comparison mirdeep2.xml @ 4:d338dbd76ea0 draft

planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/mirdeep2/mirdeep2 commit 04c75332ac618b43ce5c3f307f7866e97147e865

3:5cecae70d439

<tool id="rbc_mirdeep2" name="MiRDeep2" version="2.0.0">
    <description>identification of novel and known miRNAs</description>
    <requirements>
        <requirement type="package" version="2.0.0.8">mirdeep2</requirement>
    </requirements>
    <stdio>
        <!-- Anything other than zero is an error -->
        <exit_code range="1:" />
        <exit_code range=":-1" />
        <!-- In case the return code has not been set propery check stderr too -->
        <regex match="Error:" />
        <regex match="Exception:" />
    </stdio>
    <command>
<![CDATA[
    miRDeep2.pl
    
    $reads
    $genome
    $mappings
    
    #if $mature_this
        $mature_this
    #else
        none
    #end if
    
    #if $mature_other
        $mature_other
    #else
        none
    #end if
    
    #if $precursors
        $precursors
    #else
        none
    #end if
    
    #if $species.value != 'all'
        -t $species
    #end if
    
    #if $star_sequences
        -s $star_sequences
    #end if
    
    #if $min_read_stack
        -a $min_read_stack
    #end if
    
    #if $min_read_stack
        -a $min_read_stack
    #end if
    
    -g $max_precursors_analyze
    -b $min_score_cutoff
    $disable_randfold
    
    ; mv result*.bed result.bed 2> /dev/null
    ; mv result*.csv result.csv 2> /dev/null
    ; mv mirdeep_runs/run*/output.mrd . 2> /dev/null
    ; mv mirdeep_runs/run*/survey.csv . 2> /dev/null
    
    ## html output
    ;
    mv result*.html $html 2> /dev/null
    
    ## move pdf directory to be accessible from the new index.html
    ;
    mkdir -p $html.files_path 2> /dev/null
    ;
    mv pdfs* $html.files_path 2> /dev/null
    
]]>
    </command>
    <inputs> 
        <param name="reads" format="fasta" type="data" label="Collapsed deep sequencing reads">
            <help>
<![CDATA[
Reads in fasta format. The identifier should contain a prefix, a running
number and a '_x' to indicate the number of reads that have this sequence.

]]>
            </help>
        </param>
        <param name="genome" format="fasta" type="data" label="Genome" help="Genome contigs in fasta format. The identifiers should be unique."/>
        <param name="mappings" format="tabular" type="data" label="Mappings" help="Reads mapped against genome. Mappings should be in ARF format."/>
        <param name="mature_this" optional="true" format="fasta" type="data" label="Mature miRNA sequences for this species" 
            help="miRBase miRNA sequences in fasta format. These should be the known mature sequences for the species being analyzed."/>
        <param name="mature_other" optional="true" format="fasta" type="data" label="Mature miRNA sequences for related species">
            <help>
<![CDATA[
miRBase miRNA sequences in fasta format. These should be the pooled known
mature sequences for 1-5 species closely related to the species being analyzed.
]]>
            </help>
        </param>
        <param name="precursors" optional="true" format="fasta" type="data" label="Precursor sequences" 
            help="miRBase miRNA precursor sequences in fasta format. These should be the known precursor sequences for the species being analyzed."/>
            
        <param name="species" type="select" label="Search in species" help="If not searching in a specific species all species in your files will be analyzed. (-t)">
            <option value="all">All species</option>
            <option value="tni">tetraodon</option>
            <option value="dps">d.pseudoobscura</option>
            <option value="dya">d.yakuba</option>

            <option value="dan">d.ananassae</option>
            <option value="hsa">human</option>
            <option value="dsi">d.simulans</option>
        </param>
        <param name="star_sequences" format="fasta" type="data" optional="true" label="Star sequences" help="From miRBase in fasta format (optional) (-s)"/>
        
