DADA2 Script qiime dada2 denoise-paired \ --i-demultiplexed-seqs paired-end-demux.qza \ --p-trim-left-f 17 \ --p-trim-left-r 21 \ --p-trunc-len-f 270 \ --p-trunc-len-r 220 \ --p-max-ee-f 2.0 \ --p-max-ee-r 2.0 \ --p-pooling-method independent \ --p-chimera-method consensus \ --o-table 270-220-table.qza \ --o-representative-sequences 270-220-rep-seqs.qza \ --o-denoising-stats 270-220-denoising-stats.qza Vsearch Script qiime tools import \ --type 'SampleData[PairedEndSequencesWithQuality]' \ --input-path /home/taf1g17/please/manifest.txt \ --output-path paired-end-demux.qza \ --input-format PairedEndFastqManifestPhred33V2 qiime demux summarize \ --i-data /home/taf1g17/please/paired-end-demux.qza \ --o-visualization paired-end-demux.qzv # remove primers qiime cutadapt trim-paired \ --i-demultiplexed-sequences paired-end-demux.qza \ --p-front-f CCTACGGGNBGCASCAG \ --p-front-r GACTACNVGGGTATCTAATCC \ --o-trimmed-sequences paired-end-demux-trimmed.qza # join paired-end reads qiime vsearch join-pairs \ --i-demultiplexed-seqs paired-end-demux-trimmed.qza \ --o-joined-sequences paired-end-demux-trimmed-joined.qza # summarize quality of joining qiime demux summarize \ --i-data paired-end-demux-trimmed-joined.qza \ --o-visualization paired-end-demux-trimmed-joined.qzv # filter sequences based on q-score # for different iterations of filtering, the parameters applied as shown in the excel table screenshots in the email string as below: qiime quality-filter q-score \ --i-demux paired-end-demux-trimmed-joined.qza \ --p-min-quality 20 \ --p-quality-window 5 \ --p-min-length-fraction 0.5 \ --p-max-ambiguous 10 \ --o-filtered-sequences paired-end-demux-trimmed-joined-filtered-q20.qza \ --o-filter-stats paired-end-demux-trimmed-joined-filtered-q20-stats.qza #dereplicate qiime vsearch dereplicate-sequences \ --i-sequences paired-end-demux-trimmed-joined-filtered-q30.qza \ --o-dereplicated-table paired-end-demux-trimmed-joined-filtered-q30-table.qza \ --o-dereplicated-sequences paired-end-demux-trimmed-joined-filtered-q30-rep-seqs.qza # Vsearch OTU generation # extracting V3/V4 region from Silva 138 SSURef NR99 full-length sequence dataset qiime feature-classifier extract-reads \ --i-sequences silva-138-99-seqs.qza \ --p-f-primer CCTACGGGNBGCASCAG \ --p-r-primer GACTACNVGGGTATCTAATCC \ --p-trunc-len 600 \ --o-reads 600-silva-classifier-ref-seqs.qza # clustering features based on alignment to the 600-silva-classifier-ref-seqs.qza reference dataset above qiime vsearch cluster-features-open-reference \ --i-table paired-end-demux-trimmed-joined-filtered-q30-table.qza \ --i-sequences paired-end-demux-trimmed-joined-filtered-q30-rep-seqs.qza \ --i-reference-sequences 600-silva-classifier-ref-seqs.qza \ --p-perc-identity 0.98 \ --o-clustered-table paired-end-demux-trimmed-joined-filtered-q30-600-clustered-table.qza \ --o-clustered-sequences paired-end-demux-trimmed-joined-filtered-q30-600-rep-seqs.qza \ --o-new-reference-sequences paired-end-demux-trimmed-joined-filtered-q30-600-new-ref-seqs.qza # verifying OTU clustering topography is biologically relevant and parameter values are optimal qiime feature-table summarize \ --i-table paired-end-demux-trimmed-joined-filtered-q30-600-clustered-table.qza \ --o-visualization paired-end-demux-trimmed-joined-filtered-q30-600-clustered-table.qzv \ --m-sample-metadata-file sample-metadata.tsv qiime feature-table tabulate-seqs \ --i-data paired-end-demux-trimmed-joined-filtered-q30-600-rep-seqs.qza \ --o-visualization paired-end-demux-trimmed-joined-filtered-q30-600-rep-seqs.qzv #above shows taxonomy table - low resolution # run diversity analysis here, before chimera removal? -> dada2 w chimeras removed internally so more comparable to run diversity AFTER # Identifying chimeric sequences against the newly created, clustered reference sequence dataset qiime vsearch uchime-ref \ --i-table paired-end-demux-trimmed-joined-filtered-q30-600-clustered-table.qza \ --i-sequences paired-end-demux-trimmed-joined-filtered-q30-600-rep-seqs.qza \ --i-reference-sequences paired-end-demux-trimmed-joined-filtered-q30-600-new-ref-seqs.qza \ --o-chimeras paired-end-demux-trimmed-joined-filtered-q30-600-rep-seqs-uchime-ref-chim.qza \ --o-nonchimeras paired-end-demux-trimmed-joined-filtered-q30-600-rep-seqs-uchime-ref-nonchim.qza \ --o-stats paired-end-demux-trimmed-joined-filtered-q30-600-rep-seqs-uchime-ref-stats.qza # filtering input tables and sequences to exclude identified chimeras but retain “borderline” chimeras qiime feature-table filter-features \ --i-table paired-end-demux-trimmed-joined-filtered-q30-600-clustered-table.qza \ --m-metadata-file paired-end-demux-trimmed-joined-filtered-q30-600-rep-seqs-uchime-ref-chim.qza \ --p-exclude-ids \ --o-filtered-table paired-end-demux-trimmed-joined-filtered-q30-600-rep-seqs-uchime-ref-out-table-nonchimeric-w-borderline.qza qiime feature-table filter-seqs \ --i-data paired-end-demux-trimmed-joined-filtered-q30-600-rep-seqs.qza \ --m-metadata-file paired-end-demux-trimmed-joined-filtered-q30-600-rep-seqs-uchime-ref-chim.qza \ --p-exclude-ids \ --o-filtered-data paired-end-demux-trimmed-joined-filtered-q30-600-rep-seqs-uchime-ref-out-rep-seqs-nonchimeric-w-borderline.qza # visualising newly clustered, filtered representative sequence library qiime feature-table summarize \ --i-table paired-end-demux-trimmed-joined-filtered-q20-600-rep-seqs-uchime-ref-out-table-nonchimeric-w-borderline.qza\ --o-visualization paired-end-demux-trimmed-joined-filtered-q20-600-rep-seqs-uchime-ref-out-table-nonchimeric-w-borderline.qza