【最新版protocol】16S qiime2 ASV分析

#一、导入数据Import data
分析前需要准备的文件见上一篇文章

qiime tools import \
  --type 'SampleData[PairedEndSequencesWithQuality]' \
  --input-path sample_data/pe-33-manifest.csv \
  --output-path results/paired-end-demux.qza \
  --input-format PairedEndFastqManifestPhred33

#demux结果可视化Visualization of demux

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

#去除非生物序列（我这步去的是引物）Removing non-biological sequences

qiime cutadapt trim-paired \
  --i-demultiplexed-sequences paired-end-demux.qza \
  --p-front-f ACTCCTACGGGAGGCAGCA \
  --p-front-r GGACTACHVGGGTWTCTAAT \
  --o-trimmed-sequences paired-end-trimmed-seqs.qza

#去除引物的序列可视化Visualization of sequences removed primer

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

#合并双端序列Join paired sequences (allow 1 mismatches for at least 10 bp overlap, no limit of q-score)；这一步设置了2个参数：至少有10bp重合，每10bp里最多允许1个bp错配

time qiime vsearch join-pairs \
  --i-demultiplexed-seqs paired-end-trimmed-seqs.qza \
  --p-minovlen 10 \
  --p-maxdiffs 1 \
  --o-joined-sequences demux-joined.qza

#把上面的结果可视化Viewing a summary of joined data with read quality

qiime demux summarize \
  --i-data demux-joined-1-noqscore.qza \
  --o-visualization demux-joined.qzv

#对合并好的序列进行质控，这里推荐使用默认参数，把质量分数低于4的过滤掉Quality control of joined-sequences

qiime quality-filter q-score-joined \
  --i-demux demux-joined.qza \
  --o-filtered-sequences demux-joined-filtered.qza \
  --o-filter-stats demux-joined-filtered-stats.qza

#对质控后的合并序列可视化Visualization of filterd-paied sequence

qiime demux summarize \
  --i-data demux-joined-filtered.qza \
  --o-visualization demux-joined-filtered.qzv

#对质控后的stats文件可视化Visualization of stats results using metadata tabulate

qiime metadata tabulate \
  --m-input-file demux-joined-filtered-stats.qza \
  --o-visualization demux-joined-filtered-stats.qzv

#降噪，400这个参数如何确定，参照上一篇的教程Deblur (trim-length 400)，40是线程数

qiime deblur denoise-16S \
  --i-demultiplexed-seqs demux-joined-1-noqscore-filtered.qza \
  --p-trim-length 400 \
  --p-sample-stats \
  --p-jobs-to-start 40 \
  --o-representative-sequences rep-seqs.qza \
  --o-table table.qza \
  --o-stats deblur-stats.qza

#deblur的stats结果可视化Visualization of stats results

qiime deblur visualize-stats\
  --i-deblur-stats deblur-stats.qza \
  --o-visualization deblur-stats.qzv

#feature-table可视化Visualization of deblur table

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

#抽平feature-table，11562这个参数如何确定看上一个教程Rarefy the feature-table

qiime feature-table rarefy \
  --i-table table.qza \
  --p-sampling-depth 11562 \
  --o-rarefied-table table-rarefied.qza

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

#打开table-rarefied.qza里面有个data，打开里面的feature-table，extract就可以得到feature-table.biom，然后用下面的命令把它转为tsv格式

biom convert -i feature-table.biom -o feature-table.tsv --to-tsv --header-key taxonomy

#生成进化树和多样性参数Generate a tree for phylogenetic diversity analyse

time qiime phylogeny align-to-tree-mafft-fasttree \
  --i-sequences rep-seqs.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

###Alpha & Beta diversity analyse
#Calculate core-metric-phylogenetic

qiime diversity core-metrics-phylogenetic \
  --i-phylogeny rooted-tree.qza \
  --i-table table.qza \
  --p-sampling-depth 11562 \
  --m-metadata-file sample-metadata.tsv \
  --output-dir core-metrics-results

#稀释虚线Alpha rarefaction plotting (rarefaction curves)

time qiime diversity alpha-rarefaction \
  --i-table table.qza \
  --i-phylogeny rooted-tree.qza \
  --p-max-depth 10000 \
  --m-metadata-file sample-metadata.tsv \
  --o-visualization alpha-rarefaction.qzv

#Faith系统发育多样性可视化

qiime diversity alpha-group-significance \
  --i-alpha-diversity core-metrics-results/faith_pd_vector.qza \
  --m-metadata-file sample-metadata.tsv \
  --o-visualization core-metrics-results/faith-pd-group-significance.qzv

#Evenness 均匀度可视化（每个ASV丰度的均匀度）

qiime diversity alpha-group-significance \
  --i-alpha-diversity core-metrics-results/evenness_vector.qza \
  --m-metadata-file sample-metadata.tsv \
  --o-visualization core-metrics-results/evenness-group-significance.qzv

#Shannon diversity可视化（综合Evenness和Richness的指标）

qiime diversity alpha-group-significance \
  --i-alpha-diversity core-metrics-results/shannon_vector.qza \
  --m-metadata-file sample-metadata.tsv \
  --o-visualization core-metrics-results/shannon_vector.qzv

#Richness可视化

qiime diversity alpha-group-significance \
  --i-alpha-diversity core-metrics-results/observed_features_vector.qza \
  --m-metadata-file sample-metadata.tsv \
  --o-visualization core-metrics-results/observed_features_vector.qzv

###Annoation
##Download the feature-classifier
#mkdir training-feature-classifiers

mkdir training-feature-classifiers

#cd training-feature-classifiers

cd training-feature-classifiers

#Download the feature-classifier

wget \
  -O "silva-138-99-nb-classifier.qza" \
 https://data.qiime2.org/2020.6/common/silva-138-99-nb-classifier.qza

cd ..

#Taxonomy & visualization

time qiime feature-classifier classify-sklearn \
  --i-classifier training-feature-classifiers/silva-138-99-nb-classifier.qza \
  --i-reads rep-seqs-1-20.qza \
  --o-classification taxonomy.qza

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

qiime taxa barplot \
  --i-table table-1-20-rarefied.qza \
  --i-taxonomy taxonomy.qza \
  --m-metadata-file sample-metadata.tsv \
  --o-visualization taxa-bar-plots.qzv