#### Illumina ####


1) QIIME2 activation on WSL ################

conda activate qiime2-2020.8

2) Directory ###############

cd Illumina2

3) Import data with Casava 1.8 paired-end demultiplexed fastq ###

### Datas was already Demultiplexed, by which we used the Casava 1.8 ###
### Thus, Demultiplexing is not needed ###

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

4) Check the data ###

qiime tools peek demux-paired-end.qza

5) Add metadata ###

qiime metadata tabulate \
  --m-input-file design.tsv \
  --o-visualization metadata.qzv

6) Data visualization ###

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

7) Denoising ###

### The file "demux.qzv" can be visualized in the QIIME2 view website ###
### Trim and truncate values were obtained after check the quality plots ###
### Primers, 515F (5’ GTG YCA GCM GCC GCG GTA A 3’) and 806R (5’ GGA CTA CNV GGG TWT CTA AT 3’) ###

qiime dada2 denoise-paired \
  --i-demultiplexed-seqs demux-paired-end.qza \
  --p-trim-left-f 19 \
  --p-trunc-len-f 299 \
  --p-trim-left-r 20 \
  --p-trunc-len-r 259 \
  --o-representative-sequences rep-seqs-dada2.qza \
  --o-table table-dada2.qza \
  --o-denoising-stats stats-dada2.qza


8) Visualization of denoising results ###

qiime metadata tabulate \
  --m-input-file stats-dada2.qza \
  --o-visualization stats-dada2.qzv


9) Rename the last two tables ###

mv rep-seqs-dada2.qza rep-seqs.qza
mv table-dada2.qza table.qza


10) Summary table from previous results (ASVs and sequences) ###

qiime feature-table summarize \
  --i-table table.qza \
  --o-visualization table.qzv \
  --m-sample-metadata-file design.tsv

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


11) Taxonomic analysis ###

### Here we used SILVA 138 database

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

qiime metadata tabulate \
  --m-input-file table.qza \
  --o-visualization taxonomy_table.qzv


12) Filtering by Eukaryota, mitochondria, and chloroplast ### 

qiime taxa filter-table \
  --i-table table.qza \
  --i-taxonomy taxonomy.qza \
  --p-exclude Eukaryota,Mitochondria,Chloroplast \
  --o-filtered-table table-filtered.qza

13) Filtering by rare sfeatures (min. in 2 samples) and frequency (min. 10 counts) ###

qiime feature-table filter-features \
  --i-table table-filtered.qza \
  --p-min-frequency 10 \
  --p-min-samples 2 \
  --o-filtered-table table-filtered2.qza

### Summary table of this process (visualization)

qiime feature-table summarize \
  --i-table table-filtered2.qza \
  --o-visualization table-filtered2.qzv \
  --m-sample-metadata-file design.tsv


14) Filtering of sequences by the previous ASV filtered table ("table-filtered2.qza") ###

qiime feature-table filter-seqs \
  --i-data rep-seqs.qza \
  --i-table table-filtered2.qza \
  --o-filtered-data seq-filtered.qza

qiime feature-table tabulate-seqs \
  --i-data seq-filtered.qza \
  --o-visualization seq-filtered.qzv


15) Rarefy table-filtered2 to export it (further external analysis) ###

### Sampling depth (6418) is the maximun possible depth whitout lossing samples

qiime feature-table rarefy \
  --i-table table-filtered2.qza \
  --p-sampling-depth 6418 \
  --o-rarefied-table rarefied-table-filtered2.qza

qiime feature-table summarize \
  --i-table rarefied-table-filtered2.qza \
  --o-visualization rarefied-table-filtered2.qzv \
  --m-sample-metadata-file design.tsv


16) Exportar la Feature and Taxonomy table ###

qiime tools export \
  --input-path rarefied-table-filtered2.qza \
  --output-path exported-feature-table-filtered-rarefied

# in the folder...
biom convert -i feature-table.biom -o feature-table.tsv --to-tsv

# back to Illumina2
qiime tools export \
  --input-path taxonomy.qza \
  --output-path exported-feature-table-filtered-rarefied

############################################################################

Previous exported and rarefied data will be used in R for further analysis such as Venn diagram and Co-ocurrence network 
Now, alpha and beta diversity will be calculated in QIIME2

¡¡¡ The same sampling depth is used in rarefied table and diversity metrics ¡¡¡

############################################################################

17) Phylogenetic tree, which will be used to estimate diversity metrics ### 

### here, we used FILTERED sequences table (whitout organells, eukaryota, and rare ASVs) but no rarefied table 
# since the QIIME pluggin will make this rarefaction in this process, it only needs the sampling depth

qiime phylogeny align-to-tree-mafft-fasttree \
  --i-sequences seq-filtered.qza \
  --o-alignment aligned-rep-seqs.qza \
  --o-masked-alignment masked-aligned-rep-seqs.qza \
  --o-tree unrooted-tree.qza \
  --o-rooted-tree rooted-tree.qza

18) Alpha diversity ###

### Here, we calculate ALL diversity metrics (alpha and beta)

qiime diversity core-metrics-phylogenetic \
  --i-phylogeny rooted-tree.qza \
  --i-table table-filtered2.qza \
  --p-sampling-depth 6418 \
  --m-metadata-file design.tsv \
  --output-dir core-metrics-results-depth6418