From 91728870c3b98892b17cb840510c78200b9f768f Mon Sep 17 00:00:00 2001
From: pdiakumis <peterdiakumis@gmail.com>
Date: Tue, 31 Oct 2023 23:54:24 +1100
Subject: [PATCH 1/8] wip

---
 inst/rmd/umccr_portal/portal_summary.Rmd    | 7 ++++---
 inst/rmd/umccr_workflows/umccrise/multi.Rmd | 4 ++--
 man/portal_meta_read_athena.Rd              | 2 +-
 3 files changed, 7 insertions(+), 6 deletions(-)

diff --git a/inst/rmd/umccr_portal/portal_summary.Rmd b/inst/rmd/umccr_portal/portal_summary.Rmd
index 750ff44..9037bcd 100644
--- a/inst/rmd/umccr_portal/portal_summary.Rmd
+++ b/inst/rmd/umccr_portal/portal_summary.Rmd
@@ -111,10 +111,11 @@ get_sbj_url <- function(x, colour = NULL, account = "") {
 ```
 
 ```{r vars}
+# Get metadata for workflows run within the date range
 # options(width = 150)
 fmt1 <- "%Y-%m-%dT%H:%M:%S"
-date_start <- as.POSIXct("2023-09-15T00:00:01", format = fmt1)
-date_end <- as.POSIXct("2023-09-18T23:59:59", format = fmt1)
+date_start <- as.POSIXct("2023-10-28T00:00:01", format = fmt1)
+date_end <- as.POSIXct("2023-10-29T23:59:59", format = fmt1)
 wf_order <- c(
   "bcl_convert",
   "tso_ctdna_tumor_only",
@@ -130,7 +131,7 @@ lims_rds <- here(glue("nogit/data_portal/lims/{as.Date(date_end)}.rds"))
 # saveRDS(lims_raw, file = lims_rds)
 lims_raw <- readr::read_rds(lims_rds)
 pmeta_rds <- here(glue("nogit/data_portal/workflows/{as.Date(date_end)}.rds"))
-# pmeta_raw <- dracarys::portal_meta_read(rows = 80, account = "stg")
+# pmeta_raw <- dracarys::portal_meta_read(rows = 50, account = "prod")
 # saveRDS(pmeta_raw, file = pmeta_rds)
 pmeta_raw <- readr::read_rds(pmeta_rds)
 pmeta <- pmeta_raw |>
diff --git a/inst/rmd/umccr_workflows/umccrise/multi.Rmd b/inst/rmd/umccr_workflows/umccrise/multi.Rmd
index 21b7bb2..9547b21 100644
--- a/inst/rmd/umccr_workflows/umccrise/multi.Rmd
+++ b/inst/rmd/umccr_workflows/umccrise/multi.Rmd
@@ -183,7 +183,7 @@ dat_s3 <- dat_s3_raw |>
     hash256 = substr(hash256, 1, 8),
     portal_run_id = glue("fake.{date_dir}{hash256}")
   ) |>
-  select(-c(um_dir, date_dir, hash256, SampleID_tumor))
+  select(-c(date_dir, hash256, SampleID_tumor))
 dat_gds <- fs::dir_ls(here("nogit/umccrise/rds/results"), regexp = "x[1-5]{1}.rds") |>
   purrr::map(readr::read_rds) |>
   bind_rows()
@@ -302,7 +302,7 @@ cols_select1 <- c(
   "qc_status_hmf", "sex_hmf", "purity_hmf", "ploidy_hmf", "msi_hmf",
   "msi_mb_hmf", "contamination_hmf",
   "deleted_genes_hmf", "tmb_hmf", "tml_hmf", "wgd_hmf", "hypermutated",
-  "bpi_enabled", "portal_run_id", "portal_url"
+  "bpi_enabled", "portal_run_id", "portal_url", "um_dir"
 )
 # signatures
 dsig <- bind_rows(list(s2015 = sigs_2015, s2020 = sigs_2020), .id = "Sig_group") |>
diff --git a/man/portal_meta_read_athena.Rd b/man/portal_meta_read_athena.Rd
index 5650f99..c62efc9 100644
--- a/man/portal_meta_read_athena.Rd
+++ b/man/portal_meta_read_athena.Rd
@@ -17,7 +17,7 @@ Reads the ICA Workflows Metadata for the given workflow run IDs.
 }
 \examples{
 \dontrun{
-wfrids <- c('wfr.1e764ca00e7a43a69e2424f250a34868')
+wfrids <- c("wfr.1e764ca00e7a43a69e2424f250a34868")
 portal_meta_read_athena(wfrids)
 }
 }

From 615471d8f14f63caafd812aa647178f422e9bae5 Mon Sep 17 00:00:00 2001
From: pdiakumis <peterdiakumis@gmail.com>
Date: Wed, 1 Nov 2023 00:39:26 +1100
Subject: [PATCH 2/8] meta for sash + oncoa-wgs

---
 R/portal_meta.R | 102 ++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 102 insertions(+)

diff --git a/R/portal_meta.R b/R/portal_meta.R
index a0aee4c..a311c3a 100644
--- a/R/portal_meta.R
+++ b/R/portal_meta.R
@@ -435,6 +435,92 @@ meta_tso_ctdna_tumor_only <- function(pmeta, status = c("Succeeded")) {
     )
 }
 
+meta_sash <- function(pmeta, status = "Succeeded") {
+  # retrieve workflow runs with the given type and status
+  type <- "sash"
+  wf <- portal_meta_read(pmeta) |>
+    dplyr::filter(
+      .data$type_name == type,
+      .data$end_status %in% status
+    )
+  if (nrow(wf) == 0) {
+    return(wf)
+  }
+  # grab libid/sampleid from the input meta, and outdir from the output meta
+  d <- wf |>
+    meta_io_fromjson() |>
+    dplyr::mutate(
+      # input
+      SubjectID = purrr::map_chr(.data$input, "subject_id", .default = NA),
+      SampleID_tumor = purrr::map_chr(.data$input, "tumor_sample_id", .default = NA),
+      SampleID_normal = purrr::map_chr(.data$input, "normal_sample_id", .default = NA),
+      LibraryID_tumor = purrr::map_chr(.data$input, "tumor_library_id", .default = NA),
+      LibraryID_normal = purrr::map_chr(.data$input, "normal_library_id", .default = NA),
+      gds_indir_dragen_somatic = purrr::map_chr(.data$input, "dragen_somatic_dir", .default = NA),
+      gds_indir_dragen_germline = purrr::map_chr(.data$input, "dragen_germline_dir", .default = NA),
+      s3_indir_oncoanalyser = purrr::map_chr(.data$input, "oncoanalyser_dir", .default = NA),
+      # output
+      s3_outdir_sash = purrr::map_chr(.data$output, "output_directory", .default = NA)
+    )
+  d |>
+    dplyr::select(
+      meta_main_cols(),
+      -dplyr::any_of(c("sequence_run_id", "batch_run_id")), # NA for sash
+      "SubjectID",
+      "LibraryID_tumor",
+      "LibraryID_normal",
+      "SampleID_tumor",
+      "SampleID_normal",
+      "s3_outdir_sash",
+      "s3_indir_oncoanalyser",
+      "gds_indir_dragen_somatic",
+      "gds_indir_dragen_germline"
+    )
+}
+
+meta_oncoanalyser_wgs <- function(pmeta, status = "Succeeded") {
+  # retrieve workflow runs with the given type and status
+  type <- "oncoanalyser_wgs"
+  wf <- portal_meta_read(pmeta) |>
+    dplyr::filter(
+      .data$type_name == type,
+      .data$end_status %in% status
+    )
+  if (nrow(wf) == 0) {
+    return(wf)
+  }
+  # grab libid/sampleid from the input meta, and outdir from the output meta
+  d <- wf |>
+    meta_io_fromjson() |>
+    dplyr::mutate(
+      # input
+      SubjectID = purrr::map_chr(.data$input, "subject_id", .default = NA),
+      SampleID_tumor = purrr::map_chr(.data$input, "tumor_wgs_sample_id", .default = NA),
+      SampleID_normal = purrr::map_chr(.data$input, "normal_wgs_sample_id", .default = NA),
+      LibraryID_tumor = purrr::map_chr(.data$input, "tumor_wgs_library_id", .default = NA),
+      LibraryID_normal = purrr::map_chr(.data$input, "normal_wgs_library_id", .default = NA),
+      gds_bam_tumor = purrr::map_chr(.data$input, "tumor_wgs_bam", .default = NA),
+      gds_bam_normal = purrr::map_chr(.data$input, "normal_wgs_bam", .default = NA),
+      mode = purrr::map_chr(.data$input, "mode", .default = NA),
+      # output
+      s3_outdir_oncoanalyser = purrr::map_chr(.data$output, "output_directory", .default = NA)
+    )
+  d |>
+    dplyr::select(
+      meta_main_cols(),
+      -dplyr::any_of(c("sequence_run_id", "batch_run_id")), # NA for sash
+      "SubjectID",
+      "LibraryID_tumor",
+      "LibraryID_normal",
+      "SampleID_tumor",
+      "SampleID_normal",
+      "s3_outdir_oncoanalyser",
+      "gds_bam_tumor",
+      "gds_bam_normal"
+    )
+}
+
+
 meta_io_fromjson <- function(pmeta) {
   pmeta <- portal_meta_read(pmeta)
   pmeta |>
@@ -558,3 +644,19 @@ portal_meta_read_athena <- function(wfrids = NULL) {
   RAthena::dbGetQuery(con, q1) |>
     tibble::as_tibble()
 }
+
+
+portal_meta_read_athena_tmp <- function(x = NULL) {
+  assertthat::assert_that(!is.null(x))
+  RAthena::RAthena_options(clear_s3_resource = FALSE)
+  con <- DBI::dbConnect(
+    RAthena::athena(),
+    work_group = "data_portal",
+    rstudio_conn_tab = FALSE
+  )
+  q1 <- glue(
+    'SELECT * FROM "data_portal"."data_portal"."data_portal_workflow" {x}'
+  )
+  RAthena::dbGetQuery(con, q1) |>
+    tibble::as_tibble()
+}

From 7dda48032554d8e520e0fb3c952b4cfc29687f0e Mon Sep 17 00:00:00 2001
From: pdiakumis <peterdiakumis@gmail.com>
Date: Wed, 1 Nov 2023 08:47:23 +1100
Subject: [PATCH 3/8] meta for oncoa-wts + oncoa-wgts

