comparison rg_rnaStar.xml @ 25:1903b1fe70fc draft

Uploaded

24:a711b92d85c1

<tool id="rna_star" name="RNA-STAR" version="0.23">
    <description>Gapped-read mapper for RNA-seq data</description>
    <requirements>
        <requirement type="package" version="2.3.1z">rnastar</requirement>
        <requirement type="package" version="0.1.19">samtools</requirement>
    </requirements>
    <command>
    ##
    ## Run STAR.
    ##

        STAR
    ## Can adjust this as appropriate for the system.
    --genomeLoad NoSharedMemory

    --genomeDir ${refGenomeSource.index.fields.path} 
    --readFilesIn $input1 
    #if $singlePaired.sPaired == "paired"
            $singlePaired.input2
        #end if
        --runThreadN 4
    #if $params.settingsType == "full":
        --chimSegmentMin $params.chim_segment_min
        --chimScoreMin $params.chim_score_min
    #end if

    ## may or may not need to generate SAM tags and handle non-canonicals for Cufflinks tools.
    ${outSAMstrandField} ${outFilterIntronMotifs} ${outSAMattributes}

    ;

    ##
    ## BAM conversion.
    ##

    ## Convert aligned reads.
    samtools view -Shb Aligned.out.sam | samtools sort - Aligned.out

    ## Convert chimeric reads.
    #if $params.settingsType == "full" and $params.chim_segment_min > 0:
        ; samtools view -Shb Chimeric.out.sam | samtools sort - Chimeric.out
    #end if
    </command>

    <stdio>
        <regex match=".*" source="both" level="warning" description="generic stdout/err chatter"/>
    </stdio>

    <inputs>
        <param name="jobName" type="text" size="120" value="rna-star run" label="Job narrative (added to output names)" 
          help="Only letters, numbers and underscores (_) will be retained in this field">

            </param>
            <when value="single">
                <param format="fastqsanger,fastq,fasta" name="input1" type="data" label="RNA-Seq FASTQ file" help="Nucleotide-space: Must have Sanger-scaled quality values with ASCII offset 33"/>
            </when>
            <when value="paired">
                <param format="fastqsanger,fastq,fasta" name="input1" type="data" label="RNA-Seq FASTQ file, forward reads" help="Nucleotide-space: Must have Sanger-scaled quality values with ASCII offset 33" />
                <param format="fastqsanger,fastq,fasta" name="input2" type="data" label="RNA-Seq FASTQ file, reverse reads" help="Nucleotide-space: Must have Sanger-scaled quality values with ASCII offset 33" />
            </when>
        </conditional>

        <!-- Genome source. -->
        <conditional name="refGenomeSource">
            <param name="genomeSource" type="select" label="Will you select a reference genome from your history or use a built-in index?" help="Built-ins were indexed using default options">
                <option value="indexed">Use a built-in index</option>
                <option value="history">Use one from the history</option>
            </param>
            <when value="indexed">
            <param name="index" type="select" label="Select a reference genome">
                <options from_data_table="rnastar_indexes">
                    <filter type="sort_by" column="2"/>
                    <validator type="no_options" message="No indexes are available for the selected input dataset"/>
                </options>
            </param>
            </when>
            <when value="history">
                <param name="ownFile" type="data" format="fasta" metadata_name="dbkey" label="Select the reference genome" />
            </when>
        </conditional>
            <param name="outSAMattributes" type="select" label="Include extra sam attributes for downstream processing">
              <option value="--outSAMattributes Standard">Standard - eg for old Samtools downstream</option>
              <option value="--outSAMattributes All" selected="true">All modern Samtools attributes - see below</option>

            </when>
        </conditional>
    </inputs>

    <outputs>
       <data format="txt" name="output_log" label="${on_string}_{jobName}.log" from_work_dir="Log.final.out"/>
       <data format="interval" name="chimeric_junctions" label="${on_string}_{jobName}_starchimjunc.bed" from_work_dir="Chimeric.out.junction">
          <filter>(params['settingsType'] == 'full' and params['chim_segment_min'] > 0)</filter>
          <actions>
             <conditional name="refGenomeSource.genomeSource">
             <when value="indexed">
               <action type="metadata" name="dbkey">
                <option type="from_data_table" name="star_indexes" column="1" offset="0">
                 <filter type="param_value" column="0" value="#" compare="startswith" keep="False"/>
                  <filter type="param_value" ref="refGenomeSource.index" column="0"/>
                </option>
               </action>
             </when>

