Qiime2 Workflow - Investigating microbial size classes associated with the transmission of stony coral tissue loss disease (SCTLD)

conda activate qiime2-2022.2

Importing Files:

qiime tools import \
--type 'SampleData[PairedEndSequencesWithQuality]' \
--input-path fullfilter_raw_sequence_files \
--input-format CasavaOneEightSingleLanePerSampleDirFmt \
--output-path demux-paired-end.qza

Denoising:

qiime demux summarize \
--i-data demux-paired-end.qza \
--o-visualization demux-paired-end.qzv

qiime dada2 denoise-paired \
--i-demultiplexed-seqs demux-paired-end.qza \
--p-trim-left-f 0 \
--p-trim-left-r 0 \
--p-trunc-len-f 200 \
--p-trunc-len-r 200 \
--o-table table-dada2_notrim_trunc200.qza \
--o-representative-sequences rep-seqs-dada2_notrim_trunc200.qza \
--o-denoising-stats denoising-stats-dada2_notrim_trunc200.qza

qiime metadata tabulate \
--m-input-file denoising-stats-dada2_notrim_trunc200.qza \
--o-visualization denoising-stats-dada2_notrim_trunc200.qzv

Assigning Taxonomies:

qiime feature-classifier classify-sklearn \
--i-classifier silva-138-99-515-806-nb-classifier.qza \
--i-reads rep-seqs-dada2_notrim_trunc200.qza \
--o-classification silva_taxonomy_notrim_trunc200.qza

Removing Non-Target Sequences:

qiime taxa filter-table \
--i-table table-dada2_notrim_trunc200.qza \
--i-taxonomy silva_taxonomy_notrim_trunc200.qza \
--p-exclude chloroplast,mitochondria \
--p-include d__Bacteria,d__Archaea \
--o-filtered-table filtered-table_allSamples_noEukaryota_notrim_trunc200.qza

qiime taxa filter-seqs \
--i-sequences rep-seqs-dada2_notrim_trunc200.qza \
--i-taxonomy silva_taxonomy_notrim_trunc200.qza \
--p-exclude chloroplast,mitochondria \
--p-include d__Bacteria,d__Archaea \
--o-filtered-sequences rep-seqs_allSamples_noEukaryota_notrim_trunc200.qza 

qiime feature-table summarize \
--i-table filtered-table_allSamples_noEukaryota_notrim_trunc200.qza \
--o-visualization filtered-table_allSamples_noEukaryota_notrim_trunc200.qzv \
--m-sample-metadata-file fullfilter_metadata.txt

qiime feature-table tabulate-seqs \
--i-data rep-seqs_allSamples_noEukaryota_notrim_trunc200.qza \
--o-visualization rep-seqs_allSamples_noEukaryota_notrim_trunc200.qzv

Removing Low Quality Samples:

qiime feature-table filter-samples \
--i-table filtered-table_allSamples_noEukaryota_notrim_trunc200.qza \
--m-metadata-file fullfilter_metadata.txt \
--o-filtered-table filtered-table_allSamples_noEukaryota_notrim_trunc200_failedsamplesremoved.qza \
--p-exclude-ids \
--p-where "\"sampleid\"= 'McH-104'"OR"\"sampleid\"= 'Mcav-2SQ'"OR"\"sampleid\"= 'CnH-101-Mar'"OR"\"sampleid\"= 'CnD-22'"OR"\"sampleid\"= 'McH-103-4'"

qiime feature-table summarize \
--i-table filtered-table_allSamples_noEukaryota_notrim_trunc200_failedsamplesremoved.qza \
--o-visualization filtered-table_allSamples_noEukaryota_notrim_trunc200_failedsamplesremoved.qzv \
--m-sample-metadata-file fullfilter_metadata.txt

Generating ASV Table:

qiime feature-table transpose \
--i-table filtered-table_allSamples_noEukaryota_notrim_trunc200_failedsamplesremoved.qza \
--o-transposed-feature-table filtered-table_allSamples_noEukaryota_notrim_trunc200_failedsamplesremoved_transposed.qza

qiime metadata tabulate \
--m-input-file rep-seqs_allSamples_noEukaryota_notrim_trunc200.qza \
--m-input-file silva_taxonomy_notrim_trunc200.qza \
--m-input-file filtered-table_allSamples_noEukaryota_notrim_trunc200_failedsamplesremoved_transposed.qza \
--o-visualization ASVtable_nofailedsamples_noEukaryota.qzv

qiime tools export \
--input-path ASVtable_nofailedsamples_noEukaryota.qzv \
--output-path ASVtable_nofailedsamples_noEukaryota