---
 R/portal_meta.R | 82 +++++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 79 insertions(+), 3 deletions(-)

diff --git a/R/portal_meta.R b/R/portal_meta.R
index a311c3a..d9f29b6 100644
--- a/R/portal_meta.R
+++ b/R/portal_meta.R
@@ -465,7 +465,6 @@ meta_sash <- function(pmeta, status = "Succeeded") {
   d |>
     dplyr::select(
       meta_main_cols(),
-      -dplyr::any_of(c("sequence_run_id", "batch_run_id")), # NA for sash
       "SubjectID",
       "LibraryID_tumor",
       "LibraryID_normal",
@@ -501,14 +500,12 @@ meta_oncoanalyser_wgs <- function(pmeta, status = "Succeeded") {
       LibraryID_normal = purrr::map_chr(.data$input, "normal_wgs_library_id", .default = NA),
       gds_bam_tumor = purrr::map_chr(.data$input, "tumor_wgs_bam", .default = NA),
       gds_bam_normal = purrr::map_chr(.data$input, "normal_wgs_bam", .default = NA),
-      mode = purrr::map_chr(.data$input, "mode", .default = NA),
       # output
       s3_outdir_oncoanalyser = purrr::map_chr(.data$output, "output_directory", .default = NA)
     )
   d |>
     dplyr::select(
       meta_main_cols(),
-      -dplyr::any_of(c("sequence_run_id", "batch_run_id")), # NA for sash
       "SubjectID",
       "LibraryID_tumor",
       "LibraryID_normal",
@@ -520,6 +517,85 @@ meta_oncoanalyser_wgs <- function(pmeta, status = "Succeeded") {
     )
 }
 
+meta_oncoanalyser_wgts_existing_both <- function(pmeta, status = "Succeeded") {
+  # retrieve workflow runs with the given type and status
+  type <- "oncoanalyser_wgts_existing_both"
+  wf <- portal_meta_read(pmeta) |>
+    dplyr::filter(
+      .data$type_name == type,
+      .data$end_status %in% status
+    )
+  if (nrow(wf) == 0) {
+    return(wf)
+  }
+  # grab libid/sampleid from the input meta, and outdir from the output meta
+  d <- wf |>
+    meta_io_fromjson() |>
+    dplyr::mutate(
+      # input
+      SubjectID = purrr::map_chr(.data$input, "subject_id", .default = NA),
+      SampleID_tumor_wgs = purrr::map_chr(.data$input, "tumor_wgs_sample_id", .default = NA),
+      SampleID_normal_wgs = purrr::map_chr(.data$input, "normal_wgs_sample_id", .default = NA),
+      SampleID_tumor_wts = purrr::map_chr(.data$input, "tumor_wts_sample_id", .default = NA),
+      LibraryID_tumor_wgs = purrr::map_chr(.data$input, "tumor_wgs_library_id", .default = NA),
+      LibraryID_normal_wgs = purrr::map_chr(.data$input, "normal_wgs_library_id", .default = NA),
+      LibraryID_tumor_wts = purrr::map_chr(.data$input, "tumor_wts_library_id", .default = NA),
+      gds_bam_tumor_wgs = purrr::map_chr(.data$input, "tumor_wgs_bam", .default = NA),
+      gds_bam_normal_wgs = purrr::map_chr(.data$input, "normal_wgs_bam", .default = NA),
+      s3_bam_tumor_wts = purrr::map_chr(.data$input, "tumor_wts_bam", .default = NA),
+      s3_indir_oncoanalyser_wgs = purrr::map_chr(.data$input, "existing_wgs_dir", .default = NA),
+      s3_indir_oncoanalyser_wts = purrr::map_chr(.data$input, "existing_wts_dir", .default = NA),
+      # output
+      s3_outdir_oncoanalyser = purrr::map_chr(.data$output, "output_directory", .default = NA)
+    )
+  d |>
+    dplyr::select(
+      meta_main_cols(),
+      "SubjectID",
+      "LibraryID_tumor",
+      "LibraryID_normal",
+      "SampleID_tumor",
+      "SampleID_normal",
+      "s3_outdir_oncoanalyser",
+      "gds_bam_tumor",
+      "gds_bam_normal"
+    )
+}
+
+meta_oncoanalyser_wts <- function(pmeta, status = "Succeeded") {
+  # retrieve workflow runs with the given type and status
+  type <- "oncoanalyser_wts"
+  wf <- portal_meta_read(pmeta) |>
+    dplyr::filter(
+      .data$type_name == type,
+      .data$end_status %in% status
+    )
+  if (nrow(wf) == 0) {
+    return(wf)
+  }
+  # grab libid/sampleid from the input meta, and outdir from the output meta
+  d <- wf |>
+    meta_io_fromjson() |>
+    dplyr::mutate(
+      # input
+      mode = purrr::map_chr(.data$input, "mode", .default = NA),
+      SubjectID = purrr::map_chr(.data$input, "subject_id", .default = NA),
+      SampleID_tumor = purrr::map_chr(.data$input, "tumor_wts_sample_id", .default = NA),
+      LibraryID_tumor = purrr::map_chr(.data$input, "tumor_wts_library_id", .default = NA),
+      s3_bam_tumor = purrr::map_chr(.data$input, "tumor_wts_bam", .default = NA),
+      # output
+      s3_outdir_oncoanalyser = purrr::map_chr(.data$output, "output_directory", .default = NA)
+    )
+  d |>
+    dplyr::select(
+      meta_main_cols(),
+      "SubjectID",
+      "LibraryID_tumor",
+      "SampleID_tumor",
+      "s3_bam_tumor",
+      "s3_outdir_oncoanalyser",
+    )
+}
 
 meta_io_fromjson <- function(pmeta) {
   pmeta <- portal_meta_read(pmeta)

From 9f7eea72b533105e0321afe9a4025162d6414495 Mon Sep 17 00:00:00 2001
From: pdiakumis <peterdiakumis@gmail.com>
Date: Wed, 1 Nov 2023 10:26:03 +1100
Subject: [PATCH 4/8] add docs + tests

---
 NAMESPACE                                     |  4 +
 R/portal_meta.R                               | 73 ++++++++++++++++---
 data-raw/portal_meta.R                        |  8 +-
 man/meta_oncoanalyser_wgs.Rd                  | 23 ++++++
 man/meta_oncoanalyser_wgts_existing_both.Rd   | 23 ++++++
 man/meta_oncoanalyser_wts.Rd                  | 23 ++++++
 man/meta_sash.Rd                              | 23 ++++++
 .../test-roxytest-testexamples-portal_meta.R  | 40 +++++++++-
 8 files changed, 201 insertions(+), 16 deletions(-)
 create mode 100644 man/meta_oncoanalyser_wgs.Rd
 create mode 100644 man/meta_oncoanalyser_wgts_existing_both.Rd
 create mode 100644 man/meta_oncoanalyser_wts.Rd
 create mode 100644 man/meta_sash.Rd

diff --git a/NAMESPACE b/NAMESPACE
index 95c343f..71d5c73 100644
--- a/NAMESPACE
+++ b/NAMESPACE
@@ -44,7 +44,11 @@ export(glims_read)
 export(ica_token_validate)
 export(match_regex)
 export(meta_bcl_convert)
+export(meta_oncoanalyser_wgs)
+export(meta_oncoanalyser_wgts_existing_both)
+export(meta_oncoanalyser_wts)
 export(meta_rnasum)
+export(meta_sash)
 export(meta_tso_ctdna_tumor_only)
 export(meta_umccrise)
 export(meta_wgs_alignment_qc)
diff --git a/R/portal_meta.R b/R/portal_meta.R
index d9f29b6..5983b27 100644
--- a/R/portal_meta.R
+++ b/R/portal_meta.R
@@ -8,7 +8,7 @@
 #' pmeta <- system.file("extdata/portal_meta_top4.csv", package = "dracarys")
 #' (m <- meta_bcl_convert(pmeta))
 #' @testexamples
-#' expect_equal(sum(!is.na(m$topup_or_rerun)), 22)
+#' expect_equal(sum(!is.na(m$topup_or_rerun)), 1)
 #' expect_equal(length(unique(m$portal_run_id)), 4)
 #' @export
 meta_bcl_convert <- function(pmeta, status = "Succeeded") {
@@ -128,8 +128,8 @@ meta_wts_tumor_only <- function(pmeta, status = "Succeeded") {
 #' pmeta <- system.file("extdata/portal_meta_top4.csv", package = "dracarys")
 #' (m <- meta_rnasum(pmeta))
 #' @testexamples
-#' expect_equal(m$rnasum_dataset[1], "LAML")
-#' expect_equal(basename(m$gds_outfile_rnasum_html[4]), "MDX230277.RNAseq_report.html")
+#' expect_equal(m$rnasum_dataset[1], "PANCAN")
+#' expect_equal(basename(m$gds_outfile_rnasum_html[4]), "MDX230467.RNAseq_report.html")
 #' @export
 meta_rnasum <- function(pmeta, status = "Succeeded") {
   # retrieve workflow runs with the given type and status
@@ -397,7 +397,7 @@ meta_umccrise <- function(pmeta, status = "Succeeded") {
 #' pmeta <- system.file("extdata/portal_meta_top4.csv", package = "dracarys")
 #' (m <- meta_tso_ctdna_tumor_only(pmeta))
 #' @testexamples
-#' expect_equal(length(unique(m$portal_run_id)), 4)
+#' expect_equal(length(unique(m$portal_run_id)), 2)
 #' @export
 meta_tso_ctdna_tumor_only <- function(pmeta, status = c("Succeeded")) {
   # retrieve workflow runs with the given type and status
@@ -435,6 +435,18 @@ meta_tso_ctdna_tumor_only <- function(pmeta, status = c("Succeeded")) {
     )
 }
 
+#' Metadata for sash workflow
+#'
+#' @param pmeta Path to portal workflows metadata table, or tibble with already parsed data.
+#' @param status Workflow status to keep (default: Succeeded).
+#'
+#' @return A tibble with metadata per workflow run.
+#' @examples
+#' pmeta <- system.file("extdata/portal_meta_top4.csv", package = "dracarys")
+#' (m <- meta_sash(pmeta))
+#' @testexamples
+#' expect_equal(all(c("s3_indir_oncoanalyser", "LibraryID_tumor", "s3_outdir_sash") %in% colnames(m)), TRUE)
+#' @export
 meta_sash <- function(pmeta, status = "Succeeded") {
   # retrieve workflow runs with the given type and status
   type <- "sash"
@@ -477,6 +489,18 @@ meta_sash <- function(pmeta, status = "Succeeded") {
     )
 }
 
