From 51f9e8ff47b4d9be20b075dae72b90a8e64119b1 Mon Sep 17 00:00:00 2001
From: "Gervaise H. Henry" <gervaise.henry@utsouthwestern.edu>
Date: Tue, 19 Jan 2021 11:42:37 -0600
Subject: [PATCH] Physically move fastqc process up
---
workflow/rna-seq.nf | 92 ++++++++++++++++++++++-----------------------
1 file changed, 46 insertions(+), 46 deletions(-)
diff --git a/workflow/rna-seq.nf b/workflow/rna-seq.nf
index fac3f7b..43d3c04 100644
--- a/workflow/rna-seq.nf
+++ b/workflow/rna-seq.nf
@@ -528,6 +528,52 @@ fastqReadError.into {
fastqReadError_failPreExecutionRun_fastq
}
+/*
+ *fastqc: run fastqc on untrimmed fastq's
+*/
+process fastqc {
+ tag "${repRID}"
+
+ input:
+ path (fastq) from fastqs_fastqc
+ val fastqCountError_fastqc
+ val fastqReadError_fastqc
+
+ output:
+ path ("*.fastq.gz", includeInputs:true) into fastqs_trimData
+ path ("*_fastqc.zip") into fastqc
+ path ("rawReads.csv") into rawReadsInfer_fl
+
+ when:
+ fastqCountError_fastqc == 'false'
+ fastqReadError_fastqc == 'false'
+
+ script:
+ """
+ hostname > ${repRID}.fastqc.log
+ ulimit -a >> ${repRID}.fastqc.log
+
+ # run fastqc
+ echo -e "LOG: running fastq on raw fastqs" >> ${repRID}.fastqc.log
+ fastqc *.fastq.gz -o .
+
+ # count raw reads
+ zcat *.R1.fastq.gz | echo \$((`wc -l`/4)) > rawReads.csv
+ """
+}
+
+// Extract number of raw reads metadata into channel
+rawReadsInfer = Channel.create()
+rawReadsInfer_fl.splitCsv(sep: ",", header: false).separate(
+ rawReadsInfer
+)
+
+// Replicate inferred raw reads for multiple process inputs
+rawReadsInfer.into {
+ rawReadsInfer_aggrQC
+ rawReadsInfer_uploadQC
+}
+
/*
* trimData: trims any adapter or non-host sequences from the data
*/
@@ -1648,52 +1694,6 @@ assignedReadsInfer.into {
assignedReadsInfer_uploadQC
}
-/*
- *fastqc: run fastqc on untrimmed fastq's
-*/
-process fastqc {
- tag "${repRID}"
-
- input:
- path (fastq) from fastqs_fastqc
- val fastqCountError_fastqc
- val fastqReadError_fastqc
-
- output:
- path ("*.fastq.gz", includeInputs:true) into fastqs_trimData
- path ("*_fastqc.zip") into fastqc
- path ("rawReads.csv") into rawReadsInfer_fl
-
- when:
- fastqCountError_fastqc == 'false'
- fastqReadError_fastqc == 'false'
-
- script:
- """
- hostname > ${repRID}.fastqc.log
- ulimit -a >> ${repRID}.fastqc.log
-
- # run fastqc
- echo -e "LOG: running fastq on raw fastqs" >> ${repRID}.fastqc.log
- fastqc *.fastq.gz -o .
-
- # count raw reads
- zcat *.R1.fastq.gz | echo \$((`wc -l`/4)) > rawReads.csv
- """
-}
-
-// Extract number of raw reads metadata into channel
-rawReadsInfer = Channel.create()
-rawReadsInfer_fl.splitCsv(sep: ",", header: false).separate(
- rawReadsInfer
-)
-
-// Replicate inferred raw reads for multiple process inputs
-rawReadsInfer.into {
- rawReadsInfer_aggrQC
- rawReadsInfer_uploadQC
-}
-
/*
*dataQC: calculate transcript integrity numbers (TIN) and bin as well as calculate innerdistance of PE replicates
*/
--
GitLab