From fa11871a5efbc5211f8366743369876763241242 Mon Sep 17 00:00:00 2001
From: "Gervaise H. Henry" <gervaise.henry@utsouthwestern.edu>
Date: Wed, 5 Aug 2020 20:09:31 -0500
Subject: [PATCH] Extract raw reads
---
workflow/conf/multiqc_config.yaml | 5 +++--
workflow/rna-seq.nf | 19 +++++++++++++++----
2 files changed, 18 insertions(+), 6 deletions(-)
diff --git a/workflow/conf/multiqc_config.yaml b/workflow/conf/multiqc_config.yaml
index 3c1c535..99a861c 100644
--- a/workflow/conf/multiqc_config.yaml
+++ b/workflow/conf/multiqc_config.yaml
@@ -80,9 +80,10 @@ custom_data:
Ends
Stranded
Spike-in
+ Raw Reads
Assigned Reads
- Read Length
- TIN
+ Median Read Length
+ Median TIN
file_format: 'tsv'
section_name: 'TIN'
diff --git a/workflow/rna-seq.nf b/workflow/rna-seq.nf
index 1871139..b1cf47e 100644
--- a/workflow/rna-seq.nf
+++ b/workflow/rna-seq.nf
@@ -902,6 +902,7 @@ process fastqc {
output:
path ("*_fastqc.zip") into fastqc
+ path ("rawRead.csv") into inferMetadata_rawReads
script:
"""
@@ -911,9 +912,18 @@ process fastqc {
# run fastqc
echo -e "LOG: running fastq on raw fastqs" >> ${repRID}.fastqc.log
fastqc *.fastq.gz -o .
+
+ # count raw reads
+ zcat ${fastq[0]} | echo $((`wc -l`/4)) > rawReads.csv
"""
}
+// Extract number of raw reads metadata into channel
+rawReadsInfer = Channel.create()
+inferMetadata_rawReads.splitCsv(sep: ",", header: false).separate(
+ rawReadsInfer
+)
+
/*
*dataQC: calculate transcript integrity numbers (TIN) and bin as well as calculate innerdistance of PE replicates
*/
@@ -998,6 +1008,7 @@ process aggrQC {
val speciesI from speciesInfer_aggrQC
val readLengthM from readLengthMeta
val readLengthI from readLengthInfer
+ val rawReadsI from rawReadsInfer
val assignedReadsI from assignedReadsInfer
val tinMedI from tinMedInfer
val expRID
@@ -1018,10 +1029,10 @@ process aggrQC {
# make metadata table
echo -e "LOG: creating metadata table" >> ${repRID}.aggrQC.log
- echo -e "Source\tSpecies\tEnds\tStranded\tSpike-in\tAssigned Reads\tRead Length\tTIN" > metadata.tsv
- echo -e "Infered\t${speciesI}\t${endsI}\t${strandedI}\t${spikeI}\t-\t-\t-" >> metadata.tsv
- echo -e "Submitter\t${speciesM}\t${endsM}\t${strandedM}\t${spikeM}\t-\t${readLengthM}\t-" >> metadata.tsv
- echo -e "Measured\t-\t${endsManual}\t-\t-\t${assignedReadsI}\t${readLengthI}\t${tinMedI}" >> metadata.tsv
+ echo -e "Source\tSpecies\tEnds\tStranded\tSpike-in\tRaw Reads\tAssigned Reads\tMedian Read Length\tMedian TIN" > metadata.tsv
+ echo -e "Submitter\t${speciesM}\t${endsM}\t${strandedM}\t${spikeM}\t-\t-\t${readLengthM}\t-" >> metadata.tsv
+ echo -e "Infered\t${speciesI}\t${endsI}\t${strandedI}\t${spikeI}\t-\t-\t-\t-" >> metadata.tsv
+ echo -e "Measured\t-\t${endsManual}\t-\t-\t${rawReadsI}\t${assignedReadsI}\t${readLengthI}\t${tinMedI}" >> metadata.tsv
# remove inner distance report if it is empty (SE repRID)
echo -e "LOG: removing dummy inner distance file" >> ${repRID}.aggrQC.log
--
GitLab