+#' Metadata for oncoanalyser_wgs workflow
+#'
+#' @param pmeta Path to portal workflows metadata table, or tibble with already parsed data.
+#' @param status Workflow status to keep (default: Succeeded).
+#'
+#' @return A tibble with metadata per workflow run.
+#' @examples
+#' pmeta <- system.file("extdata/portal_meta_top4.csv", package = "dracarys")
+#' (m <- meta_oncoanalyser_wgs(pmeta))
+#' @testexamples
+#' expect_equal(all(c("s3_outdir_oncoanalyser", "LibraryID_tumor", "gds_bam_tumor") %in% colnames(m)), TRUE)
+#' @export
 meta_oncoanalyser_wgs <- function(pmeta, status = "Succeeded") {
   # retrieve workflow runs with the given type and status
   type <- "oncoanalyser_wgs"
@@ -517,6 +541,18 @@ meta_oncoanalyser_wgs <- function(pmeta, status = "Succeeded") {
     )
 }
 
+#' Metadata for oncoanalyser_wgts_existing_both workflow
+#'
+#' @param pmeta Path to portal workflows metadata table, or tibble with already parsed data.
+#' @param status Workflow status to keep (default: Succeeded).
+#'
+#' @return A tibble with metadata per workflow run.
+#' @examples
+#' pmeta <- system.file("extdata/portal_meta_top4.csv", package = "dracarys")
+#' (m <- meta_oncoanalyser_wgts_existing_both(pmeta))
+#' @testexamples
+#' expect_equal(all(c("s3_outdir_oncoanalyser", "LibraryID_tumor_wts", "gds_bam_tumor_wgs") %in% colnames(m)), TRUE)
+#' @export
 meta_oncoanalyser_wgts_existing_both <- function(pmeta, status = "Succeeded") {
   # retrieve workflow runs with the given type and status
   type <- "oncoanalyser_wgts_existing_both"
@@ -552,16 +588,33 @@ meta_oncoanalyser_wgts_existing_both <- function(pmeta, status = "Succeeded") {
     dplyr::select(
       meta_main_cols(),
       "SubjectID",
-      "LibraryID_tumor",
-      "LibraryID_normal",
-      "SampleID_tumor",
-      "SampleID_normal",
+      "LibraryID_tumor_wgs",
+      "LibraryID_normal_wgs",
+      "LibraryID_tumor_wts",
+      "SampleID_tumor_wgs",
+      "SampleID_normal_wgs",
+      "SampleID_tumor_wts",
       "s3_outdir_oncoanalyser",
-      "gds_bam_tumor",
-      "gds_bam_normal"
+      "s3_indir_oncoanalyser_wgs",
+      "s3_indir_oncoanalyser_wts",
+      "gds_bam_tumor_wgs",
+      "gds_bam_normal_wgs",
+      "s3_bam_tumor_wts"
     )
 }
 
+#' Metadata for oncoanalyser_wts workflow
+#'
+#' @param pmeta Path to portal workflows metadata table, or tibble with already parsed data.
+#' @param status Workflow status to keep (default: Succeeded).
+#'
+#' @return A tibble with metadata per workflow run.
+#' @examples
+#' pmeta <- system.file("extdata/portal_meta_top4.csv", package = "dracarys")
+#' (m <- meta_oncoanalyser_wts(pmeta))
+#' @testexamples
+#' expect_equal(all(c("s3_outdir_oncoanalyser", "LibraryID_tumor", "s3_bam_tumor") %in% colnames(m)), TRUE)
+#' @export
 meta_oncoanalyser_wts <- function(pmeta, status = "Succeeded") {
   # retrieve workflow runs with the given type and status
   type <- "oncoanalyser_wts"
diff --git a/data-raw/portal_meta.R b/data-raw/portal_meta.R
index 08189bd..56982f6 100644
--- a/data-raw/portal_meta.R
+++ b/data-raw/portal_meta.R
@@ -8,11 +8,15 @@ require(readr)
 
 wfs <- c(
   "bcl_convert", "rnasum", "tso_ctdna_tumor_only",
-  "umccrise", "wgs_alignment_qc", "wgs_tumor_normal", "wts_tumor_only"
+  "umccrise", "wgs_alignment_qc", "wgs_tumor_normal", "wts_tumor_only",
+  "wts_alignment_qc",
+  "oncoanalyser_wgs", "oncoanalyser_wgts_existing_both",
+  "oncoanalyser_wts", "sash", "star_alignment"
 )
 
+account <- "stg"
 get_top_succeeded <- function(wf, num_row = 10, num_top = 4) {
-  dracarys::portal_meta_read(params = glue::glue("&type_name={wf}"), rows = num_row) |>
+  dracarys::portal_meta_read(params = glue::glue("&type_name={wf}"), account = account, rows = num_row) |>
     dplyr::filter(.data$end_status == "Succeeded") |>
     dplyr::slice_head(n = num_top)
 }
diff --git a/man/meta_oncoanalyser_wgs.Rd b/man/meta_oncoanalyser_wgs.Rd
new file mode 100644
index 0000000..0f9d3b9
--- /dev/null
+++ b/man/meta_oncoanalyser_wgs.Rd
@@ -0,0 +1,23 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/portal_meta.R
+\name{meta_oncoanalyser_wgs}
+\alias{meta_oncoanalyser_wgs}
+\title{Metadata for oncoanalyser_wgs workflow}
+\usage{
+meta_oncoanalyser_wgs(pmeta, status = "Succeeded")
+}
+\arguments{
+\item{pmeta}{Path to portal workflows metadata table, or tibble with already parsed data.}
+
+\item{status}{Workflow status to keep (default: Succeeded).}
+}
+\value{
+A tibble with metadata per workflow run.
+}
+\description{
+Metadata for oncoanalyser_wgs workflow
+}
+\examples{
+pmeta <- system.file("extdata/portal_meta_top4.csv", package = "dracarys")
+(m <- meta_oncoanalyser_wgs(pmeta))
+}
diff --git a/man/meta_oncoanalyser_wgts_existing_both.Rd b/man/meta_oncoanalyser_wgts_existing_both.Rd
new file mode 100644
index 0000000..12c223e
--- /dev/null
+++ b/man/meta_oncoanalyser_wgts_existing_both.Rd
@@ -0,0 +1,23 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/portal_meta.R
+\name{meta_oncoanalyser_wgts_existing_both}
+\alias{meta_oncoanalyser_wgts_existing_both}
+\title{Metadata for oncoanalyser_wgts_existing_both workflow}
+\usage{
+meta_oncoanalyser_wgts_existing_both(pmeta, status = "Succeeded")
+}
+\arguments{
+\item{pmeta}{Path to portal workflows metadata table, or tibble with already parsed data.}
+
+\item{status}{Workflow status to keep (default: Succeeded).}
+}
+\value{
+A tibble with metadata per workflow run.
+}
+\description{
+Metadata for oncoanalyser_wgts_existing_both workflow
+}
+\examples{
+pmeta <- system.file("extdata/portal_meta_top4.csv", package = "dracarys")
+(m <- meta_oncoanalyser_wgts_existing_both(pmeta))
+}
diff --git a/man/meta_oncoanalyser_wts.Rd b/man/meta_oncoanalyser_wts.Rd
new file mode 100644
index 0000000..bf24a8c
--- /dev/null
+++ b/man/meta_oncoanalyser_wts.Rd
@@ -0,0 +1,23 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/portal_meta.R
+\name{meta_oncoanalyser_wts}
+\alias{meta_oncoanalyser_wts}
+\title{Metadata for oncoanalyser_wts workflow}
+\usage{
+meta_oncoanalyser_wts(pmeta, status = "Succeeded")
+}
+\arguments{
+\item{pmeta}{Path to portal workflows metadata table, or tibble with already parsed data.}
+
+\item{status}{Workflow status to keep (default: Succeeded).}
+}
+\value{
+A tibble with metadata per workflow run.
+}
+\description{
+Metadata for oncoanalyser_wts workflow
+}
+\examples{
+pmeta <- system.file("extdata/portal_meta_top4.csv", package = "dracarys")
+(m <- meta_oncoanalyser_wts(pmeta))
+}
diff --git a/man/meta_sash.Rd b/man/meta_sash.Rd
new file mode 100644
index 0000000..6577c1f
--- /dev/null
+++ b/man/meta_sash.Rd
@@ -0,0 +1,23 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/portal_meta.R
+\name{meta_sash}
+\alias{meta_sash}
+\title{Metadata for sash workflow}
+\usage{
+meta_sash(pmeta, status = "Succeeded")
+}
+\arguments{
+\item{pmeta}{Path to portal workflows metadata table, or tibble with already parsed data.}
+
+\item{status}{Workflow status to keep (default: Succeeded).}
+}
+\value{
+A tibble with metadata per workflow run.
+}
+\description{
+Metadata for sash workflow
+}
+\examples{
+pmeta <- system.file("extdata/portal_meta_top4.csv", package = "dracarys")
+(m <- meta_sash(pmeta))
+}
diff --git a/tests/testthat/test-roxytest-testexamples-portal_meta.R b/tests/testthat/test-roxytest-testexamples-portal_meta.R
index 0ad045a..873816e 100644
--- a/tests/testthat/test-roxytest-testexamples-portal_meta.R
+++ b/tests/testthat/test-roxytest-testexamples-portal_meta.R
@@ -6,7 +6,7 @@ test_that("Function meta_bcl_convert() @ L14", {
   
   pmeta <- system.file("extdata/portal_meta_top4.csv", package = "dracarys")
   (m <- meta_bcl_convert(pmeta))
-  expect_equal(sum(!is.na(m$topup_or_rerun)), 22)
+  expect_equal(sum(!is.na(m$topup_or_rerun)), 1)
   expect_equal(length(unique(m$portal_run_id)), 4)
 })
 
@@ -24,8 +24,8 @@ test_that("Function meta_rnasum() @ L134", {
   
   pmeta <- system.file("extdata/portal_meta_top4.csv", package = "dracarys")
   (m <- meta_rnasum(pmeta))
-  expect_equal(m$rnasum_dataset[1], "LAML")
-  expect_equal(basename(m$gds_outfile_rnasum_html[4]), "MDX230277.RNAseq_report.html")
+  expect_equal(m$rnasum_dataset[1], "PANCAN")
+  expect_equal(basename(m$gds_outfile_rnasum_html[4]), "MDX230467.RNAseq_report.html")
 })
 
