fixed() is applied.
`ellipseLevel`	[paraphrased from https://ggplot2.tidyverse.org/reference/stat_ellipse.html] The level at which to draw an ellipse, or, if ellipseType="euclid", the radius of the circle to be drawn.
`ellipseSegments`	[from https://ggplot2.tidyverse.org/reference/stat_ellipse.html] The number of segments to be used in drawing the ellipse.
`ellipseFill`	Logical, if 'ellipse == TRUE', this determines whether to fill the region or not.
`ellipseFillKey`	Vector of name-value pairs relating to value passed to 'ellipseFill', e.g., c(A='forestgreen', B='gold'). If NULL, the fill is controlled by whatever has already been used for 'colby' / 'colkey'.
`ellipseAlpha`	Alpha for purposes of controlling colour transparency of the ellipse region. Used when 'ellipse == TRUE'.
`ellipseLineSize`	Line width of the ellipse line when 'ellipse == TRUE'.
`ellipseLineCol`	Colour of the ellipse line when 'ellipse == TRUE'.
`xlim`	Limits of the x-axis.
`ylim`	Limits of the y-axis.
`lab`	A vector containing labels to add to the plot.
`labSize`	Size of labels.
`boxedLabels`	Logical, draw text labels in boxes.
`selectLab`	A vector containing a subset of lab to plot.
`drawConnectors`	Logical, indicating whether or not to connect plot labels to their corresponding points by line connectors.
`widthConnectors`	Line width of connectors.
`colConnectors`	Line colour of connectors.
`max.overlaps`	Equivalent of max.overlaps in ggrepel. Set to 'Inf' to always display all labels when drawConnectors = TRUE.
`maxoverlapsConnectors`	See max.overlaps.
`min.segment.length`	When drawConnectors = TRUE, specifies the minimum length of the connector line segments.
`directionConnectors`	direction in which to draw connectors. 'both', 'x', or 'y'.
`xlab`	Label for x-axis.
`xlabAngle`	Rotation angle of x-axis labels.
`xlabhjust`	Horizontal adjustment of x-axis labels.
`xlabvjust`	Vertical adjustment of x-axis labels.
`ylab`	Label for y-axis.
`ylabAngle`	Rotation angle of y-axis labels.
`ylabhjust`	Horizontal adjustment of y-axis labels.
`ylabvjust`	Vertical adjustment of y-axis labels.
`axisLabSize`	Size of x- and y-axis labels.
`title`	Plot title.
`subtitle`	Plot subtitle.
`caption`	Plot caption.
`titleLabSize`	Size of plot title.
`subtitleLabSize`	Size of plot subtitle.
`captionLabSize`	Size of plot caption.
`hline`	Draw one or more horizontal lines passing through this/these values on y-axis. For single values, only a single numerical value is necessary. For multiple lines, pass these as a vector, e.g., c(60,90).
`hlineType`	Line type for hline ('blank', 'solid', 'dashed', 'dotted', 'dotdash', 'longdash', 'twodash').
`hlineCol`	Colour of hline.
`hlineWidth`	Width of hline.
`vline`	Draw one or more vertical lines passing through this/these values on x-axis. For single values, only a single numerical value is necessary. For multiple lines, pass these as a vector, e.g., c(60,90).
`vlineType`	Line type for vline ('blank', 'solid', 'dashed', 'dotted', 'dotdash', 'longdash', 'twodash').
`vlineCol`	Colour of vline.
`vlineWidth`	Width of vline.
`gridlines.major`	Logical, indicating whether or not to draw major gridlines.
`gridlines.minor`	Logical, indicating whether or not to draw minor gridlines.
`borderWidth`	Width of the border on the x and y axes.
`borderColour`	Colour of the border on the x and y axes.
`returnPlot`	Logical, indicating whether or not to return the plot object.

Details

Draw a bi-plot, comparing 2 selected principal components / eigenvectors.

Value

A ggplot2 object.

Author(s)

Kevin Blighe <kevin@clinicalbioinformatics.co.uk>

Examples

  options(scipen=10)
  options(digits=6)

  col <- 20
  row <- 20000
  mat1 <- matrix(
    rexp(col*row, rate = 0.1),
    ncol = col)
  rownames(mat1) <- paste0('gene', 1:nrow(mat1))
  colnames(mat1) <- paste0('sample', 1:ncol(mat1))

  mat2 <- matrix(
  rexp(col*row, rate = 0.1),
    ncol = col)
  rownames(mat2) <- paste0('gene', 1:nrow(mat2))
  colnames(mat2) <- paste0('sample', (ncol(mat1)+1):(ncol(mat1)+ncol(mat2)))

  mat <- cbind(mat1, mat2)

  metadata <- data.frame(row.names = colnames(mat))
  metadata$Group <- rep(NA, ncol(mat))
  metadata$Group[seq(1,40,2)] <- 'A'
  metadata$Group[seq(2,40,2)] <- 'B'
  metadata$CRP <- sample.int(100, size=ncol(mat), replace=TRUE)
  metadata$ESR <- sample.int(100, size=ncol(mat), replace=TRUE)

  p <- pca(mat, metadata = metadata, removeVar = 0.1)

  biplot(p)

  biplot(p, colby = 'Group', shape = 'Group')

  biplot(p, colby = 'Group', colkey = c(A = 'forestgreen', B = 'gold'),
    legendPosition = 'right')

  biplot(p, colby = 'Group', colkey = c(A='forestgreen', B='gold'),
    shape = 'Group', shapekey = c(A=10, B=21), legendPosition = 'bottom')

kevinblighe/PCAtools documentation built on Oct. 22, 2023, 12:01 p.m.