6

我想为海洋生物学课程制作一个简单的系统发育树作为教育示例。我有一个分类等级的物种列表：

    Group <- c("Benthos","Benthos","Benthos","Benthos","Benthos","Benthos","Zooplankton","Zooplankton","Zooplankton","Zooplankton",
"Zooplankton","Zooplankton","Fish","Fish","Fish","Fish","Fish","Fish","Phytoplankton","Phytoplankton","Phytoplankton","Phytoplankton")
Domain <- rep("Eukaryota", length(Group))
Kingdom <- c(rep("Animalia", 18), rep("Chromalveolata", 4))
Phylum <- c("Annelida","Annelida","Arthropoda","Arthropoda","Porifera","Sipunculida","Arthropoda","Arthropoda","Arthropoda",
"Arthropoda","Echinoidermata","Chorfata","Chordata","Chordata","Chordata","Chordata","Chordata","Chordata","Heterokontophyta",
"Heterokontophyta","Heterokontophyta","Dinoflagellata")
Class <- c("Polychaeta","Polychaeta","Malacostraca","Malacostraca","Demospongiae","NA","Malacostraca","Malacostraca",
"Malacostraca","Maxillopoda","Ophiuroidea","Actinopterygii","Chondrichthyes","Chondrichthyes","Chondrichthyes","Actinopterygii",
"Actinopterygii","Actinopterygii","Bacillariophyceae","Bacillariophyceae","Prymnesiophyceae","NA")
Order <- c("NA","NA","Amphipoda","Cumacea","NA","NA","Amphipoda","Decapoda","Euphausiacea","Calanioda","NA","Gadiformes",
"NA","NA","NA","NA","Gadiformes","Gadiformes","NA","NA","NA","NA")                     
Species <- c("Nephtys sp.","Nereis sp.","Gammarus sp.","Diastylis sp.","Axinella sp.","Ph. Sipunculida","Themisto abyssorum","Decapod larvae (Zoea)",
"Thysanoessa sp.","Centropages typicus","Ophiuroidea larvae","Gadus morhua eggs / larvae","Etmopterus spinax","Amblyraja radiata",
"Chimaera monstrosa","Clupea harengus","Melanogrammus aeglefinus","Gadus morhua","Thalassiosira sp.","Cylindrotheca closterium",
"Phaeocystis pouchetii","Ph. Dinoflagellata")   
dat <- data.frame(Group, Domain, Kingdom, Phylum, Class, Order, Species)
dat

我想得到一个树状图（聚类分析），并使用 Domain 作为第一个切割点，Kindom 作为第二个，Phylum 作为第三个，等等。应该忽略缺失值（没有切割点，而是一条直线）。组应用作标签的着色类别。

我有点不确定如何从这个数据帧中制作一个距离矩阵。R有很多系统发育树包，他们似乎想要newick数据/DNA/其他高级信息。因此，我们将不胜感激。

4

2 回答 2

7

回答我自己的问题可能有点蹩脚，但我找到了一个更简单的解决方案。也许有一天它会帮助某人。

library(ape)
taxa <- as.phylo(~Kingdom/Phylum/Class/Order/Species, data = dat)

col.grp <- merge(data.frame(Species = taxa$tip.label), dat[c("Species", "Group")], by = "Species", sort = F)

cols <- ifelse(col.grp$Group == "Benthos", "burlywood4", ifelse(col.grp$Group == "Zooplankton", "blueviolet", ifelse(col.grp$Group == "Fish", "dodgerblue", ifelse(col.grp$Group == "Phytoplankton", "darkolivegreen2", ""))))

plot(taxa, type = "cladogram", tip.col = cols)

请注意，所有列都必须是因子。这演示了 R 的工作流程。虽然代码本身只有几行 =)，但找出一些东西需要一周的时间

在此处输入图像描述

于 2012-03-30T08:02:02.333 回答
3

如果您想手动绘制树（这可能不是最好的方法），您可以按如下方式开始（这不是一个完整的答案：颜色缺失，边缘太长）。这假设数据已经排序。

# Data: remove Group
dat <- data.frame(Domain, Kingdom, Phylum, Class, Order, Species)

# Start a new plot
par(mar=c(0,0,0,0))
plot(NA, xlim=c(0,ncol(dat)+1), ylim=c(0,nrow(dat)+1), 
  type="n", axes=FALSE, xlab="", ylab="", main="")

# Compute the position of each node and find all the edges to draw
positions <- NULL
links <- NULL
for(k in 1:ncol(dat)) {
  y <- tapply(1:nrow(dat), dat[,k], mean)
  y <- y[ names(y) != "NA" ]
  positions <- rbind( positions, data.frame(
    name = names(y),
    x = k,
    y = y
  ))
}
links <- apply( dat, 1, function(u) { 
  u <- u[ !is.na(u) & u != "NA" ]
  cbind(u[-length(u)],u[-1]) 
} )
links <- do.call(rbind, links)
rownames(links) <- NULL
links <- unique(links[ order(links[,1], links[,2]), ])

# Draw the edges
for(i in 1:nrow(links)) {
  from <- positions[links[i,1],]
  to   <- positions[links[i,2],]
  lines( c(from$x, from$x, to$x), c(from$y, to$y, to$y) )
}

# Add the text
text(positions$x, positions$y, label=positions$name)
于 2012-03-28T10:19:47.053 回答