 
@@ -57,6 +57,38 @@ test_that("Function meta_tso_ctdna_tumor_only() @ L402", {
   
   pmeta <- system.file("extdata/portal_meta_top4.csv", package = "dracarys")
   (m <- meta_tso_ctdna_tumor_only(pmeta))
-  expect_equal(length(unique(m$portal_run_id)), 4)
+  expect_equal(length(unique(m$portal_run_id)), 2)
+})
+
+
+test_that("Function meta_sash() @ L450", {
+  
+  pmeta <- system.file("extdata/portal_meta_top4.csv", package = "dracarys")
+  (m <- meta_sash(pmeta))
+  expect_equal(all(c("s3_indir_oncoanalyser", "LibraryID_tumor", "s3_outdir_sash") %in% colnames(m)), TRUE)
+})
+
+
+test_that("Function meta_oncoanalyser_wgs() @ L504", {
+  
+  pmeta <- system.file("extdata/portal_meta_top4.csv", package = "dracarys")
+  (m <- meta_oncoanalyser_wgs(pmeta))
+  expect_equal(all(c("s3_outdir_oncoanalyser", "LibraryID_tumor", "gds_bam_tumor") %in% colnames(m)), TRUE)
+})
+
+
+test_that("Function meta_oncoanalyser_wgts_existing_both() @ L556", {
+  
+  pmeta <- system.file("extdata/portal_meta_top4.csv", package = "dracarys")
+  (m <- meta_oncoanalyser_wgts_existing_both(pmeta))
+  expect_equal(all(c("s3_outdir_oncoanalyser", "LibraryID_tumor_wts", "gds_bam_tumor_wgs") %in% colnames(m)), TRUE)
+})
+
+
+test_that("Function meta_oncoanalyser_wts() @ L618", {
+  
+  pmeta <- system.file("extdata/portal_meta_top4.csv", package = "dracarys")
+  (m <- meta_oncoanalyser_wts(pmeta))
+  expect_equal(all(c("s3_outdir_oncoanalyser", "LibraryID_tumor", "s3_bam_tumor") %in% colnames(m)), TRUE)
 })
 

From c4f75e3f90e1e8770ea7bb4af459775ab150cf36 Mon Sep 17 00:00:00 2001
From: pdiakumis <peterdiakumis@gmail.com>
Date: Wed, 1 Nov 2023 10:53:31 +1100
Subject: [PATCH 5/8] meta for wts_alignment_qc

---
 R/portal_meta.R | 48 ++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 48 insertions(+)

diff --git a/R/portal_meta.R b/R/portal_meta.R
index 5983b27..1567dc8 100644
--- a/R/portal_meta.R
+++ b/R/portal_meta.R
@@ -222,6 +222,54 @@ meta_wgs_alignment_qc <- function(pmeta, status = "Succeeded") {
     )
 }
 
+#' Metadata for wts_alignment_qc workflow
+#'
+#' @param pmeta Path to portal workflows metadata table, or tibble with already parsed data.
+#' @param status Workflow status to keep (default: Succeeded).
+#'
+#' @return A tibble with metadata per workflow run.
+#' @examples
+#' pmeta <- system.file("extdata/portal_meta_top4.csv", package = "dracarys")
+#' (m <- meta_wts_alignment_qc(pmeta))
+#' @testexamples
+#' expect_equal("Lane" %in% colnames(m), TRUE)
+#' @export
+meta_wts_alignment_qc <- function(pmeta, status = "Succeeded") {
+  # retrieve workflow runs with the given type and status
+  type <- "wts_alignment_qc"
+  wf <- portal_meta_read(pmeta) |>
+    dplyr::filter(
+      .data$type_name == type,
+      .data$end_status %in% status
+    )
+  if (nrow(wf) == 0) {
+    return(wf)
+  }
+  d <- wf |>
+    meta_io_fromjson() |>
+    dplyr::mutate(
+      # input
+      rglb = purrr::map_chr(.data$input, list("fastq_list_rows", "rglb")),
+      rgsm = purrr::map_chr(.data$input, list("fastq_list_rows", "rgsm")),
+      lane = purrr::map_int(.data$input, list("fastq_list_rows", "lane")),
+      lane = as.character(.data$lane),
+      # output
+      gds_outdir_dragen = purrr::map_chr(.data$output, list("dragen_alignment_output_directory", "location"), .default = NA),
+      gds_outdir_multiqc = purrr::map_chr(.data$output, list("multiqc_output_directory", "location"), .default = NA),
+      SubjectID = sub("umccr__automated__wts_alignment_qc__(SBJ.*)__L.*", "\\1", .data$wfr_name),
+    )
+  d |>
+    dplyr::select(
+      dplyr::all_of(meta_main_cols()),
+      "SubjectID",
+      LibraryID = "rglb",
+      SampleID = "rgsm",
+      Lane = "lane",
+      "gds_outdir_dragen",
+      "gds_outdir_multiqc",
+    )
+}
+
 #' Metadata for wgs_tumor_normal workflow
 #'
 #' @param pmeta Path to portal workflows metadata table, or tibble with already parsed data.

From 935d494f74853dbccdbe87ec835110ba37540fe0 Mon Sep 17 00:00:00 2001
From: pdiakumis <peterdiakumis@gmail.com>
Date: Wed, 1 Nov 2023 11:02:55 +1100
Subject: [PATCH 6/8] meta for star_alignment

---
 NAMESPACE                                     |  2 +
 R/portal_meta.R                               | 49 +++++++++++++++++++
 man/meta_star_alignment.Rd                    | 23 +++++++++
 man/meta_wts_alignment_qc.Rd                  | 23 +++++++++
 .../test-roxytest-testexamples-portal_meta.R  | 30 +++++++++---
 5 files changed, 120 insertions(+), 7 deletions(-)
 create mode 100644 man/meta_star_alignment.Rd
 create mode 100644 man/meta_wts_alignment_qc.Rd

diff --git a/NAMESPACE b/NAMESPACE
index 71d5c73..d648d79 100644
--- a/NAMESPACE
+++ b/NAMESPACE
@@ -49,10 +49,12 @@ export(meta_oncoanalyser_wgts_existing_both)
 export(meta_oncoanalyser_wts)
 export(meta_rnasum)
 export(meta_sash)
+export(meta_star_alignment)
 export(meta_tso_ctdna_tumor_only)
 export(meta_umccrise)
 export(meta_wgs_alignment_qc)
 export(meta_wgs_tumor_normal)
+export(meta_wts_alignment_qc)
 export(meta_wts_tumor_only)
 export(multiqc_column_map_append)
 export(multiqc_date_fmt)
diff --git a/R/portal_meta.R b/R/portal_meta.R
index 1567dc8..3e124d1 100644
--- a/R/portal_meta.R
+++ b/R/portal_meta.R
@@ -483,6 +483,55 @@ meta_tso_ctdna_tumor_only <- function(pmeta, status = c("Succeeded")) {
     )
 }
 
+#' Metadata for star_alignment workflow
+#'
+#' @param pmeta Path to portal workflows metadata table, or tibble with already parsed data.
+#' @param status Workflow status to keep (default: Succeeded).
+#'
+#' @return A tibble with metadata per workflow run.
+#' @examples
+#' pmeta <- system.file("extdata/portal_meta_top4.csv", package = "dracarys")
+#' (m <- meta_star_alignment(pmeta))
+#' @testexamples
+#' expect_equal(all(c("s3_outdir_star", "LibraryID_tumor") %in% colnames(m)), TRUE)
+#' @export
+meta_star_alignment <- function(pmeta, status = "Succeeded") {
+  # retrieve workflow runs with the given type and status
+  type <- "star_alignment"
+  wf <- portal_meta_read(pmeta) |>
+    dplyr::filter(
+      .data$type_name == type,
+      .data$end_status %in% status
+    )
+  if (nrow(wf) == 0) {
+    return(wf)
+  }
+  # grab libid/sampleid from the input meta, and outdir from the output meta
+  d <- wf |>
+    meta_io_fromjson() |>
+    dplyr::mutate(
+      # input
+      SubjectID = purrr::map_chr(.data$input, "subject_id", .default = NA),
+      SampleID_tumor = purrr::map_chr(.data$input, "sample_id", .default = NA),
+      LibraryID_tumor = purrr::map_chr(.data$input, "library_id", .default = NA),
+      gds_fq_fwd = purrr::map_chr(.data$input, "fastq_fwd", .default = NA),
+      gds_fq_rev = purrr::map_chr(.data$input, "fastq_rev", .default = NA),
+      # output
+      s3_outdir_star = purrr::map_chr(.data$output, "output_directory", .default = NA)
+    )
+  d |>
+    dplyr::select(
+      meta_main_cols(),
+      "SubjectID",
+      "LibraryID_tumor",
+      "SampleID_tumor",
+      "s3_outdir_star",
+      "gds_fq_fwd",
+      "gds_fq_rev"
+    )
+}
+
+
 #' Metadata for sash workflow
 #'
 #' @param pmeta Path to portal workflows metadata table, or tibble with already parsed data.
diff --git a/man/meta_star_alignment.Rd b/man/meta_star_alignment.Rd
new file mode 100644
index 0000000..7af9158
--- /dev/null
+++ b/man/meta_star_alignment.Rd
@@ -0,0 +1,23 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/portal_meta.R
+\name{meta_star_alignment}
+\alias{meta_star_alignment}
+\title{Metadata for star_alignment workflow}
+\usage{
+meta_star_alignment(pmeta, status = "Succeeded")
+}
+\arguments{
+\item{pmeta}{Path to portal workflows metadata table, or tibble with already parsed data.}
+
+\item{status}{Workflow status to keep (default: Succeeded).}
+}
+\value{
+A tibble with metadata per workflow run.
+}
+\description{
+Metadata for star_alignment workflow
+}
+\examples{
+pmeta <- system.file("extdata/portal_meta_top4.csv", package = "dracarys")
+(m <- meta_star_alignment(pmeta))
+}
diff --git a/man/meta_wts_alignment_qc.Rd b/man/meta_wts_alignment_qc.Rd
new file mode 100644
index 0000000..5b2c5ed
--- /dev/null
+++ b/man/meta_wts_alignment_qc.Rd
@@ -0,0 +1,23 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/portal_meta.R
+\name{meta_wts_alignment_qc}
+\alias{meta_wts_alignment_qc}
+\title{Metadata for wts_alignment_qc workflow}
+\usage{
+meta_wts_alignment_qc(pmeta, status = "Succeeded")
+}
+\arguments{
+\item{pmeta}{Path to portal workflows metadata table, or tibble with already parsed data.}
+
+\item{status}{Workflow status to keep (default: Succeeded).}
+}
+\value{
+A tibble with metadata per workflow run.
+}
+\description{
+Metadata for wts_alignment_qc workflow
+}
+\examples{
+pmeta <- system.file("extdata/portal_meta_top4.csv", package = "dracarys")
+(m <- meta_wts_alignment_qc(pmeta))
+}
diff --git a/tests/testthat/test-roxytest-testexamples-portal_meta.R b/tests/testthat/test-roxytest-testexamples-portal_meta.R
index 873816e..ba2bda6 100644
--- a/tests/testthat/test-roxytest-testexamples-portal_meta.R
+++ b/tests/testthat/test-roxytest-testexamples-portal_meta.R
@@ -37,7 +37,15 @@ test_that("Function meta_wgs_alignment_qc() @ L189", {
 })
 
