3.QIIME.analysis

#!/bin/bash
### Remove Chimeras and Assign Taxonomy

mkdir "3.QIIME_analysis"

##1. Use USEARCH61 to identify Chimeras
#navigate to directory with seq.fna
identify_chimeric_seqs.py -i $PWD/2.split_libraries_fastq.usearch.filtered.dir/seqs.fna -m usearch61 -o $PWD/3.QIIME_analysis/Chimera_filtering_USEARCH/ -r rdp_gold.fa

##2. Filter the input seq.fna file
filter_fasta.py -f $PWD/2.split_libraries_fastq.usearch.filtered.dir/seqs.fna -o $PWD/3.QIIME_analysis/Chimera_filtering_USEARCH/seqs_chimeras_filtered.fna -s $PWD/3.QIIME_analysis/Chimera_filtering_USEARCH/chimeras.txt -n

## 3. use pick_otus.py to cluster sequences using usearch61 
pick_otus.py -m usearch61 -i $PWD/3.QIIME_analysis/Chimera_filtering_USEARCH/seqs_chimeras_filtered.fna -o $PWD/3.QIIME_analysis/USEARCH_picked_otus/

## 4. Make representative sequences 
pick_rep_set.py -i $PWD/3.QIIME_analysis/USEARCH_picked_otus/seqs_chimeras_filtered_otus.txt -f $PWD/3.QIIME_analysis/Chimera_filtering_USEARCH/seqs_chimeras_filtered.fna -o $PWD/3.QIIME_analysis/USEARCH_picked_otus/seqs_chimeras_filtered_otus_rep_set.fna

## 5. Tabulate the number of times an OTU is found in each sample (note that taxonomy assigning is not needed, as it is analyzed in 4.RDP_to_table
make_otu_table.py -i $PWD/3.QIIME_analysis/USEARCH_picked_otus/seqs_chimeras_filtered_otus.txt -o $PWD/3.QIIME_analysis/USEARCH_picked_otus/otu_table_non_chimeric.biom -e $PWD/3.QIIME_analysis/Chimera_filtering_USEARCH/chimeras.txt