R语言学习-绘制热图初步

> txt <- "ID;Zygote;2_cell;4_cell;8_cell
+ Gene_1;1;2;3;4
+ Gene_2;6;5;4;5
+ Gene_3;0.6;0.5;0.4;0.4"
> txt
[1] "ID;Zygote;2_cell;4_cell;8_cell
Gene_1;1;2;3;4
Gene_2;6;5;4;5
Gene_3;0.6;0.5;0.4;0.4"
> data2 <- read.table(text = txt,sep = ";",header = T,row.names = 1)  ##还可以这样创建数据框呢
> data2  ##列名中以数字开头的列名都加上了X。所以要尽量避免命名时以数字开头。加上check.names = F 可取消加X。
       Zygote X2_cell X4_cell X8_cell
Gene_1    1.0     2.0     3.0     4.0
Gene_2    6.0     5.0     4.0     5.0
Gene_3    0.6     0.5     0.4     0.4
> data2 <- read.table(text = txt,sep = ";",header = T,row.names = 1,check.names = F)
> data2
       Zygote 2_cell 4_cell 8_cell
Gene_1    1.0    2.0    3.0    4.0
Gene_2    6.0    5.0    4.0    5.0
Gene_3    0.6    0.5    0.4    0.4

> txt <- "ID;Zygote;2_cell;4_cell;8_cell;  ##这里句尾不能有分号
+ + Gene_1;1;2;3;4
+ + Gene_2;6;5;4;5
+ + Gene_3;0.6;0.5;0.4;0.4"
> data3 <- read.table(text = txt,sep = ";",header = T,row.names = 1)
Error in scan(file = file, what = what, sep = sep, quote = quote, dec = dec,  : 
  line 1 did not have 6 elements

##开始创建数据框

#先用matrix()将vector转变为矩阵，在as.data.frame()
#ncol：指定列数
#byrow = T：先按行填充vector内容，我还以为有bycol，后面试了下，没有这个参数!_!
> data <- c(1:6,6:1,6:1,1:6,(6:1)/10,(1:6)/10,(1:6)/10,(6:1)/10,1:6,6:1,6:1,1:6,6:1,1:6,1:6,6:1)
> data <- as.data.frame(matrix(data,ncol = 12,byrow = T))
> data
   V1  V2  V3  V4  V5  V6  V7  V8  V9 V10 V11 V12
1 1.0 2.0 3.0 4.0 5.0 6.0 6.0 5.0 4.0 3.0 2.0 1.0
2 6.0 5.0 4.0 3.0 2.0 1.0 1.0 2.0 3.0 4.0 5.0 6.0
3 0.6 0.5 0.4 0.3 0.2 0.1 0.1 0.2 0.3 0.4 0.5 0.6
4 0.1 0.2 0.3 0.4 0.5 0.6 0.6 0.5 0.4 0.3 0.2 0.1
5 1.0 2.0 3.0 4.0 5.0 6.0 6.0 5.0 4.0 3.0 2.0 1.0
6 6.0 5.0 4.0 3.0 2.0 1.0 1.0 2.0 3.0 4.0 5.0 6.0
7 6.0 5.0 4.0 3.0 2.0 1.0 1.0 2.0 3.0 4.0 5.0 6.0
8 1.0 2.0 3.0 4.0 5.0 6.0 6.0 5.0 4.0 3.0 2.0 1.0
> data_bycol <- c(1:6,6:1,6:1,1:6,(6:1)/10,(1:6)/10,(1:6)/10,(6:1)/10,1:6,6:1,6:1,1:6,6:1,1:6,1:6,6:1)
> data <- as.data.frame(matrix(data_bycol,ncol = 12,bycol = T))
Error in matrix(data_bycol, ncol = 12, bycol = T) : 参数没有用(bycol = T)

