How to loop over a large list in R?

Question

I have a Largelist data with 300 names having names and a data frame data6 with values.

Largelist data looks like below:

dput(data$name1)
c("55024", "29126", "3732", "1960", "79368", "115352", "10875", 
"2530", "348654", "3070", "29969", "9124", "10125", "143686", 
"6504", "25992", "26137")

dput(data$name2)
c("323", "836", "9976", "1407", "1840", "2289", "2317", "2739", 
"8337", "10964", "3572", "3693", "4023", "4058", "124540", "4638", 
"5214", "6238", "8115", "7049", "8459", "10791", "55884", "7494", 
"7535")

And the data6 data frame is like below:

dput(data6)

structure(list(sample1 = c(1.797420114, 2.441058007, 2.072991117, 
1.976459487, 2.153422414, 3.19334551, 1.293754109, 2.42458892, 
1.617599756, 1.706955406, 1.333884316, 2.734852229, 2.727135936, 
1.246081115, 1.729863031, 1.39318281, 1.540910675, 2.159654566, 
3.12446713, 2.942906309, 1.459526471, 3.080694772, 2.659254927, 
2.654413352, 2.539851295, 3.021233948), sample2 = c(1.893457121, 
2.515794451, 2.110657811, 1.960663021, 2.00443825, 3.117625404, 
1.157262746, 2.409548272, 1.458719384, 1.855561189, 1.263697526, 
2.756331664, 2.621355832, 1.21049778, 1.848646261, 1.247975834, 
1.725660164, 2.294596029, 3.183559871, 3.000828084, 1.638529898, 
2.965147948, 2.69031941, 2.604888992, 2.695617226, 3.024335517
), sample3 = c(2.064216543, 2.590740583, 1.739272353, 2.026633201, 
2.11544319, 3.208407354, 1.275654593, 2.360166877, 1.784837002, 
1.795149114, 1.289316392, 2.747176531, 2.7794964, 1.142444503, 
1.569541472, 1.298843972, 1.770285058, 2.443448795, 3.089447481, 
2.910612462, 1.236543553, 3.166973944, 2.66008316, 2.734142725, 
2.626122207, 2.987731358), sample4 = c(1.888713323, 2.398032239, 
2.142526217, 1.950883861, 2.023021668, 3.287045461, 1.256008953, 
2.394323766, 1.546403414, 1.800866081, 1.430312275, 2.754314046, 
2.687826087, 1.218387918, 1.696783819, 1.223212096, 1.583623673, 
2.211686144, 3.118032952, 2.956183327, 1.398410126, 3.114571708, 
2.725648336, 2.743968119, 2.612508141, 3.012197931), sample5 = c(1.900294551, 
2.44526815, 1.907689891, 2.001029682, 2.114359656, 3.204535394, 
1.254469716, 2.306233714, 1.780838868, 1.830477155, 1.359595123, 
2.730898706, 2.619532527, 1.151552352, 1.643335806, 1.19766925, 
1.747261813, 2.318571867, 3.135500762, 2.914971673, 1.460149594, 
3.000380417, 2.689031735, 2.612427905, 2.714124436, 3.045352789
)), row.names = c(18723L, 55024L, 29126L, 323L, 836L, 2739L, 
3732L, 7494L, 7535L, 2289L, 10875L, 11033L, 1960L, 4023L, 8115L, 
8337L, 1407L, 133443L, 143686L, 25992L, 6504L, 25992L, 23679L, 
35467L, 11023L, 26137L), class = "data.frame")

And the code I used:

df <- as.data.frame(data$name1)

# selected
Sig <- unique(df$name1)
library(GSVA)
set.seed(8, sample.kind = "Rounding")
core <- gsva(expr=as.matrix(data6), 
                     gset.idx.list=list(Sig), method="ssgsea")
core2 <- as.data.frame(t(core))
colnames(core2)[1] <- "name1"

And finally core2 looks like below:

           name1
sample1    2.57
sample2    2.32
sample3    2.15
sample4    2.56
sample5    1.67

I wanted to repeat the above code on all other 299 names in the list data . So again for name2 I would like to do like below:

df <- as.data.frame(data$name2)

# selected
Sig <- unique(df$name2)
library(GSVA)
set.seed(8, sample.kind = "Rounding")
core <- gsva(expr=as.matrix(data6), 
                     gset.idx.list=list(Sig), method="ssgsea")
core2 <- as.data.frame(t(core))
colnames(core2)[1] <- "name2"

And now core2 for name2

           name2
sample1    3.57
sample2    2.42
sample3    2.87
sample4    2.16
sample5    4.67

Rather than doing this for each list and getting the final result for each, I would like to loop and generate the result of core2 for all 300 names in the list as a single data frame.

How to do this in R?

Answer 1

We may use lapply/Map to loop over the columns of 'data', apply the function and then cbind the list elements

library(GSVA)
m1 <- as.matrix(data6)     
out <- do.call(cbind, Map(\(x, y)  {
     # selected
      Sig <- unique(x)
      set.seed(8, sample.kind = "Rounding")
       core <- gsva(expr=m1, 
                     gset.idx.list=list(Sig), method="ssgsea")
      core2 <- as.data.frame(t(core))
      colnames(core2)[1] <- y
      core2
     
     }, data, names(data)))
 |=======================================================================================================================================| 100%

  |=======================================================================================================================================| 100%

[1] "Normalizing..."

-output

> out
           name1     name2
sample1 1.960636 -4.549292
sample2 2.380813 -5.152423
sample3 1.380813 -4.152423
sample4 1.881693 -4.900299
sample5 1.797915 -4.733601