\name{pheatmapwh}

\alias{pheatmapwh}

\title{A modification of \code{\link[pheatmap]{pheatmap}} from the pheatmap package by Raivo Kolde: draw clustered heatmaps.}

\usage{

pheatmapwh(mat, color = colorRampPalette(rev(brewer.pal(n = 7, name =

  "RdYlBu")))(100), kmeans_k = NA, breaks = NA, border_color = "grey60",

  cellwidth = NA, cellheight = NA, scale = "none", cluster_rows = TRUE,

  cluster_cols = TRUE, clustering_distance_rows = "euclidean",

  clustering_distance_cols = "euclidean", clustering_method = "complete",

  clustering_callback = identity2, cutree_rows = NA, cutree_cols = NA,

  treeheight_row = ifelse(cluster_rows, 50, 0),

  treeheight_col = ifelse(cluster_cols, 50, 0), legend = TRUE,

  legend_breaks = NA, legend_labels = NA, annotation_row = NA,

  annotation_col = NA, annotation = NA, annotation_colors = NA,

  annotation_legend = TRUE, drop_levels = TRUE, show_rownames = T,

  show_colnames = T, main = NA, fontsize = 10, fontsize_row = fontsize,

  fontsize_col = fontsize, display_numbers = F, number_format = "\%.2f",

  number_color = "grey30", fontsize_number = 0.8 * fontsize,

  gaps_row = NULL, gaps_col = NULL, labels_row = NULL,

  labels_col = NULL, filename = NA, width = NA, height = NA,

  silent = FALSE, ...)

}

\arguments{

\item{mat}{numeric matrix of the values to be plotted.}

\item{color}{vector of colors used in heatmap.}

\item{kmeans_k}{the number of kmeans clusters to make, if we want to agggregate the

rows before drawing heatmap. If NA then the rows are not aggregated.}

\item{breaks}{a sequence of numbers that covers the range of values in mat and is one

element longer than color vector. Used for mapping values to colors. Useful, if needed

to map certain values to certain colors, to certain values. If value is NA then the

breaks are calculated automatically.}

\item{border_color}{color of cell borders on heatmap, use NA if no border should be

drawn.}

\item{cellwidth}{individual cell width in points. If left as NA, then the values

depend on the size of plotting window.}

\item{cellheight}{individual cell height in points. If left as NA,

then the values depend on the size of plotting window.}

\item{scale}{character indicating if the values should be centered and scaled in

either the row direction or the column direction, or none. Corresponding values are

\code{"row"}, \code{"column"} and \code{"none"}}

\item{cluster_rows}{boolean values determining if rows should be clustered,}

\item{cluster_cols}{boolean values determining if columns should be clustered.}

\item{clustering_distance_rows}{distance measure used in clustering rows. Possible

values are \code{"correlation"} for Pearson correlation and all the distances

supported by \code{\link{dist}}, such as \code{"euclidean"}, etc. If the value is none

of the above it is assumed that a distance matrix is provided.}

\item{clustering_distance_cols}{distance measure used in clustering columns. Possible

values the same as for clustering_distance_rows.}

\item{clustering_method}{clustering method used. Accepts the same values as

\code{\link{hclust}}.}

\item{clustering_callback}{callback function to modify the clustering. Is

called with two parameters: original \code{hclust} object and the matrix

used for clustering. Must return a \code{hclust} object.}

\item{cutree_rows}{number of clusters the rows are divided into, based on the

 hierarchical clustering (using cutree), if rows are not clustered, the

argument is ignored}

\item{cutree_cols}{similar to \code{cutree_rows}, but for columns}

\item{treeheight_row}{the height of a tree for rows, if these are clustered.

Default value 50 points.}

\item{treeheight_col}{the height of a tree for columns, if these are clustered.

