#!/bin/bash

# # takes two paired files, run trimmomatic (PE mode), and makes one interleaved file # Trimmomatic v0.32 manual: # http://www.usadellab.org/cms/uploads/supplementary/Trimmomatic/TrimmomaticManual_V0.32.pdf

TRIMMOMATIC=/usr/local/apps/a5_miseq_linux_20140604/bin/trimmomatic.jar ADAPTER=/usr/local/apps/a5_miseq_linux_20140604/adapter.fasta INTERLEAVE=/usr/local/apps/khmer/khmerEnv/bin/interleave-reads.py THREADS=24 MINLEN=75

if [ $# -ne 2 ]

  then
      echo "Please specifiy two file names!"
      exit 1

fi

# Check the files are found (code from SGA example script) file_list=“$1 $2” for input in $file_list; do

  if [ ! -f $input ]; then
      echo "Error input file $input not found"; exit 1;
  fi

done

BASE=$(basename “$1”) # delete any leading path BASE=${BASE%_*} # delete string from '_' to the end (shortest match) # BASE=${1%%_*} makes difference. What is it? # BASE=${1/_*/} echo “File name base: $BASE”

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}

# compare to a5-miseq pipeline (my $trim_cmd): # ILLUMINACLIP:$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