comparison amplicon_analysis_pipeline.xml @ 4:86a12d75ebe4 draft default tip

planemo upload for repository https://github.com/pjbriggs/Amplicon_analysis-galaxy commit 7be61b7ed35ca3deaad68d2eae384c8cd365bcb8

3:3ab198df8f3f

<tool id="amplicon_analysis_pipeline" name="Amplicon Analysis Pipeline" version="1.2.3.0">
  <description>analyse 16S rRNA data from Illumina Miseq paired-end reads</description>
  <requirements>
    <requirement type="package" version="1.2.3">amplicon_analysis_pipeline</requirement>
  </requirements>
  <stdio>
    <exit_code range="1:" />
  </stdio>
  <command><![CDATA[
  ## Set the reference database name
  #if $reference_database == "-S"
    #set reference_database_name = "silva"
  #else if $reference_database == "-H"
    #set reference_database_name = "homd"
  #else
    #set reference_database_name = "gg"
  #end if

  ## Run the amplicon analysis pipeline wrapper
  python $__tool_directory__/amplicon_analysis_pipeline.py
  ## Set options

  -O $minimum_overlap
  #end if
  #if str( $minimum_length ) != ""
  -L $minimum_length
  #end if
  -P $pipeline
  -r \$AMPLICON_ANALYSIS_REF_DATA_PATH
  #if str( $reference_database ) != ""
    ${reference_database}
  #end if
  #if str($categories_file_in) != 'None'
    -c "${categories_file_in}"
  #end if

  #end for
  &&

  ## Collect outputs
  cp Metatable_log/Metatable_mod.txt "${metatable_mod}" &&
  cp ${pipeline}_OTU_tables/multiplexed_linearized_dereplicated_mc2_repset_nonchimeras_tax_OTU_table.biom "${tax_otu_table_biom_file}" &&
  cp ${pipeline}_OTU_tables/otus.tre "${otus_tre_file}" &&
  cp RESULTS/${pipeline}_${reference_database_name}/OTUs_count.txt "${otus_count_file}" &&
  cp RESULTS/${pipeline}_${reference_database_name}/table_summary.txt "${table_summary_file}" &&
  cp Multiplexed_files/${pipeline}_pipeline/multiplexed_linearized_dereplicated_mc2_repset_nonchimeras_OTUs.fasta "${dereplicated_nonchimera_otus_fasta}" &&
  cp QUALITY_CONTROL/Reads_count.txt "$read_counts_out" &&
  cp fastqc_quality_boxplots.html "${fastqc_quality_boxplots_html}" &&

  ## HTML outputs

  ## OTU table
  mkdir $heatmap_otu_table_html.files_path &&
  cp -r RESULTS/${pipeline}_${reference_database_name}/Heatmap/js $heatmap_otu_table_html.files_path &&
  cp RESULTS/${pipeline}_${reference_database_name}/Heatmap/otu_table.html "${heatmap_otu_table_html}" &&

  ## Phylum genus barcharts
  mkdir $phylum_genus_dist_barcharts_html.files_path &&
  cp -r RESULTS/${pipeline}_${reference_database_name}/phylum_genus_charts/charts $phylum_genus_dist_barcharts_html.files_path &&
  cp -r RESULTS/${pipeline}_${reference_database_name}/phylum_genus_charts/raw_data $phylum_genus_dist_barcharts_html.files_path &&
  cp RESULTS/${pipeline}_${reference_database_name}/phylum_genus_charts/bar_charts.html "${phylum_genus_dist_barcharts_html}" &&

  ## Beta diversity weighted 2d plots
  mkdir $beta_div_even_weighted_2d_plots.files_path &&
  cp -r RESULTS/${pipeline}_${reference_database_name}/beta_div_even/weighted_2d_plot/* $beta_div_even_weighted_2d_plots.files_path &&
  cp RESULTS/${pipeline}_${reference_database_name}/beta_div_even/weighted_2d_plot/weighted_unifrac_pc_2D_PCoA_plots.html "${beta_div_even_weighted_2d_plots}" &&