        <param name="min_read_stack" optional="true" type="integer" min="0" label="Minimum read stack height">
            <help>
<![CDATA[
minimum read stack height that triggers analysis. Using this option disables
automatic estimation of the optimal value and all detected precursors are analyzed. (-a)
]]>
            </help>
        </param>
        <param name="max_precursors_analyze" type="integer" value="50000" label="Maximum precursors" 
            help="Maximum number of precursors to analyze when automatic excision gearing is used. If set to -1 all precursors will be analyzed. (-g)."/>
        <param name="min_score_cutoff" type="integer" value="0" label="Minimum miRNA score" 
            help="Minimum score cut-off for predicted novel miRNAs to be displayed in the overview table. (-b)"/>
        <param name="disable_randfold" type="boolean" truevalue="-c" falsevalue="" label="Disable randfold analysis" help="(-c)"/>
    </inputs>
    <outputs>
        <data name="tab_results" format="tabular" from_work_dir="result.csv" label="Tabular output of ${tool.name} on ${on_string}"/>
        <data format="html" name="html" label="${tool.name} on ${on_string} (html report)"/>
        <data name="pred_acc" format="tabular" from_work_dir="survey.csv" label="Prediction accuracy output of ${tool.name} on ${on_string}"/>
        <data name="bed_out" format="bed" from_work_dir="result.bed" label="Bed output of ${tool.name} on ${on_string}"/>
        <data name="mrd_out" format="txt" from_work_dir="output.mrd" label="Text output of ${tool.name} on ${on_string}"/>
    </outputs>
    <tests>
        <test>
            <param name="reads" value="reads_collapsed.fa"/>
            <param name="genome" value="cel_cluster.fa"/>
            <param name="mappings" value="reads_collapsed_vs_genome.arf"/>
            <param name="mature_this" value="mature_ref_this_species.fa"/>
            <param name="mature_other" value="mature_ref_other_species.fa"/>
            <param name="precursors" value="precursors_ref_this_species.fa"/>
            
            <output name="tab_results" file="result.csv" compare="sim_size"/>
            <output name="pred_acc" file="survey.csv" compare="sim_size"/>
            <output name="bed_out" file="result.bed" compare="sim_size"/>
            <output name="mrd_out" file="output.mrd" compare="sim_size"/>
        </test>
    </tests>
    <help>
<![CDATA[

4:d338dbd76ea0

<tool id="rbc_mirdeep2" name="MiRDeep2" version="2.0.0.8.1">
    <description>identification of novel and known miRNAs</description>
    <requirements>
        <requirement type="package" version="2.0.0.8">mirdeep2</requirement>
    </requirements>
    <command detect_errors="aggressive">
<![CDATA[
    miRDeep2.pl

    $reads
    $genome
    $mappings

    #if $mature_this
        $mature_this
    #else
        none
    #end if

    #if $mature_other
        $mature_other
    #else
        none
    #end if

    #if $precursors
        $precursors
    #else
        none
    #end if

    #if $species.value != 'all'
        -t $species
    #end if

    #if $star_sequences
        -s $star_sequences
    #end if

    #if $min_read_stack
        -a $min_read_stack
    #end if

    #if $min_read_stack
        -a $min_read_stack
    #end if

    -g $max_precursors_analyze
    -b $min_score_cutoff
    $disable_randfold

    &&

    ## html output
    mv result*.html $html 2> /dev/null

    ## move pdf directory to be accessible from the new index.html
    &&
    mkdir -p $html.files_path 2> /dev/null
    &&
    mv pdfs* $html.files_path 2> /dev/null
]]>
    </command>
    <inputs>
        <param name="reads" format="fasta" type="data" label="Collapsed deep sequencing reads">
            <help>
<![CDATA[
Reads in fasta format. The identifier should contain a prefix, a running
number and a '_x' to indicate the number of reads that have this sequence.

