Capítulo 8: clostering aglomerativo
#install.packages("dendextend")
#install.packages("corrplot")
library(dendextend)
## Warning: package 'dendextend' was built under R version 4.2.3
##
## ---------------------
## Welcome to dendextend version 1.17.1
## Type citation('dendextend') for how to cite the package.
##
## Type browseVignettes(package = 'dendextend') for the package vignette.
## The github page is: https://github.com/talgalili/dendextend/
##
## Suggestions and bug-reports can be submitted at: https://github.com/talgalili/dendextend/issues
## You may ask questions at stackoverflow, use the r and dendextend tags:
## https://stackoverflow.com/questions/tagged/dendextend
##
## To suppress this message use: suppressPackageStartupMessages(library(dendextend))
## ---------------------
##
## Attaching package: 'dendextend'
## The following object is masked from 'package:stats':
##
## cutree
library(corrplot)
## Warning: package 'corrplot' was built under R version 4.2.3
## corrplot 0.92 loaded
#Data preparation
df <- scale(USArrests)
# Subset containing 10 rows
set.seed(123)
ss <- sample(1:50, 10)
df <- df[ss,]
#Comparing dendrograms
# Compute distance matrix
res.dist <- dist(df, method = "euclidean")
# Compute 2 hierarchical clusterings
hc1 <- hclust(res.dist, method = "average")
hc2 <- hclust(res.dist, method = "ward.D2")
# Create two dendrograms
dend1 <- as.dendrogram (hc1)
dend2 <- as.dendrogram (hc2)
# Create a list to hold dendrograms
dend_list <- dendlist(dend1, dend2)
#Visual comparison of two dendrograms
#Draw a tanglegram:
tanglegram(dend1, dend2)
#Customized the tanglegram using many other options as follow:
tanglegram(dend1, dend2,
highlight_distinct_edges = FALSE, # Turn-off dashed lines
common_subtrees_color_lines = FALSE, # Turn-off line colors
common_subtrees_color_branches = TRUE, # Color common branches
main = paste("Entanglement =", round(entanglement(dend_list), 2))
)
#Correlation matrix between a list of dendrograms
# Cophenetic correlation matrix
cor.dendlist(dend_list, method = "cophenetic")
## [,1] [,2]
## [1,] 1.0000000 0.9925544
## [2,] 0.9925544 1.0000000
# Baker correlation matrix
cor.dendlist(dend_list, method = "baker")
## [,1] [,2]
## [1,] 1.0000000 0.9895528
## [2,] 0.9895528 1.0000000
# Cophenetic correlation coefficient
cor_cophenetic(dend1, dend2)
## [1] 0.9925544
# Baker correlation coefficient
cor_bakers_gamma(dend1, dend2)
## [1] 0.9895528
#COMPARING DENDROGRAMS
# Create multiple dendrograms by chaining
dend1 <- df %>% dist %>% hclust("complete") %>% as.dendrogram
dend2 <- df %>% dist %>% hclust("single") %>% as.dendrogram
dend3 <- df %>% dist %>% hclust("average") %>% as.dendrogram
dend4 <- df %>% dist %>% hclust("centroid") %>% as.dendrogram
# Compute correlation matrix
dend_list <- dendlist("Complete" = dend1, "Single" = dend2,
"Average" = dend3, "Centroid" = dend4)
cors <- cor.dendlist(dend_list)
# Print correlation matrix
round(cors, 2)
## Complete Single Average Centroid
## Complete 1.00 0.46 0.45 0.30
## Single 0.46 1.00 0.23 0.17
## Average 0.45 0.23 1.00 0.31
## Centroid 0.30 0.17 0.31 1.00
# Visualize the correlation matrix using corrplot package
corrplot(cors, "pie", "lower")
Capítulo 9: Visualización de Dendogramas
#install.packages("igraph")
library(factoextra)
## Warning: package 'factoextra' was built under R version 4.2.3
## Loading required package: ggplot2
## Welcome! Want to learn more? See two factoextra-related books at https://goo.gl/ve3WBa
library(dendextend)
library(igraph)
## Warning: package 'igraph' was built under R version 4.2.3
##
## Attaching package: 'igraph'
## The following objects are masked from 'package:stats':
##
## decompose, spectrum
## The following object is masked from 'package:base':
##
## union
# Load data
data(USArrests)
# Compute distances and hierarchical clustering
dd <- dist(scale(USArrests), method = "euclidean")
hc <- hclust(dd, method = "ward.D2")
#Visualizing dendrograms
fviz_dend(hc, cex = 0.5)