  ## Beta diversity unweighted 2d plots
  mkdir $beta_div_even_unweighted_2d_plots.files_path &&
  cp -r RESULTS/${pipeline}_${reference_database_name}/beta_div_even/unweighted_2d_plot/* $beta_div_even_unweighted_2d_plots.files_path &&
  cp RESULTS/${pipeline}_${reference_database_name}/beta_div_even/unweighted_2d_plot/unweighted_unifrac_pc_2D_PCoA_plots.html "${beta_div_even_unweighted_2d_plots}" &&

  ## Alpha diversity rarefaction plots
  mkdir $alpha_div_rarefaction_plots.files_path &&
  cp RESULTS/${pipeline}_${reference_database_name}/Alpha_diversity/rarefaction_curves/rarefaction_plots.html $alpha_div_rarefaction_plots &&
  cp -r RESULTS/${pipeline}_${reference_database_name}/Alpha_diversity/rarefaction_curves/average_plots $alpha_div_rarefaction_plots.files_path &&

  ## Categories data
  #if str($categories_file_in) != 'None'
    ## Alpha diversity boxplots
    mkdir $alpha_div_boxplots.files_path &&
    cp alpha_diversity_boxplots.html "$alpha_div_boxplots" &&
    cp RESULTS/${pipeline}_${reference_database_name}/Alpha_diversity/Alpha_diversity_boxplot/Categories_shannon/*.pdf $alpha_div_boxplots.files_path &&
  #end if

  ## Pipeline outputs (log files etc)
  mkdir $log_files.files_path &&
  cp Amplicon_analysis_pipeline.log $log_files.files_path &&

	   label="Minimum length in bp to keep sequence after overlapping"
	   help="Default is 200 (-L)" />
    <param type="integer" name="sliding_window_length" value="10"
	   label="Minimum length in bp to retain a read after trimming"
	   help="Supplied to Sickle; default is 10 (-l)" />
    <param type="select" name="pipeline"
	    label="Pipeline to use for analysis">
      <option value="Vsearch" selected="true" >Vsearch</option>
      <!--
      Remove the QIIME and Uparse options for now
      <option value="QIIME">QIIME</option>
      <option value="Uparse">Uparse</option>
      -->
    </param>
    <param type="select" name="reference_database"
	   label="Reference database">
      <option value="" selected="true">GreenGenes</option>
      <option value="-S">Silva</option>
      <option value="-H">Human Oral Microbiome Database (HOMD)</option>
    </param>
  </inputs>
  <outputs>
    <data format="tabular" name="metatable_mod"
	  label="${tool.name}:${title} Metatable_mod.txt" />
    <data format="tabular" name="read_counts_out"
	  label="${tool.name} (${pipeline}):${title} read counts" />
    <data format="biom" name="tax_otu_table_biom_file"
	  label="${tool.name} (${pipeline}):${title} tax OTU table (biom format)" />
    <data format="tabular" name="otus_tre_file"
	  label="${tool.name} (${pipeline}):${title} otus.tre" />
    <data format="html" name="phylum_genus_dist_barcharts_html"
	  label="${tool.name} (${pipeline}):${title} phylum genus dist barcharts HTML" />
    <data format="tabular" name="otus_count_file"
	  label="${tool.name} (${pipeline}):${title} OTUs count file" />
    <data format="tabular" name="table_summary_file"
	  label="${tool.name} (${pipeline}):${title} table summary file" />
    <data format="fasta" name="dereplicated_nonchimera_otus_fasta"
	  label="${tool.name} (${pipeline}):${title} multiplexed linearized dereplicated mc2 repset nonchimeras OTUs FASTA" />
    <data format="html" name="fastqc_quality_boxplots_html"
	  label="${tool.name} (${pipeline}):${title} FastQC per-base quality boxplots HTML" />
    <data format="html" name="heatmap_otu_table_html"
	  label="${tool.name} (${pipeline}):${title} heatmap OTU table HTML" />
    <data format="html" name="beta_div_even_weighted_2d_plots"
	  label="${tool.name} (${pipeline}):${title} beta diversity weighted 2D plots HTML" />
    <data format="html" name="beta_div_even_unweighted_2d_plots"
	  label="${tool.name} (${pipeline}):${title} beta diversity unweighted 2D plots HTML" />
    <data format="html" name="alpha_div_rarefaction_plots"
	  label="${tool.name} (${pipeline}):${title} alpha diversity rarefaction plots HTML" />
    <data format="html" name="alpha_div_boxplots"
	  label="${tool.name} (${pipeline}):${title} alpha diversity boxplots">
      <filter>categories_file_in is not None</filter>
    </data>
    <data format="html" name="log_files"
	  label="${tool.name} (${pipeline}):${title} log files" />
  </outputs>
  <tests>
  </tests>
  <help><![CDATA[

