创作原因目前最为常见的热图绘制R包，主要包括pheatmap和ComplexHeatmap（仅个人使用习惯）。它们强大的功能，基本可以满足所有科研人员的绘图需求。ggplot2的操作灵活性和优秀度是毋庸置疑的，也因此许多绘图包都基本需要ggplot2作为操作对象。为了开发一个基于ggplot2的热图绘制R包，我们开发了ggheatmap包，主要为了解决热图的拼图问题以及热图与ggplot2对象的灵活衔接。 链接：https://github.com/XiaoLuo-boy/ggheatmap 用法参数- data 表达矩阵（data.frame/matrix）
- color 热图颜色，建议使用colorRampPalette生成
- legendName 热图主体图例标题，默认为“Express”
- scale 数据标准化方式（"none", "row" or "column"）
- dist_method dist函数选用的方法，默认"euclidean"（可选用"euclidean", "maximum", "manhattan", "canberra", "binary" or "minkowski"）
- hclust_method hclust函数选用的方法,默认“complete”（可选用"ward.D", "ward.D2", "single", "complete", "average"， "mcquitty", "median" or "centroid" ）
- text_just_rows 行标签位置调整（hjust, vjust）
- text_just_cols 列标签位置调整（hjust, vjust）
- text_show_rows 需要特定展示的行标签
- text_show_cols 需要特定展示的列标签
- show_cluster_cols 是否展示列聚类树
- show_cluster_rows 是否展示行聚类树
可视化模拟数据devtools::install_github("XiaoLuo-boy/ggheatmap")
library(ggheatmap)
library(pheatmap)
library(aplot)
set.seed(123)
df <- matrix(runif(600,0,10),ncol = 12)
colnames(df) <- paste("sample",1:12,sep = "")
rownames(df) <- sapply(1:50, function(x)paste(sample(LETTERS,3,replace = F),collapse = ""))
head(df)
# sample1 sample2 sample3 sample4
# PIK 2.875775 0.4583117 5.999890 8.474532
# KSJ 7.883051 4.4220007 3.328235 4.975273
# WBF 4.089769 7.9892485 4.886130 3.879090
# TNY 8.830174 1.2189926 9.544738 2.464490
说明：由于是随机模拟数据，故每次运行的结果都有所不同。为了验证结果，可以利用pheatmap包进行验证绘图结果的准确性（不一定与本文相同）。
例1.行、列聚类说明：默认不对行、列聚类
ggheatmap(df,cluster_rows = T,cluster_cols = T)
pheatmap(df,color = colorRampPalette(c( "#0073c2","white","#efc000"))(100))
 ggheatmap pheatmap例2.数据标准化说明：默认不标准化
ggheatmap(df,cluster_rows = T,cluster_cols = T,scale = "column")
pheatmap(df,scale = "column",color = colorRampPalette(c( "#0073c2","white","#efc000"))(100))
 ggheatmap pheatmap例3.图例标题设置说明：默认图例标题为“Express",NULL将去除图例标题
ggheatmap(df,cluster_rows = T,cluster_cols = T,legendName = "score")
ggheatmap(df,cluster_rows = T,cluster_cols = T,legendName = NULL)
  例4.行、列标签设置说明：标签可以自由设置角度，以及水平和垂直调整。同时也支持更换标签的位置改变。
ggheatmap(df,cluster_rows = T,cluster_cols = T,text_angle_rows = 330,text_just_rows = c(1,0))
ggheatmap(df,cluster_rows = T,cluster_cols = T,text_angle_cols = 45,text_just_cols = c(1,1))
ggheatmap(df,cluster_rows = T,cluster_cols = T,text_position_cols = "top")
   说明：标签的颜色或者字体可以是单个字符，也可以是多个同等长度的字符，以实现特定标签展示。比如特异展示标志基因等等
ggheatmap(df,cluster_rows = T,cluster_cols = T,text_color_cols = "red")
ggheatmap(df,cluster_rows = T,cluster_cols = T,text_color_cols = c(rep("black",6),"red",rep("black",5)))
ggheatmap(df,cluster_rows = T,cluster_cols = T,
text_color_rows = c("red",rep("black",49)),
text_face_rows = c("bold",rep("italic",49)))
  说明：ggheatmap支持特定标签的展示，输入原数据存在的行名或者列名，即可展示所需要展示的基因。
text_rows <- sample(rownames(df),3)
text_rows
# "XDV" "WFH" "ALR"
ggheatmap(df,scale = "row",cluster_rows = T,cluster_cols = T,
text_show_rows = text_rows)
说明：只有不进行行、列聚类时，该设置才有意义
ggheatmap(df,cluster_rows = F,cluster_cols = F)
ggheatmap(df,cluster_rows = F,cluster_cols = F,
