Homec4science
Diffusion git_metatranscriptomic_LBE (master) Browse

metatran_LBE/20200723_quality_trimming.sh
5131f5b04268master

Last Change
Raw File

20200723_quality_trimming.sh
View Options

conda activate bbmap_env
export OUTDIR=/media/bioinfoteam/SCRATCH_850GB/temp_metatranscriptomic/quality_trimming
cd /media/bioinfoteam/SCRATCH_850GB/temp_metatranscriptomic/sequences
for filename1 in $(ls *'_R1.fastq')
do
fileID=`expr match "$filename1" '\([0-9]*C_L1\)'`
filename2=$fileID'_R2.fastq'
newname1=$fileID'_R1_no_adapter.fastq'
newname2=$fileID'_R2_no_adapter.fastq'
#echo '**********'
echo $fileID
echo $filename1
echo $filename2
echo $newname1
echo $newname2
#adapter trimming
bbduk.sh in1=$filename1 in2=$filename2 out1=$OUTDIR/$newname1 out2=$OUTDIR/$newname2 ref=/media/bioinfoteam/SCRATCH_850GB/temp_metatranscriptomic/truseq_adapter.fasta ktrim=r k=23 mink=11 hdist=1 tpe tbo stats=/media/bioinfoteam/SCRATCH_850GB/temp_metatranscriptomic/quality_trimming/${fileID}_stats.txt
done
#Quality trimming:
cd /media/bioinfoteam/SCRATCH_850GB/temp_metatranscriptomic/quality_trimming
for newname1 in $(ls *'_R1_no_adapter.fastq')
do
fileID=`expr match "$newname1" '\([0-9]*C_L1\)'`
newname2=$fileID'_R2_no_adapter.fastq'
#echo '**********'
echo $fileID
echo $newname1
echo $newname2
trimmed1=$fileID'_R1_trimmed.fastq'
trimmed2=$fileID'_R2_trimmed.fastq'
bbduk.sh in1=$newname1 in2=$newname2 out1=$trimmed1 out2=$trimmed2 qtrim=r trimq=20 minlen=50
done
#Quality filtering:
for newname1 in $(ls *'_R1_trimmed.fastq')
do
fileID=`expr match "$newname1" '\([0-9]*C_L1\)'`
newname2=$fileID'_R2_trimmed.fastq'
#echo '**********'
echo $fileID
echo $newname1
echo $newname2
qfiltered1=$fileID'_R1_qfiltered.fastq'
qfiltered2=$fileID'_R2_qfiltered.fastq'
bbduk.sh in1=$newname1 in2=$newname2 out1=$qfiltered1 out2=$qfiltered2 maq=20
done
c4science · Help