 
-test_that("Function meta_wgs_tumor_normal() @ L237", {
+test_that("Function meta_wts_alignment_qc() @ L237", {
+  
+  pmeta <- system.file("extdata/portal_meta_top4.csv", package = "dracarys")
+  (m <- meta_wts_alignment_qc(pmeta))
+  expect_equal("Lane" %in% colnames(m), TRUE)
+})
+
+
+test_that("Function meta_wgs_tumor_normal() @ L285", {
   
   pmeta <- system.file("extdata/portal_meta_top4.csv", package = "dracarys")
   (m <- meta_wgs_tumor_normal(pmeta))
@@ -45,7 +53,7 @@ test_that("Function meta_wgs_tumor_normal() @ L237", {
 })
 
 
-test_that("Function meta_umccrise() @ L307", {
+test_that("Function meta_umccrise() @ L355", {
   
   pmeta <- system.file("extdata/portal_meta_top4.csv", package = "dracarys")
   (m <- meta_umccrise(pmeta))
@@ -53,7 +61,7 @@ test_that("Function meta_umccrise() @ L307", {
 })
 
 
-test_that("Function meta_tso_ctdna_tumor_only() @ L402", {
+test_that("Function meta_tso_ctdna_tumor_only() @ L450", {
   
   pmeta <- system.file("extdata/portal_meta_top4.csv", package = "dracarys")
   (m <- meta_tso_ctdna_tumor_only(pmeta))
@@ -61,7 +69,15 @@ test_that("Function meta_tso_ctdna_tumor_only() @ L402", {
 })
 
 
-test_that("Function meta_sash() @ L450", {
+test_that("Function meta_star_alignment() @ L498", {
+  
+  pmeta <- system.file("extdata/portal_meta_top4.csv", package = "dracarys")
+  (m <- meta_star_alignment(pmeta))
+  expect_equal(all(c("s3_outdir_star", "LibraryID_tumor") %in% colnames(m)), TRUE)
+})
+
+
+test_that("Function meta_sash() @ L547", {
   
   pmeta <- system.file("extdata/portal_meta_top4.csv", package = "dracarys")
   (m <- meta_sash(pmeta))
@@ -69,7 +85,7 @@ test_that("Function meta_sash() @ L450", {
 })
 
 
-test_that("Function meta_oncoanalyser_wgs() @ L504", {
+test_that("Function meta_oncoanalyser_wgs() @ L601", {
   
   pmeta <- system.file("extdata/portal_meta_top4.csv", package = "dracarys")
   (m <- meta_oncoanalyser_wgs(pmeta))
@@ -77,7 +93,7 @@ test_that("Function meta_oncoanalyser_wgs() @ L504", {
 })
 
 
-test_that("Function meta_oncoanalyser_wgts_existing_both() @ L556", {
+test_that("Function meta_oncoanalyser_wgts_existing_both() @ L653", {
   
   pmeta <- system.file("extdata/portal_meta_top4.csv", package = "dracarys")
   (m <- meta_oncoanalyser_wgts_existing_both(pmeta))
@@ -85,7 +101,7 @@ test_that("Function meta_oncoanalyser_wgts_existing_both() @ L556", {
 })
 
 
-test_that("Function meta_oncoanalyser_wts() @ L618", {
+test_that("Function meta_oncoanalyser_wts() @ L715", {
   
   pmeta <- system.file("extdata/portal_meta_top4.csv", package = "dracarys")
   (m <- meta_oncoanalyser_wts(pmeta))

From 1828562771d66ea713b61d66d02b39ad9290438e Mon Sep 17 00:00:00 2001
From: pdiakumis <peterdiakumis@gmail.com>
Date: Thu, 2 Nov 2023 01:13:28 +1100
Subject: [PATCH 7/8] portal summary: add wts-alignqc/star/oncoa/sash

---
 R/portal_meta.R                          |  20 +-
 inst/rmd/umccr_portal/portal_summary.Rmd | 287 ++++++++++++++++++++---
 2 files changed, 269 insertions(+), 38 deletions(-)

diff --git a/R/portal_meta.R b/R/portal_meta.R
index 3e124d1..e74349c 100644
--- a/R/portal_meta.R
+++ b/R/portal_meta.R
@@ -512,8 +512,8 @@ meta_star_alignment <- function(pmeta, status = "Succeeded") {
     dplyr::mutate(
       # input
       SubjectID = purrr::map_chr(.data$input, "subject_id", .default = NA),
-      SampleID_tumor = purrr::map_chr(.data$input, "sample_id", .default = NA),
-      LibraryID_tumor = purrr::map_chr(.data$input, "library_id", .default = NA),
+      SampleID = purrr::map_chr(.data$input, "sample_id", .default = NA),
+      LibraryID = purrr::map_chr(.data$input, "library_id", .default = NA),
       gds_fq_fwd = purrr::map_chr(.data$input, "fastq_fwd", .default = NA),
       gds_fq_rev = purrr::map_chr(.data$input, "fastq_rev", .default = NA),
       # output
@@ -523,8 +523,8 @@ meta_star_alignment <- function(pmeta, status = "Succeeded") {
     dplyr::select(
       meta_main_cols(),
       "SubjectID",
-      "LibraryID_tumor",
-      "SampleID_tumor",
+      "LibraryID",
+      "SampleID",
       "s3_outdir_star",
       "gds_fq_fwd",
       "gds_fq_rev"
@@ -730,9 +730,9 @@ meta_oncoanalyser_wts <- function(pmeta, status = "Succeeded") {
       # input
       mode = purrr::map_chr(.data$input, "mode", .default = NA),
       SubjectID = purrr::map_chr(.data$input, "subject_id", .default = NA),
-      SampleID_tumor = purrr::map_chr(.data$input, "tumor_wts_sample_id", .default = NA),
-      LibraryID_tumor = purrr::map_chr(.data$input, "tumor_wts_library_id", .default = NA),
-      s3_bam_tumor = purrr::map_chr(.data$input, "tumor_wts_bam", .default = NA),
+      SampleID = purrr::map_chr(.data$input, "tumor_wts_sample_id", .default = NA),
+      LibraryID = purrr::map_chr(.data$input, "tumor_wts_library_id", .default = NA),
+      s3_bam = purrr::map_chr(.data$input, "tumor_wts_bam", .default = NA),
       # output
       s3_outdir_oncoanalyser = purrr::map_chr(.data$output, "output_directory", .default = NA)
     )
@@ -740,9 +740,9 @@ meta_oncoanalyser_wts <- function(pmeta, status = "Succeeded") {
     dplyr::select(
       meta_main_cols(),
       "SubjectID",
-      "LibraryID_tumor",
-      "SampleID_tumor",
-      "s3_bam_tumor",
+      "LibraryID",
+      "SampleID",
+      "s3_bam",
       "s3_outdir_oncoanalyser",
     )
 }
diff --git a/inst/rmd/umccr_portal/portal_summary.Rmd b/inst/rmd/umccr_portal/portal_summary.Rmd
index 9037bcd..b1ebb40 100644
--- a/inst/rmd/umccr_portal/portal_summary.Rmd
+++ b/inst/rmd/umccr_portal/portal_summary.Rmd
@@ -114,16 +114,22 @@ get_sbj_url <- function(x, colour = NULL, account = "") {
 # Get metadata for workflows run within the date range
 # options(width = 150)
 fmt1 <- "%Y-%m-%dT%H:%M:%S"
-date_start <- as.POSIXct("2023-10-28T00:00:01", format = fmt1)
-date_end <- as.POSIXct("2023-10-29T23:59:59", format = fmt1)
+date_start <- as.POSIXct("2023-10-27T00:00:01", format = fmt1)
+date_end <- as.POSIXct("2023-10-30T23:59:59", format = fmt1)
 wf_order <- c(
   "bcl_convert",
   "tso_ctdna_tumor_only",
   "wgs_alignment_qc",
+  "wts_alignment_qc",
   "wts_tumor_only",
   "wgs_tumor_normal",
   "umccrise",
-  "rnasum"
+  "rnasum",
+  "star_alignment",
+  "oncoanalyser_wts",
+  "oncoanalyser_wgs",
+  "oncoanalyser_wgts_existing_both",
+  "sash"
 )
 
