This script isolates the detection-threshold boxplot panel, matching the read-level detection timing view from the full analysis workflow. This code reproduces the base graphic reported in the article Single-workflow Nanopore whole genome sequencing with adaptive sampling for accelerated and comprehensive pediatric cancer profiling.

Data setup

library(dplyr)
library(tidyr)
library(ggplot2)

set.seed(99)

first_hits_long <- tidyr::crossing(
  sample_name = paste0("sample_", LETTERS[1:8]),
  variant_group_id = paste0("var", sprintf("%03d", 1:40)),
  detection_level = c(1, 5, 8, 10)
) %>%
  mutate(
    vaf_bin = sample(
      c("<5%", "5-10%", "10-25%", ">25%"),
      n(),
      replace = TRUE
    ),
    variant_type = sample(
      c("SNV", "INDEL", "BND"),
      n(),
      replace = TRUE
    ),
    panel = sample(
      c(TRUE, FALSE),
      n(),
      replace = TRUE,
      prob = c(0.7, 0.3)
    ),
    time_h = pmin(
      72,
      rgamma(n(), shape = detection_level / 2, scale = 3.5)
    )
  )

Isolated plot

p_detection <- first_hits_long %>%
  ggplot() +
  geom_boxplot(
    aes(
      x = time_h,
      y = detection_level,
      group = interaction(detection_level, variant_type),
      color = variant_type
    )
  ) +
  scale_x_continuous(
    breaks = seq(0, 72, by = 12),
    minor_breaks = seq(0, 72, by = 6)
  ) +
  scale_y_continuous(breaks = c(1, 5, 8, 10)) +
  facet_grid(
    panel ~ vaf_bin,
    labeller = labeller(
      panel = function(x) {
        ifelse(x, "In Panel Genes", "Out of Panel Genes")
      },
      vaf_bin = function(x) paste("VAF:", x)
    )
  ) +
  labs(
    x = "Sequencing Time (Hours)",
    y = "Detection Support (Number of Reads)",
    title = "Detection Time by Variant Type and VAF"
  ) +
  theme_bw(base_size = 12) +
  theme(axis.text.x = element_text(angle = 45, hjust = 1))

p_detection

Session Info

## R version 4.5.2 (2025-10-31)
## Platform: x86_64-pc-linux-gnu
## Running under: Linux Mint 22.2
## 
## Matrix products: default
## BLAS:   /usr/lib/x86_64-linux-gnu/blas/libblas.so.3.12.0 
## LAPACK: /usr/lib/x86_64-linux-gnu/lapack/liblapack.so.3.12.0  LAPACK version 3.12.0
## 
## locale:
##  [1] LC_CTYPE=en_CA.UTF-8       LC_NUMERIC=C              
##  [3] LC_TIME=en_CA.UTF-8        LC_COLLATE=en_CA.UTF-8    
##  [5] LC_MONETARY=en_CA.UTF-8    LC_MESSAGES=en_CA.UTF-8   
##  [7] LC_PAPER=en_CA.UTF-8       LC_NAME=C                 
##  [9] LC_ADDRESS=C               LC_TELEPHONE=C            
## [11] LC_MEASUREMENT=en_CA.UTF-8 LC_IDENTIFICATION=C       
## 
## time zone: America/Toronto
## tzcode source: system (glibc)
## 
## attached base packages:
## [1] stats     graphics  grDevices utils     datasets  methods   base     
## 
## loaded via a namespace (and not attached):
##  [1] digest_0.6.39   R6_2.6.1        bookdown_0.46   fastmap_1.2.0  
##  [5] xfun_0.56       blogdown_1.23   cachem_1.1.0    knitr_1.51     
##  [9] htmltools_0.5.9 rmarkdown_2.30  lifecycle_1.0.5 cli_3.6.5      
## [13] sass_0.4.10     jquerylib_0.1.4 compiler_4.5.2  tools_4.5.2    
## [17] evaluate_1.0.5  bslib_0.10.0    yaml_2.3.12     otel_0.2.0     
## [21] jsonlite_2.0.0  rlang_1.1.7