#增加列名
#colnames()
> colnames(data) <- c("Zygote","2_cell","4_cell","8_cell","Morula","ICM","ESC","4 week PGC","7 week PGC","10 week PGC","17 week PGC","00cyte")
> data
  Zygote 2_cell 4_cell 8_cell Morula ICM ESC 4 week PGC 7 week PGC
1    1.0    2.0    3.0    4.0    5.0 6.0 6.0        5.0        4.0
2    6.0    5.0    4.0    3.0    2.0 1.0 1.0        2.0        3.0
3    0.6    0.5    0.4    0.3    0.2 0.1 0.1        0.2        0.3
4    0.1    0.2    0.3    0.4    0.5 0.6 0.6        0.5        0.4
5    1.0    2.0    3.0    4.0    5.0 6.0 6.0        5.0        4.0
6    6.0    5.0    4.0    3.0    2.0 1.0 1.0        2.0        3.0
7    6.0    5.0    4.0    3.0    2.0 1.0 1.0        2.0        3.0
8    1.0    2.0    3.0    4.0    5.0 6.0 6.0        5.0        4.0
  10 week PGC 17 week PGC 00cyte
1         3.0         2.0    1.0
2         4.0         5.0    6.0
3         0.4         0.5    0.6
4         0.3         0.2    0.1
5         3.0         2.0    1.0
6         4.0         5.0    6.0
7         4.0         5.0    6.0
8         3.0         2.0    1.0
#增加行名
#rownames()
> rownames(data) <- paste("Gene",1:8,sep = "_")
> data
       Zygote 2_cell 4_cell 8_cell Morula ICM ESC 4 week PGC 7 week PGC
Gene_1    1.0    2.0    3.0    4.0    5.0 6.0 6.0        5.0        4.0
Gene_2    6.0    5.0    4.0    3.0    2.0 1.0 1.0        2.0        3.0
Gene_3    0.6    0.5    0.4    0.3    0.2 0.1 0.1        0.2        0.3
Gene_4    0.1    0.2    0.3    0.4    0.5 0.6 0.6        0.5        0.4
Gene_5    1.0    2.0    3.0    4.0    5.0 6.0 6.0        5.0        4.0
Gene_6    6.0    5.0    4.0    3.0    2.0 1.0 1.0        2.0        3.0
Gene_7    6.0    5.0    4.0    3.0    2.0 1.0 1.0        2.0        3.0
Gene_8    1.0    2.0    3.0    4.0    5.0 6.0 6.0        5.0        4.0
       10 week PGC 17 week PGC 00cyte
Gene_1         3.0         2.0    1.0
Gene_2         4.0         5.0    6.0
Gene_3         0.4         0.5    0.6
Gene_4         0.3         0.2    0.1
Gene_5         3.0         2.0    1.0
Gene_6         4.0         5.0    6.0
Gene_7         4.0         5.0    6.0
Gene_8         3.0         2.0    1.0
> class(data)
[1] "data.frame"
###paste(a,b,c...,sep = " ")
###连接a b c...多个R对象，将其转变为字符串之后连起来

> paste(1:12, c("st", "nd", "rd", rep("th", 9)))
 [1] "1 st"  "2 nd"  "3 rd"  "4 th"  "5 th"  "6 th"  "7 th"  "8 th" 
 [9] "9 th"  "10 th" "11 th" "12 th"
> paste(1:12, c("st", "nd", "rd", rep("th", 9)),sep = "")
 [1] "1st"  "2nd"  "3rd"  "4th"  "5th"  "6th"  "7th"  "8th"  "9th"  "10th"
[11] "11th" "12th"
> paste0(1:12, c("st", "nd", "rd", rep("th", 9)))  ##看起来paste0()和paste(...,sep = "")是等价的
 [1] "1st"  "2nd"  "3rd"  "4th"  "5th"  "6th"  "7th"  "8th"  "9th"  "10th"
[11] "11th" "12th"
> paste(1:12, c("st", "nd", "rd", rep("th", 9)),13:24,sep = "")
 [1] "1st13"  "2nd14"  "3rd15"  "4th16"  "5th17"  "6th18"  "7th19" 
 [8] "8th20"  "9th21"  "10th22" "11th23" "12th24"

###转换数据格式

#先安装并加载所需R包

> install.packages(c("reshape2","ggplot2")) ##复习一下同时安装多个包
> library(reshape2)
> library(ggplot2)

