我想计算df1 (class: data.frame):
中第一行与其余行之间的相关性df1 <- data.frame(
Ensembl_ID = c("ENSG00000000003", "ENSG00000000005", "ENSG00000000419",
"ENSG00000000457", "ENSG00000000460", "ENSG00000000938",
"ENSG00000000971", "ENSG00000001036", "ENSG00000001084",
"ENSG00000001167" ),
`logFC 1` = c(-0.834165161710272, 1.02199443531549,
-0.558658947885705, -0.390114219973209, -1.23551839713296,
3.11429434221998, 0.283932163407262, -1.16908518620064,
-0.597054772455507, -0.593624543273255),
`logFC 2` = c(-1.18531035488942, 0.423719727339646, -1.23261719368372,
0.0855281133529292, -1.52366830232278, 3.36692586561211,
1.00323690950956, -0.000211248816114964, -4.74738483548391,
-0.318176231083024),
`logFC 3` = c(-0.262659255267546, 1.3962481061442, -0.548673555705647,
-0.0149651083306594, -1.45458689193089, 2.54126941463459,
1.17711308509307, -1.19425284921181, 1.17788731755683,
-0.367897054652365 ),
`logFC 4` = c(-0.840752912305256, 0.536548846040064, -0.277409459604357,
-0.241073614962264, -0.875313153342293, 1.61789645804321,
0.412287101096504, -1.11846661523232, -2.6274528854429,
-0.760452698231182),
`logFC 5` = c(-0.968784779247286, -0.502809694119192, -0.231526399163731,
-0.530038395734114, -0.706006018337411, 3.58264357077653,
-0.127521010699219, 0.270523387217103, 1.68335644352003,
-0.314902131571829),
`logFC 6` = c(-0.481754175843152, -0.440784040523259, -0.532975340622715,
-0.182089795101371, -0.564807490336052, 1.74119896504534,
-0.96169805631325, -0.721782763145306, -0.433459827401695,
-0.727495835245995 ),
`logFC 7` = c(-0.889343429110847, 1.07937149728343, -0.215144871523998,
-0.92234350748557, -0.832108253417702, 2.02456082994848,
-0.0434322861759954, -0.523126561938426, -0.556984056084809,
-0.740331742513503),
`logFC 8` = c(-0.858141567384178, 1.87728717064375, -0.381047638414538,
-0.613568289061259, -1.92838339196505, 2.23393705735665,
0.635389543483408, -0.466053620529111, -1.50483745357134,
-1.33400859143521),
`logFC 9` = c(-0.486388736112514, 0.789390852922639, -0.869434195504952,
-0.70405854858187, -1.16488184095428, 2.91497178849082,
-2.10331904053714, -0.571130459068143, -0.219526004620518,
-0.301435496557957)
)
相关计算代码(我需要转置数据,因为cor函数要求列矩阵为x &y):
df2 <- cor(df1[1,],t(df1[2:10,]))
给出错误
Error in df1[2:10, ] : subscript out of bounds
然而,当我创建一个随机数据帧并运行相同的代码时,它工作得很好
# Creates a random matrix with 5 rows and 6 columns
mat=matrix(rnorm(30),5,6)
# Computes the correlation between the first row and the other 4 (cor function require transposed data)
cor(mat[1,],t(mat[2:5,]))
有人能帮我吗?请。欢迎提出任何建议。提前感谢
你可以改变一些事情。
cor
需要数值数据,所以删除第一列。- 在本例中,
mat[1,]
是一个数值向量,对于df1
,我们可以用unlist
得到。
cor(unlist(df1[1,-1]),t(df1[2:10,-1]))
# 2 3 4 5 6 7 8 9 10
#[1,] 0.136 0.0787 0.0839 0.0911 -0.341 -0.326 -0.591 0.578 0.11
使用tidyverse
library(dplyr)
df1 %>%
slice(1) %>%
select(where(is.numeric)) %>%
unlist %>%
cor(data.table::transpose(df1 %>%
slice(-1), make.names = 1) %>%
as.matrix)
ENSG00000000005 ENSG00000000419 ENSG00000000457 ENSG00000000460 ENSG00000000938 ENSG00000000971 ENSG00000001036 ENSG00000001084
[1,] 0.1360999 0.07867911 0.08393437 0.09114973 -0.341149 -0.3262614 -0.5907573 0.5779449
ENSG00000001167
[1,] 0.1100449