Read WGS Data — read_wgs

Reads WGS data, including PCGR tiers.tsv, PURPLE cnv.gene.tsv, and sv.prioritised.tsv. If the file path has been specified in the RNAsum params and is valid, it is returned. As a fallback, if the umccrise directory param has been specified, then there is an attempt to detect the file pattern in there.

Usage

read_wgs_data(p)

Arguments

p: RNAsum params list.

Value

A list of the input sample data.

Examples

p <- list(
  umccrise = system.file("rawdata/test_data/umccrised/test_sample_WGS", package = "RNAsum"),
  pcgr_tiers_tsv = system.file(
    "rawdata/test_data/umccrised/test_sample_WGS/small_variants",
    "TEST-somatic.pcgr.snvs_indels.tiers.tsv",
    package = "RNAsum"
  ),
  sash_tsv = system.file(
    "rawdata/test_data/test_sample_WGS/structural/TEST.sv.prioritised.tsv",
    package = "RNAsum"
  )
)
(res <- read_wgs_data(p))
#> $pcgr_tiers_tsv
#> # A tibble: 99 × 61
#>    CHROM POS       REF   ALT   GENOMIC_CHANGE    GENOME_VERSION VCF_SAMPLE_ID   
#>    <chr> <chr>     <chr> <chr> <chr>             <chr>          <chr>           
#>  1 3     179218303 G     A     3:g.179218303G>A  grch38         SBJ02999__PRJ22…
#>  2 17    7674894   G     A     17:g.7674894G>A   grch38         SBJ02999__PRJ22…
#>  3 13    110715614 C     G     13:g.110715614C>G grch38         SBJ02999__PRJ22…
#>  4 13    110719444 G     C     13:g.110719444G>C grch38         SBJ02999__PRJ22…
#>  5 8     20250093  C     T     8:g.20250093C>T   grch38         SBJ02999__PRJ22…
#>  6 8     13086457  C     T     8:g.13086457C>T   grch38         SBJ02999__PRJ22…
#>  7 10    31521795  G     C     10:g.31521795G>C  grch38         SBJ02999__PRJ22…
#>  8 9     132927250 G     A     9:g.132927250G>A  grch38         SBJ02999__PRJ22…
#>  9 3     47121452  G     A     3:g.47121452G>A   grch38         SBJ02999__PRJ22…
#> 10 6     117365075 G     C     6:g.117365075G>C  grch38         SBJ02999__PRJ22…
#> # ℹ 89 more rows
#> # ℹ 54 more variables: VARIANT_CLASS <chr>, SYMBOL <chr>, GENE_NAME <chr>,
#> #   CCDS <chr>, CANONICAL <chr>, ENTREZ_ID <chr>, UNIPROT_ID <chr>,
#> #   ENSEMBL_TRANSCRIPT_ID <chr>, ENSEMBL_GENE_ID <chr>, REFSEQ_MRNA <chr>,
#> #   ONCOSCORE <chr>, ONCOGENE <chr>, TUMOR_SUPPRESSOR <chr>,
#> #   ONCOGENE_EVIDENCE <chr>, TUMOR_SUPPRESSOR_EVIDENCE <chr>,
#> #   DISGENET_CUI <chr>, DISGENET_TERMS <chr>, CONSEQUENCE <chr>, …
#> 
#> $purple_gene_tsv
#> # A tibble: 25,417 × 20
#>    chromosome  start    end gene        minCopyNumber maxCopyNumber unused
#>    <chr>       <dbl>  <dbl> <chr>               <dbl>         <dbl> <chr> 
#>  1 chr1        11869  14409 DDX11L1              1.98          1.98 0     
#>  2 chr1        14404  29570 WASH7P               1.98          1.98 0     
#>  3 chr1        17369  17436 MIR6859-1            1.98          1.98 0     
#>  4 chr1        29554  31097 MIR1302-2HG          1.98          1.98 0     
#>  5 chr1        30366  30503 MIR1302-2            1.98          1.98 0     
#>  6 chr1        34554  36081 FAM138A              1.98          1.98 0     
#>  7 chr1        69091  70008 OR4F5                1.98          1.98 0     
#>  8 chr1       185217 195411 FO538757.1           1.98          1.98 0     
#>  9 chr1       187891 187958 MIR6859-2            1.98          1.98 0     
#> 10 chr1       450740 451678 OR4F29               1.98          1.98 0     
#> # ℹ 25,407 more rows
#> # ℹ 13 more variables: somaticRegions <dbl>, germlineHomDeletionRegions <dbl>,
#> #   germlineHetToHomDeletionRegions <dbl>, transcriptId <chr>,
#> #   transcriptVersion <chr>, chromosomeBand <chr>, minRegions <dbl>,
#> #   minRegionStart <dbl>, minRegionEnd <dbl>, minRegionStartSupport <chr>,
#> #   minRegionEndSupport <chr>, minRegionMethod <chr>,
#> #   minMinorAlleleCopyNumber <dbl>
#> 
#> $sv_tsv
#> NULL
#>