Differences

This shows you the differences between two versions of the page.

--- myillu_01.trimpe.sh [2016/05/07 12:49] – created hyjeong
+++ myillu_01.trimpe.sh [2021/03/17 13:09] (current) – external edit 127.0.0.1
@@ Line 1: / Line 1: @@
-====== Script myIllu_trimPE.sh ======
+====== Script <myIllu_trimPE.sh> ======
   #!/bin/bash
-#
+  #
-# takes two paired files, run trimmomatic (PE mode), and makes one interleaved file
+  # takes two paired files, run trimmomatic (PE mode), and makes one interleaved file
-# Trimmomatic v0.32 manual:
+  # Trimmomatic v0.32 manual:
-#   http://www.usadellab.org/cms/uploads/supplementary/Trimmomatic/TrimmomaticManual_V0.32.pdf
+  #   http://www.usadellab.org/cms/uploads/supplementary/Trimmomatic/TrimmomaticManual_V0.32.pdf
+  #
-TRIMMOMATIC=/usr/local/apps/a5_miseq_linux_20140604/bin/trimmomatic.jar
+  # Latest version of ngopt (a5_miseq): 20150522
-ADAPTER=/usr/local/apps/a5_miseq_linux_20140604/adapter.fasta
-INTERLEAVE=/usr/local/apps/khmer/khmerEnv/bin/interleave-reads.py
+  TRIMMOMATIC=/usr/local/apps/a5_miseq_linux_20140604/bin/trimmomatic.jar
-THREADS=24
+  ADAPTER=/usr/local/apps/a5_miseq_linux_20140604/adapter.fasta
-MINLEN=75
+  INTERLEAVE=/usr/local/apps/khmer/khmerEnv/bin/interleave-reads.py
+  THREADS=24
-if [ $# -ne 2 ]
+  MINLEN=75
-    then
+  # default MINLENG is 75 (for NGOPT, 36 bp)
-        echo "Please specifiy two file names!"
-        exit 1
+  if [ $# -ne 2 ]
-fi
+      then
+          echo "Please specifiy two file names!"
-# Check the files are found (code from SGA example script)
+          exit 1
-file_list="$1 $2"
+  fi
-for input in $file_list; do
-    if [ ! -f $input ]; then
+  # Check the files are found (code from SGA example script)
-        echo "Error input file $input not found"; exit 1;
+  file_list="$1 $2"
-    fi
+  for input in $file_list; do
-done
+      if [ ! -f $input ]; then
+          echo "Error input file $input not found"; exit 1;
+      fi
-BASE=$(basename "$1")  # delete any leading path
+  done
-BASE=${BASE%_*}           # delete string from '_' to the end (shortest match)
-# BASE=${1%%_*} makes difference. What is it?
+  # Using `basename` command is a good idea. Because the stripped BASE
-# BASE=${1/_*/}
+  # can be used as a output file prefix in "current" directory.
-echo "File name base: $BASE"
+  BASE=$(basename "$1")  # delete any leading path
+  BASE=${BASE%_*}           # delete string from '_' to the end (shortest match)
-java -jar $TRIMMOMATIC PE -threads ${THREADS} -phred33 -baseout ${BASE}.fq.gz $1 $2 ILLUMINACLIP:$ADAPTER:2:30:10 LEADING:3 TRAILING:3 SLIDINGWINDOW:4:20 MINLEN:${MINLEN}
+  # BASE=${1%%_*} makes difference. What is it? (longest match)
+  # BASE=${1/_*/} (longest match)
-# compare to a5-miseq pipeline (my $trim_cmd):
+  echo "File name base: $BASE"
-#   ILLUMINACLIP:$adapter:2:30:10 LEADING:3 TRAILING:3 SLIDINGWINDOW:4:15 MINLEN:36
+  BASE=${BASE}-trim
+  echo "File name base will be changed into ${BASE}"
-echo "Writing interleaved file ${BASE}.pe.fq from ${BASE}_1P.fq.gz ${BASE}_2P.fq.gz..."
-$INTERLEAVE -o ${BASE}.pe.fq ${BASE}_1P.fq.gz ${BASE}_2P.fq.gz
+  java -jar $TRIMMOMATIC PE -threads ${THREADS} -phred33 -baseout ${BASE}.fq.gz $1 $2 ILLUMINACLIP:$ADAPTER:2:30:10 LEADING:3 TRAILING:3 SLIDINGWINDOW:4:20 MINLEN:${MINLEN}
-echo "Deleting intermediate files (including orphan files)..."
+  # compare to a5-miseq pipeline (my $trim_cmd):
-rm ${BASE}_1U.fq.gz ${BASE}_2U.fq.gz ${BASE}_1P.fq.gz ${BASE}_2P.fq.gz
+  #   ILLUMINACLIP:$adapter:2:30:10 LEADING:3 TRAILING:3 SLIDINGWINDOW:4:15 MINLEN:36
+  echo "Writing interleaved file ${BASE}.pe.fq from ${BASE}_1P.fq.gz ${BASE}_2P.fq.gz..."
+  $INTERLEAVE -o ${BASE}.pe.fq ${BASE}_1P.fq.gz ${BASE}_2P.fq.gz
+  echo "Deleting intermediate files (including orphan files)..."
+  rm ${BASE}_1U.fq.gz ${BASE}_2U.fq.gz ${BASE}_1P.fq.gz ${BASE}_2P.fq.gz