#!/bin/bash
#SBATCH -t 4:00:00
#SBATCH --nodes=1 --ntasks-per-node=1
#SBATCH --mem=144g
#SBATCH --export=NONE
#SBATCH --mail-user=alex_labossiere@uri.edu
#SBATCH --mail-type=BEGIN,END,FAIL

echo "Script started!"

module load QIIME2/2024.2

echo "module has loaded!"

if qiime rescript filter-seqs-length-by-taxon \
    --i-sequences HOMD_16S_Refseq.qza \
    --i-taxonomy ref-taxonomy.qza \
    --p-labels Archaea Bacteria Eukaryota \
    --p-min-lens 900 1200 1400 \
    --o-filtered-seqs HOMD-15.23-16S-seqs-filt.qza \
    --o-discarded-seqs HOMD-15.23-16S-seqs-discarded.qza; then
	echo "filtered files made "
fi

if qiime rescript dereplicate \
    --i-sequences HOMD-15.23-16S-seqs-filt.qza \
    --i-taxa ref-taxonomy.qza \
    --p-mode 'uniq' \
    --o-dereplicated-sequences HOMD-15.23-16S-seqs-filt-derep-uniq.qza \
    --o-dereplicated-taxa HOMD-15.23-ref-taxonomy-derep-uniq.qza; then
	echo "depreplicated files made!"
fi

if  qiime feature-classifier extract-reads \
    --i-sequences HOMD-15.23-16S-seqs-filt-derep-uniq.qza \
    --p-f-primer AGAGTTTGATYMTGGCTCAG \
    --p-r-primer TGCTGCCTCCCGTAGRAGT \
    --p-n-jobs 2 \
    --p-read-orientation 'forward' \
    --o-reads HOMD-15.23-16S-seqs-filt-derep-uniq-29f-338r.qza; then 
	echo "primer based classifier made!"
fi


if qiime rescript dereplicate \
     --i-sequences HOMD-15.23-16S-seqs-filt-derep-uniq-29f-338r.qza \
     --i-taxa HOMD-15.23-ref-taxonomy-derep-uniq.qza \
     --p-mode 'uniq' \
     --o-dereplicated-sequences HOMD-15.23-16S-seqs-filt-derep-uniq-29f-338r.qza \
     --o-dereplicated-taxa HOMD-15.23-ref-taxonomy-derep-uniq-29f-338r.qza; then
         echo "dereplicated again!"
fi
    
 echo "Script completed successfully!"