               </action>
             </when>
             </conditional>
          </actions>
       </data>
       <data format="bam" name="chimeric_reads" label="${on_string}_${jobName}_starmappedchim.bam" 
                    from_work_dir="Chimeric.out.bam">
         <filter>(params['settingsType'] == 'full' and params['chim_segment_min'] > 0)</filter>
          <actions>
             <conditional name="refGenomeSource.genomeSource">
             <when value="indexed">
               <action type="metadata" name="dbkey">
                <option type="from_data_table" name="star_indexes" column="1" offset="0">
                 <filter type="param_value" column="0" value="#" compare="startswith" keep="False"/>
                  <filter type="param_value" ref="refGenomeSource.index" column="0"/>
                </option>
               </action>
             </when>

               </action>
             </when>
             </conditional>
          </actions>
        </data>
        <data format="interval" name="splice_junctions" label="${on_string}_${jobName}_starsplicejunct.bed" 
                   from_work_dir="SJ.out.tab">
          <actions>
             <conditional name="refGenomeSource.genomeSource">
             <when value="indexed">
               <action type="metadata" name="dbkey">
                <option type="from_data_table" name="star_indexes" column="1" offset="0">
                 <filter type="param_value" column="0" value="#" compare="startswith" keep="False"/>
                  <filter type="param_value" ref="refGenomeSource.index" column="0"/>
                </option>
               </action>
             </when>

               </action>
             </when>
             </conditional>
          </actions>
        </data>
        <data format="bam" name="mapped_reads" label="${on_string}_${jobName}_starmapped.bam" 
                    from_work_dir="Aligned.out.bam">
          <actions>
             <conditional name="refGenomeSource.genomeSource">
             <when value="indexed">
               <action type="metadata" name="dbkey">
                <option type="from_data_table" name="star_indexes" column="1" offset="0">
                 <filter type="param_value" column="0" value="#" compare="startswith" keep="False"/>
                  <filter type="param_value" ref="refGenomeSource.index" column="0"/>
                </option>
               </action>
             </when>

             </when>
             </conditional>
          </actions>
        </data>
    </outputs>
<help>

**What it does**
Runs the rna star gapped aligner. Suited to paired or single end rna-seq.

strand attribute for all alignments that contain splice junctions. The spliced alignments that have undefined
strand (i.e. containing only non-canonical junctions) will be suppressed.

If you have stranded RNA-seq data, you do not need to use any specific STAR options. Instead, you need
to run Cufflinks with the library option --library-type options. For example, cufflinks with
library-type fr-firststrand should be used for the “standard” dUTP protocol.
This option has to be used only for Cufflinks runs and not for STAR runs.

It is recommended to remove the non-canonical junctions for Cufflinks runs using –

--outFilterIntronMotifs RemoveNoncanonical
filter out alignments that contain non-canonical junctions

OR

.. _rna_star: http://code.google.com/p/rna-star/
.. _rna_starMS: http://bioinformatics.oxfordjournals.org/content/29/1/15.full
.. _Galaxy: http://getgalaxy.org

</help>
</tool>

25:1903b1fe70fc

<tool id="rna_star" name="rnastar" version="2.4.0d">
    <description>Gapped-read mapper for RNA-seq data</description>
    <requirements>
        <requirement type="package" version="2.4.0d">rnastar</requirement>
        <requirement type="package" version="0.1.19">samtools</requirement>
    </requirements>
    <command>
    ##
    ## Run STAR.
    ##
    #if str($refGenomeSource.genomeSource) == 'history':
       mkdir -p tempstargenomedir; STAR --runMode genomeGenerate --genomeDir "tempstargenomedir" --genomeFastaFiles "$refGenomeSource.ownFile" --runThreadN 2
        #if str($refGenomeSource.geneModel) != 'None':
          --sjdbOverhang "100" --sjdbGTFfile "$refGenomeSource.geneModel"
          #if str($refGenomeSource.geneModel.ext) == 'gff3':
            --sjdbGTFtagExonParentTranscript Parent
          #end if
        #end if
        ;
    #end if
    STAR
    ## Can adjust this as appropriate for the system.
    --genomeLoad NoSharedMemory
    #if str($refGenomeSource.genomeSource) == 'history':
        --genomeDir "tempstargenomedir"
    #else
        --genomeDir $refGenomeSource.index.fields.pathls 
    #end if
    --readFilesIn $singlePaired.input1 
    #if str($singlePaired.sPaired) == "paired"
            $singlePaired.input2
    #end if
        --runThreadN 4
    #if str($params.settingsType) == "full":
        --chimSegmentMin $params.chim_segment_min
        --chimScoreMin $params.chim_score_min
    #end if

