From 54248eb51283118e223f7b414a30799ee0293444 Mon Sep 17 00:00:00 2001
From: Adrian <adrian.janucik@gmail.com>
Date: Mon, 21 Aug 2023 14:41:44 +0200
Subject: [PATCH] final tested commit stage one (#14)

---
 bin/index-downstream.R                 | 75 ++++++++++++++++++++++++++
 conf/environments.config               |  5 ++
 modules/local/downstream_processing.nf |  6 +++
 modules/local/subread.nf               |  2 +-
 4 files changed, 87 insertions(+), 1 deletion(-)
 create mode 100755 bin/index-downstream.R

diff --git a/bin/index-downstream.R b/bin/index-downstream.R
new file mode 100755
index 0000000..e60e257
--- /dev/null
+++ b/bin/index-downstream.R
@@ -0,0 +1,75 @@
+#!/usr/bin/env Rscript
+
+# Setup -------------------------------------------------------------------
+args <- commandArgs(trailingOnly = TRUE)
+
+downstream_ch_file <- args[1]
+organism_in <- args[2]
+user_file <- args[3]
+
+if (organism_in == 'mouse') {
+    organism <- 'mus_musculus'
+} else if (organism_in == 'human') {
+    organism <- 'homo_sapiens'
+} else {
+    stop('Provided organism not supported...')
+}
+
+#downstream_ch_file <- "/futuriandgeDownstream/used-locally-for-testing/counts/extended_source-pipeline-out_meta_file-dockerfile.txt"
+#organism <- 'mus_musculus'
+#user_file <- "/futuriandgeDownstream/used-locally-for-testing/template-user-request.xlsx"
+
+sample_metadata <- readxl::read_excel(user_file, sheet = 'metadata')
+contrasts <- readxl::read_excel(user_file, sheet = 'comparisons')
+
+# Load --------------------------------------------------------------------
+library(futuriandgeDownstream)
+
+# F1
+print('Running futuriandgeDownstream::return_count_matrix')
+counts <- futuriandgeDownstream::return_count_matrix(downstream_ch_file)
+
+# F2
+print('Running futuriandgeDownstream::remove_mirna')
+counts_no_mirnas <- futuriandgeDownstream::remove_mirna(counts, organism)
+
+# F3
+print('Running futuriandgeDownstream::run_dge')
+dge_results <- futuriandgeDownstream::run_dge(count_matrix_raw = counts_no_mirnas,
+                       metadata_raw = sample_metadata,
+                       comparisons = contrasts)
+
+# save dge results
+print('Running save')
+save(dge_results, file = 'dge_results.RData')
+
+# F4
+print('Running splot_diagnostic_plotsave')
+futuriandgeDownstream::plot_diagnostic_plots(count_matrix_raw = counts_no_mirnas,
+                      metadata_raw = sample_metadata)
+
+# F5
+print('futuriandgeDownstream::render_dge_html_report')
+contrasts_for_report <- dplyr::mutate(contrasts, compared_gorups = paste0(
+    studied_effect,
+    '_vs_',
+    baseline
+  ))
+
+for (groups in contrasts_for_report$compared_gorups) {
+
+  sample_metadata$sample <- gsub("_T1",
+                                 "",
+                                 sample_metadata$sample_id)
+
+  futuriandgeDownstream::render_dge_html_report(
+    comparison_name = groups,
+    dge_results_in = data.frame(dge_results$dge_results[[groups]]),
+    metadata = sample_metadata,
+    norm_counts = dge_results$normalised_counts,
+    raw_counts = dge_results$raw_counts_no_gtf_miRNA,
+    organism = organism,
+    output_name = paste0(groups, ".html")
+  )
+}
+
diff --git a/conf/environments.config b/conf/environments.config
index f40001e..cb1f642 100644
--- a/conf/environments.config
+++ b/conf/environments.config
@@ -61,4 +61,9 @@
     container = 'https://depot.galaxyproject.org/singularity/multiqc:1.14--pyhdfd78af_0'
   }
 
+    withName: DESEQ2 {
+    container = 'sodzier/r-pkg-futuriandge-downstream:0.1.0'
+    containerOptions = "-B ${baseDir}/.nextflow:/futuriandgeDownstream"
+}
+
 }
diff --git a/modules/local/downstream_processing.nf b/modules/local/downstream_processing.nf
index c832266..d9403ca 100644
--- a/modules/local/downstream_processing.nf
+++ b/modules/local/downstream_processing.nf
@@ -11,11 +11,17 @@ process DESEQ2 {
     output:
     path("*"), emit: DESeq2_DOWNSTREAM_out
 
+    script:
+    def org = params.organism
+    def user_file = params.contrasts
     """
     # Merge all downstream info files
     cat *_downstream_info.txt > all_downstream_info.txt
 
     # Remove lines containing the header except for the first occurrence in the first line
     sed -i '1!{/sample_id,is_single_end,strandedness,count_matrix_path/d}' all_downstream_info.txt
+
+    index-downstream.R all_downstream_info.txt ${org} ${user_file}
+
     """  
 }
diff --git a/modules/local/subread.nf b/modules/local/subread.nf
index b07f116..f7269d4 100644
--- a/modules/local/subread.nf
+++ b/modules/local/subread.nf
@@ -42,6 +42,6 @@ process FEATURECOUNTS {
     echo "sample_id,is_single_end,strandedness,count_matrix_path" > ${meta.id}_downstream_info.txt
     
     # Write sample info to file
-    echo "${meta.id},${meta.single_end},${meta.strandedness},${PWD}/${meta.id}_featureCounts_matrix.txt" >> ${meta.id}_downstream_info.txt
+    echo "${meta.id},${meta.single_end},${meta.strandedness},\$PWD/${meta.id}_featureCounts_matrix.txt" >> ${meta.id}_downstream_info.txt
     """
 }