## Warning: The `<scale>` argument of `guides()` cannot be `FALSE`. Use "none" instead as
## of ggplot2 3.3.4.
## ℹ The deprecated feature was likely used in the factoextra package.
## Please report the issue at <]8;;https://github.com/kassambara/factoextra/issueshttps://github.com/kassambara/factoextra/issues]8;;>.
fviz_dend(hc, cex = 0.5,
main = "Dendrogram - ward.D2",
xlab = "Objects", ylab = "Distance", sub = "")
#To draw a horizontal dendrogram, type this:
fviz_dend(hc, cex = 0.5, horiz = TRUE)
#To change the plot theme
fviz_dend(hc, k = 4, # Cut in four groups
cex = 0.5, # label size
k_colors = c("#2E9FDF", "#00AFBB", "#E7B800", "#FC4E07"),
color_labels_by_k = TRUE, # color labels by groups
ggtheme = theme_gray() # Change theme
)
#
fviz_dend(hc, cex = 0.5, k = 4, # Cut in four groups
k_colors = "jco")
fviz_dend(hc, k = 4, cex = 0.4, horiz = TRUE, k_colors = "jco",
rect = TRUE, rect_border = "jco", rect_fill = TRUE)
fviz_dend(hc, cex = 0.5, k = 4,
k_colors = "jco", type = "circular")
fviz_dend(hc, k = 4, k_colors = "jco",
type = "phylogenic", repel = TRUE)
# Case of dendrogram with large data sets
#Zooming in the dendrogram
fviz_dend(hc, xlim = c(1, 20), ylim = c(1, 8))
#Plotting a sub-tree of dendrograms
# Create a plot of the whole dendrogram,
# and extract the dendrogram data
dend_plot <- fviz_dend(hc, k = 4, # Cut in four groups
cex = 0.5, # label size
k_colors = "jco"
)
dend_data <- attr(dend_plot, "dendrogram") # Extract dendrogram data
# Cut the dendrogram at height h = 10
dend_cuts <- cut(dend_data, h = 10)
# Visualize the truncated version containing
# two branches
fviz_dend(dend_cuts$upper)
## Warning in min(-diff(our_dend_heights)): ningún argumento finito para min;
## retornando Inf
# Plot the whole dendrogram
print(dend_plot)
# Plot subtree 1
fviz_dend(dend_cuts$lower[[1]], main = "Subtree 1")
# Plot subtree 2
fviz_dend(dend_cuts$lower[[2]], main = "Subtree 2")
#You can also plot circular trees as follow:
fviz_dend(dend_cuts$lower[[2]], type = "circular")
#Manipulating dendrograms using dendextend
#Standard R code for creating a dendrogram:
data <- scale(USArrests)
dist.res <- dist(data)
hc <- hclust(dist.res, method = "ward.D2")
dend <- as.dendrogram(hc)
plot(dend)
#R code for creating a dendrogram using chaining operator
library(dendextend)
dend <- USArrests[1:5,] %>% # data
scale %>% # Scale the data
dist %>% # calculate a distance matrix,
hclust(method = "ward.D2") %>% # Hierarchical clustering
as.dendrogram # Turn the object into a dendrogram.