]]>
            </help>
        </param>
        <param name="genome" format="fasta" type="data" label="Genome" help="Genome contigs in fasta format. The identifiers should be unique."/>
        <param name="mappings" format="tabular" type="data" label="Mappings" help="Reads mapped against genome. Mappings should be in ARF format."/>
        <param name="mature_this" optional="true" format="fasta" type="data" label="Mature miRNA sequences for this species"
            help="miRBase miRNA sequences in fasta format. These should be the known mature sequences for the species being analyzed."/>
        <param name="mature_other" optional="true" format="fasta" type="data" label="Mature miRNA sequences for related species">
            <help>
<![CDATA[
miRBase miRNA sequences in fasta format. These should be the pooled known
mature sequences for 1-5 species closely related to the species being analyzed.
]]>
            </help>
        </param>
        <param name="precursors" optional="true" format="fasta" type="data" label="Precursor sequences"
            help="miRBase miRNA precursor sequences in fasta format. These should be the known precursor sequences for the species being analyzed."/>

        <param name="species" type="select" label="Search in species" help="If not searching in a specific species all species in your files will be analyzed. (-t)">
            <option value="all">All species</option>
            <option value="tni">tetraodon</option>
            <option value="dps">d.pseudoobscura</option>
            <option value="dya">d.yakuba</option>

            <option value="dan">d.ananassae</option>
            <option value="hsa">human</option>
            <option value="dsi">d.simulans</option>
        </param>
        <param name="star_sequences" format="fasta" type="data" optional="true" label="Star sequences" help="From miRBase in fasta format (optional) (-s)"/>

        <param name="min_read_stack" optional="true" type="integer" min="0" label="Minimum read stack height">
            <help>
<![CDATA[
minimum read stack height that triggers analysis. Using this option disables
automatic estimation of the optimal value and all detected precursors are analyzed. (-a)
]]>
            </help>
        </param>
        <param name="max_precursors_analyze" type="integer" value="50000" label="Maximum precursors"
            help="Maximum number of precursors to analyze when automatic excision gearing is used. If set to -1 all precursors will be analyzed. (-g)."/>
        <param name="min_score_cutoff" type="integer" value="0" label="Minimum miRNA score"
            help="Minimum score cut-off for predicted novel miRNAs to be displayed in the overview table. (-b)"/>
        <param name="disable_randfold" type="boolean" truevalue="-c" falsevalue="" label="Disable randfold analysis" help="(-c)"/>
        <param name="detailed_fasta" type="boolean" checked="false" label="Detailed fasta output" help="Output fasta files of precursors, mature and star strand for both novel and known miRNAs"/>
    </inputs>
    <outputs>
        <data name="tab_results" format="tabular" from_work_dir="result*.csv" label="Tabular output of ${tool.name} on ${on_string}"/>
        <data format="html" name="html" label="${tool.name} on ${on_string} (html report)"/>
        <data name="pred_acc" format="tabular" from_work_dir="mirdeep_runs/run*/survey.csv" label="Prediction accuracy output of ${tool.name} on ${on_string}"/>
        <data name="bed_out" format="bed" from_work_dir="result*.bed" label="Bed output of ${tool.name} on ${on_string}"/>
        <data name="mrd_out" format="txt" from_work_dir="mirdeep_runs/run*/output.mrd" label="Text output of ${tool.name} on ${on_string}"/>