Phylogenetic Tree Construction:

qiime phylogeny align-to-tree-mafft-fasttree \
--i-sequences rep-seqs_allSamples_noEukaryota_notrim_trunc200.qza \
--o-alignment aligned_rep-seqs_allSamples_noEukaryota_notrim_trunc200.qza \
--o-masked-alignment masked_aligned_rep-seqs_allSamples_noEukaryota_notrim_trunc200.qza \
--o-tree unrooted-tree_allSamples_noEukaryota_notrim_trunc200.qza \
--o-rooted-tree rooted-tree_allSamples_noEukaryota_notrim_trunc200.qza

Diversity Analyses (including reagent blanks and mock communities):

qiime diversity core-metrics-phylogenetic \
--i-phylogeny rooted-tree_allSamples_noEukaryota_notrim_trunc200.qza \
--i-table filtered-table_allSamples_noEukaryota_notrim_trunc200_failedsamplesremoved.qza \
--p-sampling-depth 19051 \
--m-metadata-file fullfilter_metadata.txt \
--output-dir core-metrics-results-depth19051-allSamples-noEukaryota_notrim_trunc200_failedsamplesremoved

Diversity Analyses (reagent blanks and mock communities removed):

qiime feature-table filter-samples \
--i-table filtered-table_allSamples_noEukaryota_notrim_trunc200_failedsamplesremoved.qza \
--m-metadata-file fullfilter_metadata.txt \
--o-filtered-table filtered-table_allSamples_noEukaryota_notrim_trunc200_failedsamplesremoved_noblanks_nomocks.qza \
--p-exclude-ids \
--p-where "\"sampleid\"= 'kit_blank'"OR"\"sampleid\"= 'kitblank03May'"OR"\"sampleid\"= 'Kitblank04May'"OR"\"sampleid\"= 'kitblank05May'"OR"\"sampleid\"= 'kitblank06May'"OR"\"sampleid\"= 'mock'"OR"\"sampleid\"= 'mock2'"OR"\"sampleid\"= 'ZymoMockDNA'"OR"\"sampleid\"= 'RTSF_NTC'"

qiime feature-table summarize \
--i-table filtered-table_allSamples_noEukaryota_notrim_trunc200_failedsamplesremoved_noblanks_nomocks.qza \
--o-visualization filtered-table_allSamples_noEukaryota_notrim_trunc200_failedsamplesremoved_noblanks_nomocks.qzv \
--m-sample-metadata-file fullfilter_metadata.txt

qiime diversity core-metrics-phylogenetic \
--i-phylogeny rooted-tree_allSamples_noEukaryota_notrim_trunc200.qza \
--i-table filtered-table_allSamples_noEukaryota_notrim_trunc200_failedsamplesremoved_noblanks_nomocks.qza \
--p-sampling-depth 19051 \
--m-metadata-file fullfilter_metadata.txt \
--output-dir core-metrics-results-depth19051-noEukaryota_notrim_trunc200_failedsamplesremoved_noblanks_nomocks

Generating Rarefaction Plots:

qiime diversity alpha-rarefaction \
--i-table filtered-table_allSamples_noEukaryota_notrim_trunc200_failedsamplesremoved_noblanks_nomocks.qza \
--i-phylogeny rooted-tree_allSamples_noEukaryota_notrim_trunc200.qza \
--p-max-depth 19051 \
--m-metadata-file fullfilter_metadata.txt \
--o-visualization alpha-rarefaction_allSamples_noEukaryota_notrim_trunc200_failedsamplesremoved_noblanks_nomocks.qzv

Alpha Diversity Analyses:

qiime diversity alpha-group-significance \
--i-alpha-diversity core-metrics-results-depth19051-noEukaryota_notrim_trunc200_failedsamplesremoved_noblanks_nomocks/faith_pd_vector.qza \
--m-metadata-file fullfilter_metadata.txt \
--o-visualization core-metrics-results-depth19051-noEukaryota_notrim_trunc200_failedsamplesremoved_noblanks_nomocks/faith-pd-group-significance.qzv

qiime diversity alpha-group-significance \
--i-alpha-diversity core-metrics-results-depth19051-noEukaryota_notrim_trunc200_failedsamplesremoved_noblanks_nomocks/evenness_vector.qza \
--m-metadata-file fullfilter_metadata.txt \
--o-visualization core-metrics-results-depth19051-noEukaryota_notrim_trunc200_failedsamplesremoved_noblanks_nomocks/evenness-group-significance.qzv

qiime diversity alpha-group-significance \
--i-alpha-diversity core-metrics-results-depth19051-noEukaryota_notrim_trunc200_failedsamplesremoved_noblanks_nomocks/observed_features_vector.qza \
--m-metadata-file fullfilter_metadata.txt \
--o-visualization core-metrics-results-depth19051-noEukaryota_notrim_trunc200_failedsamplesremoved_noblanks_nomocks/observed_features-group-significance.qzv

qiime diversity alpha-group-significance \
--i-alpha-diversity core-metrics-results-depth19051-noEukaryota_notrim_trunc200_failedsamplesremoved_noblanks_nomocks/shannon_vector.qza \
--m-metadata-file fullfilter_metadata.txt \
--o-visualization core-metrics-results-depth19051-noEukaryota_notrim_trunc200_failedsamplesremoved_noblanks_nomocks/shannon-group-significance.qzv

