comparison trinity.xml @ 6:4c1d32673942 draft

Uploaded

5:f976a93748a4

<tool id="trinityrnaseq" name="Trinity" version="2.4.0">
  
    <!-- Originally written by Jeremy Goecks,
        later maintained by (in chronological order)
            bhaas, Ben Fulton, Cicada Dennis 
    -->
    <description>De novo assembly of RNA-Seq data using Trinity 2.4.0</description>
    <requirements>
        <requirement type="package" version="2.4.0">trinity</requirement>
    </requirements>
    <command>
      <![CDATA[
      python $__tool_directory__/trinity_wrapper.py --mem_per_cpu 31
      --CPU \${GALAXY_SLOTS:-4}
      #if str($inputs.paired_or_single) == "paired":
       --left $inputs.left_input --right $inputs.right_input
       #if $inputs.left_input.ext == 'fasta':
        --seqType fa
       #else:

        --seqType fq
       #end if
      #end if
      ## direct to output
      --timing trinity_out_dir/Trinity.timing
      --user $__user_id__
      --fullpath /N/dc2/scratch/tstrnity/rerun
      --dir '$adv.rerundir'
      --log $trinity_log

 ]]>
    </command>
    <stdio>
      <exit_code range="1:"   level="fatal"   description="Program failed" />
      <exit_code range=":-1"   level="fatal"   description="DRM killed job" />
    </stdio>

        </when>
        <when value="single">
          <param format="fasta,fastq" name="input" type="data" label="Single-end reads" help=""/>
        </when>
      </conditional>
      <section name="adv" title="Allow Job Rerun" expanded="False">
	<param name="rerundir" type="text" size="10" label="To make a job rerunnable, you will need to specify a unique tag to label the job, with no spaces or wierd characters." />
    </section>
    </inputs>
    <outputs>
      <data format="txt" name="trinity_log" label="${tool.name} on ${on_string}: log" />
      <data format="fasta" name="assembled_transcripts" label="${tool.name} on ${on_string}: Assembled Transcripts" from_work_dir="trinity_out_dir/Trinity.fasta"/>
    </outputs>

        <test>
  	    <param name="paired_or_single" value="paired" />
            <param name="left_input" value="Sp.cat_ds_hs.left.fq" />
            <param name="right_input" value="Sp.cat_ds_hs.right.fq" />
            <param name="adv.rerundir" value="planemo_test_2" />
            <!-- Following are not being used in this version of trinity.xml -->
            <!--
 	    <param name="paired_or_single" value="paired" />
            <param name="left_input" file="cat_Sp.left.fq" />
            <param name="right_input" file="cat_Sp.right.fq" />
            <param name="JM" value="50G" />
            <param name="CPU" value="2" />
            <param name="library_type" value="None" />
            <param name="group_pairs_distance" value="500" />
            <param name="path_reinforcement_distance" va;ue="75" />
            <param name="use_additional" value="no" />
            -->
  	    <output name="trinity_log" >
                <assert_contents>
                    <has_line_matching expression=".+" />

        </test>
    </tests>
    <help>
This instance is running Trinity version 2.4.0 and uses the following command:

	 Trinity --max_memory 240G --CPU 8 --seqType seq_type --single singlefile or --left left_file --right right_file

.. class:: infomark

Trinity_, developed at the Broad Institute and the Hebrew University of Jerusalem, represents a novel method for the efficient and robust de novo reconstruction of transcriptomes from RNA-seq data. Trinity combines three independent software modules: Inchworm, Chrysalis, and Butterfly, applied sequentially to process large volumes of RNA-seq reads. Trinity partitions the sequence data into many individual de Bruijn graphs, each representing the transcriptional complexity at a given gene or locus, and then processes each graph independently to extract full-length splicing isoforms and to tease apart transcripts derived from paralogous genes. For more information, visit Trinity's wiki page here_.

