子集有序组件和相对变量名称

Question

我有一个看起来像这样的数据帧：

PC1         PC2          PC3          PC4          PC5
TGFBI     0.05105828  0.04259313  0.001931321 -0.014739818 -0.023630707
OLFM4    -0.01093027 -0.07768484 -0.056874220 -0.011045101 -0.009762945
CD177    -0.03543697 -0.05385507 -0.073857334  0.024278031  0.009186970
LCN2     -0.01539785 -0.07883489 -0.036711308  0.014314281 -0.010042372
CEACAM8  -0.01130204 -0.08092082  0.004004276 -0.003607281 -0.008600472

这是myPCAdf$rotation的输出。我想使用 abs 值对每台 PC 进行排序，然后我想对前 n 个基因进行子集。如果我执行：

data.frame(sort(abs(myPCAdf$rotation[,"PC4"]), decreasing=TRUE)[1:50]) 

我获得了失去基因名称的值列表。 任何人都可以帮助获取一个 data.frame，其中包含每个 PC 的两列：一列包含基因名称，形成第二列中的数值排序。

提前谢谢你。

期望的输出(简短示例(：

PC1       
TGFBI     0.05105828  
HLA-DPB1  0.04843209 
OLFM4    -0.01093027 
CEACAM8  -0.01130204
LCN2     -0.01539785
CD177    -0.03543697
.............

Answer 1

你也可以尝试一个经典的 for 循环：

listed <- list() # empty list
# create a loop for each subset of data.frame 
for(i in colnames(df)) {
dats <- data.frame(gene = rownames(df), pc = df[, which(names(df) == i )])
listed[[i]] <- dats[order(abs(dats$pc),decreasing = T),]
}
do.call(cbind, listed)
PC1.gene      PC1.pc PC2.gene      PC2.pc PC3.gene       PC3.pc PC4.gene
1    TGFBI  0.05105828  CEACAM8 -0.08092082    CD177 -0.073857334    CD177
3    CD177 -0.03543697     LCN2 -0.07883489    OLFM4 -0.056874220    TGFBI
4     LCN2 -0.01539785    OLFM4 -0.07768484     LCN2 -0.036711308     LCN2
5  CEACAM8 -0.01130204    CD177 -0.05385507  CEACAM8  0.004004276    OLFM4
2    OLFM4 -0.01093027    TGFBI  0.04259313    TGFBI  0.001931321  CEACAM8
PC4.pc PC5.gene       PC5.pc
1  0.024278031    TGFBI -0.023630707
3 -0.014739818     LCN2 -0.010042372
4  0.014314281    OLFM4 -0.009762945
5 -0.011045101    CD177  0.009186970
2 -0.003607281  CEACAM8 -0.008600472

Answer 2

通过基本 R 的一个想法是拆分每一列，将行名转换为列，排序并将它们重新绑定在一起，即

do.call(cbind, 
lapply(split.default(df, seq(ncol(df))), function(i){
i$rn <- rownames(i);
rownames(i) <- NULL; 
i[order(abs(i[1]), decreasing = TRUE),]; })
)

这给了，

1.PC1    1.rn       2.PC2    2.rn        3.PC3    3.rn        4.PC4    4.rn        5.PC5    5.rn
1  0.05105828   TGFBI -0.08092082 CEACAM8 -0.073857334   CD177  0.024278031   CD177 -0.023630707   TGFBI
3 -0.03543697   CD177 -0.07883489    LCN2 -0.056874220   OLFM4 -0.014739818   TGFBI -0.010042372    LCN2
4 -0.01539785    LCN2 -0.07768484   OLFM4 -0.036711308    LCN2  0.014314281    LCN2 -0.009762945   OLFM4
5 -0.01130204 CEACAM8 -0.05385507   CD177  0.004004276 CEACAM8 -0.011045101   OLFM4  0.009186970   CD177
2 -0.01093027   OLFM4  0.04259313   TGFBI  0.001931321   TGFBI -0.003607281 CEACAM8 -0.008600472 CEACAM8