   minimum sequence length used by Pandaseq to keep a sequence after the
   overlapping. This depends on the expected amplicon length. Default is
   380 (used for V3-V4 16S sequencing; expected length ~440bp)

 * **Pipeline to use for analysis** Choose the pipeline to use for OTU
   clustering and chimera removal. The Galaxy tool currently supports
   ``Vsearch`` only. ``Uparse`` and ``QIIME`` are planned to be added
   shortly (the tools are already available for the stand-alone pipeline).

 * **Reference database** Choose between ``GreenGenes`` and ``Silva``
   databases for taxa assignment.

Click on **Execute** to start the analysis.

5. Results
**********

Results are entirely generated using QIIME scripts. The results will 
appear in the History panel when the analysis is completed

 * **Vsearch_tax_OTU_table (biom format)** The OTU table in BIOM format
   (http://biom-format.org/)

 * **Vsearch_OTUs.tree** Phylogenetic tree constructed using
   ``make_phylogeny.py`` (fasttree) QIIME script
   (http://qiime.org/scripts/make_phylogeny.html)

 * **Vsearch_phylum_genus_dist_barcharts_HTML** HTML file with bar
   charts at Phylum, Genus and Species level
   (http://qiime.org/scripts/summarize_taxa.html and
   http://qiime.org/scripts/plot_taxa_summary.html)

 * **Vsearch_OTUs_count_file** Summary of OTU counts per sample
   (http://biom-format.org/documentation/summarizing_biom_tables.html)

 * **Vsearch_table_summary_file** Summary of sequences counts per sample
   (http://biom-format.org/documentation/summarizing_biom_tables.html)

 * **Vsearch_multiplexed_linearized_dereplicated_mc2_repset_nonchimeras_OTUs.fasta**
   Fasta file with OTU sequences

 * **Vsearch_heatmap_OTU_table_HTML** Interactive OTU heatmap
   (http://qiime.org/1.8.0/scripts/make_otu_heatmap_html.html )

 * **Vsearch_beta_diversity_weighted_2D_plots_HTML** PCoA plots in HTML
   format using weighted Unifrac distance measure. Samples are grouped
   by the column names present in the Metatable file. The samples are

4:86a12d75ebe4

<tool id="amplicon_analysis_pipeline" name="Amplicon Analysis Pipeline" version="1.3.6.0">
  <description>analyse 16S rRNA data from Illumina Miseq paired-end reads</description>
  <requirements>
    <requirement type="package" version="1.3.6">amplicon_analysis_pipeline</requirement>
  </requirements>
  <stdio>
    <exit_code range="1:" />
  </stdio>
  <command><![CDATA[

