conda activate sortmerna_env

export DATABASE=/media/bioinfoteam/SCRATCH_850GB/databases/rna_families

cd /media/bioinfoteam/SCRATCH_850GB/temp_metatranscriptomic/quality_trimming

#Sort rRNA using sortmeRNA
for filename1 in $(ls *'_R1_qfiltered.fastq')

do
fileID=`expr match "$filename1" '\([0-9]*C_L1\)'`

filename2=$fileID'_R2_qfiltered.fastq'

#echo '**********'
echo $fileID
echo $filename1
echo $filename2


export OUTFILE1=/media/bioinfoteam/SCRATCH_850GB/temp_metatranscriptomic/rRNA_sorting/${fileID}_aligned

export OUTFILE2=/media/bioinfoteam/SCRATCH_850GB/temp_metatranscriptomic/rRNA_sorting/${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 -reads $filename2 -fastx --aligned $OUTFILE1 --other $OUTFILE2 -paired_in True

rm /home/bioinfoteam/sortmerna/run/kvdb/*

done


# test
filename1=/media/bioinfoteam/SCRATCH_850GB/temp_metatranscriptomic/quality_trimming/34C_L1_R1_trimmed.fastq
filename2=/media/bioinfoteam/SCRATCH_850GB/temp_metatranscriptomic/quality_trimming/34C_L1_R2_trimmed.fastq
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 $OUTDIR1 --other $OUTDIR2 -paired_in True