annotate mirdeep2.xml @ 3:5cecae70d439 draft

planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/mirdeep2/mirdeep2 commit 3103ebed1a420c7d3415b67ef532ea579edf9faa

<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.
There should be no redundancy in the sequences.
]]>
            </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="ame">a.mellifera</option>
            <option value="dmo">d.mojavensis</option>
            <option value="cel">worm</option>
            <option value="aga">a.gambiae</option>
            <option value="cbr">c.briggsae</option>
            <option value="cin">c.intestinalis</option>
            <option value="mmu">mouse</option>
            <option value="xtr">x.tropicalis</option>
            <option value="eca">horse</option>
            <option value="cfa">dog</option>
            <option value="fru">fugu</option>
            <option value="bta">cow</option>
            <option value="der">d.erecta</option>
            <option value="dgr">d.grimshawi</option>
            <option value="gga">chicken</option>
            <option value="spu">s.purpuratus</option>
            <option value="bfl">lancelet</option>
            <option value="ptr">chimp</option>
            <option value="dse">d.sechellia</option>
            <option value="dpe">d.persimilis</option>
            <option value="dvi">d.virilis</option>
            <option value="rno">rat</option>
            <option value="dme">d.melanogaster</option>
            <option value="lca">cat</option>
            <option value="sja">c.japonica</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[

**What it does**

MiRDeep2 is a software package for identification of novel and known miRNAs in deep sequencing data. Furthermore, it can be used for miRNA expression profiling across samples.

**Input**

A FASTA file with deep sequencing reads, a FASTA file of the corresponding genome, a file of mapped reads to the genome in miRDeep2 arf format, an optional fasta file with known miRNAs of the analysing species and an option fasta file of known miRNAs of related species.

Arf format:
Is a proprietary file format generated and processed by miRDeep2. It contains information of reads mapped to a reference genome. Each line in such a file contains 13 columns:

1. read identifier
2. length of read sequence
3. start position in read sequence that is mapped
4. end position in read sequence that is mapped
5. read sequence
6. identifier of the genome-part to which a read is mapped to. This is either a scaffold id or a chromosome name
7. length of the genome sequence a read is mapped to
8. start position in the genome where a read is mapped to
9. end position in the genome where a read is mapped to
10. genome sequence to which a read is mapped
11. genome strand information. Plus means the read is aligned to the sense-strand of the genome. Minus means it is aligned to the antisense-strand of the genome.
12. Number of mismatches in the read mapping
13. Edit string that indicates matches by lowercase 'm' and mismatches by uppercase 'M'


]]>
    </help>
    <citations>
        <citation type="doi">10.1093/nar/gkr688</citation>
        <citation type="doi">10.1002/0471250953.bi1210s36</citation>
    </citations>
</tool>