Counting the number of common sub elemnts between two lists-CodePudding

There are two long nested lists that have the same element names. I want to find for each elements, the number of common sub elements between two lists. The desired output will be a dataframe with two columns where the first column is the list's names (ENSGs) and the second column is the number of sub elements (chrXX_XXXX_X_X_b38) in common between two lists.

list1:

list1 <- list(ENSG00000040608 = structure(list(chr22_20230714_G_A_b38 = 0.0000953181301665087, 
                             chr22_20230737_G_A_b38 = -0.00124036704551427, 
                             chr22_20231229_T_A_b38 = 0.000808061558738542, 
                             chr22_20231474_G_A_b38 = 0.000387528601423933, 
                             chr22_20231667_C_G_b38 = -0.000120624028990859), 
                                          row.names = c(NA, -1L), 
                                          class = c("tbl_df", "tbl", "data.frame")), 
              ENSG00000020766 = structure(list(chr22_47157062_G_A_b38 = 0.00000909931572319958, 
                             chr22_47157212_G_A_b38 = -0.000124084106569373, 
                             chr22_47157394_C_G_b38 = -0.0000752774417069946, 
                             chr22_47157559_G_A_b38 = 0.0000808446315377557, 
                             chr22_47157607_T_C_b38 = 0.000237979025556899), 
                                          row.names = c(NA, -1L), 
                                          class = c("tbl_df", "tbl", "data.frame")))

list2:

list2 <- list(ENSG00000040608 = structure(list(chr22_20230714_G_A_b38 = c(1L, 1L, 1L, 2L, 1L), 
                             chr22_20230737_G_A_b38 = c(0L, 0L, 0L, 0L, 0L), 
                             chr22_20231229_T_A_b38 = c(1L, 0L, 1L, 0L, 1L), 
                             chr22_20231555_A_T_b38 = c(0L,1L, 0L, 0L, 0L), 
                             chr22_20231667_C_G_b38 = c(1L, 1L, 1L, 2L, 1L)), 
                                          row.names = c(NA, -5L), 
                                          class = c("tbl_df", "tbl", "data.frame")), 
              ENSG00000020766 = structure(list(chr22_47157062_G_A_b38 = c(0L,1L, 0L, 0L, 0L), 
                            chr22_47157212_G_A_b38 = c(0L, 0L, 1L, 1L, 2L), 
                            chr22_47157394_C_G_b38 = c(0L, 1L, 1L, 1L, 2L), 
                            chr22_47207559_T_C_b38 = c(0L, 1L, 0L, 0L, 0L)), 
                                          row.names = c(NA, -4L), 
                                          class = c("tbl_df", "tbl", "data.frame")))

CodePudding user response：

We may use map2 to loop over the corresponding elements, get the length of intersecting column names into a tibble while creating the ENSG column with .id

library(purrr)
library)(tibble)
map2_dfr(list1, list2,
    ~ tibble(common_elements = length(intersect(names(.x), 
               names(.y)))), .id = 'ENSG')

-output

# A tibble: 2 × 2
  ENSG            common_elements
  <chr>                     <int>
1 ENSG00000040608               4
2 ENSG00000020766               3