R语言-limma差异分析与heatmap绘制

Posted 2023-05-18

参考技术A #mRNA表达矩阵与GROUP文件样式，heatmap样式见文章最后

library(limma)

 mRNA <- read.table("表达矩阵.txt",sep = "\t",header = T,comment.char = "!",encoding = "UTF-8")

#mRNA数据框行名为基因名，列命为样本名称

 group <- read.table("GROUP.txt",header=T,sep = "\t",encoding = "UTF-8")

 group_CP <- group$treat 

 m_design<- model.matrix(~0+factor(group_CP))

 colnames(m_design) = levels(factor(group_CP))

 rownames(m_design)= group$ID

 contrast.matrix<-makeContrasts("P-C",levels=m_design) #注意P-C顺序，实验组要在前面否则影响上下调结果

 m_fit <- lmFit(mRNA,m_design)

 m_fit <- contrasts.fit(m_fit, contrast.matrix)

 m_fit <- eBayes(m_fit)

 m_genlist <- topTable(m_fit, coef = 1, n=Inf)  #limma结果

#将表达矩阵与差异分析结果合并

  ID_REF <- rownames(m_genlist)

  m_genlist <- data.frame(ID_REF,m_genlist)

  ID_REF <- rownames(mRNA)

  mRNA <- data.frame(ID_REF,mRNA)

  test <-merge(mRNA,m_genlist,by = "ID_REF")

  result <- subset(test,P.Value<0.05)

  row.names(result) <- result[,1]

#绘制热图

heatmap <- result[2:(nrow(group)+1)]

annotation <- data.frame(Factor = factor(group$treat)) #标注样本的分组信息

rownames(annotation) <- colnames(heatmap)

library(pheatmap)

filename <- paste("文件名",".pdf",sep="")

pdf(filename)

pheatmap(heatmap,

        annotation=annotation,

        annotation_legend = TRUE,

        main=filename ,

        scale = "row",

        show_rownames = F,

        color = colorRampPalette(c("green","black","red"))(100))

dev.off()

#表达矩阵与GROUP文件如下所示

R语言热力图综合教程-heatmapd3heatmap和ComplexHeatmap

用于绘制交互式和静态热图的R包和功能很多，包括：

• heatmap（）[R基本函数，统计数据包]：绘制一个简单的热图

• heatmap.2（）[ gplots R包]：与R base函数相比，绘制了增强的热图。

• pheatmap（）[ pheatmap R包]：绘制漂亮的热图，并提供更多控件来更改热图的外观。

• d3heatmap（）[ d3heatmap R包]：绘制交互式/可单击的热图

• ComplexHeatmap R / Bioconductor的包]：绘制，注释和排列复杂热图（用于基因组数据分析是非常有用的）

在这里，我们从描述绘制热图的5 R函数开始。接下来，我们将重点介绍ComplexHeatmap程序包，该程序包提供了一种灵活的解决方案来安排和注释多个热图。它也可以可视化来自不同来源的不同数据之间的关联

我们使用mtcars数据作为演示数据集。我们首先将数据标准化以使变量具有可比性：

df <- scale(mtcars)

# Default plot
heatmap(df, scale = "none")

如何指定调色板

col<- colorRampPalette(c("red", "white", "blue"))(256)

heatmap(df, scale = "none", col = col)

library("RColorBrewer")
col <- colorRampPalette(brewer.pal(10, "RdYlBu"))(256)

heatmap(df, scale = "none", col = col)

此外，可以使用参数RowSideColors和ColSideColors分别注释行和列。

例如，在下面的R代码中，将自定义热图，如下所示：

• RColorBrewer调色板名称用于更改外观

• 参数RowSideColors和ColSideColors分别用于注释行和列。按照行列顺序指指定颜色

heatmap是按照聚类来重排行列的，会打乱颜色。

# 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")
heatmap.2(df, scale = "none", col = bluered(100),
 trace = "none", density.info = "none")

pheatmap

这个功能十分强大，出图我们也经常选用，cutree_rows参数用于按照聚类结果进行切割。

library("pheatmap")
pheatmap(df, cutree_rows = 4)

# install.packages("d3heatmap")
library("d3heatmap")
d3heatmap(scale(mtcars), colors = "RdYlBu",
 k_row = 4, # Number of groups in rows
 k_col = 2 # Number of groups in columns
 )

pheatmap不能使用。

ComplexHeatmap 功能十分强大

• row_names_gp：设置标签自字体大小

• olumn_title：设置行，列名称标签。

library(ComplexHeatmap)
Heatmap(df,
 name = "mtcars", #title of legend
 column_title = "Variables", row_title = "Samples",
 row_names_gp = gpar(fontsize = 7) # Text size for row names
 )

要指定自定义颜色，必须使用colorRamp2（）函数[ circlize package]，如下所示：

library(circlize)
mycols <- colorRamp2(breaks = c(-2, 0, 2),
 colors = c("green", "white", "red"))
Heatmap(df, name = "mtcars", col = mycols)

更换调色板，使用RColorBrewer 中的颜色。

library("circlize")
library("RColorBrewer")
Heatmap(df, name = "mtcars",
 col = colorRamp2(c(-2, 0, 2), brewer.pal(n=3, name="RdBu")))

dendextend 同样给复杂热图聚类上色。

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))

