comparison trimmomatic.xml @ 3:f8a9a5eaca8a draft

Updated to version 0.32.3: add support for FASTQ pairs (dataset collections)

2:a60283899c6d

<tool id="trimmomatic" name="Trimmomatic" version="0.32.2">
  <description>flexible read trimming tool for Illumina NGS data</description>
  <command interpreter="bash">trimmomatic.sh
  -mx8G
  -jar \$TRIMMOMATIC_DIR/trimmomatic-0.32.jar
  #if $paired_end.is_paired_end
    PE -threads \${GALAXY_SLOTS:-6} -phred33 $fastq_r1_in $paired_end.fastq_r2_in $fastq_out_r1_paired $fastq_out_r1_unpaired $fastq_out_r2_paired $fastq_out_r2_unpaired 
  #else
    SE -threads \${GALAXY_SLOTS:-6} -phred33 $fastq_in $fastq_out
  #end if
  ## ILLUMINACLIP option
  #if $illuminaclip.do_illuminaclip
    ILLUMINACLIP:\$TRIMMOMATIC_ADAPTERS_DIR/$illuminaclip.adapter_fasta:$illuminaclip.seed_mismatches:$illuminaclip.palindrome_clip_threshold:$illuminaclip.simple_clip_threshold
  #end if

    #end if
    #if str( $op.operation.name ) == "HEADCROP"
      HEADCROP:$op.operation.headcrop
    #end if
  #end for
  </command>
  <requirements>
    <requirement type="package" version="0.32">trimmomatic</requirement>
  </requirements>
  <inputs>
    <conditional name="paired_end">
    <param name="is_paired_end" type="boolean" label="Paired end data?" truevalue="yes" falsevalue="no" checked="on" />
    <when value="no">
      <param name="fastq_in" type="data" format="fastqsanger" label="Input FASTQ file" />
    </when>
    <when value="yes">
      <param name="fastq_r1_in" type="data" format="fastqsanger"
	     label="Input FASTQ file (R1/first of pair)" />
      <param name="fastq_r2_in" type="data" format="fastqsanger"
	     label="Input FASTQ file (R2/second of pair)" />
    </when>
    </conditional>
    <conditional name="illuminaclip">
    <param name="do_illuminaclip" type="boolean" label="Perform initial ILLUMINACLIP step?" help="Cut adapter and other illumina-specific sequences from the read" truevalue="yes" falsevalue="no" checked="off" />
    <when value="yes">

	</when>
      </conditional>
    </repeat>
  </inputs>
  <outputs>
    <data format="fastqsanger" name="fastq_out_r1_paired" label="${tool.name} on ${on_string} (R1 paired)">
      <filter>paired_end['is_paired_end']</filter>
    </data>
    <data format="fastqsanger" name="fastq_out_r1_unpaired" label="${tool.name} on ${on_string} (R1 unpaired)">
      <filter>paired_end['is_paired_end']</filter>
    </data>
    <data format="fastqsanger" name="fastq_out_r2_paired" label="${tool.name} on ${on_string} (R2 paired)">
      <filter>paired_end['is_paired_end']</filter>
    </data>
    <data format="fastqsanger" name="fastq_out_r2_unpaired" label="${tool.name} on ${on_string} (R2 unpaired)">
      <filter>paired_end['is_paired_end']</filter>
    </data>
    <data format="fastqsanger" name="fastq_out" label="${tool.name} on ${on_string}">
      <filter>not paired_end['is_paired_end']</filter>
    </data>
  </outputs>
  <tests>
    <test>
      <!-- Single-end example -->
      <param name="is_paired_end" value="no" />

      tool (which is the order they will be written to the history) - the
      test framework seems to use the order and ignores the "name" attribute
      -->
      <output name="fastq_out" file="trimmomatic_se_out2.fastq" />
    </test>
  </tests>
  <help>
.. class:: infomark

**What it does**

Trimmomatic performs a variety of useful trimming tasks for illumina paired-end and

-------------

.. class:: infomark

**Outputs**

For paired-end data a particular strength of Trimmomatic is that it retains the
pairing of reads (from R1 and R2) in the filtered output files:

 * Two FASTQ files (R1-paired and R2-paired) contain one read from each pair where
   both have survived filtering.
 * Additionally two FASTQ files (R1-unpaired and R2-unpaired) contain reads where
   one of the pair failed the filtering steps.

Retaining the same order and number of reads in the filtered output fastq files is
essential for many downstream analysis tools.

For single-end data the output is a single FASTQ file containing just the filtered
reads.

 * Bolger, A.M., Lohse, M., & Usadel, B. (2014). Trimmomatic: A flexible trimmer
   for Illumina Sequence Data. Bioinformatics, btu170.

