如何将单倍型网络中的单倍型标签替换为样本名称

需求说明 #

绘制的单倍型网络中每个样本对应唯一单倍型，希望将网络圆圈的单倍型标签（如VIII）替换为样本名称（如D20B1），无需额外图例，仅保留网络结构和样本名称标签。

现有资源 #

绘图代码 #

plot(net, size=attr(net, "freq"),scale.ratio = 1, cex = 1, labels=T, 
     pie = ft, font=3, fast=T, threshold=0, show.mutation = 3, legend=F
     )

y_coord = ( par("usr")[4]) - (par("usr")[4]*0.01)
legend_coord = c((par("usr")[1]), y_coord)
#plot the legend
legend(x=legend_coord[1], y=legend_coord[2], unique(sort(sites$site)),
       fill=rainbow(length(unique(sites$site))), bty="n", cex=1)

net对象结构 #

structure(c(5, 6, 7, 8, 9, 11, 7, 13, 2, 3, 10, 12, 3, 3, 3, 
3, 3, 3, 4, 7, 1, 1, 4, 4, 2, 2, 2, 2, 2, 2, 2, 3, 4, 4, 4, 7, 
0.997829760277465, 0.997829760277465, 0.997829760277465, 0.997829760277465, 
0.997829760277465, 0.997829760277465, 0.997829760277465, 0.996746407283241, 
0.995664230495361, 0.995664230495361, 0.995664230495361, 0.992424744601474
), dim = c(12L, 4L), dimnames = list(NULL, c("", "", "step", 
"Prob")), freq = c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
1L, 1L), labels = c("I", "II", "III", "IV", "V", "VI", "VII", 
"VIII", "IX", "X", "XI", "XII", "XIII"), alter.links = structure(c(6, 
7, 8, 11, 7, 8, 9, 11, 8, 9, 11, 11, 5, 6, 7, 8, 11, 4, 5, 6, 
8, 9, 11, 9, 10, 9, 11, 13, 13, 13, 13, 13, 13, 13, 4, 9, 7, 
11, 10, 10, 10, 10, 10, 11, 13, 12, 5, 5, 5, 5, 6, 6, 6, 6, 7, 
7, 7, 8, 1, 1, 1, 1, 1, 3, 4, 4, 4, 4, 4, 5, 6, 8, 9, 3, 4, 5, 
6, 8, 9, 11, 1, 1, 2, 2, 3, 5, 7, 8, 9, 10, 1, 10, 2, 2, 2, 2, 
2, 2, 2, 2, 2, 2, 2, 2, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 
4, 4, 5, 5, 5, 5, 5, 5, 5, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 7, 7, 
0.997829760277465, 0.997829760277465, 0.997829760277465, 0.997829760277465, 
0.997829760277465, 0.997829760277465, 0.997829760277465, 0.997829760277465, 
0.997829760277465, 0.997829760277465, 0.997829760277465, 0.997829760277465, 
0.995664230495361, 0.995664230495361, 0.995664230495361, 0.995664230495361, 
0.995664230495361, 0.995664230495361, 0.995664230495361, 0.995664230495361, 
0.995664230495361, 0.995664230495361, 0.995664230495361, 0.995664230495361, 
0.995664230495361, 0.995664230495361, 0.995664230495361, 0.994583228636722, 
0.994583228636722, 0.994583228636722, 0.994583228636722, 0.994583228636722, 
0.994583228636722, 0.994583228636722, 0.99350340043119, 0.99350340043119, 
0.99350340043119, 0.99350340043119, 0.99350340043119, 0.99350340043119, 
0.99350340043119, 0.99350340043119, 0.99350340043119, 0.99350340043119, 
0.992424744601474, 0.992424744601474), dim = c(46L, 4L), dimnames = list(
NULL, c("", "", "step", "Prob"))), class = "haploNet") 

sites对象结构 #

structure(list(sample = c("D20B3", "D20B7", "D8B6", "D20B1", 
"D8B3", "D8B8", "D8B7", "D20B8", "D8B67", "D20B40", "D8B2", "D8B1", 
"D8B9"), site = c("D20B3", "D20B7", "D8B6", "D20B1", "D8B3", 
"D8B8", "D8B7", "D20B8", "D8B67", "D20B40", "D8B2", "D8B1", "D8B9"
), haplotype = c("D20B3", "D20B7", "D8B6", "D20B1", "D8B3", "D8B8", 
"D8B7", "D20B8", "D8B67", "D20B40", "D8B2", "D8B1", "D8B9")), class = "data.frame", row.names = c(NA, 
-13L))

ft生成方式 #

ft <- table(sites[3:2])
> ft
         site
haplotype D20B1 D20B3 D20B40 D20B7 D20B8 D8B1 D8B2 D8B3 D8B6 D8B67 D8B7 D8B8 D8B9
   D20B1      1     0      0     0     0    0    0    0    0     0    0    0    0
   D20B3      0     1      0     0     0    0    0    0    0     0    0    0    0
   D20B40     0     0      1     0     0    0    0    0    0     0    0    0    0
   D20B7      0     0      0     1     0    0    0    0    0     0    0    0    0
   D20B8      0     0      0     0     1    0    0    0    0     0    0    0    0
   D8B1       0     0      0     0     0    1    0    0    0     0    0    0    0
   D8B2       0     0      0     0     0    0    1    0    0     0    0    0    0
   D8B3       0     0      0     0     0    0    0    1    0     0    0    0    0
   D8B6       0     0      0     0     0    0    0    0    1     0    0    0    0
   D8B67      0     0      0     0     0    0    0    0    0     1    0    0    0
   D8B7       0     0      0     0     0    0    0    0    0     0    1    0    0
   D8B8       0     0      0     0     0    0    0    0    0     0    0    1    0
   D8B9       0     0      0     0     0    0    0    0    0     0    0    0    1

解决步骤 #

1. 替换net对象的标签：直接修改net的labels属性，将默认的罗马数字标签替换为sites中的样本名称。因为每个单倍型对应唯一样本，顺序一一匹配，直接赋值即可。

# 将net的labels替换为sites的sample列
attr(net, "labels") <- sites$sample

2. 调整绘图代码：由于标签已经是样本名称，无需再绘制图例，可删除图例相关代码；同时因为每个单倍型只对应一个样本，pie参数可以去掉（保留也不影响，但没必要）。

修改后的完整绘图代码 #

# 先替换标签
attr(net, "labels") <- sites$sample

# 绘制单倍型网络
plot(net, size=attr(net, "freq"), scale.ratio = 1, cex = 1, labels=T, 
     font=3, fast=T, threshold=0, show.mutation = 3, legend=F)

# 无需再绘制图例，删除原图例代码

说明 #

• 替换标签后，绘图时圆圈的标签会直接显示样本名称，无需额外图例即可识别每个节点对应的样本。
• 若需要调整标签大小，可修改cex参数；圆圈大小通过size参数控制，可根据需求自行调整。

内容的提问来源于stack exchange，提问作者Glubbdrubb