##QIIME ANALYSES## qiime tools import \ --type "SampleData[SequencesWithQuality]" \ --input-format SingleEndFastqManifestPhred33V2 \ --input-path /mnt/datasets/project_2/anemia/anemia_manifest_updated.txt \ --output-path ./anemia-demux.qza qiime demux summarize \ --i-data anemia-demux.qza \ --o-visualization anemia-demux.qzv qiime dada2 denoise-single \ --i-demultiplexed-seqs anemia-demux.qza \ --p-trim-left 0 \ --p-trunc-len 252 \ --o-representative-sequences anemia-rep-seqs.qza \ --o-table anemia-table.qza \ --o-denoising-stats anemia-stats.qza qiime feature-table summarize \ --i-table anemia-table.qza \ --o-visualization anemia-table.qzv \ --m-sample-metadata-file /mnt/datasets/project_2/anemia/anemia_metadata.txt qiime feature-table tabulate-seqs \ --i-data anemia-rep-seqs.qza \ --o-visualization anemia-rep-seqs.qzv qiime feature-classifier classify-sklearn \ --i-classifier /data/project2/silva-138-99-515-806-nb-classifier.qza \ --i-reads anemia-rep-seqs.qza \ --o-classification anemia-taxonomy.qza qiime metadata tabulate \ --m-input-file anemia-taxonomy.qza \ --o-visualization anemia-taxonomy.qzv qiime taxa barplot \ --i-table anemia-table.qza \ --i-taxonomy anemia-taxonomy.qza \ --m-metadata-file /mnt/datasets/project_2/anemia/anemia_metadata.txt \ --o-visualization anemia-taxa-bar-plots.qzv iime taxa filter-table \ --i-table anemia-table.qza \ --i-taxonomy anemia-taxonomy.qza \ --p-exclude mitochondria,chloroplast \ --o-filtered-table anemia-table-no-mitochondria-no-chloroplast.qza qiime phylogeny align-to-tree-mafft-fasttree \ --i-sequences anemia-rep-seqs.qza \ --o-alignment anemia-aligned-rep-seqs.qza \ --o-masked-alignment anemia-masked-aligned-rep-seqs.qza \ --o-tree anemia-unrooted-tree.qza \ --o-rooted-tree anemia-rooted-tree.qza qiime feature-table summarize \ --i-table anemia-table-no-mitochondria-no-chloroplast.qza \ --o-visualization anemia-table-no-mitochondria-no-chloroplast.qzv \ --m-sample-metadata-file /mnt/datasets/project_2/anemia/anemia_metadata.txt qiime diversity alpha-rarefaction \ --i-table anemia-table.qza \ --i-phylogeny anemia-rooted-tree.qza \ --p-max-depth 52000 \ --m-metadata-file /mnt/datasets/project_2/anemia/anemia_metadata.txt \ --o-visualization aim1_alpha-rarefaction_anemia-table.qzv # Calculate alpha- and beta-diversity metrics, retained min 30 samples qiime diversity core-metrics-phylogenetic \ --i-phylogeny anemia-rooted-tree.qza \ --i-table age-filtered-table.qza \ --p-sampling-depth 25090 \ --m-metadata-file /mnt/datasets/project_2/anemia/anemia_metadata.txt \ --output-dir core-metrics-results # Calculate alpha-group-significance qiime diversity alpha-group-significance \ --i-alpha-diversity core-metrics-results/faith_pd_vector.qza \ --m-metadata-file /mnt/datasets/project_2/anemia/anemia_metadata.txt \ --o-visualization core-metrics-results/faith-pd-group-significance.qzv qiime diversity alpha-group-significance \ --i-alpha-diversity core-metrics-results/evenness_vector.qza \ --m-metadata-file /mnt/datasets/project_2/anemia/anemia_metadata.txt \ --o-visualization core-metrics-results/evenness-group-significance.qzv # Calculate beta-group-significance qiime diversity beta-group-significance \ --i-distance-matrix core-metrics-results/unweighted_unifrac_distance_matrix.qza \ --m-metadata-file /mnt/datasets/project_2/anemia/anemia_metadata.txt \ --m-metadata-column anemia \ --o-visualization core-metrics-results/unweighted-unifrac-anemia-significance.qzv \ --p-pairwise ##PICRUSt2 analysis (The R portion of this analysis is scripted along the rest of the R analyses)## wget https://github.com/picrust/picrust2/archive/v2.5.1.tar.gz tar xvzf v2.5.1.tar.gz cd picrust2-2.5.1/ # The next command will take a while to run (about 30-45 minutes) conda env create -f picrust2-env.yaml # to activate the environment (needed to run picrust commands), you need to run the following command every time you use the picrust pipeline conda activate picrust2 # not sure what this step does lol but I ran it anyways (the server returned an error but i went ahead anyways) pip install --editable . # run the following command to check that everything installed correctly (i got one warning message but i went ahead) pytest ###### now you need to convert your data to make it readable by PICRUSt2 as an input file # navigate to the directory where you generated your rep-seqs.qza # this step will convert the rep-seqs file (a table of your ASVs) into a fasta file, which can be read by PICRUSt2 # activate QIIME2 conda activate qiime2-2021.11 # then perform the exporting step qiime tools export \ --input-path rep-seqs.qza \ --output-path rep-seqs/ # copy the new file (dna-sequences.fasta) to your working directory scp ... # copy the exported table file (feature-table.biom) to your working directory scp ... ###### now for running the PICRUSt2 pipeline # create a new screen screen -S NAME # navigate to your chosen working directory that contains your dna-sequences.fasta and feature-table.biom files # activate PICRUSt2 conda activate picrust2 # run the picrust pipeline in a single command picrust2_pipeline.py -s dna-sequences.fasta -i feature-table.biom -o picrust2_out_pipeline -p 1 # let that run in the background (could take a while) - only ended up taking 1 hour ######################## ###### now for more relevant information, it can be useful to add descriptions to the predicted metagenome/pathway abundances. Here is the code to do that: # first navigate to your picrust2_out_pipeline directory # then run the following code: add_descriptions.py -i EC_metagenome_out/pred_metagenome_unstrat.tsv.gz -m EC \ -o EC_metagenome_out/pred_metagenome_unstrat_descrip.tsv.gz add_descriptions.py -i KO_metagenome_out/pred_metagenome_unstrat.tsv.gz -m KO \ -o KO_metagenome_out/pred_metagenome_unstrat_descrip.tsv.gz add_descriptions.py -i pathways_out/path_abun_unstrat.tsv.gz -m METACYC \ -o pathways_out/path_abun_unstrat_descrip.tsv.gz # to view the files, transfer them to the local directory and unzip them into txt files.