From 89cca76e070ff36b3e5885e26ebd500553fac64a Mon Sep 17 00:00:00 2001
From: mAGLAVE <55588167+mAGLAVE@users.noreply.github.com>
Date: Thu, 14 Mar 2024 18:21:09 +0100
Subject: [PATCH 1/3] BugFix: add {} around awk terms

---
 bigr_pipelines/rnaseq/rules/029.clusterprofiler.terms.smk | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/bigr_pipelines/rnaseq/rules/029.clusterprofiler.terms.smk b/bigr_pipelines/rnaseq/rules/029.clusterprofiler.terms.smk
index 55fd02890fe..acf0b5488cd 100644
--- a/bigr_pipelines/rnaseq/rules/029.clusterprofiler.terms.smk
+++ b/bigr_pipelines/rnaseq/rules/029.clusterprofiler.terms.smk
@@ -20,7 +20,7 @@ rule term2gene_TERMS_PPI:
         tmpdir="tmp",
     params:
         begin='FS=OFS="\t"',
-        body=["print $3 FS $1"],
+        body=["{print $3 FS $1}"],
     group:
         "prepare_terms_ppi"
     log:
@@ -51,7 +51,7 @@ rule terms2name_TERMS_PPI:
         tmpdir="tmp",
     params:
         begin='FS=OFS="\t"',
-        body=["print $3 FS $4"],
+        body=["{print $3 FS $4}"],
     group:
         "prepare_terms_ppi"
     log:

From 1cd68a065db429d3f8ba373516f8482d18477e4c Mon Sep 17 00:00:00 2001
From: mAGLAVE <55588167+mAGLAVE@users.noreply.github.com>
Date: Thu, 14 Mar 2024 18:28:24 +0100
Subject: [PATCH 2/3] Bug fix in bio/deseq2/DESeqDataSetFromMatrix/wrapper.R

- set a value to x variable into the lapply function
- add a filtering step to filter count table to keep only samples from coldata file
---
 bio/deseq2/DESeqDataSetFromMatrix/wrapper.R | 16 +++++++++++-----
 1 file changed, 11 insertions(+), 5 deletions(-)

diff --git a/bio/deseq2/DESeqDataSetFromMatrix/wrapper.R b/bio/deseq2/DESeqDataSetFromMatrix/wrapper.R
index dee22e6d121..4dabb56ea1f 100755
--- a/bio/deseq2/DESeqDataSetFromMatrix/wrapper.R
+++ b/bio/deseq2/DESeqDataSetFromMatrix/wrapper.R
@@ -16,6 +16,7 @@ base::sink(log.file,type="message");
 
 base::library(package="DESeq2", quietly=TRUE);
 
+#read counts table file
 counts <- utils::read.table(
   file=snakemake@input[["counts"]],
   header = TRUE,
@@ -23,26 +24,28 @@ counts <- utils::read.table(
   stringsAsFactors = FALSE
 );
 
+#formatting counts table with genes in row names
 gene_names_col <- "genes";
 if ("count_gene_col" %in% base::names(snakemake@params)) {
   gene_names_col <- base::as.character(x=snakemake@params[["count_gene_col"]]);
 }
 rownames(counts) <- counts[, gene_names_col];
-
-numerical_columns <- base::unlist(base::lapply(x, base::is.numeric));
+numerical_columns <- base::unlist(base::lapply(counts[1,], base::is.numeric));
 counts <- counts[, numerical_columns];
 
+#filtering low counts
 count_filter <- 0;
 if ("count_filter" %in% names(snakemake@params)) {
   count_filter <- base::as.numeric(
     x = snakemake@params[["count_filter"]]
   );
 }
-
-keep <- rowSums(counts(counts)) > count_filter;
+keep <- rowSums(head(counts)) > count_filter;
 counts <- counts[keep, ];
+
 base::message("Counts loaded");
 
+#read coldata file
 coldata <- utils::read.table(
   file=snakemake@input[["coldata"]],
   header = TRUE,
@@ -51,11 +54,14 @@ coldata <- utils::read.table(
 );
 base::message("Coldata loaded");
 
+#filtering count table to keep only samples from coldata file
+counts <- counts[, colnames(counts) %in% coldata[,1]];
+
 extra <- "countData=counts, colData=coldata"
 if ("extra" %in% base::names(snakemake@params)) {
   extra <- base::paste(
     extra,
-    base::as.character(x=snakemake@params[["extra"]])
+    base::as.character(x=snakemake@params[["extra"]]),
     sep=","
   );
 }

From aad0cec868f4f47f1cf017e305229b432273dda4 Mon Sep 17 00:00:00 2001
From: mAGLAVE <55588167+mAGLAVE@users.noreply.github.com>
Date: Thu, 14 Mar 2024 18:30:44 +0100
Subject: [PATCH 3/3] Update bio/deseq2/DESeqDataSetFromMatrix/wrapper.R

remove the head that replace the counts to remove
---
 bio/deseq2/DESeqDataSetFromMatrix/wrapper.R | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/bio/deseq2/DESeqDataSetFromMatrix/wrapper.R b/bio/deseq2/DESeqDataSetFromMatrix/wrapper.R
index 4dabb56ea1f..6d95deb1d92 100755
--- a/bio/deseq2/DESeqDataSetFromMatrix/wrapper.R
+++ b/bio/deseq2/DESeqDataSetFromMatrix/wrapper.R
@@ -40,7 +40,7 @@ if ("count_filter" %in% names(snakemake@params)) {
     x = snakemake@params[["count_filter"]]
   );
 }
-keep <- rowSums(head(counts)) > count_filter;
+keep <- rowSums(counts) > count_filter;
 counts <- counts[keep, ];
 
 base::message("Counts loaded");