种系进化树分析和构建工具R工具包S

最新推荐文章于 2024-10-02 12:57:07 发布

m0_57889860

最新推荐文章于 2024-10-02 12:57:07 发布

阅读量595

点赞数 26

分类专栏：程序员文章标签： r语言开发语言

本文链接：https://blog.csdn.net/m0_57889860/article/details/138319552

版权

程序员专栏收录该内容

115 篇文章 0 订阅

订阅专栏


* 进行系统发育相关的分析：

phylotools_analysis(tree)


1. 数据可视化：


* 绘制系统发育树：

plot_tree(tree)


* 绘制节点度的分布图：

plot_degree(tree)


* 绘制节点高度的分布图：

plot_height(tree)


##  github使用示例

library(“phytools”) # load the “phytools” package.
example<-read.csv(“example.splist.csv”,header=T) # read in the example species list.
phylo<-read.tree(“PhytoPhylo.tre”) # read in the megaphylogeny.
nodes<-read.csv(“nodes.csv”,header=T) # read in the nodes information of the megaphylogeny.
result<-S.PhyloMaker(spList=example, tree=phylo, nodes=nodes) # run the function S.PhyloMaker.
str(result) # the structure of the ouput of S.PhyloMaker.
par(mfrow=c(1,3),mar=c(0,0,1,0)) # show the phylogenies of the three scenarios.
plot(result $S ce na r i o .1, ce x = 1.1, main = " S ce na r i o n O n e ") pl o t (res u lt$ Scenario.2,cex=1.1,main=“Scenarion Two”)
plot(result$Scenario.3,cex=1.1,main=“Scenarion Three”)



