Converting long format to wide format

Question

Having long format of copy number like below in which each sample has its own copy number values (segVal) in its own genomic range

> head(long)
   chromosome     start       end segVal                       sample
1:       chr1   3218923 116319008      2 TCGA-05-4417-01A-22D-1854-01
2:       chr1 116324707 120523902      1 TCGA-05-4417-01A-22D-1854-01
3:       chr1 149879545 247812431      4 TCGA-05-4417-01A-22D-1854-01
4:       chr1   3218923 104393357      2 TCGA-06-0644-01A-02D-0310-01
5:       chr1 104418619 149879545      1 TCGA-06-0644-01A-02D-0310-01
6:       chr1 149885583 247812431      2 TCGA-06-0644-01A-02D-0310-01

How I can convert this to wide format so that samples are in column having their values (however here genomic ranges should be common if I am not wrong) like

> head(wide)
 chr     start       end TCGA-05-4417-01A-22D-1854-01 TCGA-06-0644-01A-02D-0310-01 TCGA-06-0644-01A-02D-0310-01
 chr1  24254002  24291000          2          2         2
 chr3  47421002  49068000          1          0         0
 chr4  69204002  70320000          0          0         1
 chr5  58263002  59785000          0          1         1
 chr6  29010002  33287000          2          2         2
 chr7 110240002 111354000          0          0         0
>

Answer 1

Does this work for you?

library(tidyr)

options(scipen = 999)

df <- structure(list(chromosome = c("chr1", "chr1", "chr1", "chr1", 
"chr1", "chr1"), start = c(3218923L, 116324707L, 149879545L, 
3218923L, 104418619L, 149885583L), end = c(116319008L, 120523902L, 
247812431L, 104393357L, 149879545L, 247812431L), segVal = c(2L, 
1L, 4L, 2L, 1L, 2L), sample = c("TCGA-05-4417-01A-22D-1854-01", 
"TCGA-05-4417-01A-22D-1854-01", "TCGA-05-4417-01A-22D-1854-01", 
"TCGA-06-0644-01A-02D-0310-01", "TCGA-06-0644-01A-02D-0310-01", 
"TCGA-06-0644-01A-02D-0310-01")), class = "data.frame", row.names = c("1:", 
"2:", "3:", "4:", "5:", "6:"))

df <- df %>% 
pivot_wider(names_from = sample, values_from = segVal, values_fill = 0)

#> # A tibble: 6 x 5
#>   chromosome    start      end `TCGA-05-4417-01A-22D-1… `TCGA-06-0644-01A-02D-0…
#>   <chr>         <int>    <int>                    <int>                    <int>
#> 1 chr1         3218923   116319008                    2                        0                        
#> 2 chr1         116324707 120523902                    1                        0
#> 3 chr1         149879545 247812431                    4                        0
#> 4 chr1         3218923   104393357                    0                        2
#> 5 chr1         104418619 149879545                    0                        1
#> 6 chr1         149885583 247812431                    0                        2

^{Created on 2020-08-24 by the reprex package (v0.3.0)}