 lims_rds <- here(glue("nogit/data_portal/lims/{as.Date(date_end)}.rds"))
@@ -131,7 +137,7 @@ lims_rds <- here(glue("nogit/data_portal/lims/{as.Date(date_end)}.rds"))
 # saveRDS(lims_raw, file = lims_rds)
 lims_raw <- readr::read_rds(lims_rds)
 pmeta_rds <- here(glue("nogit/data_portal/workflows/{as.Date(date_end)}.rds"))
-# pmeta_raw <- dracarys::portal_meta_read(rows = 50, account = "prod")
+# pmeta_raw <- dracarys::portal_meta_read(rows = 300, account = "stg")
 # saveRDS(pmeta_raw, file = pmeta_rds)
 pmeta_raw <- readr::read_rds(pmeta_rds)
 pmeta <- pmeta_raw |>
@@ -153,9 +159,12 @@ pmeta_sumy <- pmeta |>
   ) |>
   dplyr::rowwise() |>
   dplyr::mutate(
-    sbj_lib = as.character(glue("umccr__automated__{.data$type_name}__")),
-    sbj_lib = sub(paste0(.data$sbj_lib, "(.*)__2023.*"), "\\1", .data$wfr_name),
-    sbjid = sub("(SBJ.*)__L.*", "\\1", .data$sbj_lib)
+    wfr_name = dplyr::if_else(grepl("umccr__automated", .data$wfr_name),
+      glue("{.data$wfr_name}"),
+      glue("umccr__automated__{.data$wfr_name}")
+    ),
+    sbj_lib = sub("umccr__automated__(.*?)__(SBJ.*__L.*)__202.*", "\\2", .data$wfr_name),
+    sbjid = sub("(SBJ.*?)__L.*", "\\1", .data$sbj_lib)
   ) |>
   dplyr::ungroup()
 unique_sbj <- sort(unique(pmeta_sumy$sbjid))
@@ -199,9 +208,13 @@ split(x, x$column_group) |>
   kableExtra::kable_classic(full_width = FALSE, position = "left")
 ```
 
+```{r, results='asis'}
+blank_lines()
+```
+
 ## RuntimeVis
 
-```{r vistime, fig.width=15, fig.height = 10}
+```{r vistime, fig.width=15, fig.height = 20}
 p1 <- pmeta_sumy |>
   dplyr::arrange(sbj_lib, type_name) |>
   dplyr::group_by(sbj_lib, type_name) |>
@@ -260,11 +273,14 @@ pmeta |>
   ) |>
   dplyr::left_join(lims, by = c("LibraryID", "SampleID")) |>
   dplyr::left_join(clrs1 |> dplyr::select(sbjid, sbj_url), by = c("SubjectID" = "sbjid")) |>
-  dplyr::mutate(SubjectID = dplyr::if_else(is.na(.data$sbj_url), get_sbj_url(.data$SubjectID), .data$sbj_url)) |>
+  dplyr::mutate(
+    SubjectID = dplyr::if_else(is.na(.data$sbj_url), get_sbj_url(.data$SubjectID), .data$sbj_url),
+    durationMin = round(as.numeric(difftime(end, start, units = "mins")))
+  ) |>
   dplyr::select(
     end_status, runfolder_name, SubjectID, LibraryID, SampleID, Phenotype, ExternalSubjectID,
     ProjectOwner, ProjectName, batch_name, Type, Assay, Source, Quality, Workflow,
-    start, end
+    durationMin, start, end
   ) |>
   dplyr::arrange(desc(SubjectID), start) |>
   dt_view()
@@ -287,11 +303,14 @@ pmeta |>
   dracarys::meta_tso_ctdna_tumor_only(status = c("Succeeded", "Failed")) |>
   dplyr::left_join(lims, by = c("LibraryID", "SampleID", "SubjectID")) |>
   dplyr::left_join(clrs1 |> dplyr::select(sbjid, sbj_url), by = c("SubjectID" = "sbjid")) |>
-  dplyr::mutate(SubjectID = dplyr::if_else(is.na(.data$sbj_url), get_sbj_url(.data$SubjectID), .data$sbj_url)) |>
+  dplyr::mutate(
+    SubjectID = dplyr::if_else(is.na(.data$sbj_url), get_sbj_url(.data$SubjectID), .data$sbj_url),
+    durationMin = round(as.numeric(difftime(end, start, units = "mins")))
+  ) |>
   dplyr::select(
     end_status, SubjectID, LibraryID, SampleID, Phenotype, ExternalSubjectID,
     ProjectOwner, ProjectName, Type, Assay, Source, Quality, Workflow,
-    wfr_id, start, end, gds_outdir
+    portal_run_id, wfr_id, durationMin, start, end, gds_outdir
   ) |>
   dplyr::arrange(desc(SubjectID), start) |>
   dt_view()
@@ -314,18 +333,21 @@ pmeta |>
   dracarys::meta_wgs_alignment_qc(status = c("Succeeded", "Failed")) |>
   dplyr::left_join(lims, by = c("LibraryID", "SampleID", "SubjectID")) |>
   dplyr::left_join(clrs1 |> dplyr::select(sbjid, sbj_url), by = c("SubjectID" = "sbjid")) |>
-  dplyr::mutate(SubjectID = dplyr::if_else(is.na(.data$sbj_url), get_sbj_url(.data$SubjectID), .data$sbj_url)) |>
+  dplyr::mutate(
+    SubjectID = dplyr::if_else(is.na(.data$sbj_url), get_sbj_url(.data$SubjectID), .data$sbj_url),
+    durationMin = round(as.numeric(difftime(end, start, units = "mins")))
+  ) |>
   dplyr::select(
     end_status, SubjectID, LibraryID, SampleID, Phenotype, Lane, ExternalSubjectID,
     ProjectOwner, ProjectName, Type, Assay, Source, Quality, Workflow,
-    wfr_id, start, end, gds_outdir_dragen
+    portal_run_id, wfr_id, durationMin, start, end, gds_outdir_dragen
   ) |>
   dplyr::arrange(desc(SubjectID), start) |>
   dt_view()
 ```
 
 ```{r echo=FALSE}
-wf <- "wts_tumor_only"
+wf <- "wts_alignment_qc"
 ```
 
 ### 4. `r wf`
@@ -336,16 +358,49 @@ if (!chunks1[[wf]]) {
 }
 ```
 
+```{r eval=chunks1[[wf]]}
+pmeta |>
+  dracarys::meta_wts_alignment_qc(status = c("Succeeded", "Failed")) |>
+  dplyr::left_join(lims, by = c("LibraryID", "SampleID", "SubjectID")) |>
+  dplyr::left_join(clrs1 |> dplyr::select(sbjid, sbj_url), by = c("SubjectID" = "sbjid")) |>
+  dplyr::mutate(
+    SubjectID = dplyr::if_else(is.na(.data$sbj_url), get_sbj_url(.data$SubjectID), .data$sbj_url),
+    durationMin = round(as.numeric(difftime(end, start, units = "mins")))
+  ) |>
+  dplyr::select(
+    end_status, SubjectID, LibraryID, SampleID, Phenotype, Lane, ExternalSubjectID,
+    ProjectOwner, ProjectName, Type, Assay, Source, Quality, Workflow,
+    portal_run_id, wfr_id, durationMin, start, end, gds_outdir_dragen
+  ) |>
+  dplyr::arrange(desc(SubjectID), start) |>
+  dt_view()
+```
+
+```{r echo=FALSE}
+wf <- "wts_tumor_only"
+```
+
+### 5. `r wf`
+
+```{r}
+if (!chunks1[[wf]]) {
+  kable_empty_wf(wf)
+}
+```
+
 ```{r eval=chunks1[[wf]]}
 pmeta |>
   dracarys::meta_wts_tumor_only(status = c("Succeeded", "Failed")) |>
   dplyr::left_join(lims, by = c("LibraryID", "SampleID", "SubjectID")) |>
   dplyr::left_join(clrs1 |> dplyr::select(sbjid, sbj_url), by = c("SubjectID" = "sbjid")) |>
-  dplyr::mutate(SubjectID = dplyr::if_else(is.na(.data$sbj_url), get_sbj_url(.data$SubjectID), .data$sbj_url)) |>
+  dplyr::mutate(
+    SubjectID = dplyr::if_else(is.na(.data$sbj_url), get_sbj_url(.data$SubjectID), .data$sbj_url),
+    durationMin = round(as.numeric(difftime(end, start, units = "mins")))
+  ) |>
   dplyr::select(
     end_status, SubjectID, LibraryID, SampleID, Phenotype, ExternalSubjectID, ProjectOwner, ProjectName,
     Type, Assay, Source, Quality, Workflow,
-    wfr_id, start, end, gds_outdir_dragen
+    portal_run_id, wfr_id, durationMin, start, end, gds_outdir_dragen
   ) |>
   dplyr::arrange(desc(SubjectID), start) |>
   dt_view()
@@ -355,7 +410,7 @@ pmeta |>
 wf <- "wgs_tumor_normal"
 ```
 
-### 5. `r wf`
+### 6. `r wf`
 
 ```{r}
 if (!chunks1[[wf]]) {
@@ -373,11 +428,14 @@ pmeta |>
   # include Phenotype to double-check join
   dplyr::left_join(lims, by = c("LibraryID", "SampleID", "SubjectID", "Phenotype")) |>
   dplyr::left_join(clrs1 |> dplyr::select(sbjid, sbj_url), by = c("SubjectID" = "sbjid")) |>
-  dplyr::mutate(SubjectID = dplyr::if_else(is.na(.data$sbj_url), get_sbj_url(.data$SubjectID), .data$sbj_url)) |>
+  dplyr::mutate(
+    SubjectID = dplyr::if_else(is.na(.data$sbj_url), get_sbj_url(.data$SubjectID), .data$sbj_url),
+    durationMin = round(as.numeric(difftime(end, start, units = "mins")))
+  ) |>
   dplyr::select(
     end_status, SubjectID, LibraryID, SampleID, Phenotype, ExternalSubjectID, ProjectOwner, ProjectName,
     Type, Assay, Source, Quality, Workflow,
-    wfr_id, start, end, gds_outdir_dragen_somatic, gds_outdir_dragen_germline
+    portal_run_id, wfr_id, durationMin, start, end, gds_outdir_dragen_somatic, gds_outdir_dragen_germline
   ) |>
   dplyr::arrange(desc(SubjectID), start) |>
   dt_view()
@@ -387,7 +445,7 @@ pmeta |>
 wf <- "umccrise"
 ```
 
-### 6. `r wf` {.active}
+### 7. `r wf`
 
 ```{r}
 if (!chunks1[[wf]]) {
@@ -395,7 +453,7 @@ if (!chunks1[[wf]]) {
 }
 ```
 
-```{r eval=chunks1[["umccrise"]]}
+```{r eval=chunks1[[wf]]}
 pmeta |>
   dracarys::meta_umccrise(status = c("Succeeded", "Failed")) |>
   tidyr::unite("SampleID__LibraryID___normal", SampleID_normal, LibraryID_normal, sep = "__") |>
@@ -405,11 +463,14 @@ pmeta |>
   # include Phenotype to double-check join
   dplyr::left_join(lims, by = c("LibraryID", "SampleID", "SubjectID", "Phenotype")) |>
   dplyr::left_join(clrs1 |> dplyr::select(sbjid, sbj_url), by = c("SubjectID" = "sbjid")) |>
-  dplyr::mutate(SubjectID = dplyr::if_else(is.na(.data$sbj_url), get_sbj_url(.data$SubjectID), .data$sbj_url)) |>
+  dplyr::mutate(
+    SubjectID = dplyr::if_else(is.na(.data$sbj_url), get_sbj_url(.data$SubjectID), .data$sbj_url),
+    durationMin = round(as.numeric(difftime(end, start, units = "mins")))
+  ) |>
   dplyr::select(
     end_status, SubjectID, LibraryID, SampleID, Phenotype, ExternalSubjectID,
     ProjectOwner, ProjectName, Type, Assay, Source, Quality, Workflow,
-    wfr_id, start, end, gds_outdir_umccrise
+    portal_run_id, wfr_id, durationMin, start, end, gds_outdir_umccrise
   ) |>
   dplyr::arrange(desc(SubjectID), start) |>
   dt_view()
@@ -419,7 +480,7 @@ pmeta |>
 wf <- "rnasum"
 ```
 
-### 7. `r wf`
+### 8. `r wf`
 
 ```{r}
 if (!chunks1[[wf]]) {
@@ -427,16 +488,186 @@ if (!chunks1[[wf]]) {
 }
 ```
 