复杂热图按照聚类切割分块

km/row_km:对列进行聚类拆分

# Divide into 2 groups
set.seed(2)
Heatmap(df, name = "mtcars", km = 4)

按照行进行分割聚类：column_km

# Divide into 2 groups
set.seed(2)
Heatmap(df, name = "mtcars", column_km = 4)

指定行列分隔

split :参数用于指定行的分组，用于分割热图。row_split一样

如果要对行进行聚类，使用column_split，用法一样。

# Split
# data.frame(cyl = rep(1:4,dim(mtcars)[2]))
Heatmap(df, name ="mtcars",
 split = data.frame(cyl = mtcars$cyl),
 column_split = data.frame(cyl = rep(1:2,dim(mtcars)[2])[1:11]),
 row_names_gp = gpar(fontsize = 7))

多重分隔

Heatmap(df, name ="mtcars", col = col,
 km = 4, split = mtcars$cyl)

library("cluster")
set.seed(2)
pa = pam(df, k = 3)
Heatmap(df, name = "mtcars", col = col,
 split = paste0("pam", pa$clustering))

复杂热图为什么复杂

复杂热图最强大的莫过于对于热图的注释

df <- t(df)

# 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)
# 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

复杂热图的组合

# 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

细布控制组合

draw(ht1 + ht2,
 row_title = "Two heatmaps, row title",
 row_title_gp = gpar(col = "red"),
 column_title = "Two heatmaps, column title",
 column_title_side = "bottom",
 # Gap between heatmaps
 gap = unit(0.5, "cm"))

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))

ha

## A HeatmapAnnotation object with 1 annotation
## name: heatmap_annotation_2
## position: column
## items: 24
## width: 1npc
## height: 5mm
## this object is subsetable
## 9.001mm extension on the right
##
## name annotation_type color_mapping height
## type discrete vector random 5mm

Heatmap(mat, name = "expression", km = 5, top_annotation = ha,
 # top_annotation_height = unit(4, "mm"),
 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))))

ha = HeatmapAnnotation(df = data.frame(type = type))

ha

## A HeatmapAnnotation object with 1 annotation
## name: heatmap_annotation_3
## position: column
## items: 24
## width: 1npc
## height: 5mm
## this object is subsetable
## 9.001mm extension on the right
##
## name annotation_type color_mapping height
## type discrete vector random 5mm

Heatmap(mat, name = "expression", km = 5, top_annotation = ha,
 # top_annotation_height = unit(4, "mm"),
 show_row_names = FALSE, show_column_names = FALSE) +
 Heatmap(expr$type, name = "type", width = unit(5, "mm")) +
 Heatmap(expr$type, name = "type", width = unit(5, "mm"))

如何添加多个行，或者列

# Annotation data frame

annot_df <- data.frame(cyl = mtcars$cyl, am = mtcars$am,
 mpg = mtcars$mpg)
# row.names(annot_df) = row.names(mtcars)
# Define colors for each levels of qualitative variables
# Define gradient color for continuous variable (mpg)
col = list(cyl = c("4" = "green", "6" = "gray", "8" = "darkred"),
 am = c("0" = "yellow", "1" = "orange"),
 mpg = circlize::colorRamp2(c(17, 25),
 c("lightblue", "purple")) )
# Create the heatmap annotation
ha <- HeatmapAnnotation(df = data.frame(cyl = mtcars$cyl, am = mtcars$am,
 mpg = mtcars$mpg), col = col)

# Combine the heatmap and the annotation
# df = t(df)
Heatmap(df, name = "mtcars",
 top_annotation = ha)

# Annotation data frame

annot_df <- data.frame(cyl = mtcars$cyl, am = mtcars$am,
 mpg = mtcars$mpg)
# row.names(annot_df) = row.names(mtcars)
# Define colors for each levels of qualitative variables
# Define gradient color for continuous variable (mpg)
col = list(cyl = c("4" = "green", "6" = "gray", "8" = "darkred"),
 am = c("0" = "yellow", "1" = "orange"),
 mpg = circlize::colorRamp2(c(17, 25),
 c("lightblue", "purple")) )
# Create the heatmap annotation
ha <- HeatmapAnnotation(df = data.frame(cyl = mtcars$cyl, am = mtcars$am,
 mpg = mtcars$mpg), col = col)

# Combine the heatmap and the annotation
df = t(df)
Heatmap(df, name = "mtcars") +
 Heatmap(mtcars$mpg, name = "type", width = unit(5, "mm")) +
 Heatmap(mtcars$mpg, name = "type", width = unit(5, "mm"))

Heatmap(df, name = "mtcars") +
 Heatmap(annot_df , name = "type", width = unit(5, "mm"))

densityHeatmap(scale(mtcars))

reference

https://www.datanovia.com/en/lessons/heatmap-in-r-static-and-interactive-visualization/

如需联系EasyShu团队

https://github.com/Easy-Shu/EasyShu-WeChat

数据可视化之美系列书籍

Github

https://github.com/Easy-Shu/Beautiful-Visualization-with-python

Github

https://github.com/Easy-Shu/Beautiful-Visualization-with-R