#转换数据之前，给data加上一列，使之与行名一致。

> data$ID <- rownames(data)##直接$ID创建新列，然后通过rownames()或者data的行名，赋值给data。有没有其他方式？我这里想了想用cbind()应该怎么实现
> data
       Zygote 2_cell 4_cell 8_cell Morula ICM ESC 4 week PGC 7 week PGC
Gene_1    1.0    2.0    3.0    4.0    5.0 6.0 6.0        5.0        4.0
Gene_2    6.0    5.0    4.0    3.0    2.0 1.0 1.0        2.0        3.0
Gene_3    0.6    0.5    0.4    0.3    0.2 0.1 0.1        0.2        0.3
Gene_4    0.1    0.2    0.3    0.4    0.5 0.6 0.6        0.5        0.4
Gene_5    1.0    2.0    3.0    4.0    5.0 6.0 6.0        5.0        4.0
Gene_6    6.0    5.0    4.0    3.0    2.0 1.0 1.0        2.0        3.0
Gene_7    6.0    5.0    4.0    3.0    2.0 1.0 1.0        2.0        3.0
Gene_8    1.0    2.0    3.0    4.0    5.0 6.0 6.0        5.0        4.0
       10 week PGC 17 week PGC 00cyte     ID
Gene_1         3.0         2.0    1.0 Gene_1
Gene_2         4.0         5.0    6.0 Gene_2
Gene_3         0.4         0.5    0.6 Gene_3
Gene_4         0.3         0.2    0.1 Gene_4
Gene_5         3.0         2.0    1.0 Gene_5
Gene_6         4.0         5.0    6.0 Gene_6
Gene_7         4.0         5.0    6.0 Gene_7
Gene_8         3.0         2.0    1.0 Gene_8
> data2 <- cbind(data,rownames(data))##没想到直接把rownames(data)作为新列名了。。。所以下面新建了一个列名
> data2
       Zygote 2_cell 4_cell 8_cell Morula ICM ESC 4 week PGC 7 week PGC
Gene_1    1.0    2.0    3.0    4.0    5.0 6.0 6.0        5.0        4.0
Gene_2    6.0    5.0    4.0    3.0    2.0 1.0 1.0        2.0        3.0
Gene_3    0.6    0.5    0.4    0.3    0.2 0.1 0.1        0.2        0.3
Gene_4    0.1    0.2    0.3    0.4    0.5 0.6 0.6        0.5        0.4
Gene_5    1.0    2.0    3.0    4.0    5.0 6.0 6.0        5.0        4.0
Gene_6    6.0    5.0    4.0    3.0    2.0 1.0 1.0        2.0        3.0
Gene_7    6.0    5.0    4.0    3.0    2.0 1.0 1.0        2.0        3.0
Gene_8    1.0    2.0    3.0    4.0    5.0 6.0 6.0        5.0        4.0
       10 week PGC 17 week PGC 00cyte     ID rownames(data)
Gene_1         3.0         2.0    1.0 Gene_1         Gene_1
Gene_2         4.0         5.0    6.0 Gene_2         Gene_2
Gene_3         0.4         0.5    0.6 Gene_3         Gene_3
Gene_4         0.3         0.2    0.1 Gene_4         Gene_4
Gene_5         3.0         2.0    1.0 Gene_5         Gene_5
Gene_6         4.0         5.0    6.0 Gene_6         Gene_6
Gene_7         4.0         5.0    6.0 Gene_7         Gene_7
Gene_8         3.0         2.0    1.0 Gene_8         Gene_8
> data2 <- cbind(data,ID_2 = rownames(data)) ##bingo！
> data2
       Zygote 2_cell 4_cell 8_cell Morula ICM ESC 4 week PGC 7 week PGC
Gene_1    1.0    2.0    3.0    4.0    5.0 6.0 6.0        5.0        4.0
Gene_2    6.0    5.0    4.0    3.0    2.0 1.0 1.0        2.0        3.0
Gene_3    0.6    0.5    0.4    0.3    0.2 0.1 0.1        0.2        0.3
Gene_4    0.1    0.2    0.3    0.4    0.5 0.6 0.6        0.5        0.4
Gene_5    1.0    2.0    3.0    4.0    5.0 6.0 6.0        5.0        4.0
Gene_6    6.0    5.0    4.0    3.0    2.0 1.0 1.0        2.0        3.0
Gene_7    6.0    5.0    4.0    3.0    2.0 1.0 1.0        2.0        3.0
Gene_8    1.0    2.0    3.0    4.0    5.0 6.0 6.0        5.0        4.0
       10 week PGC 17 week PGC 00cyte     ID   ID_2
Gene_1         3.0         2.0    1.0 Gene_1 Gene_1
Gene_2         4.0         5.0    6.0 Gene_2 Gene_2
Gene_3         0.4         0.5    0.6 Gene_3 Gene_3
Gene_4         0.3         0.2    0.1 Gene_4 Gene_4
Gene_5         3.0         2.0    1.0 Gene_5 Gene_5
Gene_6         4.0         5.0    6.0 Gene_6 Gene_6
Gene_7         4.0         5.0    6.0 Gene_7 Gene_7
Gene_8         3.0         2.0    1.0 Gene_8 Gene_8