Beta Diversity Analyses (PERMANOVA):

qiime diversity beta-group-significance \
--i-distance-matrix core-metrics-results-depth19051-noEukaryota_notrim_trunc200_failedsamplesremoved_noblanks_nomocks/weighted_unifrac_distance_matrix.qza \
--m-metadata-file fullfilter_metadata.txt \
--m-metadata-column exp_disease \
--o-visualization core-metrics-results-depth19051-noEukaryota_notrim_trunc200_failedsamplesremoved_noblanks_nomocks/weighted_unifrac-exp_disease-significance.qzv \
--p-pairwise

qiime diversity beta-group-significance \
--i-distance-matrix core-metrics-results-depth19051-noEukaryota_notrim_trunc200_failedsamplesremoved_noblanks_nomocks/weighted_unifrac_distance_matrix.qza \
--m-metadata-file fullfilter_metadata.txt \
--m-metadata-column species \
--o-visualization core-metrics-results-depth19051-noEukaryota_notrim_trunc200_failedsamplesremoved_noblanks_nomocks/weighted_unifrac-species-significance.qzv \
--p-pairwise

qiime diversity beta-group-significance \
--i-distance-matrix core-metrics-results-depth19051-noEukaryota_notrim_trunc200_failedsamplesremoved_noblanks_nomocks/weighted_unifrac_distance_matrix.qza \
--m-metadata-file fullfilter_metadata.txt \
--m-metadata-column Experiment \
--o-visualization core-metrics-results-depth19051-noEukaryota_notrim_trunc200_failedsamplesremoved_noblanks_nomocks/weighted_unifrac-Experiment-significance.qzv \
--p-pairwise

qiime diversity beta-group-significance \
--i-distance-matrix core-metrics-results-depth19051-noEukaryota_notrim_trunc200_failedsamplesremoved_noblanks_nomocks/weighted_unifrac_distance_matrix.qza \
--m-metadata-file fullfilter_metadata.txt \
--m-metadata-column sctld_status \
--o-visualization core-metrics-results-depth19051-noEukaryota_notrim_trunc200_failedsamplesremoved_noblanks_nomocks/weighted_unifrac-sctld_status-significance.qzv \
--p-pairwise

Beta Diversity Analyses (PERMDISP):

qiime diversity beta-group-significance \
--i-distance-matrix core-metrics-results-depth19051-noEukaryota_notrim_trunc200_failedsamplesremoved_noblanks_nomocks/weighted_unifrac_distance_matrix.qza \
--m-metadata-file fullfilter_metadata.txt \
--m-metadata-column sctld_status \
--o-visualization core-metrics-results-depth19051-noEukaryota_notrim_trunc200_failedsamplesremoved_noblanks_nomocks/weighted-unifrac-sctld_status-significance_disp.qzv \
--p-method permdisp

qiime diversity beta-group-significance \
--i-distance-matrix core-metrics-results-depth19051-noEukaryota_notrim_trunc200_failedsamplesremoved_noblanks_nomocks/weighted_unifrac_distance_matrix.qza \
--m-metadata-file fullfilter_metadata.txt \
--m-metadata-column species \
--o-visualization core-metrics-results-depth19051-noEukaryota_notrim_trunc200_failedsamplesremoved_noblanks_nomocks/weighted-unifrac-species-significance_disp.qzv \
--p-method permdisp

qiime diversity beta-group-significance \
--i-distance-matrix core-metrics-results-depth19051-noEukaryota_notrim_trunc200_failedsamplesremoved_noblanks_nomocks/weighted_unifrac_distance_matrix.qza \
--m-metadata-file fullfilter_metadata.txt \
--m-metadata-column Experiment \
--o-visualization core-metrics-results-depth19051-noEukaryota_notrim_trunc200_failedsamplesremoved_noblanks_nomocks/weighted-unifrac-Experiment-significance_disp.qzv \
--p-method permdisp

qiime diversity beta-group-significance \
--i-distance-matrix core-metrics-results-depth19051-noEukaryota_notrim_trunc200_failedsamplesremoved_noblanks_nomocks/weighted_unifrac_distance_matrix.qza \
--m-metadata-file fullfilter_metadata.txt \
--m-metadata-column exp_disease \
--o-visualization core-metrics-results-depth19051-noEukaryota_notrim_trunc200_failedsamplesremoved_noblanks_nomocks/weighted-unifrac-exp_disease-significance_disp.qzv \
--p-method permdisp

