MiSeq 16S rRNA amplicon processing


cutadapt -g GTGCCAGCNGCCGCGGTAA -g GTGCCAGCNGCNGCGGTAA -g GTGCCAGCNGCCGCGGTCA -g GTGNCAGCNGCCGCGGTAA -g GTGGCAGNCGCCNCGGNAA --paired-output r2.tmp.fastq -o r1.tmp.fastq Undetermined_S0_L001_R1_001.fastq.gz Undetermined_S0_L001_R2_001.fastq.gz


cutadapt -g GGACTACNNGGGTNTCTAAT -g GGACTACNNGGGTNTCTAAT -g GGANTACNGGGGTCTCTAAT -e 0.1 --discard-untrimmed --match-read-wildcards --paired-output trimmed.R1.fastq -o trimmed.R2.fastq r2.tmp.fastq r1.tmp.fastq


join_paired_ends.py -b Undetermined_S0_L001_I1_001.fastq.gz -f trimmed.R1.fastq -r trimmed.R2.fastq -o joined_reads


cd joined_reads

split_libraries_fastq.py -v -q 0 --max_bad_run_length 250 --min_per_read_length_fractio 0.01 --store_demultiplexed_fastq -m /mapping.txt --barcode_type golay_12 --rev_comp_mapping_barcodes -b fastqjoin.join_barcodes.fastq -i fastqjoin.join.fastq -o sl_out


cd sl_out/

usearch8 -fastq_stats seqs.fastq -log seqs.stats.log

    
usearch8 -fastq_filter seqs.fastq -fastaout seqs.filtered.fasta -fastq_maxee 0.5 -threads 24    


usearch8 -derep_fulllength seqs.filtered.fasta  --fastaout seqs.filtered.derep.fasta -sizeout -threads 28


usearch8 -sortbysize seqs.filtered.derep.fasta -minsize 2 -fastaout seqs.filtered.derep.fasta.repset.fasta


usearch8 -cluster_otus seqs.filtered.derep.fasta.repset.fasta -otus seqs.filtered.derep.fasta.repsetotus.fasta 

usearch8 -uchime_ref seqs.filtered.derep.fasta.repsetotus.fasta -db /qiime_1.9_base/lib/python2.7/site-packages/qiime_default_reference/gg_13_8_otus/rep_set/97_otus.fasta -minh 1.0 -strand plus -nonchimeras seqs.filtered.derep.repsetotus.nochimeras.fasta -threads 30


python /qiime/additional_support_files/usearch7.0.1001_i86linux64/drive5_py/fasta_number.py seqs.filtered.derep.repsetotus.nochimeras.fasta > seqs.filtered.derep.repsetotus.nochimeras.OTU.fasta


usearch8 -usearch_global seqs.filtered.fasta -db seqs.filtered.derep.repsetotus.nochimeras.OTU.fasta -strand plus -id 0.97 -uc otu.map.uc -threads 30


python /qiime/additional_support_files/usearch7.0.1001_i86linux64/drive5_py/uc2otutab_mod.py otu.map.uc > seqs.filtered.derep.repsetotus.nochimeras.OTU-table.txt


biom convert -i seqs.filtered.derep.repsetotus.nochimeras.OTU-table.txt -o seqs.filtered.derep.repsetotus.nochimeras.OTU-table.biom --table-type="OTU table" --to-hdf5 --header-key taxonomy --output-metadata-id "ConsensusLineage"


assign_taxonomy.py -t /data2/mpb/HOMD_16S_rRNA_RefSeq_V14.5.qiime.taxonomyparsed.txt -r /data2/mpb/HOMD_16S_rRNA_RefSeq_V14.5parsed.fasta -i seqs.filtered.derep.repsetotus.nochimeras.OTU.fasta -o assigned_taxonomy


biom add-metadata --sc-separated taxonomy --observation-header OTUID,taxonomy --observation-metadata-fp assigned_taxonomy_blast/seqs.filtered.derep.repsetotus.nochimeras.OTU_tax_assignments.txt -i seqs.filtered.derep.repsetotus.nochimeras.OTU-table.biom -o seqs.filtered.derep.repsetotus.nochimeras.OTU-table.taxonomy.biom


biom convert -i seqs.filtered.derep.repsetotus.nochimeras.OTU-table.taxonomy.biom -o table.from_biom_w_taxonomy.txt --to-tsv --header-key taxonomy