R：应用一个函数，该函数在数据帧的多列之间返回列表

我正在尝试应用一个函数，该函数对该列表的每个组合使用两个输入：

> c('EAS_MAF', 'AMR_MAF', 'AFR_MAF', 'EUR_MAF', 'SAS_MAF')
[1] "EAS_MAF" "AMR_MAF" "AFR_MAF" "EUR_MAF" "SAS_MAF"

要在2的每个组合中排列值，我使用combn函数：

> list <- combn(c('EAS_MAF', 'AMR_MAF', 'AFR_MAF', 'EUR_MAF', 'SAS_MAF'),2)
> list
     [,1]      [,2]      [,3]      [,4]      [,5]      [,6]      [,7]      [,8]      [,9]      [,10]    
[1,] "EAS_MAF" "EAS_MAF" "EAS_MAF" "EAS_MAF" "AMR_MAF" "AMR_MAF" "AMR_MAF" "AFR_MAF" "AFR_MAF" "EUR_MAF"
[2,] "AMR_MAF" "AFR_MAF" "EUR_MAF" "SAS_MAF" "AFR_MAF" "EUR_MAF" "SAS_MAF" "EUR_MAF" "SAS_MAF" "SAS_MAF"

> sharedCalc.func('EAS_MAF', 'AMR_MAF')
$NS
[1] 59325

$S
[1] 43434

$`NS/S`
[1] 1.365865

为了在我的列表中运行这个函数，我假设apply函数是最合适的。但是，这将返回一个不一致数组错误：

> apply(list, 2, sharedCalc.func)
Error in FUN(newX[, i], ...) : binary operation on non-conformable arrays

我还尝试了外部函数，收到了相同的错误：

> outer(list[1,], list[2,], sharedCalc.func)
Error in FUN(X, Y, ...) : binary operation on non-conformable arrays

我不知道为什么我会出错。是否可能是因为从函数返回了列表？我尝试使用lapply返回列表，但这也不起作用。以下是我的数据的dput：

> dput(head(variantTable))
structure(list(CHROM = c("1", "1", "1", "1", "1", "1"), POS = c(69224L, 
69428L, 69486L, 69487L, 69496L, 69521L), ID = c("rs568964432", 
"rs140739101", "rs548369610", "rs568226429", "rs150690004", "rs553724620"
), REF = c("A", "T", "C", "G", "G", "T"), ALT = c("T", "G", "T", 
"A", "A", "A"), AF = c(0.000399361, 0.0189696, 0.000199681, 0.000399361, 
0.000998403, 0.000399361), AC = c(2L, 95L, 1L, 2L, 5L, 2L), AN = c(5008L, 
5008L, 5008L, 5008L, 5008L, 5008L), consequence = c("nonsynonymous SNV", 
"nonsynonymous SNV", "synonymous SNV", "nonsynonymous SNV", "nonsynonymous SNV", 
"nonsynonymous SNV"), gene = c("OR4F5", "OR4F5", "OR4F5", "OR4F5", 
"OR4F5", "OR4F5"), refGene_id = c("NM_001005484", "NM_001005484", 
"NM_001005484", "NM_001005484", "NM_001005484", "NM_001005484"
), AA_change = c("('D', 'V')", "('F', 'C')", "('N', 'N')", "('A', 'T')", 
"('G', 'S')", "('I', 'N')"), X0.fold_count = c(572L, 572L, 572L, 
572L, 572L, 572L), X4.fold_count = c(141L, 141L, 141L, 141L, 
141L, 141L), EAS_MAF = c(0, 0.003, 0.001, 0, 0, 0), AMR_MAF = c(0.0029, 
0.036, 0, 0, 0.0014, 0.0029), AFR_MAF = c(0, 0.0015, 0, 0.0015, 
0.003, 0), EUR_MAF = c(0, 0.0497, 0, 0, 0, 0), SAS_MAF = c(0, 
0.0153, 0, 0, 0, 0), nonAFR_N = c(309227L, 1128036L, 262551L, 
0L, 309227L, 309227L), nonAFR_weighted = c(0.0029, 0.0261704282487438, 
0.001, 0, 0.0014, 0.0029)), .Names = c("CHROM", "POS", "ID", 
"REF", "ALT", "AF", "AC", "AN", "consequence", "gene", "refGene_id", 
"AA_change", "X0.fold_count", "X4.fold_count", "EAS_MAF", "AMR_MAF", 
"AFR_MAF", "EUR_MAF", "SAS_MAF", "nonAFR_N", "nonAFR_weighted"
), row.names = c(NA, 6L), class = "data.frame")

