Refactoring steps 01 and 02 to process all datasets at once (microarray and RNA-seq).

01-Quality_control/quality_control.R

@@ -37,12 +37,6 @@ for (i in seq_len(length(config$datasets))) {
   dataset      <- config$datasets[[i]]
   dataset_name <- dataset$dataset_name
 
-  # We only do the QC when it is necessary.
-  if (dataset$first_qc != 'TRUE') {
-    message(paste0("[", Sys.time(), "] [", dataset_name, "] QC not necessary."))
-    next
-  }
-
   # Clinical data can be used to identify bias in the experiments.
   # By default, we have the disease status, but we can also have the gender.
   dataset_groups   <- c("Disease.status")
@@ -55,6 +49,12 @@ for (i in seq_len(length(config$datasets))) {
   # We run the quality control of the current dataset (if necessary).
   if (selected_dataset_name == "" || selected_dataset_name == dataset_name) {
 
+    # We only do the QC when it is necessary.
+    if (dataset$first_qc != 'TRUE') {
+      message(paste0("[", Sys.time(), "] [", dataset_name, "] QC not necessary."))
+      next
+    }
+
     # We define the I/Os
     raw_data_subdir    <- paste0(raw_data_dir,    dataset_name, "/")
     output_data_subdir <- paste0(output_data_dir, dataset_name, "/")

01-Quality_control/run_qc.sh

@@ -5,9 +5,9 @@
 #SBATCH -N 1
 #SBATCH -n 1
 #SBATCH --mem=12GB
-#SBATCH --time=0-00:50:00
+#SBATCH --time=0-00:55:00
 #SBATCH -p batch
-#SBATCH --qos=qos-batch
+#SBATCH --qos=normal
 
 echo "== Starting run at $(date)"
 echo "== Job ID: ${SLURM_JOBID}"

02-Preprocessing/doc.sh

@@ -6,7 +6,7 @@
 #SBATCH -n 1
 #SBATCH --time=0-00:01:00
 #SBATCH -p batch
-#SBATCH --qos=qos-batch
+#SBATCH --qos=normal
 
 echo "== Starting run at $(date)"
 echo "== Job ID: ${SLURM_JOBID}"

02-Preprocessing/get_log.sh

@@ -6,7 +6,7 @@
 #SBATCH -n 1
 #SBATCH --time=0-00:02:00
 #SBATCH -p batch
-#SBATCH --qos=qos-batch
+#SBATCH --qos=normal
 
 echo "== Starting run at $(date)"
 echo "== Job ID: ${SLURM_JOBID}"

02-Preprocessing/preprocess.sh

@@ -4,9 +4,9 @@
 #SBATCH --mail-user=leon-charles.tranchevent@uni.lu
 #SBATCH -N 1
 #SBATCH -n 20
-#SBATCH --time=0-06:30:00
+#SBATCH --time=0-07:00:00
 #SBATCH -p batch
-#SBATCH --qos=qos-batch
+#SBATCH --qos=normal
 
 echo "== Starting run at $(date)"
 echo "== Job ID: ${SLURM_JOBID}"

02-Preprocessing/stabilize_variance.sh

@@ -4,9 +4,9 @@
 #SBATCH --mail-user=leon-charles.tranchevent@uni.lu
 #SBATCH -N 1
 #SBATCH -n 20
-#SBATCH --time=0-01:00:00
+#SBATCH --time=0-01:10:00
 #SBATCH -p batch
-#SBATCH --qos=qos-batch
+#SBATCH --qos=normal
 
 echo "== Starting run at $(date)"
 echo "== Job ID: ${SLURM_JOBID}"

Confs/datasets_config.yml

@@ -223,7 +223,7 @@ datasets:
   -
     dataset_name: NBB
     platform: RNAseq
-    array_type: RNAseq_EG
+    array_type: RNAseq-EG
     clinical_descriptors: DG
     first_qc: 'FALSE'
     use_oligo: 'FALSE'

Confs/platforms_config.yml

@@ -71,3 +71,19 @@ platforms:
     library_name: hugene10sttranscriptcluster.db
     cdf_name: HuGene-1_0-st-v1.r3.cdf
     mps_name: NA
+  -
+    vendor: RNAseq
+    platform_name: RNAseq-EG
+    biomart_name: ensembl_transcript_id
+    geo_name: NA
+    library_name: NA
+    cdf_name: NA
+    mps_name: NA
+  -
+    vendor: RNAseq
+    platform_name: HiSeq1000
+    biomart_name: NA
+    geo_name: NA
+    library_name: NA
+    cdf_name: NA
+    mps_name: NA