-```{r eval=chunks1[["rnasum"]]}
+```{r eval=chunks1[[wf]]}
 pmeta |>
   dracarys::meta_rnasum(status = c("Succeeded", "Failed")) |>
   dplyr::left_join(lims, by = c("LibraryID", "SampleID", "SubjectID")) |>
   dplyr::left_join(clrs1 |> dplyr::select(sbjid, sbj_url), by = c("SubjectID" = "sbjid")) |>
-  dplyr::mutate(SubjectID = dplyr::if_else(is.na(.data$sbj_url), get_sbj_url(.data$SubjectID), .data$sbj_url)) |>
+  dplyr::mutate(
+    SubjectID = dplyr::if_else(is.na(.data$sbj_url), get_sbj_url(.data$SubjectID), .data$sbj_url),
+    durationMin = round(as.numeric(difftime(end, start, units = "mins")))
+  ) |>
   dplyr::select(
     end_status, SubjectID, LibraryID, SampleID, Phenotype, rnasum_dataset, ExternalSubjectID,
     ProjectOwner, ProjectName, Type, Assay, Source, Quality, Workflow,
-    wfr_id, start, end, gds_outdir_rnasum,
+    portal_run_id, wfr_id, durationMin, start, end, gds_outdir_rnasum,
+  ) |>
+  dplyr::arrange(desc(SubjectID), start) |>
+  dt_view()
+```
+
+```{r echo=FALSE}
+wf <- "star_alignment"
+```
+
+### 9. `r wf`
+
+```{r}
+if (!chunks1[[wf]]) {
+  kable_empty_wf(wf)
+}
+```
+
+```{r eval=chunks1[[wf]]}
+pmeta |>
+  dracarys::meta_star_alignment(status = c("Succeeded", "Failed")) |>
+  dplyr::left_join(lims, by = c("LibraryID", "SampleID", "SubjectID")) |>
+  dplyr::left_join(clrs1 |> dplyr::select(sbjid, sbj_url), by = c("SubjectID" = "sbjid")) |>
+  dplyr::mutate(
+    SubjectID = dplyr::if_else(is.na(.data$sbj_url), get_sbj_url(.data$SubjectID), .data$sbj_url),
+    durationMin = round(as.numeric(difftime(end, start, units = "mins")))
+  ) |>
+  dplyr::select(
+    end_status, SubjectID, LibraryID, SampleID, Phenotype, ExternalSubjectID, ProjectOwner, ProjectName,
+    Type, Assay, Source, Quality, Workflow,
+    portal_run_id, wfr_id, durationMin, start, end, s3_outdir_star
+  ) |>
+  dplyr::arrange(desc(SubjectID), start) |>
+  dt_view()
+```
+
+```{r echo=FALSE}
+wf <- "oncoanalyser_wts"
+```
+
+### 10. `r wf`
+
+```{r}
+if (!chunks1[[wf]]) {
+  kable_empty_wf(wf)
+}
+```
+
+```{r eval=chunks1[[wf]]}
+pmeta |>
+  dracarys::meta_oncoanalyser_wts(status = c("Succeeded", "Failed")) |>
+  dplyr::left_join(lims, by = c("LibraryID", "SampleID", "SubjectID")) |>
+  dplyr::left_join(clrs1 |> dplyr::select(sbjid, sbj_url), by = c("SubjectID" = "sbjid")) |>
+  dplyr::mutate(
+    SubjectID = dplyr::if_else(is.na(.data$sbj_url), get_sbj_url(.data$SubjectID), .data$sbj_url),
+    durationMin = round(as.numeric(difftime(end, start, units = "mins")))
+  ) |>
+  dplyr::select(
+    end_status, SubjectID, LibraryID, SampleID, Phenotype, ExternalSubjectID, ProjectOwner, ProjectName,
+    Type, Assay, Source, Quality, Workflow,
+    portal_run_id, wfr_id, durationMin, start, end, s3_outdir_oncoanalyser
+  ) |>
+  dplyr::arrange(desc(SubjectID), start) |>
+  dt_view()
+```
+
+
+```{r echo=FALSE}
+wf <- "oncoanalyser_wgs"
+```
+
+### 11. `r wf`
+
+```{r}
+if (!chunks1[[wf]]) {
+  kable_empty_wf(wf)
+}
+```
+
+```{r eval=chunks1[[wf]]}
+pmeta |>
+  dracarys::meta_oncoanalyser_wgs(status = c("Succeeded", "Failed")) |>
+  tidyr::unite("SampleID__LibraryID___normal", SampleID_normal, LibraryID_normal, sep = "__") |>
+  tidyr::unite("SampleID__LibraryID___tumor", SampleID_tumor, LibraryID_tumor, sep = "__") |>
+  tidyr::pivot_longer(c("SampleID__LibraryID___normal", "SampleID__LibraryID___tumor"), names_to = c(NA, "Phenotype"), names_sep = "___", values_to = "SampleID__LibraryID") |>
+  tidyr::separate_wider_delim("SampleID__LibraryID", delim = "__", names = c("SampleID", "LibraryID")) |>
+  # include Phenotype to double-check join
+  dplyr::left_join(lims, by = c("LibraryID", "SampleID", "SubjectID", "Phenotype")) |>
+  dplyr::left_join(clrs1 |> dplyr::select(sbjid, sbj_url), by = c("SubjectID" = "sbjid")) |>
+  dplyr::mutate(
+    SubjectID = dplyr::if_else(is.na(.data$sbj_url), get_sbj_url(.data$SubjectID), .data$sbj_url),
+    durationMin = round(as.numeric(difftime(end, start, units = "mins")))
+  ) |>
+  dplyr::select(
+    end_status, SubjectID, LibraryID, SampleID, Phenotype, ExternalSubjectID,
+    ProjectOwner, ProjectName, Type, Assay, Source, Quality, Workflow,
+    portal_run_id, wfr_id, durationMin, start, end, s3_outdir_oncoanalyser
+  ) |>
+  dplyr::arrange(desc(SubjectID), start) |>
+  dt_view()
+```
+
+```{r echo=FALSE}
+wf <- "oncoanalyser_wgts_existing_both"
+```
+
+### 12. `r wf`
+
+```{r}
+if (!chunks1[[wf]]) {
+  kable_empty_wf(wf)
+}
+```
+
+```{r eval=chunks1[[wf]]}
+pmeta |>
+  dracarys::meta_oncoanalyser_wgts_existing_both(status = c("Succeeded", "Failed")) |>
+  tidyr::unite("SampleID__LibraryID___normal___wgs", SampleID_normal_wgs, LibraryID_normal_wgs, sep = "__") |>
+  tidyr::unite("SampleID__LibraryID___tumor___wgs", SampleID_tumor_wgs, LibraryID_tumor_wgs, sep = "__") |>
+  tidyr::unite("SampleID__LibraryID___tumor___wts", SampleID_tumor_wts, LibraryID_tumor_wts, sep = "__") |>
+  tidyr::pivot_longer(c("SampleID__LibraryID___normal___wgs", "SampleID__LibraryID___tumor___wgs", "SampleID__LibraryID___tumor___wts"), names_to = c(NA, "Phenotype", "WGTS"), names_sep = "___", values_to = "SampleID__LibraryID") |>
+  tidyr::separate_wider_delim("SampleID__LibraryID", delim = "__", names = c("SampleID", "LibraryID")) |>
+  # include Phenotype to double-check join
+  dplyr::left_join(lims, by = c("LibraryID", "SampleID", "SubjectID", "Phenotype")) |>
+  dplyr::left_join(clrs1 |> dplyr::select(sbjid, sbj_url), by = c("SubjectID" = "sbjid")) |>
+  dplyr::mutate(
+    SubjectID = dplyr::if_else(is.na(.data$sbj_url), get_sbj_url(.data$SubjectID), .data$sbj_url),
+    durationMin = round(as.numeric(difftime(end, start, units = "mins")))
+  ) |>
+  dplyr::select(
+    end_status, SubjectID, LibraryID, SampleID, Phenotype, WGTS, ExternalSubjectID,
+    ProjectOwner, ProjectName, Type, Assay, Source, Quality, Workflow,
+    portal_run_id, wfr_id, durationMin, start, end, s3_outdir_oncoanalyser
+  ) |>
+  dplyr::arrange(desc(SubjectID), start) |>
+  dt_view()
+```
+
+```{r echo=FALSE}
+wf <- "sash"
+```
+
+### 13. `r wf` {.active}
+
+```{r}
+if (!chunks1[[wf]]) {
+  kable_empty_wf(wf)
+}
+```
+
+```{r eval=chunks1[[wf]]}
+pmeta |>
+  dracarys::meta_sash(status = c("Succeeded", "Failed")) |>
+  tidyr::unite("SampleID__LibraryID___normal", SampleID_normal, LibraryID_normal, sep = "__") |>
+  tidyr::unite("SampleID__LibraryID___tumor", SampleID_tumor, LibraryID_tumor, sep = "__") |>
+  tidyr::pivot_longer(c("SampleID__LibraryID___normal", "SampleID__LibraryID___tumor"), names_to = c(NA, "Phenotype"), names_sep = "___", values_to = "SampleID__LibraryID") |>
+  tidyr::separate_wider_delim("SampleID__LibraryID", delim = "__", names = c("SampleID", "LibraryID")) |>
+  # include Phenotype to double-check join
+  dplyr::left_join(lims, by = c("LibraryID", "SampleID", "SubjectID", "Phenotype")) |>
+  dplyr::left_join(clrs1 |> dplyr::select(sbjid, sbj_url), by = c("SubjectID" = "sbjid")) |>
+  dplyr::mutate(
+    SubjectID = dplyr::if_else(is.na(.data$sbj_url), get_sbj_url(.data$SubjectID), .data$sbj_url),
+    durationMin = round(as.numeric(difftime(end, start, units = "mins")))
+  ) |>
+  dplyr::select(
+    end_status, SubjectID, LibraryID, SampleID, Phenotype, ExternalSubjectID,
+    ProjectOwner, ProjectName, Type, Assay, Source, Quality, Workflow,
+    portal_run_id, wfr_id, durationMin, start, end, s3_outdir_sash
   ) |>
   dplyr::arrange(desc(SubjectID), start) |>
   dt_view()

From d8917ceb28f268475107085cf5236ef8f81ba210 Mon Sep 17 00:00:00 2001
From: pdiakumis <peterdiakumis@gmail.com>
Date: Thu, 2 Nov 2023 10:56:30 +1100
Subject: [PATCH 8/8] bring durationMin to the front