请尝试以下操作：

l <- combn(c('EAS_MAF', 'AMR_MAF', 'AFR_MAF', 'EUR_MAF', 'SAS_MAF'),2)
l
     [,1]      [,2]      [,3]      [,4]      [,5]      [,6]     
[1,] "EAS_MAF" "EAS_MAF" "EAS_MAF" "EAS_MAF" "AMR_MAF" "AMR_MAF"
[2,] "AMR_MAF" "AFR_MAF" "EUR_MAF" "SAS_MAF" "AFR_MAF" "EUR_MAF"
     [,7]      [,8]      [,9]      [,10]    
[1,] "AMR_MAF" "AFR_MAF" "AFR_MAF" "EUR_MAF"
[2,] "SAS_MAF" "EUR_MAF" "SAS_MAF" "SAS_MAF"

mapply(sharedCalc.func, l[1,], l[2,])
     EAS_MAF EAS_MAF EAS_MAF EAS_MAF AMR_MAF AMR_MAF AMR_MAF AFR_MAF
NS   1       1       1       1       2       1       1       1      
S    0       0       0       0       0       0       0       0      
NS/S Inf     Inf     Inf     Inf     Inf     Inf     Inf     Inf    
     AFR_MAF EUR_MAF
NS   1       1      
S    0       0      
NS/S Inf     Inf    

您试图让R使用column1作为输入，然后转到column2，依此类推

inputs <- combn(c('EAS_MAF', 'AMR_MAF', 'AFR_MAF', 'EUR_MAF', 'SAS_MAF'),2)
output <- Map(sharedCalc.func, inputs[1, ], inputs[2, ])

---

我觉得这是mapply的案子谢谢。这很好用。是否有任何方法可以确保列名同时包含输入名称，即EAS_MAF和AMR_MAF，而不仅仅是EAS_MAF，或者必须单独完成？这正是我想要的。谢谢，谢谢。这也行得通。该函数工作正常，但我只提供了数据集的一小部分，这就是为什么它会产生这些结果。非常感谢。

out <- mapply(sharedCalc.func, l[1,], l[2,])
setNames(data.frame(out), mapply(paste, l[1,], l[2,], sep="-"))
     EAS_MAF-AMR_MAF EAS_MAF-AFR_MAF EAS_MAF-EUR_MAF EAS_MAF-SAS_MAF
NS                 1               1               1               1
S                  0               0               0               0
NS/S             Inf             Inf             Inf             Inf
     AMR_MAF-AFR_MAF AMR_MAF-EUR_MAF AMR_MAF-SAS_MAF AFR_MAF-EUR_MAF
NS                 2               1               1               1
S                  0               0               0               0
NS/S             Inf             Inf             Inf             Inf
     AFR_MAF-SAS_MAF EUR_MAF-SAS_MAF
NS                 1               1
S                  0               0
NS/S             Inf             Inf

inputs <- combn(c('EAS_MAF', 'AMR_MAF', 'AFR_MAF', 'EUR_MAF', 'SAS_MAF'),2)
output <- Map(sharedCalc.func, inputs[1, ], inputs[2, ])

output[[1]]
#    $NS
# [1] 1
# $S
# [1] 0
# $`NS/S`
# [1] Inf