  ## Convenience variable for pipeline name
  #set $pipeline_name = $pipeline.pipeline_name

  ## Set the reference database name
  #if str( $pipeline_name ) == "DADA2"
     #set reference_database_name = "silva"
  #else
     #set reference_database = $pipeline.reference_database
     #if $reference_database == "-S"
        #set reference_database_name = "silva"
     #else if $reference_database == "-H"
        #set reference_database_name = "homd"
     #else
        #set reference_database_name = "gg"
     #end if
  #end if

  ## Run the amplicon analysis pipeline wrapper
  python $__tool_directory__/amplicon_analysis_pipeline.py
  ## Set options

  -O $minimum_overlap
  #end if
  #if str( $minimum_length ) != ""
  -L $minimum_length
  #end if
  -P $pipeline_name
  -r \${AMPLICON_ANALYSIS_REF_DATA_PATH-ReferenceData}
  #if str( $pipeline_name ) != "DADA2"
    ${reference_database}
  #end if
  #if str($categories_file_in) != 'None'
    -c "${categories_file_in}"
  #end if

  #end for
  &&

  ## Collect outputs
  cp Metatable_log/Metatable_mod.txt "${metatable_mod}" &&
  #if str( $pipeline_name ) == "Vsearch"
    ## Vsearch-specific
    cp ${pipeline_name}_OTU_tables/multiplexed_linearized_dereplicated_mc2_repset_nonchimeras_tax_OTU_table.biom "${tax_otu_table_biom_file}" &&
    cp Multiplexed_files/${pipeline_name}_pipeline/multiplexed_linearized_dereplicated_mc2_repset_nonchimeras_OTUs.fasta "${dereplicated_nonchimera_otus_fasta}" &&
    cp QUALITY_CONTROL/Reads_count.txt "$read_counts_out" &&
  #else
    ## DADA2-specific
    cp ${pipeline_name}_OTU_tables/DADA2_tax_OTU_table.biom "${tax_otu_table_biom_file}" &&
    cp ${pipeline_name}_OTU_tables/seqs.fa "${dereplicated_nonchimera_otus_fasta}" &&
  #end if
  cp ${pipeline_name}_OTU_tables/otus.tre "${otus_tre_file}" &&
  cp RESULTS/${pipeline_name}_${reference_database_name}/OTUs_count.txt "${otus_count_file}" &&
  cp RESULTS/${pipeline_name}_${reference_database_name}/table_summary.txt "${table_summary_file}" &&
  cp fastqc_quality_boxplots.html "${fastqc_quality_boxplots_html}" &&

  ## OTU table heatmap
  cp RESULTS/${pipeline_name}_${reference_database_name}/Heatmap.pdf "${heatmap_otu_table_pdf}" &&

  ## HTML outputs

  ## Phylum genus barcharts
  mkdir $phylum_genus_dist_barcharts_html.files_path &&
  cp -r RESULTS/${pipeline_name}_${reference_database_name}/phylum_genus_charts/charts $phylum_genus_dist_barcharts_html.files_path &&
  cp -r RESULTS/${pipeline_name}_${reference_database_name}/phylum_genus_charts/raw_data $phylum_genus_dist_barcharts_html.files_path &&
  cp RESULTS/${pipeline_name}_${reference_database_name}/phylum_genus_charts/bar_charts.html "${phylum_genus_dist_barcharts_html}" &&

  ## Beta diversity weighted 2d plots
  mkdir $beta_div_even_weighted_2d_plots.files_path &&
  cp -r RESULTS/${pipeline_name}_${reference_database_name}/beta_div_even/weighted_2d_plot/* $beta_div_even_weighted_2d_plots.files_path &&
  cp RESULTS/${pipeline_name}_${reference_database_name}/beta_div_even/weighted_2d_plot/weighted_unifrac_pc_2D_PCoA_plots.html "${beta_div_even_weighted_2d_plots}" &&

