用数据填充R中的空数据帧

Question

我已经创建了一个空的数据框，如下面的代码所述。我正在尝试从样本中提取表达式数据，并使用它来填充数据框。

此外，如果样本不包含数据帧中特定mRNA的表达式值，我如何将0而不是安娜输入到单元格中？

任何帮助都将不胜感激！

示例代码：

sample_8765 <- data.frame(type = c("protein", "mRNA", "mRNA", "mRNA", "protein"),
                          name = c("DIABLO", "X1345", "X1234", "F1234", "p53"),
                          expression = c("1.23", "4.265", "3.44", "6.43", "8.00"))

sample_8901 <- data.frame(type = c("protein", "mRNA", "protein","mRNA", "protein"),
                          name = c("DIABLO", "X1345", "SMAC", "F4657", "MDM2"),
                          expression = c("3.24", "5.33", "4.35", "6.78", "9.11"))

sample_9084 <- data.frame(type = c("protein", "protein", "mRNA", "mRNA", "mRNA"),
                           name = c("SMAC", "DIABLO", "X1345", "F4657", "X1234" ),
                           expression = c("2.56", "8.11", "4.35", "6.78", "9.11"))

sample_ID <- c("sample_8765","sample_8901","sample_9084") #unique samples 

#seperating by type
samples <- bind_rows(mget(paste0(sample_ID)), .id = "Sample_ID") %>%
            split(.$type) 
mRNA_samples <- samples$mRNA 

mRNAs <- unique(mRNA_samples$name) #unique mRNAs 


#creating empty matrix
mRNA_df <- matrix(nrow = 4, ncol = 3)
rownames(mRNA_df) = mRNAs
colnames(mRNA_df) = sample_ID

我希望看到的输出是这样的！

#       sample_8765   sample_8901   sample_9084
#X1345  4.265          5.33           4.35
#X1234  3.44           0              9.11
#F1234  6.43           0              0
#F4657  0              6.78           6.78

Answer 1

请注意，您的“数字”实际上是字符串。像max这样的许多函数都可以工作，但它们是按字典排序的，而不是数字的。例如，当20 > 3为true时，"20" > "3"为false。

tidyverse

如果您的数字实际上是数字，则根据数字/整数更改为values_fill=list(expression=0)或=0L。

library(dplyr)
library(tidyr) # pivot_wider
bind_rows(lst(sample_8765,sample_8901,sample_9084), .id = "id") %>%
  select(name, id, expression) %>%
  pivot_wider(name, names_from = "id", values_from = "expression", values_fill = list(expression = "0"))
# # A tibble: 8 x 4
#   name   sample_8765 sample_8901 sample_9084
#   <chr>  <chr>       <chr>       <chr>      
# 1 DIABLO 1.23        3.24        8.11       
# 2 X1345  4.265       5.33        4.35       
# 3 X1234  3.44        0           9.11       
# 4 F1234  6.43        0           0          
# 5 p53    8.00        0           0          
# 6 SMAC   0           4.35        2.56       
# 7 F4657  0           6.78        6.78       
# 8 MDM2   0           9.11        0          

data.table

dat <- rbindlist(setNames(list(sample_8765,sample_8901,sample_9084),
                 nm = c("sample_8765","sample_8901","sample_9084")), idcol = "id")
dcast(dat, name ~ id, fun.aggregate = max, value.var = "expression", fill = 0)
#      name sample_8765 sample_8901 sample_9084
#    <char>      <char>      <char>      <char>
# 1: DIABLO        1.23        3.24        8.11
# 2:  F1234        6.43           0           0
# 3:  F4657           0        6.78        6.78
# 4:   MDM2           0        9.11           0
# 5:   SMAC           0        4.35        2.56
# 6:  X1234        3.44           0        9.11
# 7:  X1345       4.265        5.33        4.35
# 8:    p53        8.00           0           0

Answer 2

这里有一个非常tidyverse的方法。

library(tidyverse)

 tibble(sample_id = c("sample_8765","sample_8901","sample_9084")) %>%
   mutate(data = map(sample_id, get)) %>%
   unnest(data) %>%
   filter(type == "mRNA") %>%
   select(-type) %>%
   mutate(expression = as.numeric(expression)) %>%
   pivot_wider(names_from = "sample_id", values_from = "expression") %>%
   mutate(across(where(is.numeric), replace_na, 0))

# A tibble: 4 x 4
  name  sample_8765 sample_8901 sample_9084
  <chr>       <dbl>       <dbl>       <dbl>
1 X1345        4.26        5.33        4.35
2 X1234        3.44        0           9.11
3 F1234        6.43        0           0   
4 F4657        0           6.78        6.78

Answer 3

我们可以在xtabs中使用base R方法

xtabs(expression ~ name + id, data = transform(do.call(rbind, 
   Map(cbind, id = sample_ID, mget(sample_ID)))[c('id', 'name', 'expression')], 
         expression = as.numeric(expression)))

或用于观察值的子集

xtabs(expression ~ name + id, data = transform(subset(do.call(rbind, 
   Map(cbind, id = sample_ID, mget(sample_ID))), 
        type == 'mRNA')[c('id', 'name', 'expression')], 
         expression = as.numeric(expression)))

-output

#     id
#name    sample_8765 sample_8901 sample_9084
#  F1234       6.430       0.000       0.000
#  F4657       0.000       6.780       6.780
#  X1234       3.440       0.000       9.110
#  X1345       4.265       5.330       4.350