Default value 50 points.}

\item{legend}{logical to determine if legend should be drawn or not.}

\item{legend_breaks}{vector of breakpoints for the legend.}

\item{legend_labels}{vector of labels for the \code{legend_breaks}.}

\item{annotation_row}{data frame that specifies the annotations shown on left

 side of the heatmap. Each row defines the features for a specific row. The

rows in the data and in the annotation are matched using corresponding row

 names. Note that color schemes takes into account if variable is continuous

 or discrete.}

\item{annotation_col}{similar to annotation_row, but for columns.}

\item{annotation}{deprecated parameter that currently sets the annotation_col if it is missing}

\item{annotation_colors}{list for specifying annotation_row and

annotation_col track colors manually. It is  possible to define the colors

for only some of the features. Check examples for  details.}

\item{annotation_legend}{boolean value showing if the legend for annotation

tracks should be drawn.}

\item{drop_levels}{logical to determine if unused levels are also shown in

the legend}

\item{show_rownames}{boolean specifying if column names are be shown.}

\item{show_colnames}{boolean specifying if column names are be shown.}

\item{main}{the title of the plot}

\item{fontsize}{base fontsize for the plot}

\item{fontsize_row}{fontsize for rownames (Default: fontsize)}

\item{fontsize_col}{fontsize for colnames (Default: fontsize)}

\item{display_numbers}{logical determining if the numeric values are also printed to

the cells. If this is a matrix (with same dimensions as original matrix), the contents

of the matrix are shown instead of original values.}

\item{number_format}{format strings (C printf style) of the numbers shown in cells.

For example "\code{\%.2f}" shows 2 decimal places and "\code{\%.1e}" shows exponential

notation (see more in \code{\link{sprintf}}).}

\item{number_color}{color of the text}

\item{fontsize_number}{fontsize of the numbers displayed in cells}

\item{gaps_row}{vector of row indices that show shere to put gaps into

heatmap. Used only if the rows are not clustered. See \code{cutree_row}

to see how to introduce gaps to clustered rows.}

\item{gaps_col}{similar to gaps_row, but for columns.}

\item{labels_row}{custom labels for rows that are used instead of rownames.}

\item{labels_col}{similar to labels_row, but for columns.}

\item{filename}{file path where to save the picture. Filetype is decided by

the extension in the path. Currently following formats are supported: png, pdf, tiff,

 bmp, jpeg. Even if the plot does not fit into the plotting window, the file size is

calculated so that the plot would fit there, unless specified otherwise.}

\item{width}{manual option for determining the output file width in inches.}

\item{height}{manual option for determining the output file height in inches.}

\item{silent}{do not draw the plot (useful when using the gtable output)}

\item{\dots}{graphical parameters for the text used in plot. Parameters passed to

\code{\link{grid.text}}, see \code{\link{gpar}}.}

}

\value{

Invisibly a list of components

\itemize{

    \item \code{tree_row} the clustering of rows as \code{\link{hclust}} object

    \item \code{tree_col} the clustering of columns as \code{\link{hclust}} object

    \item \code{kmeans} the kmeans clustering of rows if parameter \code{kmeans_k} was

specified

}

}

\description{

A function to draw clustered heatmaps where one has better control over some graphical

parameters such as cell size, etc.

}

\details{

The function also allows to aggregate the rows using kmeans clustering. This is

advisable if number of rows is so big that R cannot handle their hierarchical

clustering anymore, roughly more than 1000. Instead of showing all the rows

separately one can cluster the rows in advance and show only the cluster centers.

The number of clusters can be tuned with parameter kmeans_k.