  ## Beta diversity unweighted 2d plots
  mkdir $beta_div_even_unweighted_2d_plots.files_path &&
  cp -r RESULTS/${pipeline_name}_${reference_database_name}/beta_div_even/unweighted_2d_plot/* $beta_div_even_unweighted_2d_plots.files_path &&
  cp RESULTS/${pipeline_name}_${reference_database_name}/beta_div_even/unweighted_2d_plot/unweighted_unifrac_pc_2D_PCoA_plots.html "${beta_div_even_unweighted_2d_plots}" &&

  ## Alpha diversity rarefaction plots
  mkdir $alpha_div_rarefaction_plots.files_path &&
  cp RESULTS/${pipeline_name}_${reference_database_name}/Alpha_diversity/rarefaction_curves/rarefaction_plots.html $alpha_div_rarefaction_plots &&
  cp -r RESULTS/${pipeline_name}_${reference_database_name}/Alpha_diversity/rarefaction_curves/average_plots $alpha_div_rarefaction_plots.files_path &&

  ## DADA2 error rate plots
  #if str($pipeline_name) == "DADA2"
    mkdir $dada2_error_rate_plots.files_path &&
    cp DADA2_OTU_tables/Error_rate_plots/error_rate_plots.html $dada2_error_rate_plots &&
    cp -r DADA2_OTU_tables/Error_rate_plots/*.pdf $dada2_error_rate_plots.files_path &&
  #end if

  ## Categories data
  #if str($categories_file_in) != 'None'
    ## Alpha diversity boxplots
    mkdir $alpha_div_boxplots.files_path &&
    cp alpha_diversity_boxplots.html "$alpha_div_boxplots" &&
    cp RESULTS/${pipeline_name}_${reference_database_name}/Alpha_diversity/Alpha_diversity_boxplot/Categories_shannon/*.pdf $alpha_div_boxplots.files_path &&
  #end if

  ## Pipeline outputs (log files etc)
  mkdir $log_files.files_path &&
  cp Amplicon_analysis_pipeline.log $log_files.files_path &&

	   label="Minimum length in bp to keep sequence after overlapping"
	   help="Default is 200 (-L)" />
    <param type="integer" name="sliding_window_length" value="10"
	   label="Minimum length in bp to retain a read after trimming"
	   help="Supplied to Sickle; default is 10 (-l)" />
    <conditional name="pipeline">
      <param type="select" name="pipeline_name"
	     label="Pipeline to use for analysis">
	<option value="Vsearch" selected="true" >Vsearch</option>
	<option value="DADA2">DADA2</option>
      </param>
      <when value="Vsearch">
	<param type="select" name="reference_database"
	       label="Reference database">
	  <option value="" selected="true">GreenGenes</option>
	  <option value="-S">Silva</option>
	  <option value="-H">Human Oral Microbiome Database (HOMD)</option>
	</param>
      </when>
      <when value="DADA2">
      </when>
    </conditional>
  </inputs>
  <outputs>
    <data format="tabular" name="metatable_mod"
	  label="${tool.name}:${title} Metatable_mod.txt" />
    <data format="tabular" name="read_counts_out"
	  label="${tool.name} (${pipeline.pipeline_name}):${title} read counts">
      <filter>pipeline['pipeline_name'] == 'Vsearch'</filter>
    </data>
    <data format="biom" name="tax_otu_table_biom_file"
	  label="${tool.name} (${pipeline.pipeline_name}):${title} tax OTU table (biom format)" />
    <data format="tabular" name="otus_tre_file"
	  label="${tool.name} (${pipeline.pipeline_name}):${title} otus.tre" />
    <data format="html" name="phylum_genus_dist_barcharts_html"
	  label="${tool.name} (${pipeline.pipeline_name}):${title} phylum genus dist barcharts HTML" />
    <data format="tabular" name="otus_count_file"
	  label="${tool.name} (${pipeline.pipeline_name}):${title} OTUs count file" />
    <data format="tabular" name="table_summary_file"
	  label="${tool.name} (${pipeline.pipeline_name}):${title} table summary file" />
    <data format="fasta" name="dereplicated_nonchimera_otus_fasta"
	  label="${tool.name} (${pipeline.pipeline_name}):${title} multiplexed linearized dereplicated mc2 repset nonchimeras OTUs FASTA" />
    <data format="html" name="fastqc_quality_boxplots_html"
	  label="${tool.name} (${pipeline.pipeline_name}):${title} FastQC per-base quality boxplots HTML" />
    <data format="pdf" name="heatmap_otu_table_pdf"
	  label="${tool.name} (${pipeline.pipeline_name}):${title} heatmap OTU table PDF" />
    <data format="html" name="beta_div_even_weighted_2d_plots"
	  label="${tool.name} (${pipeline.pipeline_name}):${title} beta diversity weighted 2D plots HTML" />
    <data format="html" name="beta_div_even_unweighted_2d_plots"
	  label="${tool.name} (${pipeline.pipeline_name}):${title} beta diversity unweighted 2D plots HTML" />
    <data format="html" name="alpha_div_rarefaction_plots"
	  label="${tool.name} (${pipeline.pipeline_name}):${title} alpha diversity rarefaction plots HTML" />
    <data format="html" name="dada2_error_rate_plots"
	  label="${tool.name} (${pipeline.pipeline_name}):${title} DADA2 error rate plots">
      <filter>pipeline['pipeline_name'] == 'DADA2'</filter>
    </data>
    <data format="html" name="alpha_div_boxplots"
	  label="${tool.name} (${pipeline.pipeline_name}):${title} alpha diversity boxplots">
      <filter>categories_file_in is not None</filter>
    </data>
    <data format="html" name="log_files"
	  label="${tool.name} (${pipeline.pipeline_name}):${title} log files" />
  </outputs>
  <tests>
  </tests>
  <help><![CDATA[

