导语
GUIDE ╲
热图是生信分析中最常见的可视化数据的方法，它具有丰富的色彩变化，并且能生动饱满的进行信息表达。比如可视化基因表达、显著性P值等数据。R 在可视化方面也提供了一系列功能强大、覆盖全面的函数和工具包，今天小编就总结了一些易操作且美观的热图绘图方法，一起来学习一下吧
静态热图
01
ggplot2包的ggplot函数
代码语言：javascript复制library(ggplot2)
####建立模拟数据集
set.seed(123)
Year <- rep(2006:2015, each = 4)
Quater <- rep(c('Q1','Q2','Q3','Q4'), times = 10)
Counts <- round(runif(40, min = 10, max = 200))
df <- data.frame(Year = Year, Quater = Quater, Counts = Counts)
fix(df)代码语言：javascript复制ggplot(data = df, mapping = aes(x = factor(Year),y = Quater, fill = Counts)) +
geom_tile() +
scale_fill_continuous(low = 'white', high = 'OrangeRed') +
scale_y_discrete(limits=c('Q4','Q3','Q2','Q1')) +
xlab('Year')02
heatmap函数
代码语言：javascript复制# 测试数据
a=c(12,14,17,11,16)
b=c(4,20,15,11,9)
c=c(5,7,19,8,18)
d=c(15,13,11,17,16)
e=c(12,19,16,7,9)
A=cbind(a,b,c,d,e)
require(graphics)
require(grDevices)
x <- as.matrix(A)
rc <- rainbow(nrow(x), start = 0, end = .3)
cc <- rainbow(ncol(x), start = 0, end = .3)
hv <- heatmap(x, col = cm.colors(256), scale = "column",
RowSideColors = rc, ColSideColors = cc, margins = c(5,10),
xlab = "specification variables", ylab = "Car Models")03
gplots包的heatmap.2函数
该函数能够产生高度定制的热图。使用heatmap.2绘制的热图看起有一种高级感。
（1）带密度图的热图
代码语言：javascript复制mat <- matrix(rnorm(1200), ncol=6)
heatmap.2(x=mat)（2）
代码语言：javascript复制data(mtcars)
x <- as.matrix(mtcars)
rc <- rainbow(nrow(x), start=0, end=.3)
cc <- rainbow(ncol(x), start=0, end=.3)①
代码语言：javascript复制heatmap.2(x)②
代码语言：javascript复制heatmap.2(x, Colv=full$colDendrogram[[2]],
Rowv=full$rowDendrogram[[1]],
#然后根据向量的顺序计算树状图并重新排序
breaks=full$breaks )
#将x分割成不同颜色的分界点③
代码语言：javascript复制heatmap.2(x, srtRow=45,
#标签从水平开始转动的角度
adjRow=c(0, 1),
#提供行/列标签(从左到右，从上到下)对齐的2个元素向量
srtCol=45,
adjCol=c(1,1)
)04
pheatmap包
pheatmap算是大家最常用的绘制热图的R包了。
代码语言：javascript复制library(pheatmap)
###构建示例数据
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 = "")
head(test)代码语言：javascript复制####构建行注释信息
annotation_row = data.frame(
GeneClass = factor(rep(c("Path1", "Path2", "Path3"), c(10, 4, 6)))
)
rownames(annotation_row) = paste("Gene", 1:20, sep = "")
head(annotation_row)代码语言：javascript复制####构建列注释信息
annotation_col = data.frame(
CellType = factor(rep(c("CT1", "CT2"), 5)),
Time = 1:5
)
rownames(annotation_col) = paste("Test", 1:10, sep = "")
head(annotation_col)代码语言：javascript复制pheatmap(test,
scale = "row",#对行进行归一化
clustering_method = "average",#选择聚类方法
legend_breaks = c(1:5),
#设定图例显示范围
legend_labels = c("1.0","2.0","3.0","4.0","5.0"),
#添加图例标签
#border_color = "black",
#每个格子的边框色
border=FALSE,
#去掉边框线
display_numbers = TRUE,
#在每个格子中显示相应的数值
number_color = "grey" ,
#数值字体的颜色
annotation_row = annotation_row,
annotation_col = annotation_col
#添加注释
)05
ComplexHeatmap包
ComplexHeatmap包擅长绘制复杂的热图，有很多功能，大家在实操的时候可以多多尝试。
