Function to transform mutations into "matrix" format

Source: R/make_matrix.R

Transform a data frame of mutations in long format into a data frame of trinucleotide mutations with flanking bases in a wide matrix format.

make_matrix(data, genome = "hg19")

Arguments

data

a data frame of mutations in VCF format (see vignette for details)
genome

the reference genome used ("hg19" or "hg38")

Value

make_matrix returns a data frame of mutations, one row per sample

Examples


head(example_dt) # use example data from package

#>   sample_id age chromosome  position ref alt
#> 1         1  50       chr1  94447621   G   C
#> 2         1  50       chr2 202005395   A   C
#> 3         1  50       chr7  20784978   T   A
#> 4         1  50       chr7  87179255   C   G
#> 5         1  50      chr19   1059712   G   T
#> 6         2  55       chr1  76226977   T   C
input_dt <- make_matrix(example_dt) # convert to correct format
head(input_dt)

#> # A tibble: 5 x 98
#>   sample_id   age `A[T>G]T` `C[T>A]A` `G[C>A]A` `G[C>G]G` `G[C>G]T` `A[C>G]T`
#>       <dbl> <dbl>     <dbl>     <dbl>     <dbl>     <dbl>     <dbl>     <dbl>
#> 1         1    50         1         1         1         1         1         0
#> 2         2    55         0         0         0         0         0         1
#> 3         3    72         1         1         0         0         0         0
#> 4         4    53         0         0         0         0         0         1
#> 5         5    48         0         1         1         0         0         0
#> # … with 90 more variables: C[C>A]T <dbl>, C[T>C]G <dbl>, T[C>A]C <dbl>,
#> #   T[C>A]T <dbl>, A[T>C]C <dbl>, C[T>C]C <dbl>, T[T>A]C <dbl>, C[C>G]G <dbl>,
#> #   G[C>T]A <dbl>, A[C>A]T <dbl>, C[C>A]C <dbl>, G[T>G]T <dbl>, C[C>T]C <dbl>,
#> #   T[C>T]C <dbl>, A[C>T]C <dbl>, G[C>T]C <dbl>, C[C>T]T <dbl>, T[C>T]T <dbl>,
#> #   A[C>T]T <dbl>, G[C>T]T <dbl>, C[C>T]A <dbl>, T[C>T]A <dbl>, A[C>T]A <dbl>,
#> #   C[C>T]G <dbl>, T[C>T]G <dbl>, A[C>T]G <dbl>, G[C>T]G <dbl>, A[C>A]C <dbl>,
#> #   G[C>A]C <dbl>, G[C>A]T <dbl>, C[C>A]A <dbl>, T[C>A]A <dbl>, A[C>A]A <dbl>,
#> #   C[C>A]G <dbl>, T[C>A]G <dbl>, A[C>A]G <dbl>, G[C>A]G <dbl>, C[C>G]C <dbl>,
#> #   T[C>G]C <dbl>, A[C>G]C <dbl>, G[C>G]C <dbl>, C[C>G]T <dbl>, T[C>G]T <dbl>,
#> #   C[C>G]A <dbl>, T[C>G]A <dbl>, A[C>G]A <dbl>, G[C>G]A <dbl>, T[C>G]G <dbl>,
#> #   A[C>G]G <dbl>, T[T>C]C <dbl>, G[T>C]C <dbl>, C[T>C]T <dbl>, T[T>C]T <dbl>,
#> #   A[T>C]T <dbl>, G[T>C]T <dbl>, C[T>C]A <dbl>, T[T>C]A <dbl>, A[T>C]A <dbl>,
#> #   G[T>C]A <dbl>, T[T>C]G <dbl>, A[T>C]G <dbl>, G[T>C]G <dbl>, C[T>A]C <dbl>,
#> #   A[T>A]C <dbl>, G[T>A]C <dbl>, C[T>A]T <dbl>, T[T>A]T <dbl>, A[T>A]T <dbl>,
#> #   G[T>A]T <dbl>, T[T>A]A <dbl>, A[T>A]A <dbl>, G[T>A]A <dbl>, C[T>A]G <dbl>,
#> #   T[T>A]G <dbl>, A[T>A]G <dbl>, G[T>A]G <dbl>, C[T>G]C <dbl>, T[T>G]C <dbl>,
#> #   A[T>G]C <dbl>, G[T>G]C <dbl>, C[T>G]T <dbl>, T[T>G]T <dbl>, C[T>G]A <dbl>,
#> #   T[T>G]A <dbl>, A[T>G]A <dbl>, G[T>G]A <dbl>, C[T>G]G <dbl>, T[T>G]G <dbl>,
#> #   A[T>G]G <dbl>, G[T>G]G <dbl>