## S.PhyloMaker完成分析脚本（有动手能力的可以改改）：

S.PhyloMaker<-function (tree, spList, nodes, output.spList = T, scenarios = c(“S1”, “S2”, “S3”))
{
options(scipen=999)
tree0 <- tree
spList[sapply(spList, is.factor)] <- lapply(spList[sapply(spList, is.factor)], as.character)
if (any(duplicated(spList $KaTeX parse error: Expected '}', got 'EOF' at end of input: \dots print(spList$ species[duplicated(spList $KaTeX parse error: Expected 'EOF', got '}' at position 18: \dotsecies)]) }̲ spList <- \dots$ species), ]
spList.original <- spList
spList $species <- gsub(" ", "_", spList$ species)
spList $species <- gsub("(^[[:alpha:]])", "\\U\\1", spList$ species, perl = TRUE)
spList $genus <- gsub("(^[[:alpha:]])", "\\U\\1", spList$ genus, perl = TRUE)
spList $family <- gsub("(^[[:alpha:]])", "\\U\\1", spList$ family, perl = TRUE)
rnN <- data.frame(node.label = paste(“N”, 1:length(tree $n o d e . l ab e l), se p = ""), or i N = t ree$ node.label, stringsAsFactors = FALSE)
nodes[,c(“level”,“family”,“genus”,“rn”,“bn”,“taxa”)]<-lapply(nodes[,c(“level”,“family”,“genus”,“rn”,“bn”,“taxa”)], as.character)
tree $n o d e . l ab e l < - p a s t e (" N ", 1 : l e n g t h (t ree$ node.label), sep = “”)
kk<-c()
for (i in 1:length(tree $KaTeX parse error: Expected '}', got 'EOF' at end of input: \dots,substring(tree$ tip.label[i],1,gregexpr(““,tree $KaTeX parse error: Expected 'EOF', got '}' at position 31: \dots1]][1]-1)) }̲ m<-data.fr\dots$ tip.label)
m<-merge(m,nodes[,c(“genus”,“family”)])
mX <- m
m <- m[,c(“genus”,“family”)]
m <- m[!duplicated(m $genus),] dimnames(m)[[2]][2] <- "family_in_PhytoPhylo" m<-m[,c("genus","family_in_PhytoPhylo")] m0 <- spList[!duplicated(spList$ genus), c(“genus”,“family”)]
dimnames(m0)[[2]][2] <- “family_in_spList”
mm<-merge(m0, m)
g<-mm[which(is.na(match(paste(mm $g e n u s, mm$ family_in_spList,sep=””),paste(mm $g e n u s, mm$ family_in_PhytoPhylo,sep=“")))),]
if (dim(g)[1]>0)
{
print(“Taxonomic classification not consistent between spList and PhytoPhylo.”)
print(g)
}
add.tip <- spList[which(is.na(match(spList $s p ec i es, t ree$ tip.label))), ]
status <- rep(“match(prune)”, dim(spList)[1])
status[which(is.na(match(spList $s p ec i es, t ree$ tip.label)))] <- “match(add)”
if (dim(add.tip)[1] == 0 & length(na.omit(match(spList $s p ec i es, t ree$ tip.label))) == 0)
stop(“Incorrect format of species list.”)
if (length(setdiff(spList $s p ec i es, t ree 0$ tip.label)) == 0 & length(na.omit(match(spList $s p ec i es, t ree$ tip.label))) > 0)
{
print(“There is no species needs to be added, all the species are pruned from PhytoPhylo.”)
splis <- spList.original
treeX <- drop.tip(tree0, setdiff(tree0 $t i p . l ab e l, s pl i s$ species))
splis $s t a t u s < - " ma t c h (p r u n e) " p h y l o 0 < - l i s t (S ce na r i o .1 = N ULL, S ce na r i o .2 = N ULL, S ce na r i o .3 = N ULL, Sp ec i es . l i s t = s pl i s) i f (" S 1"$ Scenario.1 <- treeX}
if (“S2” %in% scenarios) {phylo0 $KaTeX parse error: Expected 'EOF', got '}' at position 20: \dotsario.2 <- treeX}̲ if ("S\dots$ Scenario.3 <- treeX}
phylo0[sapply(phylo0, is.null)] <- NULL
return(phylo0)
stop()
}
add.tip $sor t < - "" a dd . t i p$ sort[which(!is.na(match(add.tip $g e n u s, n o d es [n o d es$ level == “G”, ] $g e n u s)))] < - " G 1" a dd . t i p$ sort[which(is.na(match(add.tip $g e n u s, n o d es [n o d es$ level == “G”, ] $KaTeX parse error: Expected 'EOF', got '&' at position 9: genus)) &̲ !is.na(match(a\dots$ family, nodes[nodes $l e v e l == " F ",]$ family)))] <- “F1”
