R语言画热图

R语言画热图的方法很多，要注意聚类的方法 （距离函数），数据是否归一化，是否含有异常值等。

1. 生成演示数据

exprs_matrix = matrix(rnorm(200), 20)
colnames(exprs_matrix) <- paste0("sample",1:10)
rownames(exprs_matrix) <- paste0("gene",1:20)

head(exprs_matrix)

# 加上样品信息
sample_anno <- data.frame('class'= c(rep("normal",4),
                                     rep("control",6)),
                          'group'= c(rep("group1",8),
                                     rep("group2",2)))
rownames(sample_anno)=colnames(exprs_matrix)
# sample_anno: 行名为样品名，列为分组信息

2. 内置heatmap函数绘制热图

n_col <- ncol(exprs_matrix)
heatmap(exprs_matrix,col=colorRampPalette(c("red","white","blue"))(64),
        ColSideColors=colorRampPalette(c("green","black","red"))(n_col))

# 主要参数：
# col：指定热图所用颜色：
# 
# ColSideColors/RowSideColors代表列、行边是否显示颜色bar
# 
# ColV/RowV表示是否按照列/行聚类，默认均为真值
# 
# cexCol/cexRow分别表示列/行标签字体大小
# 
# scale=c("row","column","none") 设置是否归一化
# 
# margins：设置热图下方及右方宽度

3. pheatmap包绘制热图

library(pheatmap)

pheatmap(exprs_matrix)
pheatmap(exprs_matrix,treeheight_row=120,
         treeheight_col=20)

# 不显示列（样品）名称
pheatmap(exprs_matrix,treeheight_row=120,
         treeheight_col=20,show_colnames = F)
# 注释样品分类信息
pheatmap(exprs_matrix,annotation=sample_anno)

# 主要参数
# cellwidth、cellheight 小方格宽度、高度
# scale: (row,column,none) 行列是否归一化
# cluster_rows、cluster_cols #是否按行、列聚类
# treeheight_row、treeheight_col #横向、纵向树高度
# annotation：加上分组信息
# display_numbers=TRUE #在小方格中显示数字

4. gplots包绘制热图

library(gplots)

rc <- rainbow(nrow(exprs_matrix), start=0, end=.3) # mock
#映射颜色到样品分类信息
ss <- factor(c(rep("normal",4),
               rep("control",6)))
levels(ss) <- c('red','blue')

heatmap.2(exprs_matrix,col = colorRampPalette(c("red","white","blue"))(64),
          hclust=function(x) hclust(x,method = 'ward.D2'),
          distfun=function(x) dist(x,method='euclidean'),
          scale = "row",
          dendrogram = 'column',
          key = TRUE, keysize = 1.5,symkey = FALSE, 
          density.info = "none",  # histogram,density,none,histogram
          #add.expr
          RowSideColors=rc, 
          ColSideColors=as.vector(ss), margin=c(8, 5),
          xlab="samples", ylab= "genes",
          main="heatmap.2 plot",
          adjCol=c(0.5,1),
          offsetRow = 0.5,
          offsetCol = 2.5,
          trace = "none", 
          cexRow = 0.5)
# heatmap.2 加样品注释信息不是很方便。

5. ggplot2包绘制热图

library(ggplot2) 
library(reshape2)

hc<-hclust(dist(exprs_matrix),method = "complete") #对行进行聚类
rowInd<-hc$order #将聚类后行的顺序存为rowInd
hc<-hclust(dist(t(exprs_matrix)),method = "complete")  #对矩阵进行转置，对原本的列进行聚类
colInd<-hc$order  #将聚类后列的顺序存为colInd
exprs_matrix<-exprs_matrix[rowInd,colInd] #将数据按照聚类结果重排行和列
dp=reshape2::melt(exprs_matrix)   #对数据进行融合，适应ggplot的数据结构，以进行热图的绘制
colnames(dp) <- c("Gene","Sample","Value")

p<-ggplot(dp,aes(x=Sample,y=Gene,fill=Value)) + #指定横纵坐标、填充值
  xlab("Genes")+ylab("Samples")+labs(title="ggplot2 heatmap") +
  geom_tile(colour="white",size=0) +
  scale_fill_gradient(low = "green",high = "red") + #定义填充颜色
  geom_text(aes(label=round(Value,2)),angle=45,size=3) #加数字

print(p)

6 .ComplexHeatmap包绘制热图

library(ComplexHeatmap)
mat <- exprs_matrix

Heatmap(mat)

# 聚类会受到异常值的影响
mat2 = mat
mat2[1, 1] = 100000
Heatmap(mat2, name = "mat", col = col_fun, 
        column_title = "a matrix with outliers")

library(circlize)
# 定义热图颜色（值和颜色的对应）
# 设置同样的值-颜色映射，方便多个热图相互比较
#summary(mat)
#min <- min(mat)
#max <- max(mat)
col_fun = colorRamp2(c(-4, 0, 4), c("green", "white", "red"))
# col_fun(seq(-3, 3))
Heatmap(mat, name = "mat", col = col_fun)

Heatmap(mat, name = "mat", col = rev(rainbow(10)), 
        column_title = "set a color vector for a continuous matrix")

discrete_mat = matrix(sample(1:4, 100, replace = TRUE), 10, 10)
colors = base::structure(1:4, names = c("1", "2", "3", "4")) # black, red, green, blue
Heatmap(discrete_mat, name = "mat", col = colors,
        column_title = "a discrete numeric matrix")

# name 热图名字
# col 设置方格颜色
# na_col；设置NA 颜色 
# column_title/row_title 列行名
# column_title_side/row_title_side 列行名位置
# show_column_dend/show_row_dend 是否关闭列/行柱状树状图
# column_dend_side/row_dend_side 列/行柱状树状图位置
# clustering_distance_rows/clustering_distance_columns  距离量度
# clustering_method_rows/clustering_method_columns 聚类方法

ha = HeatmapAnnotation(bar = sample(letters[1:3], 10, replace = TRUE))
ha = HeatmapAnnotation(
  foo = c(1:4, NA, 6:10), 
  bar = c(NA, sample(letters[1:3], 9, replace = TRUE)),
  col = list(foo = col_fun,
             bar = c("a" = "red", "b" = "green", "c" = "blue")),
  na_col = "black"
)
# col 参数：Colors corresponding to value. 
# If the mapping is discrete, the value of col should be a named vector; 
# If the mapping is continuous, the value of col should be a color mapping function.

Heatmap(mat, name = "mat", top_annotation = ha)

# 分块画热图
hc = hclust(dist(exprs_matrix)) # 行数据（gene）之间的距离
group = cutree(hc, k = 4)

Heatmap(exprs_matrix, cluster_rows = cluster_within_group(t(exprs_matrix), group), 
        row_split = 4, border = TRUE) # it would be better if also set row_split

参考：

https://jokergoo.github.io/ComplexHeatmap-reference/book/introduction.html#general-design