qiime diversity beta-group-significance \
--i-distance-matrix core-metrics-results-depth19051-noEukaryota_notrim_trunc200_failedsamplesremoved_noblanks_nomocks/weighted_unifrac_distance_matrix.qza \
--m-metadata-file fullfilter_metadata.txt \
--m-metadata-column species \
--o-visualization core-metrics-results-depth19051-noEukaryota_notrim_trunc200_failedsamplesremoved_noblanks_nomocks/weighted-unifrac-species-significance_disp_pairwise.qzv \
--p-method permdisp \
--p-pairwise

Differential Abundance Analysis (ANCOM):

qiime feature-table filter-samples \
--i-table filtered-table_allSamples_noEukaryota_notrim_trunc200_failedsamplesremoved_noblanks_nomocks.qza \
--m-metadata-file fullfilter_metadata.txt \
--o-filtered-table filtered-table_allSamples_noEukaryota_notrim_trunc200_failedsamplesremoved_noblanks_nomocks_noFSW.qza \
--p-exclude-ids \
--p-where "\"sampleid\"= 'FSW'"

qiime feature-table filter-features \
--i-table filtered-table_allSamples_noEukaryota_notrim_trunc200_failedsamplesremoved_noblanks_nomocks_noFSW.qza \
--p-min-samples 2 \
--o-filtered-table filtered-table_allSamples_noEukaryota_notrim_trunc200_failedsamplesremoved_noblanks_nomocks_noFSW_minsample2.qza

qiime feature-table filter-features \
--i-table filtered-table_allSamples_noEukaryota_notrim_trunc200_failedsamplesremoved_noblanks_nomocks_noFSW_minsample2.qza \
--p-min-frequency 10 \
--o-filtered-table filtered-table_allSamples_noEukaryota_notrim_trunc200_failedsamplesremoved_noblanks_nomocks_noFSW_minsample2_minfreq10.qza

qiime composition add-pseudocount \
  --i-table filtered-table_allSamples_noEukaryota_notrim_trunc200_failedsamplesremoved_noblanks_nomocks_noFSW_minsample2_minfreq10.qza \
  --o-composition-table comp-filtered-table_allSamples_noEukaryota_notrim_trunc200_failedsamplesremoved_noblanks_nomocks_noFSW_minsample2_minfreq10_ASVlevelcomp.qza

qiime composition ancom \
  --i-table comp-filtered-table_allSamples_noEukaryota_notrim_trunc200_failedsamplesremoved_noblanks_nomocks_noFSW_minsample2_minfreq10_ASVlevelcomp.qza \
  --m-metadata-file fullfilter_metadata.txt \
  --m-metadata-column sctld_status \
  --o-visualization ancom-sctld_status_ASVlevel.qzv

Generating Fasta File:

qiime tools export \
--input-path rep-seqs_allSamples_noEukaryota_notrim_trunc200.qza \
--output-path rep-seqs_allSamples_noEukaryota_notrim_trunc200/

Generating ASV Table (including non-target sequences):

qiime feature-table filter-samples \
--i-table table-dada2_notrim_trunc200.qza \
--m-metadata-file fullfilter_metadata.txt \
--o-filtered-table 05apr23_filtered-table_dada2_notrim_trunc200_failedsamplesremoved.qza \
--p-exclude-ids \
--p-where "\"sampleid\"= 'McH-104'"OR"\"sampleid\"= 'Mcav-2SQ'"OR"\"sampleid\"= 'CnH-101-Mar'"OR"\"sampleid\"= 'CnD-22'"OR"\"sampleid\"= 'McH-103-4'"

qiime feature-table transpose \
--i-table 05apr23_filtered-table_dada2_notrim_trunc200_failedsamplesremoved.qza \
--o-transposed-feature-table 05apr23_filtered-table_dada2_notrim_trunc200_failedsamplesremoved_transposed.qza

qiime metadata tabulate \
--m-input-file rep-seqs-dada2_notrim_trunc200.qza \
--m-input-file silva_taxonomy_notrim_trunc200.qza \
--m-input-file 05apr23_filtered-table_dada2_notrim_trunc200_failedsamplesremoved_transposed.qza \
--o-visualization 05apr23_ASVtable_nofailedsamples_stillincludesEukaryotes.qzv

qiime tools export \
--input-path 05apr23_ASVtable_nofailedsamples_stillincludesEukaryotes.qzv \
--output-path 05apr23_ASVtable_nofailedsamples_stillincludesEukaryotes