2021生信技能树R语言终极练习题

生信技能树2021生信入门线上课笔记，需要结合课程讲解服用

1.使用循环，对iris的1到4列分别画点图（plot）
方案1：我的答案

参考https://www.jianshu.com/p/4b7f3b9e4cf2

> library(patchwork)
> library(ggplot2)
> p=list()
> for(i in 1:4) {
+   p[[i]] = ggplot(data = iris, aes(x = 1:nrow(iris), y = !!iris[, i])) +
+     geom_point(aes(color = Species))+
+     labs(x = "Number", y = colnames(iris)[i], title = "")
+ }
> n=wrap_plots(p,nrow=2,guides = 'collect')
> n
> ggsave(n,filename = "practice1.png")

方案1.png

方案2：老师的参考答案

par(mfrow = c(2,2))
for(i in 1:4){
  plot(iris[,i],col = iris[,5])
}

方案2.png

2.生成一个随机数（rnorm）组成的10行6列的矩阵，列名为sample1，sample2….sample6，行名为gene1，gene2…gene10，分组为sample1、2、3属于A组，sample4、5、6属于B组。用循环对每个基因画ggplot2箱线图，并尝试拼图。
方案1：导出成单独的图再拼图

m=matrix(rnorm(1:60),nrow = 10);m
colnames(m)=paste0('sample',1:6)
rownames(m)=paste0('gene',1:10)
n=t(m);n
n=as.data.frame(n)
class(n)
#增加列
library(dplyr)
n=mutate(n,group=rep(c('A','B'),each=3));n

#画图
library(ggplot2)
plot_list =list()
for (i in 1:(ncol(n)-1)) { 
     x = ggplot(data=n,aes(x=group, y=n[,i],fill=group)) + 
       stat_boxplot(geom ='errorbar', width = 0.3)+
       geom_boxplot( width = 0.3)
     plot_list[[i]] = x+labs(x = "Group", y = colnames(n)[i], title = "") 
}
#保存图
for (i in 1:(ncol(n)-1)) { 
       file_name = paste("practice2_", i, ".tiff", sep="") 
       tiff(file_name) 
       print(plot_list[[i]]) 
       dev.off() 
}

方案1.png

方案2：老师的答案参考

#生成矩阵
exp = matrix(rnorm(60),nrow = 10)
colnames(exp) <- paste0("sample",1:6)
rownames(exp) <- paste0("gene",1:10)
exp[1:4,1:4]
#dat = cbind(t(exp),group = rep(c("A","B"),each = 3))
dat = data.frame(t(exp))
dat = mutate(dat,group = rep(c("A","B"),each = 3))
p = list()
library(ggplot2)
for(i in 1:(ncol(dat)-1)){
  p[[i]] = ggplot(data = dat,aes_string(x = "group",y=colnames(dat)[i]))+
    geom_boxplot(aes(color = group))+
    geom_jitter(aes(color = group))+
    theme_bw()
}
library(patchwork)
wrap_plots(p,nrow = 2,guides = "collect")

# 分面也行的。
exp = matrix(rnorm(60),nrow = 10)
colnames(exp) <- paste0("sample",1:6)
rownames(exp) <- paste0("gene",1:10)
exp[1:4,1:4]
dat = data.frame(t(exp))
dat = mutate(dat,group = rep(c("A","B"),each = 3))
library(tidyr)
dat2 = gather(dat,key = "gene",value = "expression",-group)
ggplot(data = dat2)+
  geom_boxplot(aes(x = group,y = expression,color = group))+
  theme_bw()+
  facet_wrap(~gene,nrow = 2)

image.png
分面.png

方案3：基于老师的答案优化我的答案

#生成矩阵
m=matrix(rnorm(1:60),nrow = 10);m
colnames(m)=paste0('sample',1:6)
rownames(m)=paste0('gene',1:10)
n=t(m);n
n=as.data.frame(n)
class(n)
#增加列
library(dplyr)
n=mutate(n,group=rep(c('A','B'),each=3));n

#画图
library(ggplot2)
plot_list =list()
for (i in 1:(ncol(n)-1)) { 
  plot_list[[i]]  = ggplot(data=n,aes(x=group, y=!!n[,i],fill=group)) + 
    stat_boxplot(geom ='errorbar', width = 0.3)+
    geom_boxplot( width = 0.3)+
    labs(x = "Group", y = colnames(n)[i], title = "") 
}
#拼图
library(patchwork)
wrap_plots(plot_list,nrow = 2,guides = "collect")

方案3.png

3. 模拟出几个类似的文件，用R实现批量重命名

> folder<-setwd('D:/Desktop/practice/test')
> files<-list.files(folder)
> for (f in files){
+   newname<-sub('test','practice',f)
+   file.rename(f,newname)
+ }
dir()
 [1] "practice2_1.png"  "practice2_10.png"
 [3] "practice2_2.png"  "practice2_3.png" 
 [5] "practice2_4.png"  "practice2_5.png" 
 [7] "practice2_6.png"  "practice2_7.png" 
 [9] "practice2_8.png"  "practice2_9.png"

修改前.png
修改后.png