在R中交叉多个数据帧

Question

StackOverflow question

Hello fellows,

I am trying to "cross" multiple dataframes with R.

My data frames are coming from a high-throughput sequencing experiments and look like the followings :

df1 :

         chr  pos orient weight in_nucleosome in_subtelo
1  NC_001133  999      +      1          TRUE       TRUE
2  NC_001133 1505      -     14         FALSE       TRUE
3  NC_001133 1525      -      2          TRUE       TRUE
4  NC_001134  480      +      1          TRUE       TRUE
5  NC_001134  509      +      2         FALSE       TRUE
6  NC_001134  539      +      3         FALSE       TRUE
7  NC_001135 1218      +      1          TRUE       TRUE
8  NC_001135 1228      +      2          TRUE       TRUE
9  NC_001135 1273      +      1          TRUE       TRUE
10 NC_001136  362      +      1          TRUE       TRUE

and

df2:

         chr                feature  start    end orient
1  NC_001133                    ARS    707    776      .
2  NC_001133                    ARS   7997   8547      .
3  NC_001133                    ARS  30946  31183      .
4  NC_001133 ARS_consensus_sequence  31002  31018      +
5  NC_001133 ARS_consensus_sequence  70418  70434      -
6  NC_001133 ARS_consensus_sequence 124463 124479      -
7  NC_001136  blocked_reading_frame 721071 721481      -
8  NC_001137  blocked_reading_frame 375215 377614      -
9  NC_001141  blocked_reading_frame  29032  30048      +
10 NC_001133                    CDS    335    649      +

What I want to do is to know for a given chromosome ("chr" here) and for each df2$feature whether or not (df2$start < df1$pos < df2$end). I would then like to add a column to df1 whose name would be the one of the considered df2feature and filled with TRUE or FALSE in respect to the condition stated earlier.

I am pretty sure that the apply family of function have to be used maybe nested in one antoher but after hours of trying I can't manage to do it.

I did it in a very inelegant, long and error prone way with nested for loops but I am convinced there is a better simpler and maybe faster solution.

Thank you for reading this,

Antoine.

Answer 1

Though it may be possible with dplyr (I tried but am not that proficient), I got it to work (I think) with foreach and iterators :

Your data:

df1 <- structure(list(chr = c("NC_001133", "NC_001133", "NC_001133", "NC_001134", "NC_001134", "NC_001134", "NC_001135", "NC_001135", "NC_001135", "NC_001136"),
                      pos = c(999L, 1505L, 1525L, 480L, 509L, 539L, 1218L, 1228L, 1273L, 362L),
                      orient = c("+", "-", "-", "+", "+", "+", "+", "+", "+", "+"),
                      weight = c(1L, 14L, 2L, 1L, 2L, 3L, 1L, 2L, 1L, 1L),
                      in_nucleosome = c(TRUE, FALSE, TRUE, TRUE, FALSE, FALSE, TRUE, TRUE, TRUE, TRUE),
                      in_subtelo = c(TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE)),
                 .Names = c("chr", "pos", "orient", "weight", "in_nucleosome", "in_subtelo"),
                 class = "data.frame",
                 row.names = c("1", "2", "3", "4", "5", "6", "7", "8", "9", "10"))

df2 <- structure(list(chr = c("NC_001133", "NC_001133", "NC_001133", "NC_001133", "NC_001133", "NC_001133", "NC_001136", "NC_001137", "NC_001141", "NC_001133"),
                      feature = c("ARS", "ARS", "ARS", "ARS_consensus_sequence", "ARS_consensus_sequence", "ARS_consensus_sequence", "blocked_reading_frame", "blocked_reading_frame", "blocked_reading_frame", "CDS"),
                      start = c(707L, 7997L, 30946L, 31002L, 70418L, 124463L, 721071L, 375215L, 29032L, 335L),
                      end = c(776L, 8547L, 31183L, 31018L, 70434L, 124479L, 721481L, 377614L, 30048L, 649L),
                      orient = c(".", ".", ".", "+", "-", "-", "-", "-", "+", "+")),
                 .Names = c("chr", "feature", "start", "end", "orient"),
                 class = "data.frame",
                 row.names = c("1", "2", "3", "4", "5", "6", "7", "8", "9", "10"))

Since I think your data does not have any matches, I'll inject some:

## to be able to find *something*
df1$pos <- c(999, 1505, 8000, 480, 509, 539, 1218, 1228, 1272, 721072)

The code:

library(foreach)
library(iterators)

## pre-populate df1 with necessary columns
for (col in unique(df2$feature)) df1[,col] <- FALSE

df1a <- foreach (subdf1 = iter(df1, by='row'), .combine=rbind) %do% {
    features <- unique(df2$feature[df2$chr== subdf1$chr])
    for (feature in features) {
        idx <- (df2$chr == subdf1$chr) & (feature == df2$feature)
        if (length(idx)) {
            subdf1[feature] <- any((df2$start[idx] < subdf1$pos) & (subdf1$pos < df2$end[idx]))
        }
    }
    subdf1
}

df1a
##          chr    pos orient weight in_nucleosome in_subtelo   ARS
## 1  NC_001133    999      +      1          TRUE       TRUE FALSE
## 2  NC_001133   1505      -     14         FALSE       TRUE FALSE
## 3  NC_001133   8000      -      2          TRUE       TRUE  TRUE
## 4  NC_001134    480      +      1          TRUE       TRUE FALSE
## 5  NC_001134    509      +      2         FALSE       TRUE FALSE
## 6  NC_001134    539      +      3         FALSE       TRUE FALSE
## 7  NC_001135   1218      +      1          TRUE       TRUE FALSE
## 8  NC_001135   1228      +      2          TRUE       TRUE FALSE
## 9  NC_001135   1272      +      1          TRUE       TRUE FALSE
## 10 NC_001136 721072      +      1          TRUE       TRUE FALSE
##    ARS_consensus_sequence blocked_reading_frame   CDS
## 1                   FALSE                 FALSE FALSE
## 2                   FALSE                 FALSE FALSE
## 3                   FALSE                 FALSE FALSE
## 4                   FALSE                 FALSE FALSE
## 5                   FALSE                 FALSE FALSE
## 6                   FALSE                 FALSE FALSE
## 7                   FALSE                 FALSE FALSE
## 8                   FALSE                 FALSE FALSE
## 9                   FALSE                 FALSE FALSE
## 10                  FALSE                  TRUE FALSE

An easy side-effect of using foreach and iterators is that, if the data is large and you use doParallel , just replace %do% with %dopar% and things go as parallel as you define. You could preface all of the above with something like:

library(doParallel)
cl <- makeCluster(detectCores() - 1) # leaving one available is "A Good Thing (tm)"
registerDoParallel(cl)

## replace %do% with %dopar%, do all of the above code

## clean up
stopCluster(cl)