Homec4science
Diffusion git_metatranscriptomic_LBE (master) Browse

metatran_LBE/20200821_sort_rRNA_mergeSample.sh
e8e71cc77a13master

Last Change
Raw File

20200821_sort_rRNA_mergeSample.sh
View Options

conda activate sortmerna_env
export DATABASE=/media/bioinfoteam/SCRATCH_850GB/databases/rna_families
cd /media/bioinfoteam/SCRATCH_850GB/temp_metatranscriptomic/quality_trimming
##################################### on merged sample -> considering as single read ######################################
for filename1 in $(ls *'_merged_qfiltered.fastq')
do
fileID=`expr match "$filename1" '\([0-9]*C_L1\)_merged'`
#echo '**********'
echo $filename1
echo $fileID
export OUTFILE1=/media/bioinfoteam/SCRATCH_850GB/temp_metatranscriptomic/rRNA_sorting_merge/${fileID}_aligned
export OUTFILE2=/media/bioinfoteam/SCRATCH_850GB/temp_metatranscriptomic/rRNA_sorting_merge/${fileID}_non_aligned
sortmerna -ref $DATABASE/rfam-5.8s-database-id98.fasta -ref $DATABASE/rfam-5s-database-id98.fasta -ref $DATABASE/silva-arc-16s-id95.fasta -ref $DATABASE/silva-arc-23s-id98.fasta -ref $DATABASE/silva-bac-16s-id90.fasta -ref $DATABASE/silva-bac-23s-id98.fasta -ref $DATABASE/silva-euk-18s-id95.fasta -ref $DATABASE/silva-euk-28s-id98.fasta -reads $filename1 -fastx --aligned $OUTFILE1 --other $OUTFILE2 -paired_in False
rm /home/bioinfoteam/sortmerna/run/kvdb/*
done
##################################### on unmerged sample -> considering as paired reads, on separated R1 and R2 ######################################
for filename1 in $(ls *'_R1_unmerged_qfiltered.fastq')
do
fileID=`expr match "$filename1" '\([0-9]*C_L1\)'`
filename2=$fileID'_R2_unmerged_qfiltered.fastq'
#echo '**********'
echo $filename1
echo $fileID
export OUTFILE1=/media/bioinfoteam/SCRATCH_850GB/temp_metatranscriptomic/rRNA_sorting_merge/${fileID}_unmerged_aligned
export OUTFILE2=/media/bioinfoteam/SCRATCH_850GB/temp_metatranscriptomic/rRNA_sorting_merge/${fileID}_unmerged_non_aligned
sortmerna -ref $DATABASE/rfam-5.8s-database-id98.fasta -ref $DATABASE/rfam-5s-database-id98.fasta -ref $DATABASE/silva-arc-16s-id95.fasta -ref $DATABASE/silva-arc-23s-id98.fasta -ref $DATABASE/silva-bac-16s-id90.fasta -ref $DATABASE/silva-bac-23s-id98.fasta -ref $DATABASE/silva-euk-18s-id95.fasta -ref $DATABASE/silva-euk-28s-id98.fasta -reads $filename1 -reads $filename2 -fastx --aligned $OUTFILE1 --other $OUTFILE2 -paired_in True
rm /home/bioinfoteam/sortmerna/run/kvdb/*
done
c4science · Help