add.tip $sor t [a dd . t i p$ sort == “F1”][duplicated(add.tip[add.tip $sor t == " F 1",]$ genus)] <- “F2”
a <- which(add.tip $KaTeX parse error: Expected '}', got 'EOF' at end of input: \dots print(add.tip$ species[a])
status[match(add.tip $s p ec i es [a], s p L i s t$ species)] <- “unmatch”
}
spList.original $s t a t u s < - s t a t u s i f (" S 1" t 1 < - t reer n N 1 < - r n N n G < - n o d es [n o d es$ level == “G”, ]
nF <- nodes[nodes $l e v e l == " F ",] d a t a < - a dd . t i p [a dd . t i p$ sort == “F1”, ]
if (dim(data)[1] > 0) {
for (i in 1:dim(data)[1]) {
n <- match(data $f ami l y [i], n F$ family)
g <- nF $g e n . n [n] s < - n F$ sp.n[n]
if (g == 1 & s == 1) {
num <- grep(nF $t a x a [n], t 1$ tip.label)
len <- t1 $e d g e . l e n g t h [ma t c h (n u m, t 1$ edge[, 2])]
t1 <- bind.tip(t1, tip.label = data $s p ec i es [i], e d g e . l e n g t h = l e n, w h ere = n u m, p os i t i o n = l e n) n F$ gen.n[n] <- g + 1
nF $s p . n [n] < - s + 1 n u m < - g re p (n F$ taxa[n], t1 $t i p . l ab e l) t 1$ node.label[match(t1 $e d g e [ma t c h (n u m, t 1$ edge[, 2]), 1], unique(t1 $e d g e [, 1]))] < - p a s t e (" NN ", t 1$ Nnode + 1, sep = “”)
rnN1 $n o d e . l ab e l [ma t c h (n F$ bn[n], rnN1 $n o d e . l ab e l)] < - p a s t e (" NN ", t 1$ Nnode + 1, sep = “”)
nF $bn [n] < - p a s t e (" NN ", t 1$ Nnode + 1, sep = “”)
nF $KaTeX parse error: Expected 'EOF', got '}' at position 33: \dots }̲ \dots$ edge[, 1])[match(nF $bn [n], t 1$ node.label)]
len <- nF $bn . b l [n] t 1 < - bin d . t i p (t 1, t i p . l ab e l = d a t a$ species[i], edge.length = len, where = num)
}
}
}
data <- add.tip[add.tip $KaTeX parse error: Expected '}', got 'EOF' at end of input: \dotsgrep(paste(data$ genus[i], "”, sep = “”), t1 $KaTeX parse error: Expected '}', got 'EOF' at end of input: \dots len <- t1$ edge.length[match(num, t1 $e d g e [, 2])] t 1 < - bin d . t i p (t 1, t i p . l ab e l = d a t a$ species[i], edge.length = len, where = num, position = len)
}
if (length(n) > 1) {
num <- fastMRCA(t1, t1 $t i p . l ab e l [min (n)], t 1$ tip.label[max(n)])
len <- fastDist(t1, t1 $t i p . l ab e l [min (n)], t 1$ tip.label[max(n)])/2
t1 <- bind.tip(t1, tip.label = data $KaTeX parse error: Expected 'EOF', got '}' at position 63: \dots }̲ \dots$ tip.label), which(!is.na(match(t1 $t i p . l ab e l, s p L i s t$ species))))
t1 <- drop.tip(t1, tip = toDrop)
Re <- which(!is.na(match(t1 $n o d e . l ab e l, r n N 1$ node.label)))
noRe <- which(is.na(match(t1 $n o d e . l ab e l, r n N 1$ node.label)))
t1 $n o d e . l ab e l [R e] < - r n N 1$ oriN[match(t1 $n o d e . l ab e l, r n N 1$ node.label)[Re]]
t1 $KaTeX parse error: Expected 'EOF', got '}' at position 28: \dotsoRe] <- "" }̲ else { \dots$ level == “G”, ]
nF <- nodes[nodes $l e v e l == " F ",] d a t a < - a dd . t i p [a dd . t i p$ sort == “F1”, ]
if (dim(data)[1] > 0) {
for (i in 1:dim(data)[1]) {
n <- match(data $f ami l y [i], n F$ family)
g <- nF $g e n . n [n] s < - n F$ sp.n[n]
if (g == 1 & s == 1) {
num <- grep(nF $t a x a [n], t 2$ tip.label)
len <- t2 $e d g e . l e n g t h [ma t c h (n u m, t 2$ edge[,2])] * sample((1:99)/100,1)
t2 <- bind.tip(t2, tip.label = data $s p ec i es [i], e d g e . l e n g t h = l e n, w h ere = n u m, p os i t i o n = l e n) n F$ gen.n[n] <- g + 1