plot(dend)
#Example
library(dendextend)
# 1. Create a customized dendrogram
mycols <- c("#2E9FDF", "#00AFBB", "#E7B800", "#FC4E07")
dend <- as.dendrogram(hc) %>%
set("branches_lwd", 1) %>% # Branches line width
set("branches_k_color", mycols, k = 4) %>% # Color branches by groups
set("labels_colors", mycols, k = 4) %>% # Color labels by groups
set("labels_cex", 0.5) # Change label size
# 2. Create plot
fviz_dend(dend)
Capítulo 10: Heatmap, estadísticas interactivas
df <- scale(mtcars)
# Default plot
heatmap(df, scale = "none")
col<- colorRampPalette(c("red", "white", "blue"))(256)
#install.packages("RColorBrewer")
library("RColorBrewer")
col <- colorRampPalette(brewer.pal(10, "RdYlBu"))(256)
# Use RColorBrewer color palette names
library("RColorBrewer")
col <- colorRampPalette(brewer.pal(10, "RdYlBu"))(256)
heatmap(df, scale = "none", col = col,
RowSideColors = rep(c("blue", "pink"), each = 16),
ColSideColors = c(rep("purple", 5), rep("orange", 6)))
# install.packages("gplots")
library("gplots")
## Warning: package 'gplots' was built under R version 4.2.3
##
## Attaching package: 'gplots'
## The following object is masked from 'package:stats':
##
## lowess
heatmap.2(df, scale = "none", col = bluered(100),
trace = "none", density.info = "none")
#install.packages("pheatmap")
library("pheatmap")
## Warning: package 'pheatmap' was built under R version 4.2.3
pheatmap(df, cutree_rows = 4)
library(dendextend)
# order for rows
Rowv <- mtcars %>% scale %>% dist %>% hclust %>% as.dendrogram %>%
set("branches_k_color", k = 3) %>% set("branches_lwd", 1.2) %>%
ladderize
# Order for columns: We must transpose the data
Colv <- mtcars %>% scale %>% t %>% dist %>% hclust %>% as.dendrogram %>%
set("branches_k_color", k = 2, value = c("orange", "blue")) %>%
set("branches_lwd", 1.2) %>%
ladderize
library(gplots)
heatmap.2(scale(mtcars), scale = "none", col = bluered(100),
Rowv = Rowv, Colv = Colv,
trace = "none", density.info = "none")
if (!requireNamespace("BiocManager", quietly = TRUE))
install.packages("BiocManager")
BiocManager::install("ComplexHeatmap")
library(ComplexHeatmap)