代码语言：javascript复制library(ComplexHeatmap)
annotation = data.frame(value = rnorm(10))
value = 1:10
anno= HeatmapAnnotation(df = annotation, points = anno_points(value),
annotation_height = c(1, 2))
#添加热图注释和散点注释
Heatmap(test,name = "test", #设定图例标题
row_title = "Test", column_title = "Gene",
#坐标标题
cluster_columns = FALSE, #对列不聚类
clustering_distance_rows = "pearson",
#设定行聚类的距离方法，默认为"euclidean"
top_annotation =anno,
#注释
)06
heatmap.plus包
heatmap.plus包非常非常简单，参数也很少。
代码语言：javascript复制library(heatmap.plus)
z = matrix(rnorm(30),nrow=5,ncol=6)
rlab = matrix(as.character(c(1:5,2:6,3:7,4:8)),nrow=5,ncol=4)
clab = matrix(as.character(c(1:6,6:1)),nrow=6,ncol=2)
colnames(rlab) = LETTERS[1:dim(rlab)[2]]
colnames(clab) = 1:dim(clab)[2]
heatmap.plus(z,ColSideColors=clab,RowSideColors=rlab)06
lattice包的levelplot函数
（1）
代码语言：javascript复制levelplot(test)（2）其他玩法
代码语言：javascript复制#构建数据
x <- seq(pi/4, 5 * pi, length.out = 100)
y <- seq(pi/4, 5 * pi, length.out = 100)
r <- as.vector(sqrt(outer(x^2, y^2, "+")))
grid <- expand.grid(x=x, y=y)
grid$z <- cos(r^2) * exp(-r/(pi^3))①
代码语言：javascript复制levelplot(z ~ x * y,
#z是一个数值响应，x, y是在矩形网格上计算的数值
grid,
#对于公式方法，一种可选的数据框架
cuts = 50,
#z的将被划分的levels数目
scales=list(log="e"),
xlab="",ylab="",
main="Weird Function", #标题
sub="with log scales", #子标题
colorkey = FALSE,
#是否在绘图旁边绘制颜色键
region = TRUE
#等高线之间的区域是否应像等值线图那样填充
)②
代码语言：javascript复制levelplot(z ~ x * y, grid,
col.regions = topo.colors(10),
#颜色变化
at = c(-Inf, seq(-0.8, 0.8, by = 0.2), Inf)
#at，数值向量，指定颜色的变化位置
)交互式热图
01
highcharter包
代码语言：javascript复制library(highcharter)
###创建数据
nyears <- 5
df <- expand.grid(seq(12) - 1, seq(nyears) - 1)
df$value <- abs(seq(nrow(df)) + 10 * rnorm(nrow(df))) + 10
df$value <- round(df$value, 2)
ds <- list_parse2(df)
##绘图
hc <- highchart() %>%
hc_chart(type = "heatmap") %>%
hc_title(text = "Simulated values by years and months") %>%
hc_xAxis(categories = month.abb) %>%
hc_yAxis(categories = 2016 - nyears + seq(nyears)) %>%
hc_add_series(name = "value", data = ds)
hc_colorAxis(hc, minColor = "#FFFFFF", maxColor = "#434348")02
heatmaply包
代码语言：javascript复制library(heatmaply)
data(mtcars)数据iris：
①
代码语言：javascript复制heatmaply(iris[,-5], k_row = 3, k_col = 2) ②
代码语言：javascript复制heatmaply(mtcars, k_row = 3, k_col = 2, grid_gap = 1)03
iheatmapr包
代码语言：javascript复制library(iheatmapr)
library(ggdendro)
#构建数据
mat <- matrix(rnorm(24), nrow = 6)
mat2 <- matrix(rnorm(24), nrow = 6)
annotation = data.frame(gender = c(rep("M", 3),rep("F",3)))
iheatmap(mat,
cluster_rows = "hclust",
cluster_cols = "hclust", #聚类方法
col_k = 3) %>%
add_iheatmap(mat2, #再添加一组热图
cluster_cols = "hclust",
col_k = 3,
row_annotation = annotation)小编总结
其实上述工具包的功能都很强大，有些小编只是针对热图方面进行简单介绍，大家可以去安装学习，借鉴到符合自己数据可视化的方法~