Load Purity and Ploidy estimates

Results from PureCN run on discovery and validation sets.

target_purity()

Value

A data.frame with columns Source, Purity, Ploidy, and dataset

Examples

pure = target_purity()
#> Warning: Missing column names filled in: 'X23' [23], 'X25' [25], 'X26' [26], 'X27' [27], 'X28' [28]
#> Warning: Duplicated column names deduplicated: 'SampleName' => 'SampleName_1' [21], 'SampleName' => 'SampleName_2' [22], 'Sample_Name_Roche' => 'Sample_Name_Roche_1' [24]
head(pure)
#> # A tibble: 6 x 4
#>   Source Purity Ploidy dataset  
#>   <chr>   <dbl>  <dbl> <chr>    
#> 1 0A4HLD   0.65   2.80 Discovery
#> 2 0A4HMC   0.33   2.66 Discovery
#> 3 0A4HX8   0.87   5.26 Discovery
#> 4 0A4I6O   0.53   1.59 Discovery
#> 5 0A4HXS   0.39   2.14 Discovery
#> 6 0A4HY5   0.66   2.51 Discovery
library(magrittr)
library(dplyr)
#> 
#> Attaching package: ‘dplyr’
#> The following object is masked from ‘package:matrixStats’:
#> 
#>     count
#> The following object is masked from ‘package:Biobase’:
#> 
#>     combine
#> The following objects are masked from ‘package:GenomicRanges’:
#> 
#>     intersect, setdiff, union
#> The following object is masked from ‘package:GenomeInfoDb’:
#> 
#>     intersect
#> The following objects are masked from ‘package:IRanges’:
#> 
#>     collapse, desc, intersect, setdiff, slice, union
#> The following objects are masked from ‘package:S4Vectors’:
#> 
#>     first, intersect, rename, setdiff, setequal, union
#> The following objects are masked from ‘package:BiocGenerics’:
#> 
#>     combine, intersect, setdiff, union
#> The following objects are masked from ‘package:dbplyr’:
#> 
#>     ident, sql
#> The following objects are masked from ‘package:stats’:
#> 
#>     filter, lag
#> The following objects are masked from ‘package:base’:
#> 
#>     intersect, setdiff, setequal, union
pure %>%
  group_by(dataset) %>%
  summarise(medploidy = median(Ploidy, na.rm=TRUE),
            medpurity = median(Purity, na.rm=TRUE),
            lowpurity = quantile(Purity, 0.1, na.rm=TRUE))
#> # A tibble: 2 x 4
#>   dataset    medploidy medpurity lowpurity
#>   <chr>          <dbl>     <dbl>     <dbl>
#> 1 Discovery       3.10      0.6      0.359
#> 2 Validation      2.92      0.55     0.252
library(ggplot2)
p = ggplot(pure, aes(x=Purity)) +
  geom_density(aes(group=dataset, color=dataset)) +
  ggtitle('Tumor Purity Estimates')
print(p)