From de6ca34031286ec0bdad7575294719c4558416fb Mon Sep 17 00:00:00 2001
From: pdiakumis <peterdiakumis@gmail.com>
Date: Tue, 1 Oct 2024 00:06:33 +1000
Subject: [PATCH] alignqc dl_and_tidy.R: add envvar checker

---
 .../alignment_qc/dl_and_tidy.R                | 12 ++++++++++-
 .../umccr_workflows/alignment_qc/summary.Rmd  | 20 ++++++++++++-------
 2 files changed, 24 insertions(+), 8 deletions(-)

diff --git a/inst/rmd/umccr_workflows/alignment_qc/dl_and_tidy.R b/inst/rmd/umccr_workflows/alignment_qc/dl_and_tidy.R
index 836e7f2..f5ed36b 100755
--- a/inst/rmd/umccr_workflows/alignment_qc/dl_and_tidy.R
+++ b/inst/rmd/umccr_workflows/alignment_qc/dl_and_tidy.R
@@ -8,6 +8,15 @@
   require(rportal, include.only = c("portaldb_query_workflow"))
 }
 
+# make sure you have logged into AWS and ICA
+c("AWS_ACCESS_KEY_ID", "AWS_SECRET_ACCESS_KEY", "AWS_REGION") |>
+  rportal::envvar_defined() |>
+  stopifnot()
+icav1_token <- Sys.getenv("ICA_ACCESS_TOKEN") |>
+  dracarys::ica_token_validate()
+# this helps keep annoying reticulate prompt away
+Sys.setenv(RETICULATE_PYTHON = Sys.getenv("CONDA_PYTHON_EXE"))
+
 query_workflow_alignqc <- function(start_date) {
   wfs <- c("wgs_alignment_qc", "wts_alignment_qc") |>
     shQuote() |>
@@ -28,7 +37,7 @@ query_limsrow_libids <- function(libids) {
 }
 
 # first read in the workflows table, extract metadata, then join with lims
-start_date <- "2024-09-09"
+start_date <- "2024-09-27"
 p_raw <- query_workflow_alignqc(start_date)
 
 wgs <- p_raw |>
@@ -76,6 +85,7 @@ meta <- d |>
         "echo ---{.data$rownum}--- && ",
         "{tidy_script} tidy --in_dir {.data$indir} ",
         "--out_dir {.data$outdir} --prefix {.data$SampleID} ",
+        "--token {icav1_token} ",
         "--format rds"
       )
     )
diff --git a/inst/rmd/umccr_workflows/alignment_qc/summary.Rmd b/inst/rmd/umccr_workflows/alignment_qc/summary.Rmd
index 7c44233..b40fbe7 100644
--- a/inst/rmd/umccr_workflows/alignment_qc/summary.Rmd
+++ b/inst/rmd/umccr_workflows/alignment_qc/summary.Rmd
@@ -9,7 +9,7 @@ output:
     highlight: kate
 params:
   title: "UMCCR Alignment QC Summary Report"
-  meta: !r here::here("inst/rmd/umccr_workflows/alignment_qc/nogit/meta/2024-09-14_wgts.rds")
+  meta: !r here::here("inst/rmd/umccr_workflows/alignment_qc/nogit/meta/2024-09-27_wgts.rds")
 description: "UMCCR Alignment QC Summary Report"
 title: "`r params$title`"
 ---
@@ -401,7 +401,8 @@ f1_plot <- ggplot() +
     subtitle = glue("Percentage of reads with average quality scores. Shows if\na subset of reads has poor quality.")
   )
 
-plotly::ggplotly(f1_plot)
+# plotly::ggplotly(f1_plot)
+f1_plot
 ```
 
 ### GC Content ('Per-Sequence GC Content')
@@ -426,7 +427,8 @@ gc_data_plot <- gc_data |>
     title = "Read GC Content",
     subtitle = glue("Total number of reads with each GC content\npercentile between 0% and 100%")
   )
-plotly::ggplotly(gc_data_plot)
+# plotly::ggplotly(gc_data_plot)
+gc_data_plot
 ```
 
 ### GC Content Quality ('GC Content Mean Quality Scores')
@@ -452,7 +454,8 @@ f1_plot <- ggplot() +
     title = "GC Content Quality",
     subtitle = glue("Average Phred-scale read mean quality for reads with\neach GC content percentile between 0% and 100%.")
   )
-plotly::ggplotly(f1_plot)
+# plotly::ggplotly(f1_plot)
+f1_plot
 ```
 
 ### Positional Base Content ('Per-Position Sequence Content')
@@ -543,7 +546,8 @@ read_len_plot <- read_len |>
     title = "Read Lengths",
     subtitle = glue("Read percentage with each observed length.")
   )
-plotly::ggplotly(read_len_plot)
+# plotly::ggplotly(read_len_plot)
+read_len_plot
 ```
 
 ### Sequence Positions ('Adapter Content')
@@ -609,7 +613,8 @@ flp <- fl1 |>
     panel.grid.minor = ggplot2::element_blank(),
     plot.title = ggplot2::element_text(colour = "#2c3e50", size = 14, face = "bold")
   )
-plotly::ggplotly(flp)
+# plotly::ggplotly(flp)
+flp
 ```
 
 ---
@@ -633,7 +638,8 @@ d_pl_plot <- d_pl_plot_data |>
   geom_line(aes(colour = umccrid, group = umccrid), na.rm = TRUE) +
   geom_point(aes(colour = umccrid), na.rm = TRUE) +
   labs(title = "Chromosome Median / Autosomal Median")
-plotly::ggplotly(d_pl_plot)
+# plotly::ggplotly(d_pl_plot)
+d_pl_plot
 ```