   minimum sequence length used by Pandaseq to keep a sequence after the
   overlapping. This depends on the expected amplicon length. Default is
   380 (used for V3-V4 16S sequencing; expected length ~440bp)

 * **Pipeline to use for analysis** Choose the pipeline to use for OTU
   clustering and chimera removal. The Galaxy tool supports the ``Vsearch``
   and ``DADA2`` pipelines.

 * **Reference database** Choose between ``GreenGenes``, ``Silva`` or
   ``HOMD`` (Human Oral Microbiome Database) for taxa assignment.

Click on **Execute** to start the analysis.

5. Results
**********

Results are entirely generated using QIIME scripts. The results will 
appear in the History panel when the analysis is completed.

The following outputs are captured:

 * **Vsearch_tax_OTU_table.biom|DADA2_tax_OTU_table.biom (biom format)**
   The OTU table in BIOM format (http://biom-format.org/)

 * **otus.tre** Phylogenetic tree constructed using ``make_phylogeny.py``
   (fasttree) QIIME script (http://qiime.org/scripts/make_phylogeny.html)

 * **Phylum_genus_dist_barcharts_HTML** HTML file with bar charts at
   Phylum, Genus and Species level
   (http://qiime.org/scripts/summarize_taxa.html and
   http://qiime.org/scripts/plot_taxa_summary.html)

 * **OTUs_count_file** Summary of OTU counts per sample
   (http://biom-format.org/documentation/summarizing_biom_tables.html)

 * **Table_summary_file** Summary of sequences counts per sample
   (http://biom-format.org/documentation/summarizing_biom_tables.html)

 * **multiplexed_linearized_dereplicated_mc2_repset_nonchimeras_OTUs.fasta|seqs.fa**
   Fasta file with OTU sequences (Vsearch|DADA2)

 * **Heatmap_PDF** OTU heatmap in PDF format
   (http://qiime.org/1.8.0/scripts/make_otu_heatmap_html.html )

 * **Vsearch_beta_diversity_weighted_2D_plots_HTML** PCoA plots in HTML
   format using weighted Unifrac distance measure. Samples are grouped
   by the column names present in the Metatable file. The samples are