levels_cols = c(paste("sample",1:12,sep = "")))
例5.聚类树的可视化说明：show_cluster_cols或show_cluster_rows必须展示，高度才有设置的意义
ggheatmap(df,cluster_rows = T,cluster_cols = T,show_cluster_cols = F)
ggheatmap(df,cluster_rows = T,cluster_cols = T,tree_height_rows = 0.05,tree_height_cols = 0.05)
说明：同上，show_cluster_cols或show_cluster_rows必须展示
ggheatmap(df,cluster_rows = T,cluster_cols = T,cluster_num = c(5,4))
ggheatmap(df,cluster_rows = T,cluster_cols = T,cluster_num = c(5,4),
tree_color_rows = c("#3B4992FF","#EE0000FF","#008B45FF","#631879FF","#008280FF"),
tree_color_cols = c("#0073C2FF", "#EFC000FF" ,"#868686FF", "#CD534CFF"))
注释说明：注释的方式基本同pheatmap
row_metaData <- data.frame(exprtype=sample(c("Up","Down"),50,replace = T),
genetype=sample(c("Metabolism","Immune","None"),50,replace = T))
rownames(row_metaData) <- rownames(df)
col_metaData <- data.frame(tissue=sample(c("Normal","Tumor"),12,replace = T),
risklevel=sample(c("High","Low"),12,replace = T))
rownames(col_metaData) <- colnames(df)
exprcol <- c("#EE0000FF","#008B45FF" )
names(exprcol) <- c("Up","Down")
genecol <- c("#EE7E30","#5D9AD3","#D0DFE6FF")
names(genecol) <- c("Metabolism","Immune","None")
tissuecol <- c("#98D352","#FF7F0E")
names(tissuecol) <- c("Normal","Tumor")
riskcol <- c("#EEA236FF","#46B8DAFF")
names(riskcol) <- c("High","Low")
col <- list(exprtype=exprcol,genetype=genecol,tissue=tissuecol,risklevel=riskcol)
ggheatmap<- ggheatmap(df,cluster_rows = T,cluster_cols = T,scale = "row",
cluster_num = c(5,3),
tree_color_rows = c("#3B4992FF","#EE0000FF","#008B45FF","#631879FF","#008280FF"),
tree_color_cols = c("#1F77B4FF","#FF7F0EFF","#2CA02CFF"),
annotation_rows = row_metaData,
annotation_cols = col_metaData,
annotation_color = col
)
综合示例情景：假设在绘制热图的时候，一方面，基因的数量太多；另一方面，你希望展示研究基因在不同样本的表达情况。 Example1 text_rows <- sample(rownames(df),5)
text_rows
# "WFH" "TAC" "MLZ" "KSJ" "BPW"
ggheatmap(df,scale = "row",cluster_rows = T,cluster_cols = T,cluster_num = c(2,3),
text_show_rows = text_rows,
text_face_rows = "bold",
text_color_rows = "red",
text_angle_cols = 45,
text_just_cols = c(1,1),
tree_color_rows = c( "#3B4992FF","#EE0000FF"),
tree_color_cols = c("#1F77B4FF","#FF7F0EFF","#2CA02CFF")
)
Example2 dat <- data.frame(marker=sample(c(1,NA),50,replace = T),
gene=rownames(df),
shape=sample(c("T","F"),50,replace = T))
p <- ggplot(dat,aes(x=1,y=gene,size=marker,color=shape,shape=shape))+
geom_point()+theme_classic()+
scale_color_manual(values = c("#D2691E","#1E87D2"))+
theme(line = element_blank(),axis.text = element_blank(),axis.title = element_blank())+
guides(size = FALSE)
ggheatmap%>%insert_right(p,width = 0.1)
image-20210522143840937结语本R包的优势是：1.比较灵活的标签设置；2.实现了heatmap与ggplot2绘图系统的联动，有助于拼图等操作；3.简单易于操作；4.聚类树可视化的优化。 本R依赖了ggplot2、ggpubr、aplot、factoextra、grDevices、stats、tibble、tidyr等R包。作为一名R语言爱好者和生信小白，真心地感激各位开发前辈的无私付出。秉承着“尊重知识，致敬原创”的原则，对于aplot包，作者已经获得余老师的许可。 image-20210522145101212此外，作为一名医学生，在学习生信和R语言的过程中，实实在在遇到过很多困难。在此特别感激“生信技能树”团队的健明老师及其他老师为众多生信小白的付出。无论是推文教程亦或线上交流群，还是公开课都能够见证各位老师对后辈的关心和照顾。
|