Please kindly acknowledge both this Galaxy tool and the Trimmomatic program if you
use it.
  </help>
  <citations>
    <!--
    See https://wiki.galaxyproject.org/Admin/Tools/ToolConfigSyntax#A.3Ccitations.3E_tag_set
    Can be either DOI or Bibtex
    Use http://www.bioinformatics.org/texmed/ to convert PubMed to Bibtex

3:f8a9a5eaca8a

<tool id="trimmomatic" name="Trimmomatic" version="0.32.3">
  <description>flexible read trimming tool for Illumina NGS data</description>
  <requirements>
    <requirement type="package" version="0.32">trimmomatic</requirement>
  </requirements>
  <stdio>
    <exit_code range="1:" />
  </stdio>
  <command interpreter="bash"><![CDATA[
  trimmomatic.sh
  -mx8G
  -jar \$TRIMMOMATIC_DIR/trimmomatic-0.32.jar
  #if $paired_end.is_paired_end
    PE -threads \${GALAXY_SLOTS:-6} -phred33
    #set $paired_input_type = $paired_end.paired_input_type_conditional.paired_input_type
    #if $paired_input_type == "pair_of_files"
      "${paired_end.paired_input_type_conditional.fastq_r1_in}"
      "${paired_end.paired_input_type_conditional.fastq_r2_in}"
      "${fastq_out_r1_paired}" "${fastq_out_r1_unpaired}"
      "${fastq_out_r2_paired}" "${fastq_out_r2_unpaired}"
    #else
      "${paired_end.paired_input_type_conditional.fastq_pair.forward}"
      "${paired_end.paired_input_type_conditional.fastq_pair.reverse}"
      "${fastq_out_paired.forward}" "${fastq_out_unpaired.forward}"
      "${fastq_out_paired.reverse}" "${fastq_out_unpaired.reverse}"
    #end if
  #else
    SE -threads \${GALAXY_SLOTS:-6} -phred33 "$fastq_in" "$fastq_out"
  #end if
  ## ILLUMINACLIP option
  #if $illuminaclip.do_illuminaclip
    ILLUMINACLIP:\$TRIMMOMATIC_ADAPTERS_DIR/$illuminaclip.adapter_fasta:$illuminaclip.seed_mismatches:$illuminaclip.palindrome_clip_threshold:$illuminaclip.simple_clip_threshold
  #end if

    #end if
    #if str( $op.operation.name ) == "HEADCROP"
      HEADCROP:$op.operation.headcrop
    #end if
  #end for
  ]]></command>
  <inputs>
    <conditional name="paired_end">
    <param name="is_paired_end" type="boolean" label="Paired end data?" truevalue="yes" falsevalue="no" checked="on" />
    <when value="no">
      <param name="fastq_in" type="data" format="fastqsanger" label="Input FASTQ file" />
    </when>
    <when value="yes">
      <conditional name="paired_input_type_conditional">
        <param name="paired_input_type" type="select" label="Input Type">
          <option value="pair_of_files" selected="true">Pair of datasets</option>
          <option value="collection">Dataset collection pair</option>
        </param>
        <when value="pair_of_files">
 	  <param name="fastq_r1_in" type="data" format="fastqsanger"
		 label="Input FASTQ file (R1/first of pair)" />
 	  <param name="fastq_r2_in" type="data" format="fastqsanger"
		 label="Input FASTQ file (R2/second of pair)" />
	</when>
        <when value="collection">
          <param name="fastq_pair" format="fastqsanger" type="data_collection"
 		 collection_type="paired"
 		 label="Select FASTQ dataset collection with R1/R2 pair" />
        </when>
      </conditional>
    </when>
    </conditional>
    <conditional name="illuminaclip">
    <param name="do_illuminaclip" type="boolean" label="Perform initial ILLUMINACLIP step?" help="Cut adapter and other illumina-specific sequences from the read" truevalue="yes" falsevalue="no" checked="off" />
    <when value="yes">