Answer 3

tidyverse解决方案可能如下所示：

f <- structure(list(PC1 = c(0.05105828, -0.01093027, -0.03543697, 
-0.01539785, -0.01130204), 
PC2 = c(0.04259313, -0.07768484, -0.05385507, 
-0.07883489, -0.08092082), 
PC3 = c(0.001931321, -0.05687422, -0.073857334, 
-0.036711308, 0.004004276), 
PC4 = c(-0.014739818, -0.011045101, 0.024278031, 
0.014314281, -0.003607281), 
PC5 = c(-0.023630707, -0.009762945, 0.00918697, 
-0.010042372, -0.008600472)), 
class = "data.frame", 
row.names = c("TGFBI", "OLFM4", "CD177", "LCN2", "CEACAM8"))
## first transfrom row names to a column
ft <- f %>% rownames_to_column(f)
## then loop through all PC columns and arrange by abs(.)
map(names(ft)[-1], 
~ ft %>% arrange(desc(abs(!!rlang::sym(.x)))) %>% 
select(rowname, !!rlang::sym(.x)))

如果您只想拥有前 10 行(例如(，请添加%>% slice(1:10)

输出

[[1]]
rowname         PC1
1   TGFBI  0.05105828
2   CD177 -0.03543697
3    LCN2 -0.01539785
4 CEACAM8 -0.01130204
5   OLFM4 -0.01093027
[[2]]
rowname         PC2
1 CEACAM8 -0.08092082
2    LCN2 -0.07883489
3   OLFM4 -0.07768484
4   CD177 -0.05385507
5   TGFBI  0.04259313
[[3]]
rowname          PC3
1   CD177 -0.073857334
2   OLFM4 -0.056874220
3    LCN2 -0.036711308
4 CEACAM8  0.004004276
5   TGFBI  0.001931321
[[4]]
rowname          PC4
1   CD177  0.024278031
2   TGFBI -0.014739818
3    LCN2  0.014314281
4   OLFM4 -0.011045101
5 CEACAM8 -0.003607281
[[5]]
rowname          PC5
1   TGFBI -0.023630707
2    LCN2 -0.010042372
3   OLFM4 -0.009762945
4   CD177  0.009186970
5 CEACAM8 -0.008600472

Answer 4

考虑将数据重塑为长格式，这是大多数数据科学操作(聚合、数据合并、统计测试、绘图、建模等(的常用结构。无需循环：

# RESHAPE WIDE TO LONG
rdf <- reshape(df, varying = list(names(df)[-ncol(df)]), times = names(df)[-ncol(df)],
v.names = "value", timevar = "PC", 
new.row.names = 1:1E5, direction = "long")
# ORDER BY INDICATOR AND VALUE COLUMNS
rdf <- with(rdf, rdf[order(rev(PC), abs(rdf$value), decreasing=TRUE), ])
# RE-ASSIGN id AS SEQUENCE COLUMN
rdf$id <- with(rdf, ave(value, PC, FUN=seq_along))
row.names(rdf) <- NULL

输出

rdf
#       gene  PC        value id
# 1    TGFBI PC1  0.051058280  1
# 2    CD177 PC1 -0.035436970  2
# 3     LCN2 PC1 -0.015397850  3
# 4  CEACAM8 PC1 -0.011302040  4
# 5    OLFM4 PC1 -0.010930270  5
# 6  CEACAM8 PC2 -0.080920820  1
# 7     LCN2 PC2 -0.078834890  2
# 8    OLFM4 PC2 -0.077684840  3
# 9    CD177 PC2 -0.053855070  4
# 10   TGFBI PC2  0.042593130  5
# 11   CD177 PC3 -0.073857334  1
# 12   OLFM4 PC3 -0.056874220  2
# 13    LCN2 PC3 -0.036711308  3
# 14 CEACAM8 PC3  0.004004276  4
# 15   TGFBI PC3  0.001931321  5
# 16   CD177 PC4  0.024278031  1
# 17   TGFBI PC4 -0.014739818  2
# 18    LCN2 PC4  0.014314281  3
# 19   OLFM4 PC4 -0.011045101  4
# 20 CEACAM8 PC4 -0.003607281  5
# 21   TGFBI PC5 -0.023630707  1
# 22    LCN2 PC5 -0.010042372  2
# 23   OLFM4 PC5 -0.009762945  3
# 24   CD177 PC5  0.009186970  4
# 25 CEACAM8 PC5 -0.008600472  5