生信入门马拉松之R语言基础-脚本项目管理、条件循环、表达矩阵和一丢丢数据挖掘(Day 7)

#ifelse()+str_detect(),王炸
samples = c("tumor1","tumor2","tumor3","normal1","normal2","normal3")
k1 = str_detect(samples,"tumor");k1
ifelse(k1,"tumor","normal")#检测samples中是否含有tumor关键词。
k2 = str_detect(samples,"normal");k2
ifelse(k2,"tumor","normal")#堪称学术造假的没有报错的错误！！！！！！
ifelse(k2,"normal","tumor")#检测samples中是否含有normal关键词。

#### (3)多个条件
#代码1
i = 0
if (i>0){
  print('+')
} else if (i==0) {
  print('0')
} else if (i< 0){
  print('-')
}#多个条件
#代码2
ifelse(i>0,"+",ifelse(i<0,"-","0"))#嵌套！！！代码2实现结果和代码1相同

library(dplyr)
x = c(-1,-1,4,5,2,0)
case_when(x>0 ~ "A",
          x==0 ~ "0",
          T ~"B")#取代不易读的ifelse函数。跟多个条件的两句代码比较看哈！！

load("deg.Rdata")
k1 = deg$a< -1 & deg$b <0.05
k2 = deg$a>1 & deg$b <0.05
x <- ifelse(k1,"down",ifelse(k2,"up","no"))
table(x)


a <- deg$a
b <- deg$b
x <- ifelse((a< -1 & b<0.05),"down",ifelse((a>1 & b<0.05),"up","no"))#我的错误代码，小洁老师曾经讲过的点，我又犯了是a< -1或a<(-1),而不是a<-1,<-是赋值符号，我这样写a<-1，相当于又将a赋值了，所以结果错误。
table(x)

for( i in 1:4){
  print(i)
}#for循环跑4次，i在第一次循环是1，第二次是2.。。第四次是4。

#批量画图
par(mfrow = c(2,2))
for(i in 1:4){
  plot(iris[,i],col = iris[,5])
}
#批量装包
pks = c("tidyr","dplyr","stringr")
for(g in pks){
  if(!require(g,character.only = T))
    install.packages(g,ask = F,update = F)#参数先忽略，可以自己探索查询看意思哦！

test<- iris[1:6,1:4]

apply(test, 2, mean)#对test每一列求平均值
apply(test, 1, sum)#对test每一行求和

### 2.lapply(list, FUN, …) 
# 对列表/向量中的每个元素实施相同的操作

lapply(1:4,rnorm)

x = list(a = 1:10,
         b = rnorm(16),
         c = seq(1,3,0.1))
slpply(x,length)#返回结果是个列表，用sapply(x,length)代码会返回一个向量

test1 <- data.frame(name = c('jimmy','nicker','Damon','Sophie'), 
                    blood_type = c("A","B","O","AB"))
test1
test2 <- data.frame(name = c('Damon','jimmy','nicker','tony'),
                    group = c("group1","group1","group2","group2"),
                    vision = c(4.2,4.3,4.9,4.5))
test2
library(dplyr)
inner_join(test1,test2,by="name")
left_join(test1,test2,by="name")#左边更重要，右边的有的留没有不留
right_join(test1,test2,by="name")#右连接
full_join(test1,test2,by="name")#左右数据都保留

x= rnorm(30)
tail(sort(x),5)
head(sort(x,decreasing = T),5)

#1. 加载test1.Rdata，将两个数据框按照probe_id列连接在一起，按共同列取交集
load("test1.Rdata")
library(dplyr)
merge1 <- merge(dat,ids,by = "probe_id")
merge <- inner_join(dat,ids,by="probe_id")
class(merge)
#2. 找出logFC最小的10个基因和logFC最大的10个基因(symbol列就是基因名)
x <- arrange(merge,logFC)
x
head(x$symbol,10)

tail(x$symbol,10)

# 表达矩阵
set.seed(10086)#使rnorm返回的可重复需要加上的代码。
exp = matrix(rnorm(18),ncol = 6)
exp = round(exp,2)#四舍五入round(exp)，取小数点后两位的函数round(exp,2)
rownames(exp) = paste0("gene",1:3)
colnames(exp) = paste0("test",1:6)
exp[,1:3] = exp[,1:3]+1
exp


library(tidyr)
library(tibble)
library(dplyr)
dat = t(exp) %>% 
  as.data.frame() %>% 
  rownames_to_column() %>% 
  mutate(group = rep(c("control","treat"),each = 3))
#rownames_to_colum()函数可以将行名改为一列

pdat = dat%>% 
  pivot_longer(cols = starts_with("gene"),
               names_to = "gene",
               values_to = "count")