nF $s p . n [n] < - s + 1 n u m < - g re p (d a t a$ species[i], t2 $t i p . l ab e l) t 2$ node.label[match(t2 $e d g e [ma t c h (n u m, t 2$ edge[, 2]), 1], unique(t2 $e d g e [, 1]))] < - p a s t e (" NN ", t 2$ Nnode + 1, sep = “”)
rnN2 $n o d e . l ab e l [ma t c h (n F$ bn[n], rnN2 $n o d e . l ab e l)] < - p a s t e (" NN ", t 2$ Nnode + 1, sep = “”)
nF $bn [n] < - p a s t e (" NN ", t 2$ Nnode + 1, sep = “”)
nF $KaTeX parse error: Expected 'EOF', got '}' at position 33: \dots }̲ \dots$ edge[, 1])[match(nF $bn [n], t 2$ node.label)]
len <- t2 $e d g e . l e n g t h [ma t c h (n u m, t 2$ edge[,2])] * sample((1:99)/100,1)
t2 <- bind.tip(t2, tip.label = data $s p ec i es [i], e d g e . l e n g t h = l e n, w h ere = n u m, p os i t i o n = l e n) n F$ gen.n[n] <- g + 1
nF $s p . n [n] < - s + 1 n u m < - g re p (d a t a$ species[i], t2 $t i p . l ab e l) t 2$ node.label[match(t2 $e d g e [ma t c h (n u m, t 2$ edge[, 2]), 1], unique(t2 $e d g e [, 1]))] < - p a s t e (" NN ", t 2$ Nnode + 1, sep = “”)
rnN2 $n o d e . l ab e l [ma t c h (n F$ bn[n], rnN2 $n o d e . l ab e l)] < - p a s t e (" NN ", t 2$ Nnode + 1, sep = “”)
nF $bn [n] < - p a s t e (" NN ", t 2$ Nnode + 1, sep = “”)
nF $bn . b l [n] < - n F$ bn.bl[n]+len
}
}
}
data <- add.tip[add.tip $KaTeX parse error: Expected '}', got 'EOF' at end of input: \dotsgrep(paste(data$ genus[i], “", sep = “”), t2 $KaTeX parse error: Expected '}', got 'EOF' at end of input: \dots len <- t2$ edge.length[match(num, t2 $e d g e [, 2])] * s am pl e ((1 : 99) /100, 1) t 2 < - bin d . t i p (t 2, t i p . l ab e l = d a t a$ species[i], edge.length = len, where = num, position = len)
}
if (length(n) > 1) {
num <- sample(n,1)
len <- t2 $e d g e . l e n g t h [ma t c h (n u m, t 2$ edge[, 2])] * sample((1:99)/100,1)
t2 <- bind.tip(t2, tip.label = data $KaTeX parse error: Expected 'EOF', got '}' at position 79: \dots }̲ \dots$ tip.label), which(!is.na(match(t2 $t i p . l ab e l, s p L i s t$ species))))
t2 <- drop.tip(t2, tip = toDrop)
Re <- which(!is.na(match(t2 $n o d e . l ab e l, r n N 2$ node.label)))
noRe <- which(is.na(match(t2 $n o d e . l ab e l, r n N 2$ node.label)))
t2 $n o d e . l ab e l [R e] < - r n N 2$ oriN[match(t2 $n o d e . l ab e l, r n N 2$ node.label)[Re]]
t2 $KaTeX parse error: Expected 'EOF', got '}' at position 28: \dotsoRe] <- "" }̲ else { \dots$ level == “G”, ]
nF <- nodes[nodes $l e v e l == " F ",] d a t a < - a dd . t i p [a dd . t i p$ sort == “F1”, ]
if (dim(data)[1] > 0) {
for (i in 1:dim(data)[1]) {
n <- match(data $f ami l y [i], n F$ family)
g <- nF $g e n . n [n] s < - n F$ sp.n[n]
if (g == 1 & s == 1) {
num <- grep(nF $t a x a [n], t 3$ tip.label)
len <- t3 $e d g e . l e n g t h [ma t c h (n u m, t 3$ edge[, 2])] * (2/3)
t3 <- bind.tip(t3, tip.label = data $s p ec i es [i], e d g e . l e n g t h = l e n, w h ere = n u m, p os i t i o n = l e n) n F$ gen.n[n] <- g + 1
nF $s p . n [n] < - s + 1 n u m < - g re p (n F$ taxa[n], t3 $t i p . l ab e l) t 3$ node.label[match(t3 $e d g e [ma t c h (n u m, t 3$ edge[, 2]), 1], unique(t3 $e d g e [, 1]))] < - p a s t e (" NN ", t 3$ Nnode + 1, sep = “”)
rnN3 $n o d e . l ab e l [ma t c h (n F$ bn[n], rnN3 $n o d e . l ab e l)] < - p a s t e (" NN ", t 3$ Nnode + 1, sep = “”)
nF $bn [n] < - p a s t e (" NN ", t 3$ Nnode + 1, sep = “”)
nF $KaTeX parse error: Expected 'EOF', got '}' at position 33: \dots }̲ \dots$ edge[, 1])[match(nF $bn [n], t 3$ node.label)]
