R语言教程，去除重复的蛋白质、基因互作关系

有的时候，蛋白质互作关系会出现重复，比如说我们有两列数据框，蛋白质a和蛋白质b可能会出现多次。

> df <-data.frame(c("a", "a", "a", "c", "c", "c", 'b', 'b'),
+                 c("a", "b", "c", "a", "b", "c", 'a', 'c'), 
+                 stringsAsFactors=F)
> 
> colnames(df)<-c("c1", "c2")
> 
> df
  c1 c2
1  a  a
2  a  b
3  a  c
4  c  a
5  c  b
6  c  c
7  b  a
8  b  c
> 
> 
> apply(df, 1, sort)
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8]
[1,] "a"  "a"  "a"  "a"  "b"  "c"  "a"  "b" 
[2,] "a"  "b"  "c"  "c"  "c"  "c"  "b"  "c" 
> 
> t(apply(df, 1, sort))
     [,1] [,2]
[1,] "a"  "a" 
[2,] "a"  "b" 
[3,] "a"  "c" 
[4,] "a"  "c" 
[5,] "b"  "c" 
[6,] "c"  "c" 
[7,] "a"  "b" 
[8,] "b"  "c" 
> 
> as.data.frame(t(apply(df, 1, sort)))
  V1 V2
1  a  a
2  a  b
3  a  c
4  a  c
5  b  c
6  c  c
7  a  b
8  b  c
> 
> unique(as.data.frame(t(apply(df, 1, sort))))
  V1 V2
1  a  a
2  a  b
3  a  c
5  b  c
6  c  c
> 
> 
> df_unique <- unique(as.data.frame(t(apply(df, 1, sort))))
> rownames(df_unique) <- 1:nrow(df_unique)
> df_unique
  V1 V2
1  a  a
2  a  b
3  a  c
4  b  c
5  c  c

df <-data.frame(c("a", "a", "a", "c", "c", "c", 'b', 'b'),
                c("a", "b", "c", "a", "b", "c", 'a', 'c'), 
                stringsAsFactors=F)

colnames(df)<-c("c1", "c2")

df


apply(df, 1, sort)

t(apply(df, 1, sort))

as.data.frame(t(apply(df, 1, sort)))

unique(as.data.frame(t(apply(df, 1, sort))))


df_unique <- unique(as.data.frame(t(apply(df, 1, sort))))
rownames(df_unique) <- 1:nrow(df_unique)
df_unique