How to find the same values between multiple vectors?

General
1

I'm trying to compare 53 vectors containing an alphanumerical code describing the residue's position inside a protein sequence. I need to make an all vs. all comparison to having shared values for each comparison step.

PER1_PASA <- as.vector(proteins2$PER1_PASA) head(PER1_PASA) [1] "THR_B1_1" "PHE_B1_2" "SER_B1_3" "VAL_B1_4" "ALA_B1_5" "VAL_B1_6"

Any Ideas, to determine which elements are shared among all the vectors, after compared all vs all. Note that is not mandatory that every vector have a term shared with all the others.

2 
(v1 <- letters[1:3])
(v2 <- letters[3:5])

intersect(v1,v2)
3

Nope, because this is how is filled a vector, I've to compare all the elements in this vector with all the elements in the other vectors, which has to be done for everyone.

4

Hi!

To help us help you, could you please prepare a reproducible example (reprex) illustrating your issue? Please have a look at this guide, to see how to create one:

5

HI, ok I'll try!

> head(proteins2)
# A tibble: 6 × 53
  AHRR_PAS AHR_PASA AHR_PASB ARNT2_P…¹ ARNT2…² ARNTL…³ ARNTL…⁴ ARNTL…⁵ ARNTL…⁶ ARNT_…⁷ ARNT_…⁸ CLOCK…⁹ CLOCK…˟ HIF1A…˟ HIF1A…˟ HIF2A…˟ HIF2A…˟ HIF3A…˟ HIF3A…˟ KCNH1 KCNH2 KCNH3
  <chr>    <chr>    <chr>    <chr>     <chr>   <chr>   <chr>   <chr>   <chr>   <chr>   <chr>   <chr>   <chr>   <chr>   <chr>   <chr>   <chr>   <chr>   <chr>   <chr> <chr> <chr>
1 PHE_B1_1 PHE_B1_1 PHE_B1_1 GLY_B1_1  GLU_B1… GLY_B1… GLU_B1… PHE_B1… GLU_B1… GLY_B1… GLU_B1… GLY_B1… GLU_B1… PHE_B1… THR_B1… PHE_B1… THR_B1… GLY_B1… ALA_B1… ASN_… PHE_… PHE_…
2 ALA_B1_2 VAL_B1_2 ARG_B1_2 PHE_B1_2  PHE_B1… PHE_B1… PHE_B1… LEU_B1… TYR_B1… PHE_B1… PHE_B1… PHE_B1… PHE_B1… VAL_B1… PHE_B1… ILE_B1… PHE_B1… PHE_B1… PHE_B1… PHE_… ILE_… VAL_…
3 LEU_B1_3 LEU_B1_3 THR_B1_3 LEU_B1_3  LEU_B1… LEU_B1… ILE_B1… PHE_B1… VAL_B1… LEU_B1… ILE_B1… PHE_B1… THR_B1… MET_B1… LEU_B1… ALA_B1… LEU_B1… VAL_B1… LEU_B1… VAL_… ILE_… LEU_…
4 VAL_B1_4 VAL_B1_4 LYS_B1_4 PHE_B1_4  SER_B1… PHE_B1… THR_B1… VAL_B1… SER_B1… PHE_B1… SER_B1… LEU_B1… SER_B1… VAL_B1… SER_B1… VAL_B1… SER_B1… MET_B1… SER_B1… LEU_… ALA_… GLY_…
5 VAL_B1_5 VAL_B1_5 HIS_B1_5 VAL_B1_5  ARG_B1… VAL_B1… ARG_B1… VAL_B1… ARG_B1… ILE_B1… ARG_B1… ALA_B1… ARG_B1… LEU_B1… ARG_B1… VAL_B1… ARG_B1… VAL_B1… ARG_B1… GLY_… ASN_… ASN_…
6 SER_B1_6 THR_B1_6 LYS_L1_1 VAL_B1_6  HIS_B1… VAL_B1… PHE_B1… GLY_B1… HIS_B1… VAL_B1… HIS_B1… ILE_B1… HIS_B1… THR_B1… HIS_B1… THR_B1… HIS_B1… LEU_B1… HIS_B1… ASN_… ALA_… ALA_…