        <data name="known_mature" format="fasta" from_work_dir="mirna_results_*/known_mature_*.fa" label="${tool.name} on ${on_string}: known mature">
            <filter>detailed_fasta</filter>
        </data>
        <data name="known_pres" format="fasta" from_work_dir="mirna_results_*/known_pres_*.fa" label="${tool.name} on ${on_string}: known precursors">
            <filter>detailed_fasta</filter>
        </data>
        <data name="known_star" format="fasta" from_work_dir="mirna_results_*/known_star_*.fa" label="${tool.name} on ${on_string}: known star">
            <filter>detailed_fasta</filter>
        </data>
        <data name="not_mature" format="fasta" from_work_dir="mirna_results_*/not_mature_*.fa" label="${tool.name} on ${on_string}: not detected mature">
            <filter>detailed_fasta</filter>
        </data>
        <data name="not_pres" format="fasta" from_work_dir="mirna_results_*/not_pres_*.fa" label="${tool.name} on ${on_string}: not detected precursors">
            <filter>detailed_fasta</filter>
        </data>
        <data name="not_star" format="fasta" from_work_dir="mirna_results_*/not_star_*.fa" label="${tool.name} on ${on_string}: not detected star">
            <filter>detailed_fasta</filter>
        </data>
        <data name="novel_mature" format="fasta" from_work_dir="mirna_results_*/novel_mature_*.fa" label="${tool.name} on ${on_string}: novel mature">
            <filter>detailed_fasta</filter>
        </data>
        <data name="novel_pres" format="fasta" from_work_dir="mirna_results_*/novel_pres_*.fa" label="${tool.name} on ${on_string}: novel precursors">
            <filter>detailed_fasta</filter>
        </data>
        <data name="novel_star" format="fasta" from_work_dir="mirna_results_*/novel_star_*.fa" label="${tool.name} on ${on_string}: novel star">
            <filter>detailed_fasta</filter>
        </data>
    </outputs>
    <tests>
        <test>
            <param name="reads" value="reads_collapsed.fa"/>
            <param name="genome" value="cel_cluster.fa"/>
            <param name="mappings" value="reads_collapsed_vs_genome.arf"/>
            <param name="mature_this" value="mature_ref_this_species.fa"/>
            <param name="mature_other" value="mature_ref_other_species.fa"/>
            <param name="precursors" value="precursors_ref_this_species.fa"/>

            <output name="tab_results" file="result.csv" compare="sim_size"/>
            <output name="pred_acc" file="survey.csv" compare="sim_size"/>
            <output name="bed_out" file="result.bed" compare="sim_size"/>
            <output name="mrd_out" file="output.mrd" compare="sim_size"/>
        </test>
        <test>
            <param name="reads" value="reads_collapsed.fa"/>
            <param name="genome" value="cel_cluster.fa"/>
            <param name="mappings" value="reads_collapsed_vs_genome.arf"/>
            <param name="mature_this" value="mature_ref_this_species.fa"/>
            <param name="mature_other" value="mature_ref_other_species.fa"/>
            <param name="precursors" value="precursors_ref_this_species.fa"/>
            <param name="detailed_fasta" value="true"/>

            <output name="tab_results" file="result.csv" compare="sim_size"/>
            <output name="pred_acc" file="survey.csv" compare="sim_size"/>
            <output name="bed_out" file="result.bed" compare="sim_size"/>
            <output name="mrd_out" file="output.mrd" compare="sim_size"/>

            <output name="known_mature" file="detailed_fasta/known_mature.fa" compare="sim_size"/>
            <output name="known_pres" file="detailed_fasta/known_pres.fa" compare="sim_size"/>
            <output name="known_star" file="detailed_fasta/known_star.fa" compare="sim_size"/>
            <output name="not_mature" file="detailed_fasta/not_mature.fa" compare="sim_size"/>
            <output name="not_pres" file="detailed_fasta/not_pres.fa" compare="sim_size"/>
            <output name="not_star" file="detailed_fasta/not_star.fa" compare="sim_size"/>
            <output name="novel_mature" file="detailed_fasta/novel_mature.fa" compare="sim_size"/>
            <output name="novel_pres" file="detailed_fasta/novel_pres.fa" compare="sim_size"/>
            <output name="novel_star" file="detailed_fasta/novel_star.fa" compare="sim_size"/>
        </test>
    </tests>
    <help>
<![CDATA[