|
.1300574 0.1190069 0.7666394 0.28407356 3
[4,] -0.9125118 0.1799797 0.5045226 0.2596132 -0.58052230 4
[5,] 1.0000000 2.0000000 3.0000000 4.0000000 5.00000000 5
[6,] 2.0000000 10.0000000 11.0000000 13.0000000 4.00000000 6
[7,] -1.2649111 -0.6324555 0.0000000 0.6324555 1.26491106 7
> cbind(a, seven=1:7)
seven
[1,] -0.4125356 0.1219293 -0.4763589 -0.9717165 1.09162243 1
[2,] 1.8778966 -0.1171794 2.9295352 1.3383662 -0.03269026 2
[3,] 0.8754092 0.1300574 0.1190069 0.7666394 0.28407356 3
[4,] -0.9125118 0.1799797 0.5045226 0.2596132 -0.58052230 4
[5,] 1.0000000 2.0000000 3.0000000 4.0000000 5.00000000 5
[6,] 2.0000000 10.0000000 11.0000000 13.0000000 4.00000000 6
[7,] -1.2649111 -0.6324555 0.0000000 0.6324555 1.26491106 7
# rbind: row bind
> rbind(a,1:5)
[,1] [,2] [,3] [,4] [,5]
[1,] -0.4125356 0.1219293 -0.4763589 -0.9717165 1.09162243
[2,] 1.8778966 -0.1171794 2.9295352 1.3383662 -0.03269026
[3,] 0.8754092 0.1300574 0.1190069 0.7666394 0.28407356
[4,] -0.9125118 0.1799797 0.5045226 0.2596132 -0.58052230
[5,] 1.0000000 2.0000000 3.0000000 4.0000000 5.00000000
[6,] 2.0000000 10.0000000 11.0000000 13.0000000 4.00000000
[7,] -1.2649111 -0.6324555 0.0000000 0.6324555 1.26491106
[8,] 1.0000000 2.0000000 3.0000000 4.0000000 5.00000000
# 计算每一行的mad (中值绝对偏差，一般认为比方差的鲁棒性更强，更少受异常值的影响，更能反映数据间的差异)1表示矩阵行，2表示矩阵列，也可以是c(1,2)
> apply(a,1,mad)
[1] 0.7923976 2.0327283 0.2447279 0.4811672 1.4826000 4.4478000 0.9376786
# 计算每一行的var (方差)
# apply表示对数据（第一个参数）的每一行 (第二个参数赋值为1) 或每一列 (2)操作。最后返回一个列表
> apply(a,1,var)
[1] 0.6160264 1.6811161 0.1298913 0.3659391 2.5000000 22.5000000 1.0000000
# 计算每一列的平均值
> apply(a,2,mean)
[1] 0.4519068 1.6689045 2.4395294 2.7179083 1.5753421
# 取出中值绝对偏差大于0.5的行
> b = a[apply(a,1,mad)>0.5,]
> b
[,1] [,2] [,3] [,4] [,5]
[1,] -0.4125356 0.1219293 -0.4763589 -0.9717165 1.09162243
[2,] 1.8778966 -0.1171794 2.9295352 1.3383662 -0.03269026
[3,] 1.0000000 2.0000000 3.0000000 4.0000000 5.00000000
[4,] 2.0000000 10.0000000 11.0000000 13.0000000 4.00000000
[5,] -1.2649111 -0.6324555 0.0000000 0.6324555 1.26491106
# 矩阵按照mad的大小降序排列
> c = b[order(apply(b,1,mad), decreasing=T),]
> c
[,1] [,2] [,3] [,4] [,5]
[1,] 2.0000000 10.0000000 11.0000000 13.0000000 4.00000000
[2,] 1.8778966 -0.1171794 2.9295352 1.3383662 -0.03269026
[3,] 1.0000000 2.0000000 3.0000000 4.0000000 5.00000000
[4,] -1.2649111 -0.6324555 0.0000000 0.6324555 1.26491106
[5,] -0.4125356 0.1219293 -0.4763589 -0.9717165 1.09162243
> rownames(c) <- paste('Gene', letters[1:5], sep="_")
> colnames(c) <- toupper(letters[1:5])
> c
A B C D E
Gene_a 2.0000000 10.0000000 11.0000000 13.0000000 4.00000000
Gene_b 1.8778966 -0.1171794 2.9295352 1.3383662 -0.03269026
Gene_c 1.0000000 2.0000000 3.0000000 4.0000000 5.00000000
Gene_d -1.2649111 -0.6324555 0.0000000 0.6324555 1.26491106
Gene_e -0.4125356 0.1219293 -0.4763589 -0.9717165 1.09162243
# 矩阵转置
> expr = t(c)
> expr
Gene_a Gene_b Gene_c Gene_d Gene_e
A 2 1.87789657 1 -1.2649111 -0.4125356
B 10 -0.11717937 2 -0.6324555 0.1219293
C 11 2.92953522 3 0.0000000 -0.4763589
D 13 1.33836620 4 0.6324555 -0.9717165
E 4 -0.03269026 5 1.2649111 1.0916224
# 矩阵值的替换
> expr2 = expr
> expr2[expr2<0] = 0
> expr2
Gen |