From 859a400056ba9d44ecb32e11c3535558eaa9f966 Mon Sep 17 00:00:00 2001
From: mraves2 <116661291+mraves2@users.noreply.github.com>
Date: Thu, 30 Apr 2026 13:39:23 +0200
Subject: [PATCH] Revert "Feature/refactor_DIMS_MakeInit"

---
 DIMS/MakeInit.R                               | 29 ++++++++++++++++++
 DIMS/MakeInit.nf                              | 18 +++++++++++
 DIMS/ParseSamplesheet.R                       | 19 ------------
 DIMS/ParseSamplesheet.nf                      | 18 -----------
 .../parse_samplesheet_functions.R             | 30 -------------------
 .../testthat/parse_samplesheet_functions.R    | 24 ---------------
 6 files changed, 47 insertions(+), 91 deletions(-)
 create mode 100644 DIMS/MakeInit.R
 create mode 100644 DIMS/MakeInit.nf
 delete mode 100644 DIMS/ParseSamplesheet.R
 delete mode 100644 DIMS/ParseSamplesheet.nf
 delete mode 100644 DIMS/preprocessing/parse_samplesheet_functions.R
 delete mode 100644 DIMS/tests/testthat/parse_samplesheet_functions.R

diff --git a/DIMS/MakeInit.R b/DIMS/MakeInit.R
new file mode 100644
index 00000000..9ff22623
--- /dev/null
+++ b/DIMS/MakeInit.R
@@ -0,0 +1,29 @@
+# define parameters
+args <- commandArgs(trailingOnly = TRUE)
+
+sample_sheet <- read.csv(args[1], sep = "\t")
+nr_replicates <- as.numeric(args[2])
+
+sample_names <- trimws(as.vector(unlist(sample_sheet[1])))
+nr_sample_groups <- length(sample_names) / nr_replicates
+group_names <- trimws(as.vector(unlist(sample_sheet[2])))
+group_names <- gsub("[^-.[:alnum:]]", "_", group_names)
+group_names_unique <- unique(group_names)
+
+# generate the replication pattern
+repl_pattern <- c()
+for (sample_group in 1:nr_sample_groups) {
+  replicates_persample <- c()
+  for (repl in nr_replicates:1) {
+    index <- ((sample_group * nr_replicates) - repl) + 1
+    replicates_persample <- c(replicates_persample, sample_names[index])
+  }
+  repl_pattern <- c(repl_pattern, list(replicates_persample))
+}
+
+names(repl_pattern) <- group_names_unique
+
+# preview the replication pattern
+print(tail(repl_pattern))
+
+save(repl_pattern, file = "init.RData")
diff --git a/DIMS/MakeInit.nf b/DIMS/MakeInit.nf
new file mode 100644
index 00000000..7aae0e46
--- /dev/null
+++ b/DIMS/MakeInit.nf
@@ -0,0 +1,18 @@
+process MakeInit {
+    tag "DIMS MakeInit"
+    label 'MakeInit'
+    container = 'docker://umcugenbioinf/dims:1.3'
+    shell = ['/bin/bash', '-euo', 'pipefail']
+
+    input:
+       path(samplesheet) 
+       val(nr_replicates)
+
+    output:
+       path('init.RData')
+
+    script:
+        """
+        Rscript ${baseDir}/CustomModules/DIMS/MakeInit.R $samplesheet $nr_replicates 
+        """
+}
diff --git a/DIMS/ParseSamplesheet.R b/DIMS/ParseSamplesheet.R
deleted file mode 100644
index 806486fb..00000000
--- a/DIMS/ParseSamplesheet.R
+++ /dev/null
@@ -1,19 +0,0 @@
-# define parameters
-args <- commandArgs(trailingOnly = TRUE)
-
-sample_sheet <- as.data.frame(read.csv(args[1], sep = "\t"))
-preprocessing_scripts_dir <- args[2]
-
-# load in function script
-source(paste0(preprocessing_scripts_dir, "parse_samplesheet_functions.R"))
-
-# generate the replication pattern
-repl_pattern <- generate_repl_pattern(sample_sheet)
-
-# write the replication pattern to text file for troubleshooting purposes
-sink("replication_pattern.txt")
-print(repl_pattern)
-sink()
-
-# save replication pattern to file
-save(repl_pattern, file = "init.RData")
diff --git a/DIMS/ParseSamplesheet.nf b/DIMS/ParseSamplesheet.nf