6:4c1d32673942

<tool id="trinityrnaseq" name="Trinity" version="2.4.0">
  
    <!-- Original written by Jeremy Goecks,
        later development/maintenance by (in chronological order)
            bhaas, Ben Fulton, Cicada Dennis 
    -->
    <description>De novo assembly of RNA-Seq data using Trinity 2.4.0</description>
    <requirements>
        <requirement type="package" version="2.7">python</requirement>
        <requirement type="package">subprocess32</requirement>
        <requirement type="package">samtools</requirement>
        <requirement type="package">bzip2</requirement>
        <requirement type="package" version="2.4.0">trinity</requirement>
    </requirements>
    <command>
      <![CDATA[
      python $__tool_directory__/trinity_wrapper.py 
      --CPU \${GALAXY_SLOTS:-4}
      --max_memory \${TRINITY_MAX_MEMORY:-31G}
      #if str($inputs.paired_or_single) == "paired":
       --left $inputs.left_input --right $inputs.right_input
       #if $inputs.left_input.ext == 'fasta':
        --seqType fa
       #else:

        --seqType fq
       #end if
      #end if
      ## direct to output
      --timing trinity_out_dir/Trinity.timing
      --log $trinity_log

 ]]>
      <!-- The fullpath, dir, and user options (preceed with dashes) can be
           used in the trinity_wrapper.py command to create rerunable jobs.
           We are not supporting rerunable jobs in this release of this tool.
        fullpath \${TRINITY_RERUN_PREFIX}
        dir '$adv.rerundir'
        user $__user_id__
      mem_per_cpu 31
      -->
    </command>
    <stdio>
      <exit_code range="1:"   level="fatal"   description="Program failed" />
      <exit_code range=":-1"   level="fatal"   description="DRM killed job" />
    </stdio>

        </when>
        <when value="single">
          <param format="fasta,fastq" name="input" type="data" label="Single-end reads" help=""/>
        </when>
      </conditional>
      <!-- The following section was used to aid in creating rerunable jobs.
           We are not supporting rerunable jobs in this release of this tool.
      <section name="adv" title="Allow Job Rerun" expanded="False">
        <param name="rerundir" type="text" size="10" label="To make a job rerunnable, you will need to specify a unique tag to label the job, with no spaces or wierd characters." />
      </section>
      -->
    </inputs>
    <outputs>
      <data format="txt" name="trinity_log" label="${tool.name} on ${on_string}: log" />
      <data format="fasta" name="assembled_transcripts" label="${tool.name} on ${on_string}: Assembled Transcripts" from_work_dir="trinity_out_dir/Trinity.fasta"/>
    </outputs>

        <test>
  	    <param name="paired_or_single" value="paired" />
            <param name="left_input" value="Sp.cat_ds_hs.left.fq" />
            <param name="right_input" value="Sp.cat_ds_hs.right.fq" />
            <param name="adv.rerundir" value="planemo_test_2" />
            <!-- Following parameters are not used in this version of this tool. -->
            <!--
            <param name="JM" value="50G" />
            <param name="CPU" value="2" />
            <param name="library_type" value="None" />
            <param name="group_pairs_distance" value="500" />
            <param name="path_reinforcement_distance" value="75" />
            <param name="use_additional" value="no" />
            -->
  	    <output name="trinity_log" >
                <assert_contents>
                    <has_line_matching expression=".+" />

        </test>
    </tests>
    <help>
This instance is running Trinity version 2.4.0 and uses the following command:

	 Trinity --max_memory \${TRINITY_MAX_MEMORY:-31G} --CPU \${GALAXY_SLOTS:-4} --seqType seq_type --single singlefile or --left left_file --right right_file
         Define TRINITY_MAX_MEMORY and GALAXY_SLOTS to change the default values for --max_memory and --CPU.

.. class:: infomark

Trinity_, developed at the Broad Institute and the Hebrew University of Jerusalem, represents a novel method for the efficient and robust de novo reconstruction of transcriptomes from RNA-seq data. Trinity combines three independent software modules: Inchworm, Chrysalis, and Butterfly, applied sequentially to process large volumes of RNA-seq reads. Trinity partitions the sequence data into many individual de Bruijn graphs, each representing the transcriptional complexity at a given gene or locus, and then processes each graph independently to extract full-length splicing isoforms and to tease apart transcripts derived from paralogous genes. For more information, visit Trinity's wiki page here_.