if ((2/3)*nF $r n . b l [n] <= n F$ bn.bl[n]) { len <-(nF $r n . b l [n] - n F$ bn.bl[n])/2 }
if ((2/3)*nF $r n . b l [n] > n F$ bn.bl[n]) { len <-nF $r n . b l [n] * 2/3 - n F$ bn.bl[n] }
t3 <- bind.tip(t3, tip.label = data $s p ec i es [i], e d g e . l e n g t h = l e n, w h ere = n u m, p os i t i o n = l e n) n F$ gen.n[n] <- g + 1
nF $s p . n [n] < - s + 1 n u m < - u ni q u e (t 3$ edge[, 1])[match(nF $bn [n], t 3$ node.label)]
t3 $n o d e . l ab e l [ma t c h (t 3$ edge[match(num, t3 $e d g e [, 2]), 1], u ni q u e (t 3$ edge[, 1]))] <- paste(“NN”, t3 $N n o d e + 1, se p = "") r n N 3$ node.label[match(nF $bn [n], r n N 3$ node.label)]<- paste(“NN”, t3 $N n o d e + 1, se p = "") n F$ bn[n] <- paste(“NN”, t3 $N n o d e + 1, se p = "") n F$ bn.bl[n] <- len+nF $KaTeX parse error: Expected 'EOF', got '}' at position 26: \dots }̲ \dots$ edge[, 1])[match(nF $bn [n], t 3$ node.label)]
len <- nF $bn . b l [n] t 3 < - bin d . t i p (t 3, t i p . l ab e l = d a t a$ species[i], edge.length = len, where = num)
}
}
}
data <- add.tip[add.tip $KaTeX parse error: Expected '}', got 'EOF' at end of input: \dotsgrep(paste(data$ genus[i], "”, sep = “”), t3 $KaTeX parse error: Expected '}', got 'EOF' at end of input: \dots len <- t3$ edge.length[match(n, t3 $e d g e [, 2])] /2 t 3 < - bin d . t i p (t 3, t i p . l ab e l = d a t a$ species[i], edge.length = len, where = n, position = len)
nG $s p . n [ma t c h (d a t a$ genus[i], nG $g e n u s)] < - l e n g t h (n) + 1 n u < - g re p (p a s t e (d a t a$ genus[i], “_”, sep = “”), t3 $t i p . l ab e l) n u m < - f a s tMRC A (t 3, t 3$ tip.label[nu[1]], t3 $t i p . l ab e l [n u [2]]) t 3$ node.label[match(num, unique(t3 $e d g e [, 1]))] < - p a s t e (" NN ", t 3$ Nnode + 1, sep = “”)
rnN3 $n o d e . l ab e l [ma t c h (n G$ bn[n], rnN3 $n o d e . l ab e l)] < - p a s t e (" NN ", t 3$ Nnode + 1, sep = “”)
nG $bn [ma t c h (d a t a$ genus[i], nG $g e n u s)] < - p a s t e (" NN ", t 3$ Nnode + 1, sep = “”)
nG $bn . b l [ma t c h (d a t a$ genus[i], nG $KaTeX parse error: Expected 'EOF', got '}' at position 32: \dots }̲ \dots$ tip.label[min(n)], t3 $t i p . l ab e l [ma x (n)]) l e n < - a s . n u m er i c (b r an c hin g . t im es (t 3)) [ma t c h (n u m, u ni q u e (t 3$ edge[, 1]))]
t3 <- bind.tip(t3, tip.label = data $KaTeX parse error: Expected 'EOF', got '}' at position 61: \dots }̲ } \dots$ tip.label), which(!is.na(match(t3 $t i p . l ab e l, s p L i s t$ species))))
t3 <- drop.tip(t3, tip = toDrop)
Re <- which(!is.na(match(t3 $n o d e . l ab e l, r n N 3$ node.label)))
noRe <- which(is.na(match(t3 $n o d e . l ab e l, r n N 3$ node.label)))
t3 $n o d e . l ab e l [R e] < - r n N 3$ oriN[match(t3 $n o d e . l ab e l, r n N 3$ node.label)[Re]]
t3$node.label[noRe] <- “”
}
else {
t3 <- NULL
}
if (output.spList == FALSE)
spList <- NULL
phylo <- list(Scenario.1 = t1, Scenario.2 = t2, Scenario.3 = t3, Species.list = spList.original)

最全的Linux教程，Linux从入门到精通

======================

linux从入门到精通(第2版)
Linux系统移植
Linux驱动开发入门与实战
LINUX 系统移植第2版
Linux开源网络全栈详解从DPDK到OpenFlow

华为18级工程师呕心沥血撰写3000页Linux学习笔记教程

第一份《Linux从入门到精通》466页

====================

内容简介

====

本书是获得了很多读者好评的Linux经典畅销书**《Linux从入门到精通》的第2版**。本书第1版出版后曾经多次印刷，并被51CTO读书频道评为“最受读者喜爱的原创IT技术图书奖”。本书第﹖版以最新的Ubuntu 12.04为版本，循序渐进地向读者介绍了Linux 的基础应用、系统管理、网络应用、娱乐和办公、程序开发、服务器配置、系统安全等。本书附带1张光盘，内容为本书配套多媒体教学视频。另外,本书还为读者提供了大量的Linux学习资料和Ubuntu安装镜像文件，供读者免费下载。

华为18级工程师呕心沥血撰写3000页Linux学习笔记教程