}

\examples{

# Create test matrix

test = matrix(rnorm(200), 20, 10)

test[1:10, seq(1, 10, 2)] = test[1:10, seq(1, 10, 2)] + 3

test[11:20, seq(2, 10, 2)] = test[11:20, seq(2, 10, 2)] + 2

test[15:20, seq(2, 10, 2)] = test[15:20, seq(2, 10, 2)] + 4

colnames(test) = paste("Test", 1:10, sep = "")

rownames(test) = paste("Gene", 1:20, sep = "")

# Draw heatmaps

pheatmapwh(test)

pheatmapwh(test, kmeans_k = 2)

pheatmapwh(test, scale = "row", clustering_distance_rows = "correlation")

pheatmapwh(test, color = colorRampPalette(c("navy", "white", "firebrick3"))(50))

pheatmapwh(test, cluster_row = FALSE)

pheatmapwh(test, legend = FALSE)

# Show text within cells

pheatmapwh(test, display_numbers = TRUE)

pheatmapwh(test, display_numbers = TRUE, number_format = "\\\%.1e")

pheatmapwh(test, display_numbers = matrix(ifelse(test > 5, "*", ""), nrow(test)))

pheatmapwh(test, cluster_row = FALSE, legend_breaks = -1:4, legend_labels = c("0",

"1e-4", "1e-3", "1e-2", "1e-1", "1"))

# Fix cell sizes and save to file with correct size

pheatmapwh(test, cellwidth = 15, cellheight = 12, main = "Example heatmap")

pheatmapwh(test, cellwidth = 15, cellheight = 12, fontsize = 8, filename = "test.pdf")

# Generate annotations for rows and columns

annotation_col = data.frame(

                    CellType = factor(rep(c("CT1", "CT2"), 5)),

                    Time = 1:5

                )

rownames(annotation_col) = paste("Test", 1:10, sep = "")

annotation_row = data.frame(

                    GeneClass = factor(rep(c("Path1", "Path2", "Path3"), c(10, 4, 6)))

                )

rownames(annotation_row) = paste("Gene", 1:20, sep = "")

# Display row and color annotations

pheatmapwh(test, annotation_col = annotation_col)

pheatmapwh(test, annotation_col = annotation_col, annotation_legend = FALSE)

pheatmapwh(test, annotation_col = annotation_col, annotation_row = annotation_row)

# Specify colors

ann_colors = list(

    Time = c("white", "firebrick"),

    CellType = c(CT1 = "#1B9E77", CT2 = "#D95F02"),

    GeneClass = c(Path1 = "#7570B3", Path2 = "#E7298A", Path3 = "#66A61E")

)

pheatmapwh(test, annotation_col = annotation_col, annotation_colors = ann_colors, main = "Title")

pheatmapwh(test, annotation_col = annotation_col, annotation_row = annotation_row,

         annotation_colors = ann_colors)

pheatmapwh(test, annotation_col = annotation_col, annotation_colors = ann_colors[2])

# Gaps in heatmaps

pheatmapwh(test, annotation_col = annotation_col, cluster_rows = FALSE, gaps_row = c(10, 14))

pheatmapwh(test, annotation_col = annotation_col, cluster_rows = FALSE, gaps_row = c(10, 14),

         cutree_col = 2)

# Show custom strings as row/col names

labels_row = c("", "", "", "", "", "", "", "", "", "", "", "", "", "", "",

"", "", "Il10", "Il15", "Il1b")

pheatmapwh(test, annotation_col = annotation_col, labels_row = labels_row)

# Specifying clustering from distance matrix

drows = dist(test, method = "minkowski")

dcols = dist(t(test), method = "minkowski")

pheatmapwh(test, clustering_distance_rows = drows, clustering_distance_cols = dcols)

# Modify ordering of the clusters using clustering callback option

callback = function(hc, mat){

    sv = svd(t(mat))$v[,1]

    dend = reorder(as.dendrogram(hc), wts = sv)

    as.hclust(dend)

}

pheatmapwh(test, clustering_callback = callback)

\dontrun{

# Same using dendsort package

library(dendsort)

callback = function(hc, ...){dendsort(hc)}

pheatmapwh(test, clustering_callback = callback)

}

}

\author{

Raivo Kolde <rkolde@gmail.com>

}