Divide one value in a data.frame by another in an alternate data.frame base on row and column meta data

user_12897592 0
Viewed 34

I have one data frame with structure =

Gene    Transcript_ID   V1  V2  V3  V4
1   ENSG00000000003.14  ENST00000612152.4   0   6   0   3
2   ENSG00000000003.14  ENST00000373020.8   4   0   5   0
3   ENSG00000000003.14  ENST00000614008.4   0   0   0   0
4   ENSG00000000003.14  ENST00000496771.5   0   3   0   0

And I have the aggregated totals by Gene in another dataframe with structure =

Category                V1       V2      V3      V4    
1 ENSG00000000003.14     4.00       9.00    5.00    3.00  
2 ENSG00000000005.6      0.00       0.00    0.00    0.00  
3 ENSG00000000419.12     61.00      94.00  103.00   71.00  
4 ENSG00000000457.14     577.01     698.20  815.49  697.72

I want to divide the values in data.frame 1, by the corresponding aggregate values in dataframe2 to give the relative proportions of all values.

Is there a nice simple bit of syntax someone can apply here please? Much appreciated!

bioinformatics statistics r
2 Answers

We could use a join here

library(data.table)
nm1 <- paste0("V", 1:4)
setDT(df1)[, (nm1) := lapply(.SD, as.numeric), .SDcols = nm1]
df1[df2, (nm1) := Map(`/`, mget(nm1),
         mget(paste0("i.", nm1))), on = .(Gene = Category)]

-output

 df1
                 Gene     Transcript_ID V1        V2 V3 V4
1: ENSG00000000003.14 ENST00000612152.4  0 0.6666667  0  1
2: ENSG00000000003.14 ENST00000373020.8  1 0.0000000  1  0
3: ENSG00000000003.14 ENST00000614008.4  0 0.0000000  0  0
4: ENSG00000000003.14 ENST00000496771.5  0 0.3333333  0  0

data

df1 <- structure(list(Gene = c("ENSG00000000003.14", "ENSG00000000003.14", 
"ENSG00000000003.14", "ENSG00000000003.14"), Transcript_ID = c("ENST00000612152.4", 
"ENST00000373020.8", "ENST00000614008.4", "ENST00000496771.5"
), V1 = c(0L, 4L, 0L, 0L), V2 = c(6L, 0L, 0L, 3L), V3 = c(0L, 
5L, 0L, 0L), V4 = c(3L, 0L, 0L, 0L)), class = "data.frame", row.names = c("1", 
"2", "3", "4"))

df2 <- structure(list(Category = c("ENSG00000000003.14", "ENSG00000000005.6", 
"ENSG00000000419.12", "ENSG00000000457.14"), V1 = c(4, 0, 61, 
577.01), V2 = c(9, 0, 94, 698.2), V3 = c(5, 0, 103, 815.49), 
    V4 = c(3, 0, 71, 697.72)), class = "data.frame", row.names = c("1", 
"2", "3", "4"))
user_37322710

You could also do:

df1 %>%
  left_join(df2, c('Gene' = 'Category')) %>%
  pivot_longer(starts_with('V'),
    names_to = c('name','.value'), names_sep = '[.]') %>%
  mutate(value = x/y, x = NULL, y = NULL) %>%
  pivot_wider()

# A tibble: 4 x 6
  Gene        Transcript_ID     V1    V2    V3    V4
  <chr>       <chr>          <dbl> <dbl> <dbl> <dbl>
1 ENSG000000~ ENST000006121~     0 0.667     0     1
2 ENSG000000~ ENST000003730~     1 0         1     0
3 ENSG000000~ ENST000006140~     0 0         0     0
4 ENSG000000~ ENST000004967~     0 0.333     0     0
user_83802720
Related