From 97e72a8b200c9d04da19660e5607ca4aedb6e82c Mon Sep 17 00:00:00 2001
From: "Gervaise H. Henry" <gervaise.henry@utsouthwestern.edu>
Date: Mon, 3 Aug 2020 15:42:09 -0500
Subject: [PATCH] Nextflow-ify bash command to extract median read length
---
workflow/rna-seq.nf | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/workflow/rna-seq.nf b/workflow/rna-seq.nf
index e155a94..3e7e3aa 100644
--- a/workflow/rna-seq.nf
+++ b/workflow/rna-seq.nf
@@ -299,14 +299,14 @@ process trimData {
if [ "${ends}" == "se" ]
then
trim_galore --gzip -q 25 --illumina --length 35 --basename ${repRID} -j `nproc` ${fastq[0]}
- readLength=\$(zcat *_trimmed.fq.gz | awk '\{if(NR%4==2) print length(\${1})}' | sort -n | awk '\{a[NR]=$0}END\{print(NR%2==1)?a[int(NR/2)+1]:(a[NR/2]+a[NR/2+1])/2}')
+ readLength=\$(zcat *_trimmed.fq.gz | awk '{if(NR%4==2) print length(\${1})}' | sort -n | awk '{a[NR]=$0}END{print(NR%2==1)?a[int(NR/2)+1]:(a[NR/2]+a[NR/2+1])/2}')
elif [ "${ends}" == "pe" ]
then
trim_galore --gzip -q 25 --illumina --length 35 --paired --basename ${repRID} -j `nproc` ${fastq[0]} ${fastq[1]}
- readLength=\$(zcat *_1.fq.gz | awk '\{if(NR%4==2) print length(\${1})}' | sort -n | awk '\{a[NR]=$0}END\{print(NR%2==1)?a[int(NR/2)+1]:(a[NR/2]+a[NR/2+1])/2}')
+ readLength=\$(zcat *_1.fq.gz | awk '{if(NR%4==2) print length(\${1})}' | sort -n | awk '{a[NR]=$0}END{print(NR%2==1)?a[int(NR/2)+1]:(a[NR/2]+a[NR/2+1])/2}')
fi
echo -e "LOG: trimmed" >> ${repRID}.trimData.log
- echo -e "LOG: average trimmed read length: /${readLength}" >> ${repRID}.trimData.log
+ echo -e "LOG: average trimmed read length: \${readLength}" >> ${repRID}.trimData.log
# save read length file
echo -e "\${readLength}" > readLength.csv
--
GitLab