deleted file mode 100644
index e0fc055b..00000000
--- a/DIMS/ParseSamplesheet.nf
+++ /dev/null
@@ -1,18 +0,0 @@
-process ParseSamplesheet {
-    tag "DIMS ParseSamplesheet"
-    label 'ParseSamplesheet'
-    container = 'docker://umcugenbioinf/dims:1.3'
-
-    input:
-       path(samplesheet) 
-       val(preprocessing_scripts_dir)
-
-    output:
-       path('init.RData'), emit: rdata_file
-       path('replication_pattern.txt'), emit: repl_pattern_txtfile
-
-    script:
-        """
-        Rscript ${baseDir}/CustomModules/DIMS/ParseSamplesheet.R $samplesheet $preprocessing_scripts_dir
-        """
-}
diff --git a/DIMS/preprocessing/parse_samplesheet_functions.R b/DIMS/preprocessing/parse_samplesheet_functions.R
deleted file mode 100644
index 9107ba6a..00000000
--- a/DIMS/preprocessing/parse_samplesheet_functions.R
+++ /dev/null
@@ -1,30 +0,0 @@
-# function for parse_samplesheet
-
-#' Generate replication pattern list based on information in sample_sheet
-#'
-#' @param sample_sheet: matrix of file names and sample names
-#'
-#' @return ints_sorted: list of sample names with corresponding file names (technical replicates)
-generate_repl_pattern <- function(sample_sheet) {
-  # get the file name and sample name columns from the samplesheet
-  file_name_col <- grep("File_Name|File Name", colnames(sample_sheet), ignore.case = TRUE)
-  sample_name_col <- grep("Sample_Name|Sample Name", colnames(sample_sheet), ignore.case = TRUE)
-  # get the unique sample names from the samplesheet
-    sample_names <- sample_sheet[sample_name_col] |>
-    unlist() |>
-    as.vector() |>
-    trimws() |>
-    unique() |>
-    sort()
-  # remove all characters from sample_names which are not letters, numbers, hyphens and periods
-  sample_names <- gsub("[^-.[:alnum:]]", "_", sample_names)
-
-  # create replication pattern (which technical replicates belong to which sample)
-  repl_pattern <- split(
-    sample_sheet[[file_name_col]],
-    sample_sheet[[sample_name_col]]
-  )
-
-  return(repl_pattern)
-}
-
diff --git a/DIMS/tests/testthat/parse_samplesheet_functions.R b/DIMS/tests/testthat/parse_samplesheet_functions.R
deleted file mode 100644
index 8e467967..00000000
--- a/DIMS/tests/testthat/parse_samplesheet_functions.R
+++ /dev/null
@@ -1,24 +0,0 @@
-# unit tests for ParseSamplesheet
-# function: generate_repl_pattern
-
-# source all functions for ParseSamplesheet
-source("../../preprocessing/parse_samplesheet_functions.R")
-
-# test generate_repl_pattern
-testthat::test_that("replication pattern is correctly generated", {
-  # create sample sheet tot test on:
-  test_file_names <- paste0(rep("RES_20260101_", 6), sprintf("%03d", 1:6))
-  test_sample_names <- sort(rep(c("C1", "P2", "P3"), 2))
-  test_sample_sheet <- as.data.frame(cbind(File_Name = test_file_names, Sample_Name = test_sample_names))
-
-  # test that a list of length 3 is generated
-  expect_length(generate_repl_pattern(test_sample_sheet), 3)
-  # test list names
-  expect_equal(names(generate_repl_pattern(test_sample_sheet)), unique(test_sample_names), TRUE)
-  
-  # test what happens if any sample name is used twice
-  test_sample_names <- gsub("P3", "P2", test_sample_names)
-  test_sample_sheet <- as.data.frame(cbind(File_Name = test_file_names, Sample_Name = test_sample_names))
-  expect_length(generate_repl_pattern(test_sample_sheet), 2)
-  expect_length(generate_repl_pattern(test_sample_sheet)$P2, 4)
-})