---
 inst/rmd/umccr_portal/portal_summary.Rmd | 54 ++++++++++++------------
 1 file changed, 27 insertions(+), 27 deletions(-)

diff --git a/inst/rmd/umccr_portal/portal_summary.Rmd b/inst/rmd/umccr_portal/portal_summary.Rmd
index b1ebb40..1753033 100644
--- a/inst/rmd/umccr_portal/portal_summary.Rmd
+++ b/inst/rmd/umccr_portal/portal_summary.Rmd
@@ -115,7 +115,7 @@ get_sbj_url <- function(x, colour = NULL, account = "") {
 # options(width = 150)
 fmt1 <- "%Y-%m-%dT%H:%M:%S"
 date_start <- as.POSIXct("2023-10-27T00:00:01", format = fmt1)
-date_end <- as.POSIXct("2023-10-30T23:59:59", format = fmt1)
+date_end <- as.POSIXct("2023-10-31T23:59:59", format = fmt1)
 wf_order <- c(
   "bcl_convert",
   "tso_ctdna_tumor_only",
@@ -278,9 +278,9 @@ pmeta |>
     durationMin = round(as.numeric(difftime(end, start, units = "mins")))
   ) |>
   dplyr::select(
-    end_status, runfolder_name, SubjectID, LibraryID, SampleID, Phenotype, ExternalSubjectID,
+    end_status, durationMin, runfolder_name, SubjectID, LibraryID, SampleID, Phenotype, ExternalSubjectID,
     ProjectOwner, ProjectName, batch_name, Type, Assay, Source, Quality, Workflow,
-    durationMin, start, end
+    start, end
   ) |>
   dplyr::arrange(desc(SubjectID), start) |>
   dt_view()
@@ -308,9 +308,9 @@ pmeta |>
     durationMin = round(as.numeric(difftime(end, start, units = "mins")))
   ) |>
   dplyr::select(
-    end_status, SubjectID, LibraryID, SampleID, Phenotype, ExternalSubjectID,
+    end_status, durationMin, SubjectID, LibraryID, SampleID, Phenotype, ExternalSubjectID,
     ProjectOwner, ProjectName, Type, Assay, Source, Quality, Workflow,
-    portal_run_id, wfr_id, durationMin, start, end, gds_outdir
+    portal_run_id, wfr_id, start, end, gds_outdir
   ) |>
   dplyr::arrange(desc(SubjectID), start) |>
   dt_view()
@@ -338,9 +338,9 @@ pmeta |>
     durationMin = round(as.numeric(difftime(end, start, units = "mins")))
   ) |>
   dplyr::select(
-    end_status, SubjectID, LibraryID, SampleID, Phenotype, Lane, ExternalSubjectID,
+    end_status, durationMin, SubjectID, LibraryID, SampleID, Phenotype, Lane, ExternalSubjectID,
     ProjectOwner, ProjectName, Type, Assay, Source, Quality, Workflow,
-    portal_run_id, wfr_id, durationMin, start, end, gds_outdir_dragen
+    portal_run_id, wfr_id, start, end, gds_outdir_dragen
   ) |>
   dplyr::arrange(desc(SubjectID), start) |>
   dt_view()
@@ -368,9 +368,9 @@ pmeta |>
     durationMin = round(as.numeric(difftime(end, start, units = "mins")))
   ) |>
   dplyr::select(
-    end_status, SubjectID, LibraryID, SampleID, Phenotype, Lane, ExternalSubjectID,
+    end_status, durationMin, SubjectID, LibraryID, SampleID, Phenotype, Lane, ExternalSubjectID,
     ProjectOwner, ProjectName, Type, Assay, Source, Quality, Workflow,
-    portal_run_id, wfr_id, durationMin, start, end, gds_outdir_dragen
+    portal_run_id, wfr_id, start, end, gds_outdir_dragen
   ) |>
   dplyr::arrange(desc(SubjectID), start) |>
   dt_view()
@@ -398,9 +398,9 @@ pmeta |>
     durationMin = round(as.numeric(difftime(end, start, units = "mins")))
   ) |>
   dplyr::select(
-    end_status, SubjectID, LibraryID, SampleID, Phenotype, ExternalSubjectID, ProjectOwner, ProjectName,
+    end_status, durationMin, SubjectID, LibraryID, SampleID, Phenotype, ExternalSubjectID, ProjectOwner, ProjectName,
     Type, Assay, Source, Quality, Workflow,
-    portal_run_id, wfr_id, durationMin, start, end, gds_outdir_dragen
+    portal_run_id, wfr_id, start, end, gds_outdir_dragen
   ) |>
   dplyr::arrange(desc(SubjectID), start) |>
   dt_view()
@@ -433,9 +433,9 @@ pmeta |>
     durationMin = round(as.numeric(difftime(end, start, units = "mins")))
   ) |>
   dplyr::select(
-    end_status, SubjectID, LibraryID, SampleID, Phenotype, ExternalSubjectID, ProjectOwner, ProjectName,
+    end_status, durationMin, SubjectID, LibraryID, SampleID, Phenotype, ExternalSubjectID, ProjectOwner, ProjectName,
     Type, Assay, Source, Quality, Workflow,
-    portal_run_id, wfr_id, durationMin, start, end, gds_outdir_dragen_somatic, gds_outdir_dragen_germline
+    portal_run_id, wfr_id, start, end, gds_outdir_dragen_somatic, gds_outdir_dragen_germline
   ) |>
   dplyr::arrange(desc(SubjectID), start) |>
   dt_view()
@@ -468,9 +468,9 @@ pmeta |>
     durationMin = round(as.numeric(difftime(end, start, units = "mins")))
   ) |>
   dplyr::select(
-    end_status, SubjectID, LibraryID, SampleID, Phenotype, ExternalSubjectID,
+    end_status, durationMin, SubjectID, LibraryID, SampleID, Phenotype, ExternalSubjectID,
     ProjectOwner, ProjectName, Type, Assay, Source, Quality, Workflow,
-    portal_run_id, wfr_id, durationMin, start, end, gds_outdir_umccrise
+    portal_run_id, wfr_id, start, end, gds_outdir_umccrise
   ) |>
   dplyr::arrange(desc(SubjectID), start) |>
   dt_view()
@@ -498,9 +498,9 @@ pmeta |>
     durationMin = round(as.numeric(difftime(end, start, units = "mins")))
   ) |>
   dplyr::select(
-    end_status, SubjectID, LibraryID, SampleID, Phenotype, rnasum_dataset, ExternalSubjectID,
+    end_status, durationMin, SubjectID, LibraryID, SampleID, Phenotype, rnasum_dataset, ExternalSubjectID,
     ProjectOwner, ProjectName, Type, Assay, Source, Quality, Workflow,
-    portal_run_id, wfr_id, durationMin, start, end, gds_outdir_rnasum,
+    portal_run_id, wfr_id, start, end, gds_outdir_rnasum,
   ) |>
   dplyr::arrange(desc(SubjectID), start) |>
   dt_view()
@@ -528,9 +528,9 @@ pmeta |>
     durationMin = round(as.numeric(difftime(end, start, units = "mins")))
   ) |>
   dplyr::select(
-    end_status, SubjectID, LibraryID, SampleID, Phenotype, ExternalSubjectID, ProjectOwner, ProjectName,
+    end_status, durationMin, SubjectID, LibraryID, SampleID, Phenotype, ExternalSubjectID, ProjectOwner, ProjectName,
     Type, Assay, Source, Quality, Workflow,
-    portal_run_id, wfr_id, durationMin, start, end, s3_outdir_star
+    portal_run_id, wfr_id, start, end, s3_outdir_star
   ) |>
   dplyr::arrange(desc(SubjectID), start) |>
   dt_view()
@@ -558,9 +558,9 @@ pmeta |>
     durationMin = round(as.numeric(difftime(end, start, units = "mins")))
   ) |>
   dplyr::select(
-    end_status, SubjectID, LibraryID, SampleID, Phenotype, ExternalSubjectID, ProjectOwner, ProjectName,
+    end_status, durationMin, SubjectID, LibraryID, SampleID, Phenotype, ExternalSubjectID, ProjectOwner, ProjectName,
     Type, Assay, Source, Quality, Workflow,
-    portal_run_id, wfr_id, durationMin, start, end, s3_outdir_oncoanalyser
+    portal_run_id, wfr_id, start, end, s3_outdir_oncoanalyser
   ) |>
   dplyr::arrange(desc(SubjectID), start) |>
   dt_view()
@@ -594,9 +594,9 @@ pmeta |>
     durationMin = round(as.numeric(difftime(end, start, units = "mins")))
   ) |>
   dplyr::select(
-    end_status, SubjectID, LibraryID, SampleID, Phenotype, ExternalSubjectID,
+    end_status, durationMin, SubjectID, LibraryID, SampleID, Phenotype, ExternalSubjectID,
     ProjectOwner, ProjectName, Type, Assay, Source, Quality, Workflow,
-    portal_run_id, wfr_id, durationMin, start, end, s3_outdir_oncoanalyser
+    portal_run_id, wfr_id, start, end, s3_outdir_oncoanalyser
   ) |>
   dplyr::arrange(desc(SubjectID), start) |>
   dt_view()
@@ -630,9 +630,9 @@ pmeta |>
     durationMin = round(as.numeric(difftime(end, start, units = "mins")))
   ) |>
   dplyr::select(
-    end_status, SubjectID, LibraryID, SampleID, Phenotype, WGTS, ExternalSubjectID,
+    end_status, durationMin, SubjectID, LibraryID, SampleID, Phenotype, WGTS, ExternalSubjectID,
     ProjectOwner, ProjectName, Type, Assay, Source, Quality, Workflow,
-    portal_run_id, wfr_id, durationMin, start, end, s3_outdir_oncoanalyser
+    portal_run_id, wfr_id, start, end, s3_outdir_oncoanalyser
   ) |>
   dplyr::arrange(desc(SubjectID), start) |>
   dt_view()
@@ -665,9 +665,9 @@ pmeta |>
     durationMin = round(as.numeric(difftime(end, start, units = "mins")))
   ) |>
   dplyr::select(
-    end_status, SubjectID, LibraryID, SampleID, Phenotype, ExternalSubjectID,
+    end_status, durationMin, SubjectID, LibraryID, SampleID, Phenotype, ExternalSubjectID,
     ProjectOwner, ProjectName, Type, Assay, Source, Quality, Workflow,
-    portal_run_id, wfr_id, durationMin, start, end, s3_outdir_sash
+    portal_run_id, wfr_id, start, end, s3_outdir_sash
   ) |>
   dplyr::arrange(desc(SubjectID), start) |>
   dt_view()