qiime.workflow.sh

# loading raw data
gunzip lane1_NoIndex_L001_R1_001.fastq.gz
gunzip lane1_NoIndex_L001_R2_001.fastq.gz
gunzip lane1_NoIndex_L001_R3_001.fastq.gz

# fix barcode headers to match R1 headers
cat lane1_NoIndex_L001_R2_001.fastq | sed 's/2:N:[0-9]\+:/1:N:0:/g' > barcodes.fixed.fastq

# validate mapping file
validate_mapping_file.py -m CDC1_MAP.txt -o corrected_map

# join forward and reverse reads
join_paired_ends.py --min_overlap 10 --perc_max_diff 20 --forward_reads_fp lane1_NoIndex_L001_R1_001.fastq --reverse_reads_fp lane1_NoIndex_L001_R3_001.fastq --index_reads_fp barcodes.fixed.fastq --output_dir 1_join_paired_ends

# split libraries
split_libraries_fastq.py -i 1_join_paired_ends/fastqjoin.join.fastq --rev_comp_mapping_barcodes -o split_out_paired_cdc1/ -b 1_join_paired_ends/fastqjoin.join_barcodes.fastq -m CDC1_MAP.txt -s 1000000000

# if necessary, combine sequences from multiple experiments here
cat cdc1/split_out_paired_cdc1/seqs.fna cdc2/split_out_paired_cdc2/seqs.fna HMAC/split_out_paired_hmac/seqs.fna  > combined_hmac_cdc_seqs_071615.fna

# pick de novo OTUs using split_libraries output
pick_de_novo_otus.py -i combined_hmac_cdc_seqs_071615.fna -o hmac_cdc_otus

#now remove chimeras from rep_set_aligned fasta file using a reference aligned fasta file (http://greengenes.lbl.gov/Download/Sequence_Data/Fasta_data_files/)
#(make sure all files used in this step are in one directory, otherwise chimerslayer won't work)
identify_chimeric_seqs.py -m ChimeraSlayer -i combined_hmac_cdc_seqs_071615_rep_set_aligned.fasta -a core_set_aligned.fasta.imputed -o chimeric_seqs_core.txt

#remove chimeric sequences from alignment before filtering and tree building
filter_fasta.py -f combined_hmac_cdc_seqs_071615_rep_set_aligned.fasta -o non_chimeric_rep_set_aligned.fasta -s chimeric_seqs_core.txt -n

#filter alignment (i.e. get rid of blank spaces)
filter_alignment.py -i non_chimeric_rep_set_aligned.fasta -o non_chimeric_filtered_alignment/

#make tree; later can add tree to phyloseq object in R
make_phylogeny.py -i non_chimeric_filtered_alignment/non_chimeric_rep_set_aligned_pfiltered.fasta -o CH_non_chimeric.tre

#make otu table, otu_map is file created after first step (in uclust_picked_otus folder) and taxonomy file is in uclust_assigned_taxonomy folder; at same time, remove sequences that failed alignment
#make_otu_table.py -i uclust_picked_otus/combined_hmac_cdc_seqs_071615_otus.txt -o otu_table_no_fails.biom -e pynast_aligned_seqs/combined_hmac_cdc_seqs_071615_rep_set_failures.fasta -t uclust_assigned_taxonomy/combined_hmac_cdc_seqs_071615_rep_set_tax_assignments.txt

#filter out chimeras
#filter_otus_from_otu_table.py -i otu_table_no_fails.biom -o otu_table_no_fails_chims.biom -e pynast_aligned_seqs/chimeraSlayer/chimeric_seqs_core.txt

#remove singletons from biome file
#filter_otus_from_otu_table.py -i otu_table_no_fails_chims.biom -o otu_table_no_fails_chims_singles.biom -n 2