## Loading required package: grid
## ========================================
## ComplexHeatmap version 2.14.0
## Bioconductor page: http://bioconductor.org/packages/ComplexHeatmap/
## Github page: https://github.com/jokergoo/ComplexHeatmap
## Documentation: http://jokergoo.github.io/ComplexHeatmap-reference
##
## If you use it in published research, please cite either one:
## - Gu, Z. Complex Heatmap Visualization. iMeta 2022.
## - Gu, Z. Complex heatmaps reveal patterns and correlations in multidimensional
## genomic data. Bioinformatics 2016.
##
##
## The new InteractiveComplexHeatmap package can directly export static
## complex heatmaps into an interactive Shiny app with zero effort. Have a try!
##
## This message can be suppressed by:
## suppressPackageStartupMessages(library(ComplexHeatmap))
## ========================================
## ! pheatmap() has been masked by ComplexHeatmap::pheatmap(). Most of the arguments
## in the original pheatmap() are identically supported in the new function. You
## can still use the original function by explicitly calling pheatmap::pheatmap().
##
## Attaching package: 'ComplexHeatmap'
## The following object is masked from 'package:pheatmap':
##
## pheatmap
Heatmap(df,
name = "mtcars", #title of legend
column_title = "Variables", row_title = "Samples",
row_names_gp = gpar(fontsize = 7) # Text size for row names
)
library(circlize)
## Warning: package 'circlize' was built under R version 4.2.3
## ========================================
## circlize version 0.4.15
## CRAN page: https://cran.r-project.org/package=circlize
## Github page: https://github.com/jokergoo/circlize
## Documentation: https://jokergoo.github.io/circlize_book/book/
##
## If you use it in published research, please cite:
## Gu, Z. circlize implements and enhances circular visualization
## in R. Bioinformatics 2014.
##
## This message can be suppressed by:
## suppressPackageStartupMessages(library(circlize))
## ========================================
##
## Attaching package: 'circlize'
## The following object is masked from 'package:igraph':
##
## degree
mycols <- colorRamp2(breaks = c(-2, 0, 2),
colors = c("green", "white", "red"))
Heatmap(df, name = "mtcars", col = mycols)
library("circlize")
library("RColorBrewer")
Heatmap(df, name = "mtcars",
col = colorRamp2(c(-2, 0, 2), brewer.pal(n=3, name="RdBu")))
library(dendextend)
row_dend = hclust(dist(df)) # row clustering
col_dend = hclust(dist(t(df))) # column clustering
Heatmap(df, name = "mtcars",
row_names_gp = gpar(fontsize = 6.5),
cluster_rows = color_branches(row_dend, k = 4),
cluster_columns = color_branches(col_dend, k = 2))
# Divide into 2 groups
set.seed(2)
Heatmap(df, name = "mtcars", k = 2)
# split by a vector specifying rowgroups
Heatmap(df, name = "mtcars", split = mtcars$cyl,
row_names_gp = gpar(fontsize = 7))
# Split by combining multiple variables
Heatmap(df, name ="mtcars",
split = data.frame(cyl = mtcars$cyl, am = mtcars$am),
row_names_gp = gpar(fontsize = 7))
# Define some graphics to display the distribution of columns
.hist = anno_histogram(df, gp = gpar(fill = "lightblue"))
.density = anno_density(df, type = "line", gp = gpar(col = "blue"))
ha_mix_top = HeatmapAnnotation(
hist = .hist, density = .density,
height = unit(3.8, "cm")
)
# Define some graphics to display the distribution of rows
.violin = anno_density(df, type = "violin",
gp = gpar(fill = "lightblue"), which = "row")
.boxplot = anno_boxplot(df, which = "row")
ha_mix_right = HeatmapAnnotation(violin = .violin, bxplt = .boxplot,
which = "row", width = unit(4, "cm"))
# Combine annotation with heatmap
Heatmap(df, name = "mtcars",
column_names_gp = gpar(fontsize = 8),
top_annotation = ha_mix_top) + ha_mix_right
# Heatmap 1
ht1 = Heatmap(df, name = "ht1", km = 2,
column_names_gp = gpar(fontsize = 9))
# Heatmap 2
ht2 = Heatmap(df, name = "ht2",
col = circlize::colorRamp2(c(-2, 0, 2), c("green", "white", "red")),
column_names_gp = gpar(fontsize = 9))
# Combine the two heatmaps
ht1 + ht2
expr <- readRDS(paste0(system.file(package = "ComplexHeatmap"),
"/extdata/gene_expression.rds"))
mat <- as.matrix(expr[, grep("cell", colnames(expr))])
type <- gsub("s\\d+_", "", colnames(mat))
ha = HeatmapAnnotation(
df = data.frame(type = type),
annotation_height = unit(4, "mm")
)
Heatmap(mat, name = "expression", km = 5, top_annotation = ha,
show_row_names = FALSE, show_column_names = FALSE) +
Heatmap(expr$length, name = "length", width = unit(5, "mm"),
col = circlize::colorRamp2(c(0, 100000), c("white", "orange"))) +
Heatmap(expr$type, name = "type", width = unit(5, "mm")) +
Heatmap(expr$chr, name = "chr", width = unit(5, "mm"),
col = circlize::rand_color(length(unique(expr$chr))))