This is the data frame, after that, I've extracted each column as vectors

AHRR <- as.vector(proteins2$AHRR_PAS)
AHR_PASA <-  as.vector(proteins2$AHR_PASA)
AHR_PASB <- as.vector(proteins2$AHR_PASB)

and they look like this

> print(AHR_PASA)
  [1] "PHE_B1_1"  "VAL_B1_2"  "LEU_B1_3"  "VAL_B1_4"  "VAL_B1_5"  "THR_B1_6"  "THR_L1_1"  "ASP_L1_2"  "ALA_L1_3"  "LEU_B2_1"  "VAL_B2_2"  "PHE_B2_3"  "TYR_B2_4"  "ALA_B2_5" 
 [15] "SER_L2_1"  "SER_H1_1"  "THR_H1_2"  "ILE_H1_3"  "GLN_H1_4"  "ASP_H1_5"  "TYR_H1_6"  "LEU_H1_7"  "GLY_L3_1"  "PHE_L3_2"  "GLN_L3_3"  "GLN_H2_1"  "SER_H2_2"  "ASP_H2_3" 
 [29] "VAL_H2_4"  "ILE_L4_1"  "HIS_L4_2"  "GLN_L4_3"  "SER_L4_4"  "VAL_H3_1"  "TYR_H3_2"  "GLU_H3_3"  "LEU_L5_1"  "ILE_L5_2"  "HIS_L5_3"  "THR_L5_4"  "GLU_L5_5"  "ASP_L5_6" 
 [43] "ARG_H4_1"  "ALA_H4_2"  "GLU_H4_3"  "PHE_H4_4"  "GLN_H4_5"  "ARG_H4_6"  "GLN_H4_7"  "LEU_H4_8"  "HIS_L6_1"  "TRP_L6_2"  "ALA_L6_3"  "LEU_L6_4"  "ASN_L6_5"  "PRO_L6_6" 
 [57] "SER_L6_7"  "GLN_L6_8"  "CYS_L6_9"  "THR_L6_10" "GLU_L6_11" "SER_L6_12" "GLY_L6_13" "GLN_L6_14" "GLY_L6_15" "ILE_L6_16" "GLU_L6_17" "GLU_L6_18" "ALA_L6_19" "THR_L6_20"
 [71] "GLY_L6_21" "LEU_L6_22" "PRO_L6_23" "GLN_L6_24" "THR_L6_25" "VAL_L6_26" "VAL_L6_27" "CYS_L6_28" "TYR_L6_29" "ASN_L6_30" "PRO_L6_31" "ASP_L6_32" "GLN_L6_33" "ILE_L6_34"
 [85] "PRO_L6_35" "PRO_L6_36" "GLU_L6_37" "ASN_L6_38" "SER_L6_39" "PRO_L6_40" "LEU_L6_41" "MET_L6_42" "GLU_B3_1"  "ARG_B3_2"  "CYS_B3_3"  "PHE_B3_4"  "ILE_B3_5"  "CYS_B3_6" 
 [99] "ARG_B3_7"  "LEU_B3_8"  "ARG_B3_9"  "CYS_L7_1"  "LEU_L7_2"  "LEU_L7_3"  "ASP_L7_4"  "ASN_L7_5"  "SER_L7_6"  "SER_L7_7"  "GLY_L7_8"  "PHE_B4_1"  "LEU_B4_2"  "ALA_B4_3" 
[113] "MET_B4_4"  "ASN_B4_5"  "PHE_B4_6"  "GLN_B4_7"  "GLY_B4_8"  "LYS_B4_9"  "LEU_B4_10" "LYS_B4_11" "TYR_B4_12" "LEU_B4_13" "HIS_L8_1"  "GLY_L8_2"  "GLN_L8_3"  "LYS_L8_4" 
[127] "LYS_L8_5"  "LYS_L8_6"  "GLY_L8_7"  "LYS_L8_8"  "ASP_L8_9"  "GLY_L8_10" "SER_L8_11" "ILE_L8_12" "LEU_L8_13" "PRO_L8_14" "PRO_L8_15" "GLN_B5_1"  "LEU_B5_2"  "ALA_B5_3" 
[141] "LEU_B5_4"  "PHE_B5_5"  "ALA_B5_6"  "ILE_B5_7"  "ALA_B5_8"  "THR_B5_9"  "PRO_B5_10" NA          NA          NA          NA          NA          NA          NA         
[155] NA          NA          NA          NA          NA          NA          NA          NA          NA          NA          NA          NA          NA          NA         
[169] NA          NA

The issue came here, how I can compare and find the shared terms (ES: term="LEU_L8_13") and with which vector is shared?

6

Here is an example to start you off
I determine the elements that are possible to be shared; then for each I get an output of where they appear.
as a further step I count how many columns the shareable term appears in.

library(tidyverse)

(yourstart <- data.frame(v1=letters[1:6],
                        v2=letters[6:11],
                        v3=letters[c(1,2,3,4,9,11)]))

(shareable_terms <- sort(unique(unlist(yourstart))))

#for each shareable term find where it is
(results_1 <- map(shareable_terms,
       ~{yourstart |>
           summarise(across(.fns=\(x) .x %in% x))}) |> 
  set_names(shareable_terms))

(results_2 <- map(results_1,
                  ~length(.x[.x==TRUE])))
1 Like
7

This topic was automatically closed 21 days after the last reply. New replies are no longer allowed.

If you have a query related to it or one of the replies, start a new topic and refer back with a link.