	</when>
      </conditional>
    </repeat>
  </inputs>
  <outputs>
    <data format="fastqsanger" name="fastq_out_r1_paired" label="${tool.name} on ${paired_end.paired_input_type_conditional.fastq_r1_in.name} (R1 paired)">
      <filter>paired_end['is_paired_end']</filter>
      <filter>paired_end['paired_input_type_conditional']['paired_input_type'] == "pair_of_files"</filter>
    </data>
    <data format="fastqsanger" name="fastq_out_r2_paired" label="${tool.name} on ${paired_end.paired_input_type_conditional.fastq_r2_in.name} (R2 paired)">
      <filter>paired_end['is_paired_end']</filter>
      <filter>paired_end['paired_input_type_conditional']['paired_input_type'] == "pair_of_files"</filter>
    </data>
    <data format="fastqsanger" name="fastq_out_r1_unpaired" label="${tool.name} on ${paired_end.paired_input_type_conditional.fastq_r1_in.name} (R1 unpaired)">
      <filter>paired_end['is_paired_end']</filter>
      <filter>paired_end['paired_input_type_conditional']['paired_input_type'] == "pair_of_files"</filter>
    </data>
    <data format="fastqsanger" name="fastq_out_r2_unpaired" label="${tool.name} on ${paired_end.paired_input_type_conditional.fastq_r2_in.name} (R2 unpaired)">
      <filter>paired_end['is_paired_end']</filter>
      <filter>paired_end['paired_input_type_conditional']['paired_input_type'] == "pair_of_files"</filter>
    </data>
    <data format="fastqsanger" name="fastq_out" label="${tool.name} on ${paired_end.fastq_in.name}">
      <filter>not paired_end['is_paired_end']</filter>
    </data>
    <collection name="fastq_out_paired" type="paired" label="${tool.name} on ${paired_end.paired_input_type_conditional.fastq_pair.name}: paired">
      <data name="forward" format="fastqsanger" label="${tool.name} on ${paired_end.paired_input_type_conditional.fastq_pair.forward.name} (R1 paired)" />
      <data name="reverse" format="fastqsanger" label="${tool.name} on ${paired_end.paired_input_type_conditional.fastq_pair.reverse.name} (R2 paired)" />
      <filter>paired_end['is_paired_end']</filter>
      <filter>paired_end['paired_input_type_conditional']['paired_input_type'] == "collection"</filter>
    </collection>
    <collection name="fastq_out_unpaired" type="paired" label="${tool.name} on ${paired_end.paired_input_type_conditional.fastq_pair.name}: unpaired">
      <data name="forward" format="fastqsanger" label="${tool.name} on ${paired_end.paired_input_type_conditional.fastq_pair.forward.name} (R1 unpaired)" />
      <data name="reverse" format="fastqsanger" label="${tool.name} on ${paired_end.paired_input_type_conditional.fastq_pair.reverse.name} (R2 unpaired)" />
      <filter>paired_end['is_paired_end']</filter>
      <filter>paired_end['paired_input_type_conditional']['paired_input_type'] == "collection"</filter>
    </collection>
  </outputs>
  <tests>
    <test>
      <!-- Single-end example -->
      <param name="is_paired_end" value="no" />

      tool (which is the order they will be written to the history) - the
      test framework seems to use the order and ignores the "name" attribute
      -->
      <output name="fastq_out" file="trimmomatic_se_out2.fastq" />
    </test>
    <test>
      <!-- Paired-end with dataset collection -->
      <param name="is_paired_end" value="yes" />
      <param name="paired_input_type" value="collection" />
      <param name="fastq_pair">
        <collection type="paired">
          <element name="forward" value="Illumina_SG_R1.fastq" ftype="fastqsanger" />
          <element name="reverse" value="Illumina_SG_R2.fastq" ftype="fastqsanger"/>
        </collection>
      </param>
      <param name="operations_0|operation|name" value="SLIDINGWINDOW" />
      <output_collection name="fastq_out_paired" type="paired">
	<element name="forward" file="trimmomatic_pe_r1_paired_out1.fastq" />
	<element name="reverse" file="trimmomatic_pe_r2_paired_out1.fastq" />
      </output_collection>
      <output_collection name="fastq_out_unpaired" type="paired">
	<element name="forward" file="trimmomatic_pe_r1_unpaired_out1.fastq" />
	<element name="reverse" file="trimmomatic_pe_r2_unpaired_out1.fastq" />
      </output_collection>
    </test>
  </tests>
  <help><![CDATA[
.. class:: infomark

**What it does**

Trimmomatic performs a variety of useful trimming tasks for illumina paired-end and

-------------

.. class:: infomark

**Inputs**

For single-end data this Trimmomatic tool accepts a single FASTQ file; for
paired-end data it will accept either two FASTQ files (R1 and R2), or a
dataset collection containing the R1/R2 FASTQ pair.

.. class:: infomark

**Outputs**

For paired-end data a particular strength of Trimmomatic is that it retains the
pairing of reads (from R1 and R2) in the filtered output files:

 * Two FASTQ files (R1-paired and R2-paired) contain one read from each pair where
   both have survived filtering.
 * Additionally two FASTQ files (R1-unpaired and R2-unpaired) contain reads where
   one of the pair failed the filtering steps.

.. class:: warningmark

If the input consists of a dataset collection with the R1/R2 FASTQ pair then
the outputs will also inclue two dataset collections: one for the 'paired'
outputs and one for the 'unpaired' (as described above)

Retaining the same order and number of reads in the filtered output fastq files is
essential for many downstream analysis tools.

For single-end data the output is a single FASTQ file containing just the filtered
reads.

 * Bolger, A.M., Lohse, M., & Usadel, B. (2014). Trimmomatic: A flexible trimmer
   for Illumina Sequence Data. Bioinformatics, btu170.

Please kindly acknowledge both this Galaxy tool and the Trimmomatic program if you
use it.
  ]]></help>
  <citations>
    <!--
    See https://wiki.galaxyproject.org/Admin/Tools/ToolConfigSyntax#A.3Ccitations.3E_tag_set
    Can be either DOI or Bibtex
    Use http://www.bioinformatics.org/texmed/ to convert PubMed to Bibtex