    ## may or may not need to generate SAM tags and handle non-canonicals for Cufflinks tools.
    $outSAMstrandField $outFilterIntronMotifs $outSAMattributes

    ;
    ##
    ## BAM conversion.
    ##

    ## Convert aligned reads.
    samtools view -Shb Aligned.out.sam | samtools sort - AlignedSorted 2&gt;/dev/null 

    ## Convert chimeric reads.
    #if str($params.settingsType) == "full" and $params.chim_segment_min > 0:
        ; samtools view -Shb Chimeric.out.sam | samtools sort - ChimericSorted 2&gt;/dev/null 
    #end if
    </command>

    <stdio>
        <regex match=".*" source="both" level="warning" description="Some stderr/stdout text"/>
    </stdio>

    <inputs>
        <param name="jobName" type="text" size="120" value="rna-star run" label="Job narrative (added to output names)" 
          help="Only letters, numbers and underscores (_) will be retained in this field">

            </param>
            <when value="single">
                <param format="fastqsanger,fastq,fasta" name="input1" type="data" label="RNA-Seq FASTQ file" help="Nucleotide-space: Must have Sanger-scaled quality values with ASCII offset 33"/>
            </when>
            <when value="paired">
                <param format="fastqsanger,fastq,fasta" name="input1" type="data" label="RNA-Seq FASTQ file, forward reads" 
            help="Nucleotide-space: Must have Sanger-scaled quality values with ASCII offset 33" />
                <param format="fastqsanger,fastq,fasta" name="input2" type="data" label="RNA-Seq FASTQ file, reverse reads"
            help="Nucleotide-space: Must have Sanger-scaled quality values with ASCII offset 33" />
            </when>
        </conditional>

        <!-- Genome source. -->
        <conditional name="refGenomeSource">
            <param name="genomeSource" type="select" label="Will you select a reference genome from your history or use a built-in index?" help="Built-ins were indexed using default options">
                <option value="indexed" selected="True">Use a built-in index</option>
                <option value="history">Index and use a genome fasta file from my current history</option>
            </param>
            <when value="indexed">
            <param name="index" type="select" label="Select a reference genome">
                <options from_data_table="rnastar_index">
                    <filter type="sort_by" column="2"/>
                    <validator type="no_options" message="No indexes are available for the selected input dataset"/>
                </options>
            </param>
            </when>
            <when value="history">
                <param name="ownFile" type="data" format="fasta" metadata_name="dbkey" label="Select the reference genome" />
                <param name="geneModel" type="data" format="gff3,gtf" label="Gene model (gff3,gtf) file for splice junctions. Leave blank for none"
                optional="true" help="Optional. If supplied, the index file will retain exon junction information for mapping splices" />
            </when>
        </conditional>
            <param name="outSAMattributes" type="select" label="Include extra sam attributes for downstream processing">
              <option value="--outSAMattributes Standard">Standard - eg for old Samtools downstream</option>
              <option value="--outSAMattributes All" selected="true">All modern Samtools attributes - see below</option>

            </when>
        </conditional>
    </inputs>

    <outputs>
       <data format="txt" name="output_log" label="${jobName}.log" from_work_dir="Log.final.out"/>
       <data format="interval" name="chimeric_junctions" label="${jobName}_starchimjunc.bed" from_work_dir="Chimeric.out.junction">
          <filter>(params['settingsType'] == 'full' and params['chim_segment_min'] > 0)</filter>
          <actions>
             <conditional name="refGenomeSource.genomeSource">
             <when value="indexed">
               <action type="metadata" name="dbkey">
                <option type="from_data_table" name="rnastar_index" column="1" offset="0">
                 <filter type="param_value" column="0" value="#" compare="startswith" keep="False"/>
                  <filter type="param_value" ref="refGenomeSource.index" column="0"/>
                </option>
               </action>
             </when>

               </action>
             </when>
             </conditional>
          </actions>
       </data>
       <data format="bam" name="chimeric_reads" label="${jobName}_starmappedchim.bam" 
                    from_work_dir="ChimericSorted.bam">
         <filter>(params['settingsType'] == 'full' and params['chim_segment_min'] > 0)</filter>
          <actions>
             <conditional name="refGenomeSource.genomeSource">
             <when value="indexed">
               <action type="metadata" name="dbkey">
                <option type="from_data_table" name="rnastar_index" column="1" offset="0">
                 <filter type="param_value" column="0" value="#" compare="startswith" keep="False"/>
                  <filter type="param_value" ref="refGenomeSource.index" column="0"/>
                </option>
               </action>
             </when>

               </action>
             </when>
             </conditional>
          </actions>
        </data>
        <data format="interval" name="splice_junctions" label="${jobName}_starsplicejunct.bed" 
                   from_work_dir="SJ.out.tab">
          <actions>
             <conditional name="refGenomeSource.genomeSource">
             <when value="indexed">
               <action type="metadata" name="dbkey">
                <option type="from_data_table" name="rnastar_index" column="1" offset="0">
                 <filter type="param_value" column="0" value="#" compare="startswith" keep="False"/>
                  <filter type="param_value" ref="refGenomeSource.index" column="0"/>
                </option>
               </action>
             </when>

               </action>
             </when>
             </conditional>
          </actions>
        </data>
        <data format="bam" name="mapped_reads" label="${jobName}_starmapped.bam" 
                    from_work_dir="AlignedSorted.bam">
          <actions>
             <conditional name="refGenomeSource.genomeSource">
             <when value="indexed">
               <action type="metadata" name="dbkey">
                <option type="from_data_table" name="rnastar_index" column="1" offset="0">
                 <filter type="param_value" column="0" value="#" compare="startswith" keep="False"/>
                  <filter type="param_value" ref="refGenomeSource.index" column="0"/>
                </option>
               </action>
             </when>

             </when>
             </conditional>
          </actions>
        </data>
    </outputs>
    <tests>
        <test>
 <param name='input1' value='tophat_in2.fastqsanger' ftype='fastqsanger' />
 <param name='jobName' value='rnastar_test' />
 <param name='genomeSource' value='history' />
 <param name='ownFile' value='tophat_test.fa' />
 <param name='sPaired' value='single' />
 <param name='outSAMattributes' value='--outSAMattributes All' />
 <param name='outSAMstrandField' value='--outSAMstrandField intronMotif' />
 <param name='outFilterIntronMotifs' value='--outFilterIntronMotifs RemoveNoncanonical' />
 <output name='output_log' file='rnastar_test.log' compare='diff' lines_diff = '10'/>
 <output name='splice_junctions' file="rnastar_test_splicejunctions.bed" compare="sim_size" delta="200"/>
 <output name='mapped_reads' file="rnastar_test_mapped_reads.bam" compare="sim_size" delta="200" />
        </test>
    </tests>
<help>

**What it does**
Runs the rna star gapped aligner. Suited to paired or single end rna-seq.

strand attribute for all alignments that contain splice junctions. The spliced alignments that have undefined
strand (i.e. containing only non-canonical junctions) will be suppressed.

If you have stranded RNA-seq data, you do not need to use any specific STAR options. Instead, you need
to run Cufflinks with the library option --library-type options. For example, cufflinks with
library-type fr-firststrand should be used for the b

It is recommended to remove the non-canonical junctions for Cufflinks runs using b


--outFilterIntronMotifs RemoveNoncanonical
filter out alignments that contain non-canonical junctions

OR

.. _rna_star: http://code.google.com/p/rna-star/
.. _rna_starMS: http://bioinformatics.oxfordjournals.org/content/29/1/15.full
.. _Galaxy: http://getgalaxy.org

</help>
<citations>
    <citation type="doi">doi: 10.1093/bioinformatics/bts635</citation>
</citations>
</tool>